{ "302ai": { "api": "https://api.302.ai/v1", "doc": "https://doc.302.ai", "env": [ "302AI_API_KEY" ], "iconURL": "https://models.dev/logos/302ai.svg", "id": "302ai", "models": { "MiniMax-M1": { "attachment": false, "cost": { "input": 0.132, "output": 1.254 }, "description": "MiniMax-M1 is an AI model provided by 302ai.", "family": "minimax", "id": "MiniMax-M1", "last_updated": "2025-06-16", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M1", "open_weights": false, "reasoning": false, "release_date": "2025-06-16", "temperature": true, "tool_call": true }, "MiniMax-M2": { "attachment": false, "cost": { "input": 0.33, "output": 1.32 }, "description": "MiniMax-M2 is an AI model provided by 302ai.", "id": "MiniMax-M2", "last_updated": "2025-10-26", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2", "open_weights": false, "reasoning": false, "release_date": "2025-10-26", "temperature": true, "tool_call": true }, "MiniMax-M2.1": { "attachment": false, "cost": { "input": 0.3, "output": 1.2 }, "description": "MiniMax-M2.1 is an AI model provided by 302ai.", "id": "MiniMax-M2.1", "last_updated": "2025-12-19", "limit": { "context": 1000000, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.1", "open_weights": false, "reasoning": false, "release_date": "2025-12-19", "temperature": true, "tool_call": true }, "MiniMax-M2.7": { "attachment": false, "cost": { "input": 0.3, "output": 1.2 }, "description": "MiniMax-M2.7 is an AI model provided by 302ai.", "id": "MiniMax-M2.7", "last_updated": "2026-03-19", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.7", "open_weights": false, "reasoning": false, "release_date": "2026-03-19", "temperature": true, "tool_call": true }, "MiniMax-M2.7-highspeed": { "attachment": false, "cost": { "input": 0.6, "output": 4.8 }, "description": "MiniMax-M2.7-highspeed is an AI model provided by 302ai.", "id": "MiniMax-M2.7-highspeed", "last_updated": "2026-03-19", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.7-highspeed", "open_weights": false, "reasoning": false, "release_date": "2026-03-19", "temperature": true, "tool_call": true }, "chatgpt-4o-latest": { "attachment": true, "cost": { "input": 5, "output": 15 }, "description": "chatgpt-4o-latest is an AI model provided by 302ai.", "family": "gpt", "id": "chatgpt-4o-latest", "knowledge": "2023-09", "last_updated": "2024-08-08", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "chatgpt-4o-latest", "open_weights": false, "reasoning": false, "release_date": "2024-08-08", "temperature": true, "tool_call": false }, "claude-3-5-haiku-20241022": { "attachment": true, "cost": { "input": 0.8, "output": 4 }, "description": "claude-3-5-haiku-20241022 is an AI model provided by 302ai.", "family": "claude-haiku", "id": "claude-3-5-haiku-20241022", "knowledge": "2024-07-31", "last_updated": "2024-10-22", "limit": { "context": 200000, "output": 8192 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "claude-3-5-haiku-20241022", "open_weights": false, "reasoning": false, "release_date": "2024-10-22", "temperature": true, "tool_call": true }, "claude-3-5-haiku-latest": { "attachment": true, "cost": { "input": 0.8, "output": 4 }, "description": "claude-3-5-haiku-latest is an AI model provided by 302ai.", "family": "claude-haiku", "id": "claude-3-5-haiku-latest", "knowledge": "2024-07-31", "last_updated": "2024-10-22", "limit": { "context": 200000, "output": 8192 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "claude-3-5-haiku-latest", "open_weights": false, "reasoning": false, "release_date": "2024-10-22", "temperature": true, "tool_call": true }, "claude-haiku-4-5": { "attachment": true, "cost": { "input": 1, "output": 5 }, "description": "claude-haiku-4-5 is an AI model provided by 302ai.", "family": "claude-haiku", "id": "claude-haiku-4-5", "knowledge": "2025-02-28", "last_updated": "2025-10-16", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "claude-haiku-4-5", "open_weights": false, "reasoning": true, "release_date": "2025-10-16", "temperature": true, "tool_call": true }, "claude-haiku-4-5-20251001": { "attachment": true, "cost": { "input": 1, "output": 5 }, "description": "claude-haiku-4-5-20251001 is an AI model provided by 302ai.", "family": "claude-haiku", "id": "claude-haiku-4-5-20251001", "knowledge": "2025-02-28", "last_updated": "2025-10-16", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "claude-haiku-4-5-20251001", "open_weights": false, "reasoning": true, "release_date": "2025-10-16", "temperature": true, "tool_call": true }, "claude-opus-4-1-20250805": { "attachment": true, "cost": { "input": 15, "output": 75 }, "description": "claude-opus-4-1-20250805 is an AI model provided by 302ai.", "family": "claude-opus", "id": "claude-opus-4-1-20250805", "knowledge": "2025-03-31", "last_updated": "2025-08-05", "limit": { "context": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "claude-opus-4-1-20250805", "open_weights": false, "reasoning": true, "release_date": "2025-08-05", "temperature": true, "tool_call": true }, "claude-opus-4-1-20250805-thinking": { "attachment": true, "cost": { "input": 15, "output": 75 }, "description": "claude-opus-4-1-20250805-thinking is an AI model provided by 302ai.", "id": "claude-opus-4-1-20250805-thinking", "knowledge": "2025-03", "last_updated": "2025-05-27", "limit": { "context": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "claude-opus-4-1-20250805-thinking", "open_weights": false, "reasoning": true, "release_date": "2025-05-27", "temperature": true, "tool_call": true }, "claude-opus-4-20250514": { "attachment": true, "cost": { "input": 15, "output": 75 }, "description": "claude-opus-4-20250514 is an AI model provided by 302ai.", "family": "claude-opus", "id": "claude-opus-4-20250514", "knowledge": "2025-03-31", "last_updated": "2025-05-22", "limit": { "context": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "claude-opus-4-20250514", "open_weights": false, "reasoning": true, "release_date": "2025-05-22", "temperature": true, "tool_call": true }, "claude-opus-4-5": { "attachment": true, "cost": { "input": 5, "output": 25 }, "description": "claude-opus-4-5 is an AI model provided by 302ai.", "family": "claude-opus", "id": "claude-opus-4-5", "knowledge": "2025-03-31", "last_updated": "2025-11-25", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "claude-opus-4-5", "open_weights": false, "reasoning": true, "release_date": "2025-11-25", "temperature": true, "tool_call": true }, "claude-opus-4-5-20251101": { "attachment": true, "cost": { "input": 5, "output": 25 }, "description": "claude-opus-4-5-20251101 is an AI model provided by 302ai.", "family": "claude-opus", "id": "claude-opus-4-5-20251101", "knowledge": "2025-03-31", "last_updated": "2025-11-25", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "claude-opus-4-5-20251101", "open_weights": false, "reasoning": true, "release_date": "2025-11-25", "temperature": true, "tool_call": true }, "claude-opus-4-5-20251101-thinking": { "attachment": true, "cost": { "input": 5, "output": 25 }, "description": "claude-opus-4-5-20251101-thinking is an AI model provided by 302ai.", "id": "claude-opus-4-5-20251101-thinking", "knowledge": "2025-03", "last_updated": "2025-11-25", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "claude-opus-4-5-20251101-thinking", "open_weights": false, "reasoning": true, "release_date": "2025-11-25", "temperature": true, "tool_call": true }, "claude-opus-4-6": { "attachment": true, "cost": { "input": 5, "output": 25 }, "description": "claude-opus-4-6 is an AI model provided by 302ai.", "family": "claude-opus", "id": "claude-opus-4-6", "knowledge": "2025-05-31", "last_updated": "2026-03-13", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "claude-opus-4-6", "open_weights": false, "reasoning": true, "release_date": "2026-02-06", "temperature": true, "tool_call": true }, "claude-opus-4-6-thinking": { "attachment": true, "cost": { "input": 5, "output": 25 }, "description": "claude-opus-4-6-thinking is an AI model provided by 302ai.", "id": "claude-opus-4-6-thinking", "knowledge": "2025-05", "last_updated": "2026-03-13", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "claude-opus-4-6-thinking", "open_weights": false, "reasoning": true, "release_date": "2026-02-06", "temperature": true, "tool_call": true }, "claude-opus-4-7": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "context_over_200k": { "cache_read": 1, "cache_write": 12.5, "input": 10, "output": 37.5 }, "input": 5, "output": 25, "tiers": [ { "cache_read": 1, "cache_write": 12.5, "input": 10, "output": 37.5, "tier": { "size": 200000, "type": "context" } } ] }, "description": "claude-opus-4-7 is an AI model provided by 302ai.", "family": "claude-opus", "id": "claude-opus-4-7", "knowledge": "2026-01-31", "last_updated": "2026-04-17", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "claude-opus-4-7", "open_weights": false, "reasoning": true, "release_date": "2026-04-17", "temperature": true, "tool_call": true }, "claude-sonnet-4-20250514": { "attachment": true, "cost": { "input": 3, "output": 15 }, "description": "claude-sonnet-4-20250514 is an AI model provided by 302ai.", "family": "claude-sonnet", "id": "claude-sonnet-4-20250514", "knowledge": "2025-03-31", "last_updated": "2025-05-22", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "claude-sonnet-4-20250514", "open_weights": false, "reasoning": true, "release_date": "2025-05-22", "temperature": true, "tool_call": true }, "claude-sonnet-4-5": { "attachment": true, "cost": { "input": 3, "output": 15 }, "description": "claude-sonnet-4-5 is an AI model provided by 302ai.", "family": "claude-sonnet", "id": "claude-sonnet-4-5", "knowledge": "2025-07-31", "last_updated": "2025-09-30", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "claude-sonnet-4-5", "open_weights": false, "reasoning": true, "release_date": "2025-09-30", "temperature": true, "tool_call": true }, "claude-sonnet-4-5-20250929": { "attachment": true, "cost": { "input": 3, "output": 15 }, "description": "claude-sonnet-4-5-20250929 is an AI model provided by 302ai.", "family": "claude-sonnet", "id": "claude-sonnet-4-5-20250929", "knowledge": "2025-07-31", "last_updated": "2025-09-30", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "claude-sonnet-4-5-20250929", "open_weights": false, "reasoning": true, "release_date": "2025-09-30", "temperature": true, "tool_call": true }, "claude-sonnet-4-5-20250929-thinking": { "attachment": true, "cost": { "input": 3, "output": 15 }, "description": "claude-sonnet-4-5-20250929-thinking is an AI model provided by 302ai.", "id": "claude-sonnet-4-5-20250929-thinking", "knowledge": "2025-03", "last_updated": "2025-09-30", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "claude-sonnet-4-5-20250929-thinking", "open_weights": false, "reasoning": true, "release_date": "2025-09-30", "temperature": true, "tool_call": true }, "claude-sonnet-4-6": { "attachment": true, "cost": { "input": 3, "output": 15 }, "description": "claude-sonnet-4-6 is an AI model provided by 302ai.", "family": "claude-sonnet", "id": "claude-sonnet-4-6", "knowledge": "2025-08-31", "last_updated": "2026-03-13", "limit": { "context": 1000000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "claude-sonnet-4-6", "open_weights": false, "reasoning": true, "release_date": "2026-02-18", "temperature": true, "tool_call": true }, "claude-sonnet-4-6-thinking": { "attachment": true, "cost": { "input": 3, "output": 15 }, "description": "claude-sonnet-4-6-thinking is an AI model provided by 302ai.", "id": "claude-sonnet-4-6-thinking", "knowledge": "2025-08", "last_updated": "2026-03-13", "limit": { "context": 1000000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "claude-sonnet-4-6-thinking", "open_weights": false, "reasoning": true, "release_date": "2026-02-18", "temperature": true, "tool_call": true }, "deepseek-chat": { "attachment": false, "cost": { "input": 0.29, "output": 0.43 }, "description": "Deepseek-Chat is an AI model provided by 302ai.", "family": "deepseek", "id": "deepseek-chat", "knowledge": "2024-07", "last_updated": "2024-11-29", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Deepseek-Chat", "open_weights": false, "reasoning": false, "release_date": "2024-11-29", "temperature": true, "tool_call": true }, "deepseek-reasoner": { "attachment": false, "cost": { "input": 0.29, "output": 0.43 }, "description": "Deepseek-Reasoner is an AI model provided by 302ai.", "family": "deepseek-thinking", "id": "deepseek-reasoner", "knowledge": "2024-07", "last_updated": "2025-01-20", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Deepseek-Reasoner", "open_weights": false, "reasoning": true, "release_date": "2025-01-20", "temperature": true, "tool_call": true }, "deepseek-v3.2": { "attachment": false, "cost": { "input": 0.29, "output": 0.43 }, "description": "deepseek-v3.2 is an AI model provided by 302ai.", "id": "deepseek-v3.2", "knowledge": "2024-12", "last_updated": "2025-12-01", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "deepseek-v3.2", "open_weights": false, "reasoning": false, "release_date": "2025-12-01", "temperature": true, "tool_call": true }, "deepseek-v3.2-thinking": { "attachment": false, "cost": { "input": 0.29, "output": 0.43 }, "description": "DeepSeek-V3.2-Thinking is an AI model provided by 302ai.", "id": "deepseek-v3.2-thinking", "knowledge": "2024-12", "last_updated": "2025-12-01", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek-V3.2-Thinking", "open_weights": false, "reasoning": true, "release_date": "2025-12-01", "temperature": true, "tool_call": true }, "doubao-seed-1-6-thinking-250715": { "attachment": true, "cost": { "input": 0.121, "output": 1.21 }, "description": "doubao-seed-1-6-thinking-250715 is an AI model provided by 302ai.", "id": "doubao-seed-1-6-thinking-250715", "last_updated": "2025-07-15", "limit": { "context": 256000, "output": 16000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "doubao-seed-1-6-thinking-250715", "open_weights": false, "reasoning": true, "release_date": "2025-07-15", "temperature": true, "tool_call": true }, "doubao-seed-1-6-vision-250815": { "attachment": true, "cost": { "input": 0.114, "output": 1.143 }, "description": "doubao-seed-1-6-vision-250815 is an AI model provided by 302ai.", "id": "doubao-seed-1-6-vision-250815", "last_updated": "2025-09-30", "limit": { "context": 256000, "output": 32000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "doubao-seed-1-6-vision-250815", "open_weights": false, "reasoning": false, "release_date": "2025-09-30", "temperature": true, "tool_call": true }, "doubao-seed-1-8-251215": { "attachment": true, "cost": { "input": 0.114, "output": 0.286 }, "description": "doubao-seed-1-8-251215 is an AI model provided by 302ai.", "id": "doubao-seed-1-8-251215", "last_updated": "2025-12-18", "limit": { "context": 224000, "output": 64000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "doubao-seed-1-8-251215", "open_weights": false, "reasoning": false, "release_date": "2025-12-18", "temperature": true, "tool_call": true }, "doubao-seed-code-preview-251028": { "attachment": true, "cost": { "input": 0.17, "output": 1.14 }, "description": "doubao-seed-code-preview-251028 is an AI model provided by 302ai.", "id": "doubao-seed-code-preview-251028", "last_updated": "2025-11-11", "limit": { "context": 256000, "output": 32000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "doubao-seed-code-preview-251028", "open_weights": false, "reasoning": false, "release_date": "2025-11-11", "temperature": true, "tool_call": true }, "gemini-2.0-flash-lite": { "attachment": true, "cost": { "input": 0.075, "output": 0.3 }, "description": "gemini-2.0-flash-lite is an AI model provided by 302ai.", "family": "gemini-flash-lite", "id": "gemini-2.0-flash-lite", "knowledge": "2024-11", "last_updated": "2025-06-16", "limit": { "context": 2000000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "gemini-2.0-flash-lite", "open_weights": false, "reasoning": false, "release_date": "2025-06-16", "temperature": true, "tool_call": false }, "gemini-2.5-flash": { "attachment": true, "cost": { "input": 0.3, "output": 2.5 }, "description": "gemini-2.5-flash is an AI model provided by 302ai.", "family": "gemini-flash", "id": "gemini-2.5-flash", "knowledge": "2025-01", "last_updated": "2025-06-17", "limit": { "context": 1000000, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "gemini-2.5-flash", "open_weights": false, "reasoning": false, "release_date": "2025-06-17", "temperature": true, "tool_call": true }, "gemini-2.5-flash-image": { "attachment": true, "cost": { "input": 0.3, "output": 30 }, "description": "gemini-2.5-flash-image is an AI model provided by 302ai.", "id": "gemini-2.5-flash-image", "knowledge": "2025-01", "last_updated": "2025-10-08", "limit": { "context": 32768, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "gemini-2.5-flash-image", "open_weights": false, "reasoning": false, "release_date": "2025-10-08", "temperature": true, "tool_call": false }, "gemini-2.5-flash-lite-preview-09-2025": { "attachment": true, "cost": { "input": 0.1, "output": 0.4 }, "description": "gemini-2.5-flash-lite-preview-09-2025 is an AI model provided by 302ai.", "id": "gemini-2.5-flash-lite-preview-09-2025", "knowledge": "2025-01", "last_updated": "2025-09-26", "limit": { "context": 1000000, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "gemini-2.5-flash-lite-preview-09-2025", "open_weights": false, "reasoning": false, "release_date": "2025-09-26", "temperature": true, "tool_call": true }, "gemini-2.5-flash-nothink": { "attachment": true, "cost": { "input": 0.3, "output": 2.5 }, "description": "gemini-2.5-flash-nothink is an AI model provided by 302ai.", "family": "gemini-flash", "id": "gemini-2.5-flash-nothink", "knowledge": "2025-01", "last_updated": "2025-06-24", "limit": { "context": 1000000, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "gemini-2.5-flash-nothink", "open_weights": false, "reasoning": false, "release_date": "2025-06-24", "temperature": true, "tool_call": true }, "gemini-2.5-flash-preview-09-2025": { "attachment": true, "cost": { "input": 0.3, "output": 2.5 }, "description": "gemini-2.5-flash-preview-09-2025 is an AI model provided by 302ai.", "id": "gemini-2.5-flash-preview-09-2025", "knowledge": "2025-01", "last_updated": "2025-09-26", "limit": { "context": 1000000, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "gemini-2.5-flash-preview-09-2025", "open_weights": false, "reasoning": false, "release_date": "2025-09-26", "temperature": true, "tool_call": true }, "gemini-2.5-pro": { "attachment": true, "cost": { "input": 1.25, "output": 10 }, "description": "gemini-2.5-pro is an AI model provided by 302ai.", "family": "gemini-pro", "id": "gemini-2.5-pro", "knowledge": "2025-01", "last_updated": "2025-06-17", "limit": { "context": 1000000, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "gemini-2.5-pro", "open_weights": false, "reasoning": false, "release_date": "2025-06-17", "temperature": true, "tool_call": true }, "gemini-3-flash-preview": { "attachment": true, "cost": { "input": 0.5, "output": 3 }, "description": "gemini-3-flash-preview is an AI model provided by 302ai.", "id": "gemini-3-flash-preview", "knowledge": "2025-06", "last_updated": "2025-12-18", "limit": { "context": 1000000, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "gemini-3-flash-preview", "open_weights": false, "reasoning": false, "release_date": "2025-12-18", "temperature": true, "tool_call": true }, "gemini-3-pro-image-preview": { "attachment": true, "cost": { "input": 2, "output": 120 }, "description": "gemini-3-pro-image-preview is an AI model provided by 302ai.", "id": "gemini-3-pro-image-preview", "knowledge": "2025-06", "last_updated": "2025-11-20", "limit": { "context": 32768, "output": 64000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "gemini-3-pro-image-preview", "open_weights": false, "reasoning": false, "release_date": "2025-11-20", "temperature": true, "tool_call": false }, "gemini-3-pro-preview": { "attachment": true, "cost": { "input": 2, "output": 12 }, "description": "gemini-3-pro-preview is an AI model provided by 302ai.", "id": "gemini-3-pro-preview", "knowledge": "2025-06", "last_updated": "2025-11-19", "limit": { "context": 1000000, "output": 64000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "gemini-3-pro-preview", "open_weights": false, "reasoning": false, "release_date": "2025-11-19", "temperature": true, "tool_call": true }, "gemini-3.1-flash-image-preview": { "attachment": true, "cost": { "input": 0.5, "output": 60 }, "description": "gemini-3.1-flash-image-preview is an AI model provided by 302ai.", "id": "gemini-3.1-flash-image-preview", "knowledge": "2025-01", "last_updated": "2026-02-27", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text", "image" ] }, "name": "gemini-3.1-flash-image-preview", "open_weights": false, "reasoning": false, "release_date": "2026-02-27", "temperature": true, "tool_call": false }, "glm-4.5": { "attachment": false, "cost": { "input": 0.286, "output": 1.142 }, "description": "GLM-4.5 is an AI model provided by 302ai.", "family": "glm", "id": "glm-4.5", "knowledge": "2025-04", "last_updated": "2025-07-29", "limit": { "context": 131072, "output": 98304 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.5", "open_weights": true, "reasoning": true, "release_date": "2025-07-29", "temperature": true, "tool_call": true }, "glm-4.5-air": { "attachment": false, "cost": { "input": 0.1143, "output": 0.286 }, "description": "glm-4.5-air is an AI model provided by 302ai.", "family": "glm-air", "id": "glm-4.5-air", "knowledge": "2025-04", "last_updated": "2025-07-29", "limit": { "context": 131072, "output": 98304 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "glm-4.5-air", "open_weights": true, "reasoning": true, "release_date": "2025-07-29", "temperature": true, "tool_call": true }, "glm-4.5-airx": { "attachment": false, "cost": { "input": 0.572, "output": 1.714 }, "description": "glm-4.5-airx is an AI model provided by 302ai.", "family": "glm", "id": "glm-4.5-airx", "knowledge": "2025-04", "last_updated": "2025-07-29", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "glm-4.5-airx", "open_weights": false, "reasoning": false, "release_date": "2025-07-29", "temperature": true, "tool_call": true }, "glm-4.5-x": { "attachment": false, "cost": { "input": 1.143, "output": 2.29 }, "description": "glm-4.5-x is an AI model provided by 302ai.", "family": "glm", "id": "glm-4.5-x", "knowledge": "2025-04", "last_updated": "2025-07-29", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "glm-4.5-x", "open_weights": false, "reasoning": false, "release_date": "2025-07-29", "temperature": true, "tool_call": true }, "glm-4.5v": { "attachment": true, "cost": { "input": 0.29, "output": 0.86 }, "description": "GLM-4.5V is an AI model provided by 302ai.", "family": "glm", "id": "glm-4.5v", "knowledge": "2025-04", "last_updated": "2025-08-12", "limit": { "context": 64000, "output": 16384 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "GLM-4.5V", "open_weights": true, "reasoning": true, "release_date": "2025-08-12", "temperature": true, "tool_call": true }, "glm-4.6": { "attachment": false, "cost": { "input": 0.286, "output": 1.142 }, "description": "glm-4.6 is an AI model provided by 302ai.", "family": "glm", "id": "glm-4.6", "knowledge": "2025-04", "last_updated": "2025-09-30", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "glm-4.6", "open_weights": true, "reasoning": true, "release_date": "2025-09-30", "temperature": true, "tool_call": true }, "glm-4.6v": { "attachment": true, "cost": { "input": 0.145, "output": 0.43 }, "description": "GLM-4.6V is an AI model provided by 302ai.", "family": "glm", "id": "glm-4.6v", "knowledge": "2025-04", "last_updated": "2025-12-08", "limit": { "context": 128000, "output": 32768 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "GLM-4.6V", "open_weights": true, "reasoning": true, "release_date": "2025-12-08", "temperature": true, "tool_call": true }, "glm-4.7": { "attachment": false, "cost": { "input": 0.286, "output": 1.142 }, "description": "glm-4.7 is an AI model provided by 302ai.", "family": "glm", "id": "glm-4.7", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-04", "last_updated": "2025-12-22", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "glm-4.7", "open_weights": true, "reasoning": true, "release_date": "2025-12-22", "temperature": true, "tool_call": true }, "glm-4.7-flashx": { "attachment": false, "cost": { "input": 0.0715, "output": 0.429 }, "description": "glm-4.7-flashx is an AI model provided by 302ai.", "family": "glm-flash", "id": "glm-4.7-flashx", "knowledge": "2025-04", "last_updated": "2026-01-20", "limit": { "context": 200000, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "glm-4.7-flashx", "open_weights": true, "reasoning": true, "release_date": "2026-01-20", "temperature": true, "tool_call": true }, "glm-5": { "attachment": false, "cost": { "input": 0.6, "output": 2.6 }, "description": "glm-5 is an AI model provided by 302ai.", "family": "glm", "id": "glm-5", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-02-12", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "glm-5", "open_weights": true, "reasoning": true, "release_date": "2026-02-12", "temperature": true, "tool_call": true }, "glm-5-turbo": { "attachment": false, "cost": { "input": 0.72, "output": 3.2 }, "description": "glm-5-turbo is an AI model provided by 302ai.", "family": "glm", "id": "glm-5-turbo", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-03-16", "limit": { "context": 200000, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "glm-5-turbo", "open_weights": false, "reasoning": true, "release_date": "2026-03-16", "structured_output": true, "temperature": true, "tool_call": true }, "glm-5.1": { "attachment": false, "cost": { "input": 0.86, "output": 3.5 }, "description": "glm-5.1 is an AI model provided by 302ai.", "family": "glm", "id": "glm-5.1", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-10", "limit": { "context": 200000, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "glm-5.1", "open_weights": false, "reasoning": true, "release_date": "2026-04-10", "structured_output": true, "temperature": true, "tool_call": true }, "glm-5v-turbo": { "attachment": true, "cost": { "input": 0.72, "output": 3.2 }, "description": "GLM-5V-Turbo is an AI model provided by 302ai.", "family": "glm", "id": "glm-5v-turbo", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-02", "limit": { "context": 200000, "output": 131072 }, "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "name": "GLM-5V-Turbo", "open_weights": false, "reasoning": true, "release_date": "2026-04-02", "temperature": true, "tool_call": true }, "glm-for-coding": { "attachment": false, "cost": { "input": 0.086, "output": 0.343 }, "description": "glm-for-coding is an AI model provided by 302ai.", "family": "glm", "id": "glm-for-coding", "last_updated": "2025-09-30", "limit": { "context": 200000, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "glm-for-coding", "open_weights": false, "reasoning": true, "release_date": "2025-09-30", "temperature": true, "tool_call": true }, "gpt-4.1": { "attachment": true, "cost": { "input": 2, "output": 8 }, "description": "gpt-4.1 is an AI model provided by 302ai.", "family": "gpt", "id": "gpt-4.1", "knowledge": "2024-04", "last_updated": "2025-04-14", "limit": { "context": 1047576, "output": 32768 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "gpt-4.1", "open_weights": false, "reasoning": false, "release_date": "2025-04-14", "structured_output": true, "temperature": true, "tool_call": true }, "gpt-4.1-mini": { "attachment": true, "cost": { "input": 0.4, "output": 1.6 }, "description": "gpt-4.1-mini is an AI model provided by 302ai.", "family": "gpt-mini", "id": "gpt-4.1-mini", "knowledge": "2024-04", "last_updated": "2025-04-14", "limit": { "context": 1047576, "output": 32768 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "gpt-4.1-mini", "open_weights": false, "reasoning": false, "release_date": "2025-04-14", "structured_output": true, "temperature": true, "tool_call": true }, "gpt-4.1-nano": { "attachment": true, "cost": { "input": 0.1, "output": 0.4 }, "description": "gpt-4.1-nano is an AI model provided by 302ai.", "family": "gpt-nano", "id": "gpt-4.1-nano", "knowledge": "2024-04", "last_updated": "2025-04-14", "limit": { "context": 1047576, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "gpt-4.1-nano", "open_weights": false, "reasoning": false, "release_date": "2025-04-14", "structured_output": true, "temperature": true, "tool_call": true }, "gpt-4o": { "attachment": true, "cost": { "input": 2.5, "output": 10 }, "description": "gpt-4o is an AI model provided by 302ai.", "family": "gpt", "id": "gpt-4o", "knowledge": "2023-09", "last_updated": "2024-05-13", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "gpt-4o", "open_weights": false, "reasoning": false, "release_date": "2024-05-13", "structured_output": true, "temperature": true, "tool_call": true }, "gpt-5": { "attachment": true, "cost": { "input": 1.25, "output": 10 }, "description": "gpt-5 is an AI model provided by 302ai.", "family": "gpt", "id": "gpt-5", "knowledge": "2024-09-30", "last_updated": "2025-08-08", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "gpt-5", "open_weights": false, "reasoning": true, "release_date": "2025-08-08", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5-mini": { "attachment": true, "cost": { "input": 0.25, "output": 2 }, "description": "gpt-5-mini is an AI model provided by 302ai.", "family": "gpt-mini", "id": "gpt-5-mini", "knowledge": "2024-05-30", "last_updated": "2025-08-08", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "gpt-5-mini", "open_weights": false, "reasoning": true, "release_date": "2025-08-08", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5-pro": { "attachment": true, "cost": { "input": 15, "output": 120 }, "description": "gpt-5-pro is an AI model provided by 302ai.", "family": "gpt-pro", "id": "gpt-5-pro", "knowledge": "2024-09-30", "last_updated": "2025-10-08", "limit": { "context": 400000, "input": 272000, "output": 272000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "gpt-5-pro", "open_weights": false, "reasoning": true, "release_date": "2025-10-08", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5-thinking": { "attachment": true, "cost": { "input": 1.25, "output": 10 }, "description": "gpt-5-thinking is an AI model provided by 302ai.", "id": "gpt-5-thinking", "knowledge": "2024-10", "last_updated": "2025-08-08", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "gpt-5-thinking", "open_weights": false, "reasoning": true, "release_date": "2025-08-08", "temperature": true, "tool_call": true }, "gpt-5.1": { "attachment": true, "cost": { "input": 1.25, "output": 10 }, "description": "gpt-5.1 is an AI model provided by 302ai.", "family": "gpt", "id": "gpt-5.1", "knowledge": "2024-09-30", "last_updated": "2025-11-14", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "gpt-5.1", "open_weights": false, "reasoning": true, "release_date": "2025-11-14", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.1-chat-latest": { "attachment": true, "cost": { "input": 1.25, "output": 10 }, "description": "gpt-5.1-chat-latest is an AI model provided by 302ai.", "family": "gpt-codex", "id": "gpt-5.1-chat-latest", "knowledge": "2024-09-30", "last_updated": "2025-11-14", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "gpt-5.1-chat-latest", "open_weights": false, "reasoning": true, "release_date": "2025-11-14", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.2": { "attachment": true, "cost": { "input": 1.75, "output": 14 }, "description": "gpt-5.2 is an AI model provided by 302ai.", "family": "gpt", "id": "gpt-5.2", "knowledge": "2025-08-31", "last_updated": "2025-12-12", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "gpt-5.2", "open_weights": false, "reasoning": true, "release_date": "2025-12-12", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.2-chat-latest": { "attachment": true, "cost": { "input": 1.75, "output": 14 }, "description": "gpt-5.2-chat-latest is an AI model provided by 302ai.", "family": "gpt-codex", "id": "gpt-5.2-chat-latest", "knowledge": "2025-08-31", "last_updated": "2025-12-12", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "gpt-5.2-chat-latest", "open_weights": false, "reasoning": true, "release_date": "2025-12-12", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.4": { "attachment": true, "cost": { "cache_read": 0.25, "cache_write": 0, "context_over_200k": { "input": 5, "output": 22.5 }, "input": 2.5, "output": 15, "tiers": [ { "input": 5, "output": 22.5, "tier": { "size": 272000, "type": "context" } } ] }, "description": "gpt-5.4 is an AI model provided by 302ai.", "family": "gpt", "id": "gpt-5.4", "knowledge": "2025-08-31", "last_updated": "2026-03-05", "limit": { "context": 1050000, "input": 922000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "gpt-5.4", "open_weights": false, "reasoning": true, "release_date": "2026-03-05", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.4-mini": { "attachment": true, "cost": { "input": 0.75, "output": 4.5 }, "description": "gpt-5.4-mini is an AI model provided by 302ai.", "family": "gpt-mini", "id": "gpt-5.4-mini", "knowledge": "2025-08-31", "last_updated": "2026-03-19", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "gpt-5.4-mini", "open_weights": false, "reasoning": true, "release_date": "2026-03-19", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.4-mini-2026-03-17": { "attachment": true, "cost": { "input": 0.75, "output": 4.5 }, "description": "gpt-5.4-mini-2026-03-17 is an AI model provided by 302ai.", "family": "gpt-mini", "id": "gpt-5.4-mini-2026-03-17", "knowledge": "2025-08-31", "last_updated": "2026-03-19", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "gpt-5.4-mini-2026-03-17", "open_weights": false, "reasoning": true, "release_date": "2026-03-19", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.4-nano": { "attachment": true, "cost": { "input": 0.2, "output": 1.25 }, "description": "gpt-5.4-nano is an AI model provided by 302ai.", "family": "gpt-nano", "id": "gpt-5.4-nano", "knowledge": "2025-08-31", "last_updated": "2026-03-19", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "gpt-5.4-nano", "open_weights": false, "reasoning": true, "release_date": "2026-03-19", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.4-nano-2026-03-17": { "attachment": true, "cost": { "input": 0.2, "output": 1.25 }, "description": "gpt-5.4-nano-2026-03-17 is an AI model provided by 302ai.", "family": "gpt-nano", "id": "gpt-5.4-nano-2026-03-17", "knowledge": "2025-08-31", "last_updated": "2026-03-19", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "gpt-5.4-nano-2026-03-17", "open_weights": false, "reasoning": true, "release_date": "2026-03-19", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.4-pro": { "attachment": true, "cost": { "cache_read": 0, "cache_write": 0, "context_over_200k": { "input": 60, "output": 270 }, "input": 30, "output": 180, "tiers": [ { "input": 60, "output": 270, "tier": { "size": 272000, "type": "context" } } ] }, "description": "gpt-5.4-pro is an AI model provided by 302ai.", "family": "gpt-pro", "id": "gpt-5.4-pro", "knowledge": "2025-08-31", "last_updated": "2026-03-05", "limit": { "context": 1050000, "input": 922000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "gpt-5.4-pro", "open_weights": false, "reasoning": true, "release_date": "2026-03-05", "structured_output": false, "temperature": false, "tool_call": true }, "grok-4-1-fast-non-reasoning": { "attachment": true, "cost": { "input": 0.2, "output": 0.5 }, "description": "grok-4-1-fast-non-reasoning is an AI model provided by 302ai.", "id": "grok-4-1-fast-non-reasoning", "knowledge": "2025-06", "last_updated": "2025-11-20", "limit": { "context": 2000000, "output": 30000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "grok-4-1-fast-non-reasoning", "open_weights": false, "reasoning": false, "release_date": "2025-11-20", "temperature": true, "tool_call": true }, "grok-4-1-fast-reasoning": { "attachment": true, "cost": { "input": 0.2, "output": 0.5 }, "description": "grok-4-1-fast-reasoning is an AI model provided by 302ai.", "id": "grok-4-1-fast-reasoning", "knowledge": "2025-06", "last_updated": "2025-11-20", "limit": { "context": 2000000, "output": 30000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "grok-4-1-fast-reasoning", "open_weights": false, "reasoning": true, "release_date": "2025-11-20", "temperature": true, "tool_call": true }, "grok-4-fast-non-reasoning": { "attachment": true, "cost": { "input": 0.2, "output": 0.5 }, "description": "grok-4-fast-non-reasoning is an AI model provided by 302ai.", "id": "grok-4-fast-non-reasoning", "knowledge": "2025-06", "last_updated": "2025-09-23", "limit": { "context": 2000000, "output": 30000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "grok-4-fast-non-reasoning", "open_weights": false, "reasoning": false, "release_date": "2025-09-23", "temperature": true, "tool_call": true }, "grok-4-fast-reasoning": { "attachment": true, "cost": { "input": 0.2, "output": 0.5 }, "description": "grok-4-fast-reasoning is an AI model provided by 302ai.", "id": "grok-4-fast-reasoning", "knowledge": "2025-06", "last_updated": "2025-09-23", "limit": { "context": 2000000, "output": 30000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "grok-4-fast-reasoning", "open_weights": false, "reasoning": true, "release_date": "2025-09-23", "temperature": true, "tool_call": true }, "grok-4.1": { "attachment": true, "cost": { "input": 2, "output": 10 }, "description": "grok-4.1 is an AI model provided by 302ai.", "id": "grok-4.1", "knowledge": "2025-06", "last_updated": "2025-11-18", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "grok-4.1", "open_weights": false, "reasoning": false, "release_date": "2025-11-18", "temperature": true, "tool_call": true }, "grok-4.20-beta-0309-non-reasoning": { "attachment": true, "cost": { "input": 2, "output": 6 }, "description": "grok-4.20-beta-0309-non-reasoning is an AI model provided by 302ai.", "id": "grok-4.20-beta-0309-non-reasoning", "last_updated": "2026-03-16", "limit": { "context": 2000000, "output": 30000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "grok-4.20-beta-0309-non-reasoning", "open_weights": false, "reasoning": false, "release_date": "2026-03-16", "temperature": true, "tool_call": true }, "grok-4.20-beta-0309-reasoning": { "attachment": true, "cost": { "input": 2, "output": 6 }, "description": "grok-4.20-beta-0309-reasoning is an AI model provided by 302ai.", "id": "grok-4.20-beta-0309-reasoning", "last_updated": "2026-03-16", "limit": { "context": 2000000, "output": 30000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "grok-4.20-beta-0309-reasoning", "open_weights": false, "reasoning": true, "release_date": "2026-03-16", "temperature": true, "tool_call": true }, "grok-4.20-multi-agent-beta-0309": { "attachment": true, "cost": { "input": 2, "output": 6 }, "description": "grok-4.20-multi-agent-beta-0309 is an AI model provided by 302ai.", "id": "grok-4.20-multi-agent-beta-0309", "last_updated": "2026-03-16", "limit": { "context": 2000000, "output": 30000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "grok-4.20-multi-agent-beta-0309", "open_weights": false, "reasoning": true, "release_date": "2026-03-16", "temperature": true, "tool_call": true }, "kimi-k2-0905-preview": { "attachment": false, "cost": { "input": 0.632, "output": 2.53 }, "description": "kimi-k2-0905-preview is an AI model provided by 302ai.", "id": "kimi-k2-0905-preview", "knowledge": "2025-06", "last_updated": "2025-09-05", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "kimi-k2-0905-preview", "open_weights": false, "reasoning": false, "release_date": "2025-09-05", "temperature": true, "tool_call": true }, "kimi-k2-thinking": { "attachment": false, "cost": { "input": 0.575, "output": 2.3 }, "description": "kimi-k2-thinking is an AI model provided by 302ai.", "id": "kimi-k2-thinking", "knowledge": "2025-06", "last_updated": "2025-09-05", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "kimi-k2-thinking", "open_weights": false, "reasoning": true, "release_date": "2025-09-05", "temperature": true, "tool_call": true }, "kimi-k2-thinking-turbo": { "attachment": false, "cost": { "input": 1.265, "output": 9.119 }, "description": "kimi-k2-thinking-turbo is an AI model provided by 302ai.", "id": "kimi-k2-thinking-turbo", "knowledge": "2025-06", "last_updated": "2025-09-05", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "kimi-k2-thinking-turbo", "open_weights": false, "reasoning": true, "release_date": "2025-09-05", "temperature": true, "tool_call": true }, "ministral-14b-2512": { "attachment": true, "cost": { "input": 0.33, "output": 0.33 }, "description": "ministral-14b-2512 is an AI model provided by 302ai.", "id": "ministral-14b-2512", "knowledge": "2024-12", "last_updated": "2025-12-16", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "ministral-14b-2512", "open_weights": false, "reasoning": false, "release_date": "2025-12-16", "temperature": true, "tool_call": true }, "mistral-large-2512": { "attachment": true, "cost": { "input": 1.1, "output": 3.3 }, "description": "mistral-large-2512 is an AI model provided by 302ai.", "id": "mistral-large-2512", "knowledge": "2024-12", "last_updated": "2025-12-16", "limit": { "context": 128000, "output": 262144 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "mistral-large-2512", "open_weights": false, "reasoning": false, "release_date": "2025-12-16", "temperature": true, "tool_call": true }, "qwen-flash": { "attachment": false, "cost": { "input": 0.022, "output": 0.22 }, "description": "Qwen-Flash is an AI model provided by 302ai.", "id": "qwen-flash", "last_updated": "2025-07-28", "limit": { "context": 1000000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen-Flash", "open_weights": false, "reasoning": false, "release_date": "2025-07-28", "temperature": true, "tool_call": true }, "qwen-max-latest": { "attachment": false, "cost": { "input": 0.343, "output": 1.372 }, "description": "Qwen-Max-Latest is an AI model provided by 302ai.", "family": "qwen", "id": "qwen-max-latest", "knowledge": "2024-11", "last_updated": "2025-01-25", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen-Max-Latest", "open_weights": false, "reasoning": false, "release_date": "2024-04-03", "temperature": true, "tool_call": true }, "qwen-plus": { "attachment": false, "cost": { "input": 0.12, "output": 1.2 }, "description": "Qwen-Plus is an AI model provided by 302ai.", "family": "qwen", "id": "qwen-plus", "knowledge": "2024-10", "last_updated": "2024-07-23", "limit": { "context": 1000000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen-Plus", "open_weights": false, "reasoning": false, "release_date": "2024-07-23", "temperature": true, "tool_call": true }, "qwen3-235b-a22b": { "attachment": false, "cost": { "input": 0.29, "output": 2.86 }, "description": "Qwen3-235B-A22B is an AI model provided by 302ai.", "family": "qwen", "id": "qwen3-235b-a22b", "knowledge": "2025-04", "last_updated": "2025-04-29", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3-235B-A22B", "open_weights": false, "reasoning": false, "release_date": "2025-04-29", "temperature": true, "tool_call": true }, "qwen3-235b-a22b-instruct-2507": { "attachment": false, "cost": { "input": 0.29, "output": 1.143 }, "description": "qwen3-235b-a22b-instruct-2507 is an AI model provided by 302ai.", "id": "qwen3-235b-a22b-instruct-2507", "knowledge": "2025-04", "last_updated": "2025-07-30", "limit": { "context": 128000, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "qwen3-235b-a22b-instruct-2507", "open_weights": false, "reasoning": false, "release_date": "2025-07-30", "temperature": true, "tool_call": true }, "qwen3-30b-a3b": { "attachment": false, "cost": { "input": 0.11, "output": 1.08 }, "description": "Qwen3-30B-A3B is an AI model provided by 302ai.", "family": "qwen", "id": "qwen3-30b-a3b", "knowledge": "2025-04", "last_updated": "2025-04-29", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3-30B-A3B", "open_weights": false, "reasoning": false, "release_date": "2025-04-29", "temperature": true, "tool_call": true }, "qwen3-coder-480b-a35b-instruct": { "attachment": false, "cost": { "input": 0.86, "output": 3.43 }, "description": "qwen3-coder-480b-a35b-instruct is an AI model provided by 302ai.", "id": "qwen3-coder-480b-a35b-instruct", "knowledge": "2025-04", "last_updated": "2025-07-23", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "qwen3-coder-480b-a35b-instruct", "open_weights": false, "reasoning": false, "release_date": "2025-07-23", "temperature": true, "tool_call": true }, "qwen3-max-2025-09-23": { "attachment": false, "cost": { "input": 0.86, "output": 3.43 }, "description": "qwen3-max-2025-09-23 is an AI model provided by 302ai.", "id": "qwen3-max-2025-09-23", "knowledge": "2025-04", "last_updated": "2025-09-24", "limit": { "context": 258048, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "qwen3-max-2025-09-23", "open_weights": false, "reasoning": false, "release_date": "2025-09-24", "temperature": true, "tool_call": true } }, "name": "302.AI", "npm": "@ai-sdk/openai-compatible" }, "abacus": { "api": "https://routellm.abacus.ai/v1", "doc": "https://abacus.ai/help/api", "env": [ "ABACUS_API_KEY" ], "iconURL": "https://models.dev/logos/abacus.svg", "id": "abacus", "models": { "Qwen/QwQ-32B": { "attachment": false, "cost": { "input": 0.4, "output": 0.4 }, "description": "QwQ 32B is an AI model provided by abacus.", "family": "qwen", "id": "Qwen/QwQ-32B", "last_updated": "2024-11-28", "limit": { "context": 32768, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "QwQ 32B", "open_weights": true, "reasoning": true, "release_date": "2024-11-28", "temperature": true, "tool_call": true }, "Qwen/Qwen2.5-72B-Instruct": { "attachment": false, "cost": { "input": 0.11, "output": 0.38 }, "description": "Qwen 2.5 72B Instruct is an AI model provided by abacus.", "family": "qwen", "id": "Qwen/Qwen2.5-72B-Instruct", "last_updated": "2024-09-19", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen 2.5 72B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-09-19", "temperature": true, "tool_call": true }, "Qwen/Qwen3-235B-A22B-Instruct-2507": { "attachment": false, "cost": { "input": 0.13, "output": 0.6 }, "description": "Qwen3 235B A22B Instruct is an AI model provided by abacus.", "family": "qwen", "id": "Qwen/Qwen3-235B-A22B-Instruct-2507", "last_updated": "2025-07-01", "limit": { "context": 262144, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 235B A22B Instruct", "open_weights": true, "reasoning": true, "release_date": "2025-07-01", "temperature": true, "tool_call": true }, "Qwen/Qwen3-32B": { "attachment": false, "cost": { "input": 0.09, "output": 0.29 }, "description": "Qwen3 32B is an AI model provided by abacus.", "family": "qwen", "id": "Qwen/Qwen3-32B", "last_updated": "2025-04-29", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 32B", "open_weights": true, "reasoning": true, "release_date": "2025-04-29", "temperature": true, "tool_call": true }, "Qwen/qwen3-coder-480b-a35b-instruct": { "attachment": false, "cost": { "input": 0.29, "output": 1.2 }, "description": "Qwen3 Coder 480B A35B Instruct is an AI model provided by abacus.", "family": "qwen", "id": "Qwen/qwen3-coder-480b-a35b-instruct", "last_updated": "2025-07-22", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Coder 480B A35B Instruct", "open_weights": true, "reasoning": true, "release_date": "2025-07-22", "temperature": true, "tool_call": true }, "claude-3-7-sonnet-20250219": { "attachment": true, "cost": { "input": 3, "output": 15 }, "description": "Claude Sonnet 3.7 is an AI model provided by abacus.", "family": "claude-sonnet", "id": "claude-3-7-sonnet-20250219", "knowledge": "2024-10-31", "last_updated": "2025-02-19", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 3.7", "open_weights": false, "reasoning": true, "release_date": "2025-02-19", "temperature": true, "tool_call": true }, "claude-haiku-4-5-20251001": { "attachment": true, "cost": { "input": 1, "output": 5 }, "description": "Claude Haiku 4.5 is an AI model provided by abacus.", "family": "claude-haiku", "id": "claude-haiku-4-5-20251001", "knowledge": "2025-02-28", "last_updated": "2025-10-15", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Haiku 4.5", "open_weights": false, "reasoning": true, "release_date": "2025-10-15", "temperature": true, "tool_call": true }, "claude-opus-4-1-20250805": { "attachment": true, "cost": { "input": 15, "output": 75 }, "description": "Claude Opus 4.1 is an AI model provided by abacus.", "family": "claude-opus", "id": "claude-opus-4-1-20250805", "last_updated": "2025-08-05", "limit": { "context": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.1", "open_weights": false, "reasoning": true, "release_date": "2025-08-05", "temperature": true, "tool_call": true }, "claude-opus-4-20250514": { "attachment": true, "cost": { "input": 15, "output": 75 }, "description": "Claude Opus 4 is an AI model provided by abacus.", "family": "claude-opus", "id": "claude-opus-4-20250514", "last_updated": "2025-05-14", "limit": { "context": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4", "open_weights": false, "reasoning": true, "release_date": "2025-05-14", "temperature": true, "tool_call": true }, "claude-opus-4-5-20251101": { "attachment": true, "cost": { "input": 5, "output": 25 }, "description": "Claude Opus 4.5 is an AI model provided by abacus.", "family": "claude-opus", "id": "claude-opus-4-5-20251101", "knowledge": "2025-03-31", "last_updated": "2025-11-01", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.5", "open_weights": false, "reasoning": true, "release_date": "2025-11-01", "temperature": true, "tool_call": true }, "claude-opus-4-6": { "attachment": true, "cost": { "input": 5, "output": 25 }, "description": "Claude Opus 4.6 is an AI model provided by abacus.", "family": "claude-opus", "id": "claude-opus-4-6", "knowledge": "2025-05-31", "last_updated": "2026-02-05", "limit": { "context": 200000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.6", "open_weights": false, "reasoning": true, "release_date": "2026-02-05", "temperature": true, "tool_call": true }, "claude-sonnet-4-20250514": { "attachment": true, "cost": { "input": 3, "output": 15 }, "description": "Claude Sonnet 4 is an AI model provided by abacus.", "family": "claude-sonnet", "id": "claude-sonnet-4-20250514", "last_updated": "2025-05-14", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4", "open_weights": false, "reasoning": true, "release_date": "2025-05-14", "temperature": true, "tool_call": true }, "claude-sonnet-4-5-20250929": { "attachment": true, "cost": { "input": 3, "output": 15 }, "description": "Claude Sonnet 4.5 is an AI model provided by abacus.", "family": "claude-sonnet", "id": "claude-sonnet-4-5-20250929", "knowledge": "2025-07-31", "last_updated": "2025-09-29", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.5", "open_weights": false, "reasoning": true, "release_date": "2025-09-29", "temperature": true, "tool_call": true }, "claude-sonnet-4-6": { "attachment": true, "cost": { "input": 3, "output": 15 }, "description": "Claude Sonnet 4.6 is an AI model provided by abacus.", "family": "claude-sonnet", "id": "claude-sonnet-4-6", "knowledge": "2025-08-31", "last_updated": "2026-02-17", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.6", "open_weights": false, "reasoning": true, "release_date": "2026-02-17", "temperature": true, "tool_call": true }, "deepseek-ai/DeepSeek-R1": { "attachment": false, "cost": { "input": 3, "output": 7 }, "description": "DeepSeek R1 is an AI model provided by abacus.", "family": "deepseek-thinking", "id": "deepseek-ai/DeepSeek-R1", "last_updated": "2025-01-20", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek R1", "open_weights": true, "reasoning": true, "release_date": "2025-01-20", "temperature": true, "tool_call": true }, "deepseek-ai/DeepSeek-V3.1-Terminus": { "attachment": false, "cost": { "input": 0.27, "output": 1 }, "description": "DeepSeek V3.1 Terminus is an AI model provided by abacus.", "family": "deepseek", "id": "deepseek-ai/DeepSeek-V3.1-Terminus", "last_updated": "2025-06-01", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3.1 Terminus", "open_weights": true, "reasoning": true, "release_date": "2025-06-01", "temperature": true, "tool_call": true }, "deepseek-ai/DeepSeek-V3.2": { "attachment": false, "cost": { "input": 0.27, "output": 0.4 }, "description": "DeepSeek V3.2 is an AI model provided by abacus.", "family": "deepseek", "id": "deepseek-ai/DeepSeek-V3.2", "last_updated": "2025-06-15", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3.2", "open_weights": true, "reasoning": true, "release_date": "2025-06-15", "temperature": true, "tool_call": true }, "deepseek/deepseek-v3.1": { "attachment": false, "cost": { "input": 0.55, "output": 1.66 }, "description": "DeepSeek V3.1 is an AI model provided by abacus.", "family": "deepseek", "id": "deepseek/deepseek-v3.1", "last_updated": "2025-01-20", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3.1", "open_weights": true, "reasoning": true, "release_date": "2025-01-20", "temperature": true, "tool_call": true }, "gemini-2.5-flash": { "attachment": true, "cost": { "input": 0.3, "output": 2.5 }, "description": "Gemini 2.5 Flash is an AI model provided by abacus.", "family": "gemini-flash", "id": "gemini-2.5-flash", "knowledge": "2025-01", "last_updated": "2025-06-05", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Flash", "open_weights": false, "reasoning": true, "release_date": "2025-03-20", "temperature": true, "tool_call": true }, "gemini-2.5-pro": { "attachment": true, "cost": { "input": 1.25, "output": 10 }, "description": "Gemini 2.5 Pro is an AI model provided by abacus.", "family": "gemini-pro", "id": "gemini-2.5-pro", "knowledge": "2025-01", "last_updated": "2025-03-25", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Pro", "open_weights": false, "reasoning": true, "release_date": "2025-03-25", "temperature": true, "tool_call": true }, "gemini-3-flash-preview": { "attachment": true, "cost": { "input": 0.5, "output": 3 }, "description": "Gemini 3 Flash Preview is an AI model provided by abacus.", "family": "gemini-flash", "id": "gemini-3-flash-preview", "knowledge": "2025-01", "last_updated": "2025-12-17", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 3 Flash Preview", "open_weights": false, "reasoning": true, "release_date": "2025-12-17", "temperature": true, "tool_call": true }, "gemini-3.1-flash-lite-preview": { "attachment": true, "cost": { "cache_read": 0.025, "cache_write": 1, "input": 0.25, "output": 1.5 }, "description": "Gemini 3.1 Flash Lite Preview is an AI model provided by abacus.", "family": "gemini-flash", "id": "gemini-3.1-flash-lite-preview", "last_updated": "2026-03-01", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 3.1 Flash Lite Preview", "open_weights": false, "reasoning": true, "release_date": "2026-03-01", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-3.1-pro-preview": { "attachment": true, "cost": { "input": 2, "output": 12 }, "description": "Gemini 3.1 Pro Preview is an AI model provided by abacus.", "family": "gemini-pro", "id": "gemini-3.1-pro-preview", "knowledge": "2025-01", "last_updated": "2026-02-19", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "name": "Gemini 3.1 Pro Preview", "open_weights": false, "reasoning": true, "release_date": "2026-02-19", "structured_output": true, "temperature": true, "tool_call": true }, "gpt-4.1": { "attachment": true, "cost": { "input": 2, "output": 8 }, "description": "GPT-4.1 is an AI model provided by abacus.", "family": "gpt", "id": "gpt-4.1", "knowledge": "2024-04", "last_updated": "2025-04-14", "limit": { "context": 1047576, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4.1", "open_weights": false, "reasoning": false, "release_date": "2025-04-14", "temperature": true, "tool_call": true }, "gpt-4.1-mini": { "attachment": true, "cost": { "input": 0.4, "output": 1.6 }, "description": "GPT-4.1 Mini is an AI model provided by abacus.", "family": "gpt", "id": "gpt-4.1-mini", "knowledge": "2024-04", "last_updated": "2025-04-14", "limit": { "context": 1047576, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4.1 Mini", "open_weights": false, "reasoning": false, "release_date": "2025-04-14", "temperature": true, "tool_call": true }, "gpt-4.1-nano": { "attachment": true, "cost": { "input": 0.1, "output": 0.4 }, "description": "GPT-4.1 Nano is an AI model provided by abacus.", "family": "gpt", "id": "gpt-4.1-nano", "knowledge": "2024-04", "last_updated": "2025-04-14", "limit": { "context": 1047576, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4.1 Nano", "open_weights": false, "reasoning": false, "release_date": "2025-04-14", "temperature": true, "tool_call": true }, "gpt-4o-2024-11-20": { "attachment": true, "cost": { "input": 2.5, "output": 10 }, "description": "GPT-4o (2024-11-20) is an AI model provided by abacus.", "family": "gpt", "id": "gpt-4o-2024-11-20", "knowledge": "2024-10", "last_updated": "2024-11-20", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image", "audio" ], "output": [ "text" ] }, "name": "GPT-4o (2024-11-20)", "open_weights": false, "reasoning": false, "release_date": "2024-11-20", "temperature": true, "tool_call": true }, "gpt-4o-mini": { "attachment": true, "cost": { "input": 0.15, "output": 0.6 }, "description": "GPT-4o Mini is an AI model provided by abacus.", "family": "gpt", "id": "gpt-4o-mini", "knowledge": "2024-04", "last_updated": "2024-07-18", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4o Mini", "open_weights": false, "reasoning": false, "release_date": "2024-07-18", "temperature": true, "tool_call": true }, "gpt-5": { "attachment": true, "cost": { "input": 1.25, "output": 10 }, "description": "GPT-5 is an AI model provided by abacus.", "family": "gpt", "id": "gpt-5", "knowledge": "2024-09-30", "last_updated": "2025-08-07", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "temperature": false, "tool_call": true }, "gpt-5-codex": { "attachment": false, "cost": { "input": 1.25, "output": 10 }, "description": "GPT-5 Codex is an AI model provided by abacus.", "family": "gpt", "id": "gpt-5-codex", "knowledge": "2024-09-30", "last_updated": "2025-09-15", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5 Codex", "open_weights": false, "reasoning": true, "release_date": "2025-09-15", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5-mini": { "attachment": true, "cost": { "input": 0.25, "output": 2 }, "description": "GPT-5 Mini is an AI model provided by abacus.", "family": "gpt-mini", "id": "gpt-5-mini", "knowledge": "2024-05-30", "last_updated": "2025-08-07", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5 Mini", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "temperature": false, "tool_call": true }, "gpt-5-nano": { "attachment": true, "cost": { "input": 0.05, "output": 0.4 }, "description": "GPT-5 Nano is an AI model provided by abacus.", "family": "gpt-nano", "id": "gpt-5-nano", "knowledge": "2024-05-30", "last_updated": "2025-08-07", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5 Nano", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "temperature": false, "tool_call": true }, "gpt-5.1": { "attachment": true, "cost": { "input": 1.25, "output": 10 }, "description": "GPT-5.1 is an AI model provided by abacus.", "family": "gpt", "id": "gpt-5.1", "knowledge": "2024-09-30", "last_updated": "2025-11-13", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.1", "open_weights": false, "reasoning": true, "release_date": "2025-11-13", "temperature": false, "tool_call": true }, "gpt-5.1-chat-latest": { "attachment": true, "cost": { "input": 1.25, "output": 10 }, "description": "GPT-5.1 Chat Latest is an AI model provided by abacus.", "family": "gpt", "id": "gpt-5.1-chat-latest", "knowledge": "2024-09-30", "last_updated": "2025-11-13", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.1 Chat Latest", "open_weights": false, "reasoning": true, "release_date": "2025-11-13", "temperature": false, "tool_call": true }, "gpt-5.1-codex": { "attachment": true, "cost": { "input": 1.25, "output": 10 }, "description": "GPT-5.1 Codex is an AI model provided by abacus.", "family": "gpt", "id": "gpt-5.1-codex", "knowledge": "2024-09-30", "last_updated": "2025-11-13", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.1 Codex", "open_weights": false, "reasoning": true, "release_date": "2025-11-13", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.1-codex-max": { "attachment": true, "cost": { "input": 1.25, "output": 10 }, "description": "GPT-5.1 Codex Max is an AI model provided by abacus.", "family": "gpt", "id": "gpt-5.1-codex-max", "knowledge": "2024-09-30", "last_updated": "2025-11-13", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.1 Codex Max", "open_weights": false, "reasoning": true, "release_date": "2025-11-13", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.2": { "attachment": true, "cost": { "input": 1.75, "output": 14 }, "description": "GPT-5.2 is an AI model provided by abacus.", "family": "gpt", "id": "gpt-5.2", "knowledge": "2025-08-31", "last_updated": "2025-12-11", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.2", "open_weights": false, "reasoning": true, "release_date": "2025-12-11", "temperature": false, "tool_call": true }, "gpt-5.2-chat-latest": { "attachment": true, "cost": { "input": 1.75, "output": 14 }, "description": "GPT-5.2 Chat Latest is an AI model provided by abacus.", "family": "gpt", "id": "gpt-5.2-chat-latest", "knowledge": "2024-09-30", "last_updated": "2026-01-01", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.2 Chat Latest", "open_weights": false, "reasoning": true, "release_date": "2026-01-01", "temperature": true, "tool_call": true }, "gpt-5.2-codex": { "attachment": true, "cost": { "input": 1.75, "output": 14 }, "description": "GPT-5.2 Codex is an AI model provided by abacus.", "family": "gpt", "id": "gpt-5.2-codex", "knowledge": "2025-08-31", "last_updated": "2025-12-11", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.2 Codex", "open_weights": false, "reasoning": true, "release_date": "2025-12-11", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.3-chat-latest": { "attachment": true, "cost": { "input": 1.75, "output": 14 }, "description": "GPT-5.3 Chat Latest is an AI model provided by abacus.", "family": "gpt", "id": "gpt-5.3-chat-latest", "last_updated": "2026-03-01", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.3 Chat Latest", "open_weights": false, "reasoning": true, "release_date": "2026-03-01", "temperature": true, "tool_call": true }, "gpt-5.3-codex": { "attachment": true, "cost": { "input": 1.75, "output": 14 }, "description": "GPT-5.3 Codex is an AI model provided by abacus.", "family": "gpt", "id": "gpt-5.3-codex", "knowledge": "2025-08-31", "last_updated": "2026-02-05", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.3 Codex", "open_weights": false, "reasoning": true, "release_date": "2026-02-05", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.3-codex-xhigh": { "attachment": true, "cost": { "input": 1.75, "output": 14 }, "description": "GPT-5.3 Codex XHigh is an AI model provided by abacus.", "family": "gpt", "id": "gpt-5.3-codex-xhigh", "knowledge": "2025-08-31", "last_updated": "2026-02-05", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.3 Codex XHigh", "open_weights": false, "reasoning": true, "release_date": "2026-02-05", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.4": { "attachment": true, "cost": { "input": 2.5, "output": 15 }, "description": "GPT-5.4 is an AI model provided by abacus.", "family": "gpt", "id": "gpt-5.4", "knowledge": "2025-08-31", "last_updated": "2026-03-05", "limit": { "context": 1050000, "input": 922000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.4", "open_weights": false, "reasoning": true, "release_date": "2026-03-05", "structured_output": true, "temperature": false, "tool_call": true }, "grok-4-0709": { "attachment": true, "cost": { "input": 3, "output": 15 }, "description": "Grok 4 is an AI model provided by abacus.", "family": "grok", "id": "grok-4-0709", "last_updated": "2025-07-09", "limit": { "context": 256000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 4", "open_weights": false, "reasoning": true, "release_date": "2025-07-09", "temperature": true, "tool_call": true }, "grok-4-1-fast-non-reasoning": { "attachment": true, "cost": { "input": 0.2, "output": 0.5 }, "description": "Grok 4.1 Fast (Non-Reasoning) is an AI model provided by abacus.", "family": "grok", "id": "grok-4-1-fast-non-reasoning", "last_updated": "2025-11-17", "limit": { "context": 2000000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 4.1 Fast (Non-Reasoning)", "open_weights": false, "reasoning": false, "release_date": "2025-11-17", "temperature": true, "tool_call": true }, "grok-4-fast-non-reasoning": { "attachment": true, "cost": { "input": 0.2, "output": 0.5 }, "description": "Grok 4 Fast (Non-Reasoning) is an AI model provided by abacus.", "family": "grok", "id": "grok-4-fast-non-reasoning", "last_updated": "2025-07-09", "limit": { "context": 2000000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 4 Fast (Non-Reasoning)", "open_weights": false, "reasoning": false, "release_date": "2025-07-09", "temperature": true, "tool_call": true }, "grok-code-fast-1": { "attachment": true, "cost": { "input": 0.2, "output": 1.5 }, "description": "Grok Code Fast 1 is an AI model provided by abacus.", "family": "grok", "id": "grok-code-fast-1", "last_updated": "2025-09-01", "limit": { "context": 256000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok Code Fast 1", "open_weights": false, "reasoning": false, "release_date": "2025-09-01", "temperature": true, "tool_call": true }, "kimi-k2-turbo-preview": { "attachment": false, "cost": { "input": 0.15, "output": 8 }, "description": "Kimi K2 Turbo Preview is an AI model provided by abacus.", "family": "kimi", "id": "kimi-k2-turbo-preview", "last_updated": "2025-07-08", "limit": { "context": 256000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 Turbo Preview", "open_weights": false, "reasoning": false, "release_date": "2025-07-08", "temperature": true, "tool_call": true }, "kimi-k2.5": { "attachment": false, "cost": { "input": 0.6, "output": 3 }, "description": "Kimi K2.5 is an AI model provided by abacus.", "family": "kimi", "id": "kimi-k2.5", "knowledge": "2025-01", "last_updated": "2026-01", "limit": { "context": 262144, "output": 32768 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Kimi K2.5", "open_weights": true, "reasoning": true, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "llama-3.3-70b-versatile": { "attachment": false, "cost": { "input": 0.59, "output": 0.79 }, "description": "Llama 3.3 70B Versatile is an AI model provided by abacus.", "family": "llama", "id": "llama-3.3-70b-versatile", "last_updated": "2024-12-06", "limit": { "context": 128000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B Versatile", "open_weights": true, "reasoning": false, "release_date": "2024-12-06", "temperature": true, "tool_call": true }, "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { "attachment": true, "cost": { "input": 0.14, "output": 0.59 }, "description": "Llama 4 Maverick 17B 128E Instruct FP8 is an AI model provided by abacus.", "family": "llama", "id": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8", "knowledge": "2024-08", "last_updated": "2025-04-05", "limit": { "context": 1000000, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Llama 4 Maverick 17B 128E Instruct FP8", "open_weights": true, "reasoning": false, "release_date": "2025-04-05", "temperature": true, "tool_call": true }, "meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo": { "attachment": false, "cost": { "input": 3.5, "output": 3.5 }, "description": "Llama 3.1 405B Instruct Turbo is an AI model provided by abacus.", "family": "llama", "id": "meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo", "last_updated": "2024-07-23", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.1 405B Instruct Turbo", "open_weights": true, "reasoning": false, "release_date": "2024-07-23", "temperature": true, "tool_call": true }, "meta-llama/Meta-Llama-3.1-8B-Instruct": { "attachment": false, "cost": { "input": 0.02, "output": 0.05 }, "description": "Llama 3.1 8B Instruct is an AI model provided by abacus.", "family": "llama", "id": "meta-llama/Meta-Llama-3.1-8B-Instruct", "last_updated": "2024-07-23", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.1 8B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-07-23", "temperature": true, "tool_call": true }, "o3": { "attachment": true, "cost": { "input": 2, "output": 8 }, "description": "o3 is an AI model provided by abacus.", "family": "o", "id": "o3", "knowledge": "2024-05", "last_updated": "2025-04-16", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "o3", "open_weights": false, "reasoning": true, "release_date": "2025-04-16", "temperature": false, "tool_call": true }, "o3-mini": { "attachment": false, "cost": { "input": 1.1, "output": 4.4 }, "description": "o3-mini is an AI model provided by abacus.", "family": "o-mini", "id": "o3-mini", "knowledge": "2024-05", "last_updated": "2025-01-29", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "o3-mini", "open_weights": false, "reasoning": true, "release_date": "2024-12-20", "temperature": false, "tool_call": true }, "o3-pro": { "attachment": true, "cost": { "input": 20, "output": 40 }, "description": "o3-pro is an AI model provided by abacus.", "family": "o-pro", "id": "o3-pro", "knowledge": "2024-05", "last_updated": "2025-06-10", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "o3-pro", "open_weights": false, "reasoning": true, "release_date": "2025-06-10", "temperature": false, "tool_call": true }, "o4-mini": { "attachment": true, "cost": { "input": 1.1, "output": 4.4 }, "description": "o4-mini is an AI model provided by abacus.", "family": "o-mini", "id": "o4-mini", "knowledge": "2024-05", "last_updated": "2025-04-16", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "o4-mini", "open_weights": false, "reasoning": true, "release_date": "2025-04-16", "temperature": false, "tool_call": true }, "openai/gpt-oss-120b": { "attachment": true, "cost": { "input": 0.08, "output": 0.44 }, "description": "GPT-OSS 120B is an AI model provided by abacus.", "family": "gpt-oss", "id": "openai/gpt-oss-120b", "last_updated": "2025-08-05", "limit": { "context": 128000, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-OSS 120B", "open_weights": true, "reasoning": true, "release_date": "2025-08-05", "temperature": true, "tool_call": true }, "qwen-2.5-coder-32b": { "attachment": false, "cost": { "input": 0.79, "output": 0.79 }, "description": "Qwen 2.5 Coder 32B is an AI model provided by abacus.", "family": "qwen", "id": "qwen-2.5-coder-32b", "last_updated": "2024-11-11", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen 2.5 Coder 32B", "open_weights": true, "reasoning": false, "release_date": "2024-11-11", "temperature": true, "tool_call": true }, "qwen3-max": { "attachment": false, "cost": { "input": 1.2, "output": 6 }, "description": "Qwen3 Max is an AI model provided by abacus.", "family": "qwen", "id": "qwen3-max", "last_updated": "2025-05-28", "limit": { "context": 131072, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Max", "open_weights": false, "reasoning": true, "release_date": "2025-05-28", "temperature": true, "tool_call": true }, "route-llm": { "attachment": true, "cost": { "input": 3, "output": 15 }, "description": "Route LLM is an AI model provided by abacus.", "family": "gpt", "id": "route-llm", "knowledge": "2024-10", "last_updated": "2024-01-01", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Route LLM", "open_weights": false, "reasoning": false, "release_date": "2024-01-01", "temperature": true, "tool_call": true }, "zai-org/glm-4.5": { "attachment": false, "cost": { "input": 0.6, "output": 2.2 }, "description": "GLM-4.5 is an AI model provided by abacus.", "family": "glm", "id": "zai-org/glm-4.5", "last_updated": "2025-07-28", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.5", "open_weights": true, "reasoning": true, "release_date": "2025-07-28", "temperature": true, "tool_call": true }, "zai-org/glm-4.6": { "attachment": false, "cost": { "input": 0.6, "output": 2.2 }, "description": "GLM-4.6 is an AI model provided by abacus.", "family": "glm", "id": "zai-org/glm-4.6", "last_updated": "2025-03-01", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.6", "open_weights": true, "reasoning": false, "release_date": "2025-03-01", "temperature": true, "tool_call": true }, "zai-org/glm-4.7": { "attachment": false, "cost": { "input": 0.6, "output": 2.2 }, "description": "GLM-4.7 is an AI model provided by abacus.", "family": "glm", "id": "zai-org/glm-4.7", "last_updated": "2025-06-01", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.7", "open_weights": true, "reasoning": false, "release_date": "2025-06-01", "temperature": true, "tool_call": true }, "zai-org/glm-5": { "attachment": false, "cost": { "input": 1, "output": 3.2 }, "description": "GLM-5 is an AI model provided by abacus.", "family": "glm", "id": "zai-org/glm-5", "last_updated": "2026-02-11", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5", "open_weights": true, "reasoning": true, "release_date": "2026-02-11", "temperature": true, "tool_call": true } }, "name": "Abacus", "npm": "@ai-sdk/openai-compatible" }, "abliteration-ai": { "api": "https://api.abliteration.ai/v1", "doc": "https://docs.abliteration.ai/models", "env": [ "ABLIT_KEY" ], "iconURL": "https://models.dev/logos/abliteration-ai.svg", "id": "abliteration-ai", "models": { "abliterated-model": { "attachment": true, "cost": { "input": 3, "output": 3 }, "description": "Abliterated Model is an AI model provided by abliteration-ai.", "id": "abliterated-model", "last_updated": "2026-01-06", "limit": { "context": 150000, "input": 150000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Abliterated Model", "open_weights": true, "reasoning": false, "release_date": "2026-01-06", "structured_output": false, "temperature": true, "tool_call": true } }, "name": "abliteration.ai", "npm": "@ai-sdk/openai-compatible" }, "aihubmix": { "doc": "https://docs.aihubmix.com", "env": [ "AIHUBMIX_API_KEY" ], "iconURL": "https://models.dev/logos/aihubmix.svg", "id": "aihubmix", "models": { "alicloud-deepseek-v4-flash": { "attachment": false, "cost": { "cache_read": 0.028, "input": 0.14, "output": 0.28 }, "description": "DeepSeek V4 Flash (Alibaba Cloud) is an AI model provided by aihubmix.", "family": "deepseek-flash", "id": "alicloud-deepseek-v4-flash", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-05", "last_updated": "2026-04-24", "limit": { "context": 1000000, "output": 384000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V4 Flash (Alibaba Cloud)", "open_weights": true, "reasoning": true, "release_date": "2026-04-24", "structured_output": true, "temperature": true, "tool_call": true }, "alicloud-deepseek-v4-pro": { "attachment": false, "cost": { "cache_read": 0.13, "input": 1.69, "output": 3.38 }, "description": "DeepSeek V4 Pro (Alibaba Cloud) is an AI model provided by aihubmix.", "family": "deepseek-thinking", "id": "alicloud-deepseek-v4-pro", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-05", "last_updated": "2026-04-24", "limit": { "context": 1000000, "output": 384000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V4 Pro (Alibaba Cloud)", "open_weights": true, "reasoning": true, "release_date": "2026-04-24", "structured_output": true, "temperature": true, "tool_call": true }, "alicloud-glm-5.1": { "attachment": false, "cost": { "cache_read": 0.169, "cache_write": 1.05625, "input": 0.84, "output": 3.38 }, "description": "GLM-5.1 (Alibaba Cloud) is an AI model provided by aihubmix.", "family": "glm", "id": "alicloud-glm-5.1", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-03-27", "limit": { "context": 200000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5.1 (Alibaba Cloud)", "open_weights": true, "reasoning": true, "release_date": "2026-03-27", "structured_output": true, "temperature": true, "tool_call": true }, "claude-opus-4-6": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "context_over_200k": { "cache_read": 1, "cache_write": 12.5, "input": 10, "output": 37.5 }, "input": 5, "output": 25, "tiers": [ { "cache_read": 1, "cache_write": 12.5, "input": 10, "output": 37.5, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Claude Opus 4.6 is an AI model provided by aihubmix.", "family": "claude-opus", "id": "claude-opus-4-6", "interleaved": true, "knowledge": "2025-05-31", "last_updated": "2026-03-13", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.6", "open_weights": false, "reasoning": true, "release_date": "2026-02-05", "structured_output": true, "temperature": true, "tool_call": true }, "claude-opus-4-6-think": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "context_over_200k": { "cache_read": 1, "cache_write": 12.5, "input": 10, "output": 37.5 }, "input": 5, "output": 25, "tiers": [ { "cache_read": 1, "cache_write": 12.5, "input": 10, "output": 37.5, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Claude Opus 4.6 Thinking is an AI model provided by aihubmix.", "family": "claude-opus", "id": "claude-opus-4-6-think", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-05-31", "last_updated": "2026-03-13", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.6 Thinking", "open_weights": false, "reasoning": true, "release_date": "2026-02-05", "structured_output": true, "temperature": true, "tool_call": true }, "claude-opus-4-7": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "context_over_200k": { "cache_read": 1, "cache_write": 12.5, "input": 10, "output": 37.5 }, "input": 5, "output": 25, "tiers": [ { "cache_read": 1, "cache_write": 12.5, "input": 10, "output": 37.5, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Claude Opus 4.7 is an AI model provided by aihubmix.", "family": "claude-opus", "id": "claude-opus-4-7", "interleaved": true, "knowledge": "2026-01-31", "last_updated": "2026-04-16", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.7", "open_weights": false, "reasoning": true, "release_date": "2026-04-16", "structured_output": true, "temperature": false, "tool_call": true }, "claude-opus-4-7-think": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "context_over_200k": { "cache_read": 1, "cache_write": 12.5, "input": 10, "output": 37.5 }, "input": 5, "output": 25, "tiers": [ { "cache_read": 1, "cache_write": 12.5, "input": 10, "output": 37.5, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Claude Opus 4.7 Thinking is an AI model provided by aihubmix.", "family": "claude-opus", "id": "claude-opus-4-7-think", "interleaved": { "field": "reasoning_content" }, "knowledge": "2026-01-31", "last_updated": "2026-04-16", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.7 Thinking", "open_weights": false, "reasoning": true, "release_date": "2026-04-16", "structured_output": true, "temperature": false, "tool_call": true }, "claude-sonnet-4-6": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "context_over_200k": { "cache_read": 0.6, "cache_write": 7.5, "input": 6, "output": 22.5 }, "input": 3, "output": 15, "tiers": [ { "cache_read": 0.6, "cache_write": 7.5, "input": 6, "output": 22.5, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Claude Sonnet 4.6 is an AI model provided by aihubmix.", "family": "claude-sonnet", "id": "claude-sonnet-4-6", "interleaved": true, "knowledge": "2025-08-31", "last_updated": "2026-03-13", "limit": { "context": 1000000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.6", "open_weights": false, "reasoning": true, "release_date": "2026-02-17", "structured_output": true, "temperature": true, "tool_call": true }, "claude-sonnet-4-6-think": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "context_over_200k": { "cache_read": 0.6, "cache_write": 7.5, "input": 6, "output": 22.5 }, "input": 3, "output": 15, "tiers": [ { "cache_read": 0.6, "cache_write": 7.5, "input": 6, "output": 22.5, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Claude Sonnet 4.6 Thinking is an AI model provided by aihubmix.", "family": "claude-sonnet", "id": "claude-sonnet-4-6-think", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-08-31", "last_updated": "2026-03-13", "limit": { "context": 1000000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.6 Thinking", "open_weights": false, "reasoning": true, "release_date": "2026-02-17", "structured_output": true, "temperature": true, "tool_call": true }, "coding-glm-5.1": { "attachment": false, "cost": { "cache_read": 0.013, "input": 0.06, "output": 0.22 }, "description": "Coding GLM 5.1 is an AI model provided by aihubmix.", "family": "glm", "id": "coding-glm-5.1", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-11", "limit": { "context": 200000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Coding GLM 5.1", "open_weights": true, "reasoning": true, "release_date": "2026-04-11", "structured_output": true, "temperature": true, "tool_call": true }, "coding-glm-5.1-free": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Coding GLM 5.1 (free) is an AI model provided by aihubmix.", "family": "glm-free", "id": "coding-glm-5.1-free", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-11", "limit": { "context": 200000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Coding GLM 5.1 (free)", "open_weights": true, "reasoning": true, "release_date": "2026-04-11", "structured_output": true, "temperature": true, "tool_call": true }, "coding-minimax-m2.7": { "attachment": false, "cost": { "input": 0.2, "output": 0.2 }, "description": "Coding MiniMax M2.7 is an AI model provided by aihubmix.", "family": "minimax", "id": "coding-minimax-m2.7", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-03-18", "limit": { "context": 204800, "output": 128100 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Coding MiniMax M2.7", "open_weights": true, "reasoning": true, "release_date": "2026-03-18", "structured_output": true, "temperature": true, "tool_call": true }, "coding-minimax-m2.7-free": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Coding MiniMax M2.7 (Free) is an AI model provided by aihubmix.", "family": "minimax-free", "id": "coding-minimax-m2.7-free", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-03-18", "limit": { "context": 204800, "output": 128100 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Coding MiniMax M2.7 (Free)", "open_weights": true, "reasoning": true, "release_date": "2026-03-18", "structured_output": true, "temperature": true, "tool_call": true }, "coding-minimax-m2.7-highspeed": { "attachment": false, "cost": { "input": 0.2, "output": 0.2 }, "description": "Coding MiniMax M2.7 Highspeed is an AI model provided by aihubmix.", "family": "minimax", "id": "coding-minimax-m2.7-highspeed", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-03-18", "limit": { "context": 204800, "output": 128100 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Coding MiniMax M2.7 Highspeed", "open_weights": true, "reasoning": true, "release_date": "2026-03-18", "structured_output": true, "temperature": true, "tool_call": true }, "coding-xiaomi-mimo-v2.5": { "attachment": true, "cost": { "cache_read": 0.016, "context_over_200k": { "cache_read": 0.032, "input": 0.16, "output": 0.8 }, "input": 0.08, "output": 0.4, "tiers": [ { "cache_read": 0.032, "input": 0.16, "output": 0.8, "tier": { "size": 256000, "type": "context" } } ] }, "description": "Coding Xiaomi MiMo-V2.5 is an AI model provided by aihubmix.", "family": "mimo-v2.5", "id": "coding-xiaomi-mimo-v2.5", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-12", "last_updated": "2026-05-13", "limit": { "context": 1048576, "output": 131072 }, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "name": "Coding Xiaomi MiMo-V2.5", "open_weights": true, "reasoning": true, "release_date": "2026-04-22", "temperature": true, "tool_call": true }, "coding-xiaomi-mimo-v2.5-pro": { "attachment": false, "cost": { "cache_read": 0.04, "context_over_200k": { "cache_read": 0.08, "input": 0.4, "output": 1.2 }, "input": 0.2, "output": 0.6, "tiers": [ { "cache_read": 0.08, "input": 0.4, "output": 1.2, "tier": { "size": 256000, "type": "context" } } ] }, "description": "Coding Xiaomi MiMo-V2.5-Pro is an AI model provided by aihubmix.", "family": "mimo-v2.5-pro", "id": "coding-xiaomi-mimo-v2.5-pro", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-12", "last_updated": "2026-05-13", "limit": { "context": 1048576, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Coding Xiaomi MiMo-V2.5-Pro", "open_weights": true, "reasoning": true, "release_date": "2026-04-22", "temperature": true, "tool_call": true }, "deep-deepseek-v4-flash": { "attachment": false, "cost": { "cache_read": 0.0308, "input": 0.154, "output": 0.308 }, "description": "DeepSeek V4 Flash (DeepSeek) is an AI model provided by aihubmix.", "family": "deepseek-flash", "id": "deep-deepseek-v4-flash", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-05", "last_updated": "2026-04-24", "limit": { "context": 1000000, "output": 384000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V4 Flash (DeepSeek)", "open_weights": true, "reasoning": true, "release_date": "2026-04-24", "structured_output": true, "temperature": true, "tool_call": true }, "deep-deepseek-v4-pro": { "attachment": false, "cost": { "cache_read": 0.004302, "input": 0.478, "output": 0.956 }, "description": "DeepSeek V4 Pro (DeepSeek) is an AI model provided by aihubmix.", "family": "deepseek-thinking", "id": "deep-deepseek-v4-pro", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-05", "last_updated": "2026-04-24", "limit": { "context": 1000000, "output": 384000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V4 Pro (DeepSeek)", "open_weights": true, "reasoning": true, "release_date": "2026-04-24", "structured_output": true, "temperature": true, "tool_call": true }, "doubao-seed-2-0-code-preview": { "attachment": true, "cost": { "cache_read": 0.09644, "input": 0.48, "output": 2.41, "tiers": [ { "cache_read": 0.144656, "input": 0.72, "output": 3.62, "tier": { "size": 32000, "type": "context" } }, { "cache_read": 0.28932, "input": 1.45, "output": 7.23, "tier": { "size": 128000, "type": "context" } } ] }, "description": "Doubao Seed 2.0 Code Preview is an AI model provided by aihubmix.", "family": "seed", "id": "doubao-seed-2-0-code-preview", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-02-14", "limit": { "context": 256000, "output": 128000 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Doubao Seed 2.0 Code Preview", "open_weights": false, "reasoning": true, "release_date": "2026-02-14", "structured_output": true, "temperature": true, "tool_call": true }, "doubao-seed-2-0-lite-260428": { "attachment": true, "cost": { "cache_read": 0.01692, "input": 0.08, "input_audio": 1.269, "output": 0.51, "tiers": [ { "cache_read": 0.02536, "input": 0.13, "input_audio": 1.902, "output": 0.76, "tier": { "size": 32000, "type": "context" } }, { "cache_read": 0.05072, "input": 0.25, "input_audio": 3.804, "output": 1.52, "tier": { "size": 128000, "type": "context" } } ] }, "description": "Doubao Seed 2.0 Lite 260428 is an AI model provided by aihubmix.", "family": "seed", "id": "doubao-seed-2-0-lite-260428", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-28", "limit": { "context": 256000, "output": 128000 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Doubao Seed 2.0 Lite 260428", "open_weights": false, "reasoning": true, "release_date": "2026-04-28", "structured_output": true, "temperature": true, "tool_call": true }, "doubao-seed-2-0-mini-260428": { "attachment": true, "cost": { "cache_read": 0.00564, "input": 0.03, "input_audio": 0.423, "output": 0.28, "tiers": [ { "cache_read": 0.01128, "input": 0.06, "input_audio": 0.846, "output": 0.56, "tier": { "size": 32000, "type": "context" } }, { "cache_read": 0.02256, "input": 0.11, "input_audio": 1.692, "output": 1.13, "tier": { "size": 128000, "type": "context" } } ] }, "description": "Doubao Seed 2.0 Mini 260428 is an AI model provided by aihubmix.", "family": "seed", "id": "doubao-seed-2-0-mini-260428", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-28", "limit": { "context": 256000, "output": 128000 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Doubao Seed 2.0 Mini 260428", "open_weights": false, "reasoning": true, "release_date": "2026-04-28", "structured_output": true, "temperature": true, "tool_call": true }, "doubao-seed-2-0-pro": { "attachment": true, "cost": { "cache_read": 0.09644, "input": 0.48, "output": 2.41, "tiers": [ { "cache_read": 0.144656, "input": 0.72, "output": 3.62, "tier": { "size": 32000, "type": "context" } }, { "cache_read": 0.28932, "input": 1.45, "output": 7.23, "tier": { "size": 128000, "type": "context" } } ] }, "description": "Doubao Seed 2.0 Pro is an AI model provided by aihubmix.", "family": "seed", "id": "doubao-seed-2-0-pro", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-02-14", "limit": { "context": 256000, "output": 128000 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Doubao Seed 2.0 Pro", "open_weights": false, "reasoning": true, "release_date": "2026-02-14", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-2.5-flash": { "attachment": true, "cost": { "cache_read": 0.03, "input": 0.3, "input_audio": 1, "output": 2.5 }, "description": "Gemini 2.5 Flash is an AI model provided by aihubmix.", "family": "gemini-flash", "id": "gemini-2.5-flash", "knowledge": "2025-01", "last_updated": "2025-06-05", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Flash", "open_weights": false, "reasoning": true, "release_date": "2025-03-20", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-2.5-pro": { "attachment": true, "cost": { "cache_read": 0.125, "context_over_200k": { "cache_read": 0.25, "input": 2.5, "output": 15 }, "input": 1.25, "output": 10, "tiers": [ { "cache_read": 0.25, "input": 2.5, "output": 15, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Gemini 2.5 Pro is an AI model provided by aihubmix.", "family": "gemini-pro", "id": "gemini-2.5-pro", "knowledge": "2025-01", "last_updated": "2025-06-05", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Pro", "open_weights": false, "reasoning": true, "release_date": "2025-03-20", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-3-flash-preview": { "attachment": true, "cost": { "cache_read": 0.05, "context_over_200k": { "cache_read": 0.05, "input": 0.5, "output": 3 }, "input": 0.5, "output": 3, "tiers": [ { "cache_read": 0.05, "input": 0.5, "output": 3, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Gemini 3 Flash Preview is an AI model provided by aihubmix.", "family": "gemini-flash", "id": "gemini-3-flash-preview", "knowledge": "2025-01", "last_updated": "2025-12-17", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 3 Flash Preview", "open_weights": false, "reasoning": true, "release_date": "2025-12-17", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-3.1-flash-lite": { "attachment": true, "cost": { "cache_read": 0.025, "cache_write": 1, "input": 0.25, "output": 1.5 }, "description": "Gemini 3.1 Flash Lite is an AI model provided by aihubmix.", "family": "gemini-flash-lite", "id": "gemini-3.1-flash-lite", "knowledge": "2025-01", "last_updated": "2026-05-07", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 3.1 Flash Lite", "open_weights": false, "reasoning": true, "release_date": "2026-05-07", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-3.1-pro-preview": { "attachment": true, "cost": { "cache_read": 0.2, "context_over_200k": { "cache_read": 0.4, "input": 4, "output": 18 }, "input": 2, "output": 12, "tiers": [ { "cache_read": 0.4, "input": 4, "output": 18, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Gemini 3.1 Pro Preview is an AI model provided by aihubmix.", "family": "gemini-pro", "id": "gemini-3.1-pro-preview", "knowledge": "2025-01", "last_updated": "2026-02-19", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 3.1 Pro Preview", "open_weights": false, "reasoning": true, "release_date": "2026-02-19", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-3.1-pro-preview-customtools": { "attachment": true, "cost": { "cache_read": 0.2, "context_over_200k": { "cache_read": 0.4, "input": 4, "output": 18 }, "input": 2, "output": 12, "tiers": [ { "cache_read": 0.4, "input": 4, "output": 18, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Gemini 3.1 Pro Preview Custom Tools is an AI model provided by aihubmix.", "family": "gemini-pro", "id": "gemini-3.1-pro-preview-customtools", "knowledge": "2025-01", "last_updated": "2026-02-19", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 3.1 Pro Preview Custom Tools", "open_weights": false, "reasoning": true, "release_date": "2026-02-19", "structured_output": true, "temperature": true, "tool_call": true }, "glm-5v-turbo": { "attachment": true, "cost": { "cache_read": 0.169008, "input": 0.7042, "output": 3.09848 }, "description": "GLM 5 Vision Turbo is an AI model provided by aihubmix.", "family": "glmv", "id": "glm-5v-turbo", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-05-09", "limit": { "context": 200000, "output": 128000 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "GLM 5 Vision Turbo", "open_weights": false, "reasoning": true, "release_date": "2026-05-09", "structured_output": true, "temperature": true, "tool_call": true }, "gpt-5.1": { "attachment": true, "cost": { "cache_read": 0.13, "input": 1.25, "output": 10 }, "description": "GPT-5.1 is an AI model provided by aihubmix.", "family": "gpt", "id": "gpt-5.1", "knowledge": "2024-09-30", "last_updated": "2025-11-13", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.1", "open_weights": false, "reasoning": true, "release_date": "2025-11-13", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.1-codex": { "attachment": true, "cost": { "cache_read": 0.125, "input": 1.25, "output": 10 }, "description": "GPT-5.1 Codex is an AI model provided by aihubmix.", "family": "gpt-codex", "id": "gpt-5.1-codex", "knowledge": "2024-09-30", "last_updated": "2025-11-13", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.1 Codex", "open_weights": false, "reasoning": true, "release_date": "2025-11-13", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.1-codex-mini": { "attachment": true, "cost": { "cache_read": 0.025, "input": 0.25, "output": 2 }, "description": "GPT-5.1 Codex mini is an AI model provided by aihubmix.", "family": "gpt-codex", "id": "gpt-5.1-codex-mini", "knowledge": "2024-09-30", "last_updated": "2025-11-13", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.1 Codex mini", "open_weights": false, "reasoning": true, "release_date": "2025-11-13", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.2": { "attachment": true, "cost": { "cache_read": 0.175, "input": 1.75, "output": 14 }, "description": "GPT-5.2 is an AI model provided by aihubmix.", "family": "gpt", "id": "gpt-5.2", "knowledge": "2025-08-31", "last_updated": "2025-12-11", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.2", "open_weights": false, "reasoning": true, "release_date": "2025-12-11", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.2-codex": { "attachment": true, "cost": { "cache_read": 0.175, "input": 1.75, "output": 14 }, "description": "GPT-5.2 Codex is an AI model provided by aihubmix.", "family": "gpt-codex", "id": "gpt-5.2-codex", "knowledge": "2025-08-31", "last_updated": "2025-12-11", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.2 Codex", "open_weights": false, "reasoning": true, "release_date": "2025-12-11", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.3-codex": { "attachment": true, "cost": { "cache_read": 0.175, "input": 1.75, "output": 14 }, "description": "GPT-5.3 Codex is an AI model provided by aihubmix.", "family": "gpt-codex", "id": "gpt-5.3-codex", "knowledge": "2025-08-31", "last_updated": "2026-02-05", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.3 Codex", "open_weights": false, "reasoning": true, "release_date": "2026-02-05", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.4": { "attachment": true, "cost": { "cache_read": 0.25, "context_over_200k": { "cache_read": 0.5, "input": 5, "output": 22.5 }, "input": 2.5, "output": 15, "tiers": [ { "cache_read": 0.5, "input": 5, "output": 22.5, "tier": { "size": 272000, "type": "context" } } ] }, "description": "GPT-5.4 is an AI model provided by aihubmix.", "experimental": { "modes": { "fast": { "cost": { "cache_read": 0.5, "input": 5, "output": 30 }, "provider": { "body": { "service_tier": "priority" } } } } }, "family": "gpt", "id": "gpt-5.4", "knowledge": "2025-08-31", "last_updated": "2026-03-05", "limit": { "context": 1050000, "input": 922000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.4", "open_weights": false, "reasoning": true, "release_date": "2026-03-05", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.4-mini": { "attachment": true, "cost": { "cache_read": 0.075, "input": 0.75, "output": 4.5 }, "description": "GPT-5.4 mini is an AI model provided by aihubmix.", "experimental": { "modes": { "fast": { "cost": { "cache_read": 0.15, "input": 1.5, "output": 9 }, "provider": { "body": { "service_tier": "priority" } } } } }, "family": "gpt-mini", "id": "gpt-5.4-mini", "knowledge": "2025-08-31", "last_updated": "2026-03-17", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.4 mini", "open_weights": false, "reasoning": true, "release_date": "2026-03-17", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.5": { "attachment": true, "cost": { "cache_read": 0.5, "context_over_200k": { "cache_read": 1, "input": 10, "output": 45 }, "input": 5, "output": 30, "tiers": [ { "cache_read": 1, "input": 10, "output": 45, "tier": { "size": 272000, "type": "context" } } ] }, "description": "GPT-5.5 is an AI model provided by aihubmix.", "experimental": { "modes": { "fast": { "cost": { "cache_read": 1.25, "input": 12.5, "output": 75 }, "provider": { "body": { "service_tier": "priority" } } } } }, "family": "gpt", "id": "gpt-5.5", "knowledge": "2025-12-01", "last_updated": "2026-04-23", "limit": { "context": 1050000, "input": 922000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.5", "open_weights": false, "reasoning": true, "release_date": "2026-04-23", "structured_output": true, "temperature": false, "tool_call": true }, "grok-4.3": { "attachment": true, "cost": { "cache_read": 0.2, "context_over_200k": { "cache_read": 0.4, "input": 2.5, "output": 5 }, "input": 1.25, "output": 2.5, "tiers": [ { "cache_read": 0.4, "input": 2.5, "output": 5, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Grok 4.3 is an AI model provided by aihubmix.", "family": "grok", "id": "grok-4.3", "last_updated": "2026-05-01", "limit": { "context": 1000000, "output": 1000000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 4.3", "open_weights": false, "reasoning": true, "release_date": "2026-05-01", "structured_output": true, "temperature": true, "tool_call": true }, "kimi-k2.5": { "attachment": true, "cost": { "cache_read": 0.1, "input": 0.6, "output": 3 }, "description": "Kimi K2.5 is an AI model provided by aihubmix.", "family": "kimi-k2.5", "id": "kimi-k2.5", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-01", "last_updated": "2026-01", "limit": { "context": 262144, "output": 32768 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Kimi K2.5", "open_weights": true, "reasoning": true, "release_date": "2026-01", "structured_output": true, "temperature": false, "tool_call": true }, "kimi-k2.6": { "attachment": true, "cost": { "cache_read": 0.16, "input": 0.95, "output": 4 }, "description": "Kimi K2.6 is an AI model provided by aihubmix.", "family": "kimi-k2.6", "id": "kimi-k2.6", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-01", "last_updated": "2026-04-21", "limit": { "context": 262144, "output": 32768 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Kimi K2.6", "open_weights": true, "reasoning": true, "release_date": "2026-04-21", "structured_output": true, "temperature": false, "tool_call": true }, "minimax-m2.7": { "attachment": false, "cost": { "cache_read": 0.06, "cache_write": 0.375, "input": 0.3, "output": 1.2 }, "description": "MiniMax M2.7 is an AI model provided by aihubmix.", "family": "minimax", "id": "minimax-m2.7", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-03-18", "limit": { "context": 204800, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M2.7", "open_weights": true, "reasoning": true, "release_date": "2026-03-18", "structured_output": true, "temperature": true, "tool_call": true }, "qwen3.6-flash": { "attachment": true, "cost": { "cache_read": 0.0169, "cache_write": 0.21125, "context_over_200k": { "cache_read": 0.0676, "cache_write": 0.845, "input": 0.68, "output": 4.06 }, "input": 0.17, "output": 1.01, "tiers": [ { "cache_read": 0.0676, "cache_write": 0.845, "input": 0.68, "output": 4.06, "tier": { "size": 256000, "type": "context" } } ] }, "description": "Qwen3.6 Flash is an AI model provided by aihubmix.", "family": "qwen3.6", "id": "qwen3.6-flash", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-04", "last_updated": "2026-04-02", "limit": { "context": 991000, "output": 64000 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen3.6 Flash", "open_weights": false, "reasoning": true, "release_date": "2026-04-02", "structured_output": true, "temperature": true, "tool_call": true }, "qwen3.6-max-preview": { "attachment": false, "cost": { "cache_read": 0.1268, "cache_write": 1.585, "input": 1.27, "output": 7.61, "tiers": [ { "cache_read": 0.2112, "cache_write": 2.64, "input": 2.11, "output": 12.67, "tier": { "size": 128000, "type": "context" } } ] }, "description": "Qwen3.6 Max Preview is an AI model provided by aihubmix.", "family": "qwen3.6", "id": "qwen3.6-max-preview", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-04", "last_updated": "2026-05-09", "limit": { "context": 240000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3.6 Max Preview", "open_weights": false, "reasoning": true, "release_date": "2026-05-09", "structured_output": true, "temperature": true, "tool_call": true }, "qwen3.6-plus": { "attachment": true, "cost": { "cache_read": 0.0282, "cache_write": 0.3525, "context_over_200k": { "cache_read": 0.1128, "cache_write": 1.41, "input": 1.13, "output": 6.77 }, "input": 0.28, "output": 1.69, "tiers": [ { "cache_read": 0.1128, "cache_write": 1.41, "input": 1.13, "output": 6.77, "tier": { "size": 256000, "type": "context" } } ] }, "description": "Qwen3.6 Plus is an AI model provided by aihubmix.", "family": "qwen3.6", "id": "qwen3.6-plus", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-04", "last_updated": "2026-05-09", "limit": { "context": 991000, "output": 64000 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen3.6 Plus", "open_weights": false, "reasoning": true, "release_date": "2026-05-09", "structured_output": true, "temperature": true, "tool_call": true }, "xiaomi-mimo-v2.5": { "attachment": true, "cost": { "cache_read": 0.088, "context_over_200k": { "cache_read": 0.176, "input": 0.88, "output": 4.4 }, "input": 0.44, "output": 2.2, "tiers": [ { "cache_read": 0.176, "input": 0.88, "output": 4.4, "tier": { "size": 256000, "type": "context" } } ] }, "description": "Xiaomi MiMo-V2.5 is an AI model provided by aihubmix.", "family": "mimo-v2.5", "id": "xiaomi-mimo-v2.5", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-12", "last_updated": "2026-05-13", "limit": { "context": 1048576, "output": 131072 }, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "name": "Xiaomi MiMo-V2.5", "open_weights": true, "reasoning": true, "release_date": "2026-04-22", "temperature": true, "tool_call": true }, "xiaomi-mimo-v2.5-free": { "attachment": true, "cost": { "cache_read": 0, "input": 0, "output": 0 }, "description": "Xiaomi MiMo-V2.5 (free) is an AI model provided by aihubmix.", "family": "mimo-v2.5", "id": "xiaomi-mimo-v2.5-free", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-12", "last_updated": "2026-05-13", "limit": { "context": 1048576, "output": 131072 }, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "name": "Xiaomi MiMo-V2.5 (free)", "open_weights": true, "reasoning": true, "release_date": "2026-04-22", "temperature": true, "tool_call": true }, "xiaomi-mimo-v2.5-pro": { "attachment": false, "cost": { "cache_read": 0.22, "context_over_200k": { "cache_read": 0.44, "input": 2.2, "output": 6.6 }, "input": 1.1, "output": 3.3, "tiers": [ { "cache_read": 0.44, "input": 2.2, "output": 6.6, "tier": { "size": 256000, "type": "context" } } ] }, "description": "Xiaomi MiMo-V2.5-Pro is an AI model provided by aihubmix.", "family": "mimo-v2.5-pro", "id": "xiaomi-mimo-v2.5-pro", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-12", "last_updated": "2026-05-13", "limit": { "context": 1048576, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Xiaomi MiMo-V2.5-Pro", "open_weights": true, "reasoning": true, "release_date": "2026-04-22", "temperature": true, "tool_call": true }, "xiaomi-mimo-v2.5-pro-free": { "attachment": false, "cost": { "cache_read": 0, "input": 0, "output": 0 }, "description": "Xiaomi MiMo-V2.5-Pro (free) is an AI model provided by aihubmix.", "family": "mimo-v2.5-pro", "id": "xiaomi-mimo-v2.5-pro-free", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-12", "last_updated": "2026-05-13", "limit": { "context": 1048576, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Xiaomi MiMo-V2.5-Pro (free)", "open_weights": true, "reasoning": true, "release_date": "2026-04-22", "temperature": true, "tool_call": true }, "zai-glm-5.1": { "attachment": false, "cost": { "cache_read": 0.183112, "input": 0.845, "output": 3.38 }, "description": "GLM-5.1 (Z.ai) is an AI model provided by aihubmix.", "family": "glm", "id": "zai-glm-5.1", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-03-27", "limit": { "context": 200000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5.1 (Z.ai)", "open_weights": true, "reasoning": true, "release_date": "2026-03-27", "structured_output": true, "temperature": true, "tool_call": true } }, "name": "AIHubMix", "npm": "@aihubmix/ai-sdk-provider" }, "alibaba": { "api": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "doc": "https://www.alibabacloud.com/help/en/model-studio/models", "env": [ "DASHSCOPE_API_KEY" ], "iconURL": "https://models.dev/logos/alibaba.svg", "id": "alibaba", "lobeIcon": "Qwen.Color", "models": { "deepseek-r1": { "cost": { "input": 4, "output": 16 }, "description": "DeepSeek-R1 extensively applied reinforcement learning techniques in the post-training phase. With only a small amount of labeled data, it significantly improved the model’s reasoning ability. The model performs well and demonstrates strong capabilities in tasks such as mathematics, coding, and natural language reasoning.", "id": "deepseek-r1", "limit": { "context": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek R1" }, "qvq-max": { "attachment": false, "cost": { "input": 1.2, "output": 4.8 }, "description": "QVQ Max is an AI model provided by alibaba.", "family": "qvq", "id": "qvq-max", "knowledge": "2024-04", "last_updated": "2025-03-25", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "QVQ Max", "open_weights": false, "reasoning": true, "release_date": "2025-03-25", "temperature": true, "tool_call": true }, "qwen-flash": { "attachment": false, "cost": { "input": 0.05, "output": 0.4 }, "description": "Qwen Flash is an AI model provided by alibaba.", "family": "qwen", "id": "qwen-flash", "knowledge": "2024-04", "last_updated": "2025-07-28", "limit": { "context": 1000000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen Flash", "open_weights": false, "reasoning": true, "release_date": "2025-07-28", "temperature": true, "tool_call": true }, "qwen-max": { "attachment": false, "cost": { "input": 1.6, "output": 6.4 }, "description": "Qwen Max is an AI model provided by alibaba.", "family": "qwen", "id": "qwen-max", "knowledge": "2024-04", "last_updated": "2025-01-25", "limit": { "context": 32768, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen Max", "open_weights": false, "reasoning": false, "release_date": "2024-04-03", "temperature": true, "tool_call": true }, "qwen-mt-plus": { "attachment": false, "cost": { "input": 2.46, "output": 7.37 }, "description": "Qwen-MT Plus is an AI model provided by alibaba.", "family": "qwen", "id": "qwen-mt-plus", "knowledge": "2024-04", "last_updated": "2025-01", "limit": { "context": 16384, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen-MT Plus", "open_weights": false, "reasoning": false, "release_date": "2025-01", "temperature": true, "tool_call": false }, "qwen-mt-turbo": { "attachment": false, "cost": { "input": 0.16, "output": 0.49 }, "description": "Qwen-MT Turbo is an AI model provided by alibaba.", "family": "qwen", "id": "qwen-mt-turbo", "knowledge": "2024-04", "last_updated": "2025-01", "limit": { "context": 16384, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen-MT Turbo", "open_weights": false, "reasoning": false, "release_date": "2025-01", "temperature": true, "tool_call": false }, "qwen-omni-turbo": { "attachment": false, "cost": { "input": 0.07, "input_audio": 4.44, "output": 0.27, "output_audio": 8.89 }, "description": "Qwen-Omni Turbo is an AI model provided by alibaba.", "family": "qwen", "id": "qwen-omni-turbo", "knowledge": "2024-04", "last_updated": "2025-03-26", "limit": { "context": 32768, "output": 2048 }, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text", "audio" ] }, "name": "Qwen-Omni Turbo", "open_weights": false, "reasoning": false, "release_date": "2025-01-19", "temperature": true, "tool_call": true }, "qwen-omni-turbo-realtime": { "attachment": false, "cost": { "input": 0.27, "input_audio": 4.44, "output": 1.07, "output_audio": 8.89 }, "description": "Qwen-Omni Turbo Realtime is an AI model provided by alibaba.", "family": "qwen", "id": "qwen-omni-turbo-realtime", "knowledge": "2024-04", "last_updated": "2025-05-08", "limit": { "context": 32768, "output": 2048 }, "modalities": { "input": [ "text", "image", "audio" ], "output": [ "text", "audio" ] }, "name": "Qwen-Omni Turbo Realtime", "open_weights": false, "reasoning": false, "release_date": "2025-05-08", "temperature": true, "tool_call": true }, "qwen-plus": { "attachment": false, "cost": { "input": 0.4, "output": 1.2, "reasoning": 4 }, "description": "Qwen Plus is an AI model provided by alibaba.", "family": "qwen", "id": "qwen-plus", "knowledge": "2024-04", "last_updated": "2025-09-11", "limit": { "context": 1000000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen Plus", "open_weights": false, "reasoning": true, "release_date": "2024-01-25", "temperature": true, "tool_call": true }, "qwen-plus-character-ja": { "attachment": false, "cost": { "input": 0.5, "output": 1.4 }, "description": "Qwen Plus Character (Japanese) is an AI model provided by alibaba.", "family": "qwen", "id": "qwen-plus-character-ja", "knowledge": "2024-04", "last_updated": "2024-01", "limit": { "context": 8192, "output": 512 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen Plus Character (Japanese)", "open_weights": false, "reasoning": false, "release_date": "2024-01", "temperature": true, "tool_call": true }, "qwen-turbo": { "attachment": false, "cost": { "input": 0.05, "output": 0.2, "reasoning": 0.5 }, "description": "Qwen Turbo is an AI model provided by alibaba.", "family": "qwen", "id": "qwen-turbo", "knowledge": "2024-04", "last_updated": "2025-04-28", "limit": { "context": 1000000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen Turbo", "open_weights": false, "reasoning": true, "release_date": "2024-11-01", "temperature": true, "tool_call": true }, "qwen-vl-max": { "attachment": false, "cost": { "input": 0.8, "output": 3.2 }, "description": "Qwen-VL Max is an AI model provided by alibaba.", "family": "qwen", "id": "qwen-vl-max", "knowledge": "2024-04", "last_updated": "2025-08-13", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen-VL Max", "open_weights": false, "reasoning": false, "release_date": "2024-04-08", "temperature": true, "tool_call": true }, "qwen-vl-ocr": { "attachment": false, "cost": { "input": 0.72, "output": 0.72 }, "description": "Qwen-VL OCR is an AI model provided by alibaba.", "family": "qwen", "id": "qwen-vl-ocr", "knowledge": "2024-04", "last_updated": "2025-04-13", "limit": { "context": 34096, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen-VL OCR", "open_weights": false, "reasoning": false, "release_date": "2024-10-28", "temperature": true, "tool_call": false }, "qwen-vl-plus": { "attachment": false, "cost": { "input": 0.21, "output": 0.63 }, "description": "Qwen-VL Plus is an AI model provided by alibaba.", "family": "qwen", "id": "qwen-vl-plus", "knowledge": "2024-04", "last_updated": "2025-08-15", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen-VL Plus", "open_weights": false, "reasoning": false, "release_date": "2024-01-25", "temperature": true, "tool_call": true }, "qwen2-5-14b-instruct": { "attachment": false, "cost": { "input": 0.35, "output": 1.4 }, "description": "Qwen2.5 14B Instruct is an AI model provided by alibaba.", "family": "qwen", "id": "qwen2-5-14b-instruct", "knowledge": "2024-04", "last_updated": "2024-09", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen2.5 14B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-09", "temperature": true, "tool_call": true }, "qwen2-5-32b-instruct": { "attachment": false, "cost": { "input": 0.7, "output": 2.8 }, "description": "Qwen2.5 32B Instruct is an AI model provided by alibaba.", "family": "qwen", "id": "qwen2-5-32b-instruct", "knowledge": "2024-04", "last_updated": "2024-09", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen2.5 32B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-09", "temperature": true, "tool_call": true }, "qwen2-5-72b-instruct": { "attachment": false, "cost": { "input": 1.4, "output": 5.6 }, "description": "Qwen2.5 72B Instruct is an AI model provided by alibaba.", "family": "qwen", "id": "qwen2-5-72b-instruct", "knowledge": "2024-04", "last_updated": "2024-09", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen2.5 72B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-09", "temperature": true, "tool_call": true }, "qwen2-5-7b-instruct": { "attachment": false, "cost": { "input": 0.175, "output": 0.7 }, "description": "Qwen2.5 7B Instruct is an AI model provided by alibaba.", "family": "qwen", "id": "qwen2-5-7b-instruct", "knowledge": "2024-04", "last_updated": "2024-09", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen2.5 7B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-09", "temperature": true, "tool_call": true }, "qwen2-5-omni-7b": { "attachment": false, "cost": { "input": 0.1, "input_audio": 6.76, "output": 0.4 }, "description": "Qwen2.5-Omni 7B is an AI model provided by alibaba.", "family": "qwen", "id": "qwen2-5-omni-7b", "knowledge": "2024-04", "last_updated": "2024-12", "limit": { "context": 32768, "output": 2048 }, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text", "audio" ] }, "name": "Qwen2.5-Omni 7B", "open_weights": true, "reasoning": false, "release_date": "2024-12", "temperature": true, "tool_call": true }, "qwen2-5-vl-72b-instruct": { "attachment": false, "cost": { "input": 2.8, "output": 8.4 }, "description": "Qwen2.5-VL 72B Instruct is an AI model provided by alibaba.", "family": "qwen", "id": "qwen2-5-vl-72b-instruct", "knowledge": "2024-04", "last_updated": "2024-09", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen2.5-VL 72B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-09", "temperature": true, "tool_call": true }, "qwen2-5-vl-7b-instruct": { "attachment": false, "cost": { "input": 0.35, "output": 1.05 }, "description": "Qwen2.5-VL 7B Instruct is an AI model provided by alibaba.", "family": "qwen", "id": "qwen2-5-vl-7b-instruct", "knowledge": "2024-04", "last_updated": "2024-09", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen2.5-VL 7B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-09", "temperature": true, "tool_call": true }, "qwen3-14b": { "attachment": false, "cost": { "input": 0.35, "output": 1.4, "reasoning": 4.2 }, "description": "Qwen3 14B is an AI model provided by alibaba.", "family": "qwen", "id": "qwen3-14b", "knowledge": "2025-04", "last_updated": "2025-04", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 14B", "open_weights": true, "reasoning": true, "release_date": "2025-04", "temperature": true, "tool_call": true }, "qwen3-235b-a22b": { "attachment": false, "cost": { "input": 0.7, "output": 2.8, "reasoning": 8.4 }, "description": "Qwen3 235B-A22B is an AI model provided by alibaba.", "family": "qwen", "id": "qwen3-235b-a22b", "knowledge": "2025-04", "last_updated": "2025-04", "limit": { "context": 131072, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 235B-A22B", "open_weights": true, "reasoning": true, "release_date": "2025-04", "temperature": true, "tool_call": true }, "qwen3-32b": { "attachment": false, "cost": { "input": 0.7, "output": 2.8, "reasoning": 8.4 }, "description": "Qwen3 32B is an AI model provided by alibaba.", "family": "qwen", "id": "qwen3-32b", "knowledge": "2025-04", "last_updated": "2025-04", "limit": { "context": 131072, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 32B", "open_weights": true, "reasoning": true, "release_date": "2025-04", "temperature": true, "tool_call": true }, "qwen3-8b": { "attachment": false, "cost": { "input": 0.18, "output": 0.7, "reasoning": 2.1 }, "description": "Qwen3 8B is an AI model provided by alibaba.", "family": "qwen", "id": "qwen3-8b", "knowledge": "2025-04", "last_updated": "2025-04", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 8B", "open_weights": true, "reasoning": true, "release_date": "2025-04", "temperature": true, "tool_call": true }, "qwen3-asr-flash": { "attachment": false, "cost": { "input": 0.035, "output": 0.035 }, "description": "Qwen3-ASR Flash is an AI model provided by alibaba.", "family": "qwen", "id": "qwen3-asr-flash", "knowledge": "2024-04", "last_updated": "2025-09-08", "limit": { "context": 53248, "output": 4096 }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "name": "Qwen3-ASR Flash", "open_weights": false, "reasoning": false, "release_date": "2025-09-08", "temperature": false, "tool_call": false }, "qwen3-coder-30b-a3b-instruct": { "attachment": false, "cost": { "input": 0.45, "output": 2.25 }, "description": "Qwen3-Coder 30B-A3B Instruct is an AI model provided by alibaba.", "family": "qwen", "id": "qwen3-coder-30b-a3b-instruct", "knowledge": "2025-04", "last_updated": "2025-04", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3-Coder 30B-A3B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-04", "temperature": true, "tool_call": true }, "qwen3-coder-480b-a35b-instruct": { "attachment": false, "cost": { "input": 1.5, "output": 7.5 }, "description": "Qwen3-Coder 480B-A35B Instruct is an AI model provided by alibaba.", "family": "qwen", "id": "qwen3-coder-480b-a35b-instruct", "knowledge": "2025-04", "last_updated": "2025-04", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3-Coder 480B-A35B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-04", "temperature": true, "tool_call": true }, "qwen3-coder-flash": { "attachment": false, "cost": { "input": 0.3, "output": 1.5 }, "description": "Qwen3 Coder Flash is an AI model provided by alibaba.", "family": "qwen", "id": "qwen3-coder-flash", "knowledge": "2025-04", "last_updated": "2025-07-28", "limit": { "context": 1000000, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Coder Flash", "open_weights": false, "reasoning": false, "release_date": "2025-07-28", "temperature": true, "tool_call": true }, "qwen3-coder-plus": { "attachment": false, "cost": { "input": 1, "output": 5 }, "description": "Qwen3 Coder Plus is an AI model provided by alibaba.", "family": "qwen", "id": "qwen3-coder-plus", "knowledge": "2025-04", "last_updated": "2025-07-23", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Coder Plus", "open_weights": true, "reasoning": false, "release_date": "2025-07-23", "temperature": true, "tool_call": true }, "qwen3-livetranslate-flash-realtime": { "attachment": false, "cost": { "input": 10, "input_audio": 10, "output": 10, "output_audio": 38 }, "description": "Qwen3-LiveTranslate Flash Realtime is an AI model provided by alibaba.", "family": "qwen", "id": "qwen3-livetranslate-flash-realtime", "knowledge": "2024-04", "last_updated": "2025-09-22", "limit": { "context": 53248, "output": 4096 }, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text", "audio" ] }, "name": "Qwen3-LiveTranslate Flash Realtime", "open_weights": false, "reasoning": false, "release_date": "2025-09-22", "temperature": true, "tool_call": false }, "qwen3-max": { "attachment": false, "cost": { "input": 1.2, "output": 6 }, "description": "Qwen3 Max is an AI model provided by alibaba.", "family": "qwen", "id": "qwen3-max", "knowledge": "2025-04", "last_updated": "2025-09-23", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Max", "open_weights": false, "reasoning": false, "release_date": "2025-09-23", "temperature": true, "tool_call": true }, "qwen3-next-80b-a3b-instruct": { "attachment": false, "cost": { "input": 0.5, "output": 2 }, "description": "Qwen3-Next 80B-A3B Instruct is an AI model provided by alibaba.", "family": "qwen", "id": "qwen3-next-80b-a3b-instruct", "knowledge": "2025-04", "last_updated": "2025-09", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3-Next 80B-A3B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-09", "temperature": true, "tool_call": true }, "qwen3-next-80b-a3b-thinking": { "attachment": false, "cost": { "input": 0.5, "output": 6 }, "description": "Qwen3-Next 80B-A3B (Thinking) is an AI model provided by alibaba.", "family": "qwen", "id": "qwen3-next-80b-a3b-thinking", "knowledge": "2025-04", "last_updated": "2025-09", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3-Next 80B-A3B (Thinking)", "open_weights": true, "reasoning": true, "release_date": "2025-09", "temperature": true, "tool_call": true }, "qwen3-omni-flash": { "attachment": false, "cost": { "input": 0.43, "input_audio": 3.81, "output": 1.66, "output_audio": 15.11 }, "description": "Qwen3-Omni Flash is an AI model provided by alibaba.", "family": "qwen", "id": "qwen3-omni-flash", "knowledge": "2024-04", "last_updated": "2025-09-15", "limit": { "context": 65536, "output": 16384 }, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text", "audio" ] }, "name": "Qwen3-Omni Flash", "open_weights": false, "reasoning": true, "release_date": "2025-09-15", "temperature": true, "tool_call": true }, "qwen3-omni-flash-realtime": { "attachment": false, "cost": { "input": 0.52, "input_audio": 4.57, "output": 1.99, "output_audio": 18.13 }, "description": "Qwen3-Omni Flash Realtime is an AI model provided by alibaba.", "family": "qwen", "id": "qwen3-omni-flash-realtime", "knowledge": "2024-04", "last_updated": "2025-09-15", "limit": { "context": 65536, "output": 16384 }, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text", "audio" ] }, "name": "Qwen3-Omni Flash Realtime", "open_weights": false, "reasoning": false, "release_date": "2025-09-15", "temperature": true, "tool_call": true }, "qwen3-vl-235b-a22b": { "attachment": false, "cost": { "input": 0.7, "output": 2.8, "reasoning": 8.4 }, "description": "Qwen3-VL 235B-A22B is an AI model provided by alibaba.", "family": "qwen", "id": "qwen3-vl-235b-a22b", "knowledge": "2025-04", "last_updated": "2025-04", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen3-VL 235B-A22B", "open_weights": true, "reasoning": true, "release_date": "2025-04", "temperature": true, "tool_call": true }, "qwen3-vl-30b-a3b": { "attachment": false, "cost": { "input": 0.2, "output": 0.8, "reasoning": 2.4 }, "description": "Qwen3-VL 30B-A3B is an AI model provided by alibaba.", "family": "qwen", "id": "qwen3-vl-30b-a3b", "knowledge": "2025-04", "last_updated": "2025-04", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen3-VL 30B-A3B", "open_weights": true, "reasoning": true, "release_date": "2025-04", "temperature": true, "tool_call": true }, "qwen3-vl-plus": { "attachment": false, "cost": { "input": 0.2, "output": 1.6, "reasoning": 4.8 }, "description": "Qwen3-VL Plus is an AI model provided by alibaba.", "family": "qwen", "id": "qwen3-vl-plus", "knowledge": "2025-04", "last_updated": "2025-09-23", "limit": { "context": 262144, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen3-VL Plus", "open_weights": false, "reasoning": true, "release_date": "2025-09-23", "temperature": true, "tool_call": true }, "qwen3.5-122b-a10b": { "attachment": true, "cost": { "input": 0.4, "output": 3.2 }, "description": "Qwen3.5 122B-A10B is an AI model provided by alibaba.", "family": "qwen", "id": "qwen3.5-122b-a10b", "last_updated": "2026-02-23", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text" ] }, "name": "Qwen3.5 122B-A10B", "open_weights": true, "reasoning": true, "release_date": "2026-02-23", "structured_output": true, "temperature": true, "tool_call": true }, "qwen3.5-27b": { "attachment": true, "cost": { "input": 0.3, "output": 2.4 }, "description": "Qwen3.5 27B is an AI model provided by alibaba.", "family": "qwen", "id": "qwen3.5-27b", "last_updated": "2026-02-23", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text" ] }, "name": "Qwen3.5 27B", "open_weights": true, "reasoning": true, "release_date": "2026-02-23", "structured_output": true, "temperature": true, "tool_call": true }, "qwen3.5-35b-a3b": { "attachment": true, "cost": { "input": 0.25, "output": 2 }, "description": "Qwen3.5 35B-A3B is an AI model provided by alibaba.", "family": "qwen", "id": "qwen3.5-35b-a3b", "last_updated": "2026-02-23", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text" ] }, "name": "Qwen3.5 35B-A3B", "open_weights": true, "reasoning": true, "release_date": "2026-02-23", "structured_output": true, "temperature": true, "tool_call": true }, "qwen3.5-397b-a17b": { "attachment": true, "cost": { "input": 0.6, "output": 3.6 }, "description": "Qwen3.5 397B-A17B is an AI model provided by alibaba.", "family": "qwen", "id": "qwen3.5-397b-a17b", "last_updated": "2026-02-15", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text" ] }, "name": "Qwen3.5 397B-A17B", "open_weights": true, "reasoning": true, "release_date": "2026-02-15", "structured_output": true, "temperature": true, "tool_call": true }, "qwen3.5-plus": { "attachment": false, "cost": { "input": 0.4, "output": 2.4, "reasoning": 2.4 }, "description": "Qwen3.5 Plus is an AI model provided by alibaba.", "family": "qwen", "id": "qwen3.5-plus", "knowledge": "2025-04", "last_updated": "2026-02-16", "limit": { "context": 1000000, "output": 65536 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen3.5 Plus", "open_weights": false, "reasoning": true, "release_date": "2026-02-16", "temperature": true, "tool_call": true }, "qwen3.6-27b": { "attachment": true, "cost": { "input": 0.6, "output": 3.6 }, "description": "Qwen3.6 27B is an AI model provided by alibaba.", "family": "qwen", "id": "qwen3.6-27b", "last_updated": "2026-04-22", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text" ] }, "name": "Qwen3.6 27B", "open_weights": true, "reasoning": true, "release_date": "2026-04-22", "structured_output": true, "temperature": true, "tool_call": true }, "qwen3.6-35b-a3b": { "attachment": true, "cost": { "input": 0.248, "output": 1.485 }, "description": "Qwen3.6 35B-A3B is an AI model provided by alibaba.", "family": "qwen", "id": "qwen3.6-35b-a3b", "last_updated": "2026-04-17", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text" ] }, "name": "Qwen3.6 35B-A3B", "open_weights": true, "reasoning": true, "release_date": "2026-04-17", "structured_output": true, "temperature": true, "tool_call": true }, "qwen3.6-max-preview": { "attachment": false, "cost": { "cache_read": 0.13, "cache_write": 1.625, "input": 1.3, "output": 7.8 }, "description": "Qwen3.6 Max Preview is an AI model provided by alibaba.", "family": "qwen", "id": "qwen3.6-max-preview", "knowledge": "2025-04", "last_updated": "2026-04-20", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3.6 Max Preview", "open_weights": false, "reasoning": true, "release_date": "2026-04-20", "temperature": true, "tool_call": true }, "qwen3.6-plus": { "attachment": false, "cost": { "cache_read": 0.05, "cache_write": 0.625, "context_over_200k": { "cache_read": 0.2, "cache_write": 2.5, "input": 2, "output": 6 }, "input": 0.5, "output": 3, "tiers": [ { "cache_read": 0.2, "cache_write": 2.5, "input": 2, "output": 6, "tier": { "size": 256000, "type": "context" } } ] }, "description": "Qwen3.6 Plus is an AI model provided by alibaba.", "family": "qwen", "id": "qwen3.6-plus", "knowledge": "2025-04", "last_updated": "2026-04-02", "limit": { "context": 1000000, "output": 65536 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen3.6 Plus", "open_weights": false, "reasoning": true, "release_date": "2026-04-02", "temperature": true, "tool_call": true }, "qwq-plus": { "attachment": false, "cost": { "input": 0.8, "output": 2.4 }, "description": "QwQ Plus is an AI model provided by alibaba.", "family": "qwen", "id": "qwq-plus", "knowledge": "2024-04", "last_updated": "2025-03-05", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "QwQ Plus", "open_weights": false, "reasoning": true, "release_date": "2025-03-05", "temperature": true, "tool_call": true } }, "name": "Alibaba", "npm": "@ai-sdk/openai-compatible" }, "alibaba-cn": { "api": "https://dashscope.aliyuncs.com/compatible-mode/v1", "doc": "https://www.alibabacloud.com/help/en/model-studio/models", "env": [ "DASHSCOPE_API_KEY" ], "iconURL": "https://models.dev/logos/alibaba-cn.svg", "id": "alibaba-cn", "models": { "MiniMax-M2.5": { "attachment": false, "cost": { "input": 0.3, "output": 1.2 }, "description": "MiniMax-M2.5 is an AI model provided by alibaba-cn.", "family": "minimax", "id": "MiniMax-M2.5", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-02-12", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.5", "open_weights": true, "reasoning": true, "release_date": "2026-02-12", "temperature": true, "tool_call": true }, "MiniMax/MiniMax-M2.7": { "attachment": false, "cost": { "cache_read": 0.06, "cache_write": 0.375, "input": 0.3, "output": 1.2 }, "description": "MiniMax-M2.7 is an AI model provided by alibaba-cn.", "family": "minimax", "id": "MiniMax/MiniMax-M2.7", "last_updated": "2026-03-18", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.7", "open_weights": true, "reasoning": true, "release_date": "2026-03-18", "temperature": true, "tool_call": true }, "deepseek-r1": { "attachment": false, "cost": { "input": 0.574, "output": 2.294 }, "description": "DeepSeek R1 is an AI model provided by alibaba-cn.", "family": "deepseek-thinking", "id": "deepseek-r1", "last_updated": "2025-01-01", "limit": { "context": 131072, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek R1", "open_weights": false, "reasoning": true, "release_date": "2025-01-01", "temperature": true, "tool_call": true }, "deepseek-r1-0528": { "attachment": false, "cost": { "input": 0.574, "output": 2.294 }, "description": "DeepSeek R1 0528 is an AI model provided by alibaba-cn.", "family": "deepseek-thinking", "id": "deepseek-r1-0528", "last_updated": "2025-05-28", "limit": { "context": 131072, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek R1 0528", "open_weights": false, "reasoning": true, "release_date": "2025-05-28", "temperature": true, "tool_call": true }, "deepseek-r1-distill-llama-70b": { "attachment": false, "cost": { "input": 0.287, "output": 0.861 }, "description": "DeepSeek R1 Distill Llama 70B is an AI model provided by alibaba-cn.", "family": "deepseek-thinking", "id": "deepseek-r1-distill-llama-70b", "last_updated": "2025-01-01", "limit": { "context": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek R1 Distill Llama 70B", "open_weights": false, "reasoning": true, "release_date": "2025-01-01", "temperature": true, "tool_call": true }, "deepseek-r1-distill-llama-8b": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "DeepSeek R1 Distill Llama 8B is an AI model provided by alibaba-cn.", "family": "deepseek-thinking", "id": "deepseek-r1-distill-llama-8b", "last_updated": "2025-01-01", "limit": { "context": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek R1 Distill Llama 8B", "open_weights": false, "reasoning": true, "release_date": "2025-01-01", "temperature": true, "tool_call": true }, "deepseek-r1-distill-qwen-1-5b": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "DeepSeek R1 Distill Qwen 1.5B is an AI model provided by alibaba-cn.", "family": "qwen", "id": "deepseek-r1-distill-qwen-1-5b", "last_updated": "2025-01-01", "limit": { "context": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek R1 Distill Qwen 1.5B", "open_weights": false, "reasoning": true, "release_date": "2025-01-01", "temperature": true, "tool_call": true }, "deepseek-r1-distill-qwen-14b": { "attachment": false, "cost": { "input": 0.144, "output": 0.431 }, "description": "DeepSeek R1 Distill Qwen 14B is an AI model provided by alibaba-cn.", "family": "qwen", "id": "deepseek-r1-distill-qwen-14b", "last_updated": "2025-01-01", "limit": { "context": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek R1 Distill Qwen 14B", "open_weights": false, "reasoning": true, "release_date": "2025-01-01", "temperature": true, "tool_call": true }, "deepseek-r1-distill-qwen-32b": { "attachment": false, "cost": { "input": 0.287, "output": 0.861 }, "description": "DeepSeek R1 Distill Qwen 32B is an AI model provided by alibaba-cn.", "family": "qwen", "id": "deepseek-r1-distill-qwen-32b", "last_updated": "2025-01-01", "limit": { "context": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek R1 Distill Qwen 32B", "open_weights": false, "reasoning": true, "release_date": "2025-01-01", "temperature": true, "tool_call": true }, "deepseek-r1-distill-qwen-7b": { "attachment": false, "cost": { "input": 0.072, "output": 0.144 }, "description": "DeepSeek R1 Distill Qwen 7B is an AI model provided by alibaba-cn.", "family": "qwen", "id": "deepseek-r1-distill-qwen-7b", "last_updated": "2025-01-01", "limit": { "context": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek R1 Distill Qwen 7B", "open_weights": false, "reasoning": true, "release_date": "2025-01-01", "temperature": true, "tool_call": true }, "deepseek-v3": { "attachment": false, "cost": { "input": 0.287, "output": 1.147 }, "description": "DeepSeek V3 is an AI model provided by alibaba-cn.", "family": "deepseek", "id": "deepseek-v3", "last_updated": "2024-12-01", "limit": { "context": 65536, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3", "open_weights": false, "reasoning": false, "release_date": "2024-12-01", "temperature": true, "tool_call": true }, "deepseek-v3-1": { "attachment": false, "cost": { "input": 0.574, "output": 1.721 }, "description": "DeepSeek V3.1 is an AI model provided by alibaba-cn.", "family": "deepseek", "id": "deepseek-v3-1", "last_updated": "2025-01-01", "limit": { "context": 131072, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3.1", "open_weights": false, "reasoning": false, "release_date": "2025-01-01", "temperature": true, "tool_call": true }, "deepseek-v3-2-exp": { "attachment": false, "cost": { "input": 0.287, "output": 0.431 }, "description": "DeepSeek V3.2 Exp is an AI model provided by alibaba-cn.", "family": "deepseek", "id": "deepseek-v3-2-exp", "last_updated": "2025-01-01", "limit": { "context": 131072, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3.2 Exp", "open_weights": false, "reasoning": false, "release_date": "2025-01-01", "temperature": true, "tool_call": true }, "deepseek-v4-flash": { "attachment": false, "cost": { "cache_read": 0.028, "input": 0.14, "output": 0.28 }, "description": "DeepSeek V4 Flash is an AI model provided by alibaba-cn.", "family": "deepseek-flash", "id": "deepseek-v4-flash", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-05", "last_updated": "2026-04-24", "limit": { "context": 1000000, "output": 384000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V4 Flash", "open_weights": true, "reasoning": true, "release_date": "2026-04-24", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek-v4-pro": { "attachment": false, "cost": { "cache_read": 0.145, "input": 1.74, "output": 3.48 }, "description": "DeepSeek V4 Pro is an AI model provided by alibaba-cn.", "family": "deepseek-thinking", "id": "deepseek-v4-pro", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-05", "last_updated": "2026-04-24", "limit": { "context": 1000000, "output": 384000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V4 Pro", "open_weights": true, "reasoning": true, "release_date": "2026-04-24", "structured_output": true, "temperature": true, "tool_call": true }, "glm-5": { "attachment": false, "cost": { "input": 0.86, "output": 3.15 }, "description": "GLM-5 is an AI model provided by alibaba-cn.", "family": "glm", "id": "glm-5", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-02-11", "limit": { "context": 202752, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5", "open_weights": false, "reasoning": true, "release_date": "2026-02-11", "temperature": true, "tool_call": true }, "glm-5.1": { "attachment": false, "cost": { "cache_read": 0.17, "input": 0.87, "output": 3.48 }, "description": "GLM-5.1 is an AI model provided by alibaba-cn.", "family": "glm", "id": "glm-5.1", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-14", "limit": { "context": 202752, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5.1", "open_weights": true, "reasoning": true, "release_date": "2026-04-14", "structured_output": true, "temperature": true, "tool_call": true }, "kimi-k2-thinking": { "attachment": false, "cost": { "input": 0.574, "output": 2.294 }, "description": "Moonshot Kimi K2 Thinking is an AI model provided by alibaba-cn.", "family": "kimi", "id": "kimi-k2-thinking", "interleaved": { "field": "reasoning_content" }, "last_updated": "2025-11-06", "limit": { "context": 262144, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Moonshot Kimi K2 Thinking", "open_weights": true, "reasoning": true, "release_date": "2025-11-06", "structured_output": true, "temperature": true, "tool_call": true }, "kimi-k2.5": { "attachment": false, "cost": { "input": 0.574, "output": 2.411 }, "description": "Moonshot Kimi K2.5 is an AI model provided by alibaba-cn.", "family": "kimi", "id": "kimi-k2.5", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-01", "last_updated": "2026-01-27", "limit": { "context": 262144, "output": 32768 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Moonshot Kimi K2.5", "open_weights": true, "reasoning": true, "release_date": "2026-01-27", "structured_output": false, "temperature": true, "tool_call": true }, "kimi-k2.6": { "attachment": true, "cost": { "input": 0.929, "output": 3.858 }, "description": "Moonshot Kimi K2.6 is an AI model provided by alibaba-cn.", "family": "kimi", "id": "kimi-k2.6", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-01", "last_updated": "2026-04-21", "limit": { "context": 262144, "output": 16384 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Moonshot Kimi K2.6", "open_weights": true, "reasoning": true, "release_date": "2026-04-21", "structured_output": false, "temperature": true, "tool_call": true }, "kimi/kimi-k2.5": { "attachment": false, "cost": { "cache_read": 0.1, "input": 0.6, "output": 3 }, "description": "kimi/kimi-k2.5 is an AI model provided by alibaba-cn.", "family": "kimi", "id": "kimi/kimi-k2.5", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-01", "last_updated": "2026-01-27", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "kimi/kimi-k2.5", "open_weights": true, "reasoning": true, "release_date": "2026-01-27", "structured_output": true, "temperature": false, "tool_call": true }, "moonshot-kimi-k2-instruct": { "attachment": false, "cost": { "input": 0.574, "output": 2.294 }, "description": "Moonshot Kimi K2 Instruct is an AI model provided by alibaba-cn.", "family": "kimi", "id": "moonshot-kimi-k2-instruct", "last_updated": "2025-01-01", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Moonshot Kimi K2 Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-01-01", "structured_output": false, "temperature": true, "tool_call": true }, "qvq-max": { "attachment": false, "cost": { "input": 1.147, "output": 4.588 }, "description": "QVQ Max is an AI model provided by alibaba-cn.", "family": "qvq", "id": "qvq-max", "knowledge": "2024-04", "last_updated": "2025-03-25", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "QVQ Max", "open_weights": false, "reasoning": true, "release_date": "2025-03-25", "temperature": true, "tool_call": true }, "qwen-deep-research": { "attachment": false, "cost": { "input": 7.742, "output": 23.367 }, "description": "Qwen Deep Research is an AI model provided by alibaba-cn.", "family": "qwen", "id": "qwen-deep-research", "knowledge": "2024-04", "last_updated": "2024-01", "limit": { "context": 1000000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen Deep Research", "open_weights": false, "reasoning": false, "release_date": "2024-01", "temperature": true, "tool_call": true }, "qwen-doc-turbo": { "attachment": false, "cost": { "input": 0.087, "output": 0.144 }, "description": "Qwen Doc Turbo is an AI model provided by alibaba-cn.", "family": "qwen", "id": "qwen-doc-turbo", "knowledge": "2024-04", "last_updated": "2024-01", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen Doc Turbo", "open_weights": false, "reasoning": false, "release_date": "2024-01", "temperature": true, "tool_call": true }, "qwen-flash": { "attachment": false, "cost": { "input": 0.022, "output": 0.216 }, "description": "Qwen Flash is an AI model provided by alibaba-cn.", "family": "qwen", "id": "qwen-flash", "knowledge": "2024-04", "last_updated": "2025-07-28", "limit": { "context": 1000000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen Flash", "open_weights": false, "reasoning": true, "release_date": "2025-07-28", "temperature": true, "tool_call": true }, "qwen-long": { "attachment": false, "cost": { "input": 0.072, "output": 0.287 }, "description": "Qwen Long is an AI model provided by alibaba-cn.", "family": "qwen", "id": "qwen-long", "knowledge": "2024-04", "last_updated": "2025-01-25", "limit": { "context": 10000000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen Long", "open_weights": false, "reasoning": false, "release_date": "2025-01-25", "temperature": true, "tool_call": true }, "qwen-math-plus": { "attachment": false, "cost": { "input": 0.574, "output": 1.721 }, "description": "Qwen Math Plus is an AI model provided by alibaba-cn.", "family": "qwen", "id": "qwen-math-plus", "knowledge": "2024-04", "last_updated": "2024-09-19", "limit": { "context": 4096, "output": 3072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen Math Plus", "open_weights": false, "reasoning": false, "release_date": "2024-08-16", "temperature": true, "tool_call": true }, "qwen-math-turbo": { "attachment": false, "cost": { "input": 0.287, "output": 0.861 }, "description": "Qwen Math Turbo is an AI model provided by alibaba-cn.", "family": "qwen", "id": "qwen-math-turbo", "knowledge": "2024-04", "last_updated": "2024-09-19", "limit": { "context": 4096, "output": 3072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen Math Turbo", "open_weights": false, "reasoning": false, "release_date": "2024-09-19", "temperature": true, "tool_call": true }, "qwen-max": { "attachment": false, "cost": { "input": 0.345, "output": 1.377 }, "description": "Qwen Max is an AI model provided by alibaba-cn.", "family": "qwen", "id": "qwen-max", "knowledge": "2024-04", "last_updated": "2025-01-25", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen Max", "open_weights": false, "reasoning": false, "release_date": "2024-04-03", "temperature": true, "tool_call": true }, "qwen-mt-plus": { "attachment": false, "cost": { "input": 0.259, "output": 0.775 }, "description": "Qwen-MT Plus is an AI model provided by alibaba-cn.", "family": "qwen", "id": "qwen-mt-plus", "knowledge": "2024-04", "last_updated": "2025-01", "limit": { "context": 16384, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen-MT Plus", "open_weights": false, "reasoning": false, "release_date": "2025-01", "temperature": true, "tool_call": false }, "qwen-mt-turbo": { "attachment": false, "cost": { "input": 0.101, "output": 0.28 }, "description": "Qwen-MT Turbo is an AI model provided by alibaba-cn.", "family": "qwen", "id": "qwen-mt-turbo", "knowledge": "2024-04", "last_updated": "2025-01", "limit": { "context": 16384, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen-MT Turbo", "open_weights": false, "reasoning": false, "release_date": "2025-01", "temperature": true, "tool_call": false }, "qwen-omni-turbo": { "attachment": false, "cost": { "input": 0.058, "input_audio": 3.584, "output": 0.23, "output_audio": 7.168 }, "description": "Qwen-Omni Turbo is an AI model provided by alibaba-cn.", "family": "qwen", "id": "qwen-omni-turbo", "knowledge": "2024-04", "last_updated": "2025-03-26", "limit": { "context": 32768, "output": 2048 }, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text", "audio" ] }, "name": "Qwen-Omni Turbo", "open_weights": false, "reasoning": false, "release_date": "2025-01-19", "temperature": true, "tool_call": true }, "qwen-omni-turbo-realtime": { "attachment": false, "cost": { "input": 0.23, "input_audio": 3.584, "output": 0.918, "output_audio": 7.168 }, "description": "Qwen-Omni Turbo Realtime is an AI model provided by alibaba-cn.", "family": "qwen", "id": "qwen-omni-turbo-realtime", "knowledge": "2024-04", "last_updated": "2025-05-08", "limit": { "context": 32768, "output": 2048 }, "modalities": { "input": [ "text", "image", "audio" ], "output": [ "text", "audio" ] }, "name": "Qwen-Omni Turbo Realtime", "open_weights": false, "reasoning": false, "release_date": "2025-05-08", "temperature": true, "tool_call": true }, "qwen-plus": { "attachment": false, "cost": { "input": 0.115, "output": 0.287, "reasoning": 1.147 }, "description": "Qwen Plus is an AI model provided by alibaba-cn.", "family": "qwen", "id": "qwen-plus", "knowledge": "2024-04", "last_updated": "2025-09-11", "limit": { "context": 1000000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen Plus", "open_weights": false, "reasoning": true, "release_date": "2024-01-25", "temperature": true, "tool_call": true }, "qwen-plus-character": { "attachment": false, "cost": { "input": 0.115, "output": 0.287 }, "description": "Qwen Plus Character is an AI model provided by alibaba-cn.", "family": "qwen", "id": "qwen-plus-character", "knowledge": "2024-04", "last_updated": "2024-01", "limit": { "context": 32768, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen Plus Character", "open_weights": false, "reasoning": false, "release_date": "2024-01", "temperature": true, "tool_call": true }, "qwen-turbo": { "attachment": false, "cost": { "input": 0.044, "output": 0.087, "reasoning": 0.431 }, "description": "Qwen Turbo is an AI model provided by alibaba-cn.", "family": "qwen", "id": "qwen-turbo", "knowledge": "2024-04", "last_updated": "2025-07-15", "limit": { "context": 1000000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen Turbo", "open_weights": false, "reasoning": true, "release_date": "2024-11-01", "temperature": true, "tool_call": true }, "qwen-vl-max": { "attachment": false, "cost": { "input": 0.23, "output": 0.574 }, "description": "Qwen-VL Max is an AI model provided by alibaba-cn.", "family": "qwen", "id": "qwen-vl-max", "knowledge": "2024-04", "last_updated": "2025-08-13", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen-VL Max", "open_weights": false, "reasoning": false, "release_date": "2024-04-08", "temperature": true, "tool_call": true }, "qwen-vl-ocr": { "attachment": false, "cost": { "input": 0.717, "output": 0.717 }, "description": "Qwen-VL OCR is an AI model provided by alibaba-cn.", "family": "qwen", "id": "qwen-vl-ocr", "knowledge": "2024-04", "last_updated": "2025-04-13", "limit": { "context": 34096, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen-VL OCR", "open_weights": false, "reasoning": false, "release_date": "2024-10-28", "temperature": true, "tool_call": false }, "qwen-vl-plus": { "attachment": false, "cost": { "input": 0.115, "output": 0.287 }, "description": "Qwen-VL Plus is an AI model provided by alibaba-cn.", "family": "qwen", "id": "qwen-vl-plus", "knowledge": "2024-04", "last_updated": "2025-08-15", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen-VL Plus", "open_weights": false, "reasoning": false, "release_date": "2024-01-25", "temperature": true, "tool_call": true }, "qwen2-5-14b-instruct": { "attachment": false, "cost": { "input": 0.144, "output": 0.431 }, "description": "Qwen2.5 14B Instruct is an AI model provided by alibaba-cn.", "family": "qwen", "id": "qwen2-5-14b-instruct", "knowledge": "2024-04", "last_updated": "2024-09", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen2.5 14B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-09", "temperature": true, "tool_call": true }, "qwen2-5-32b-instruct": { "attachment": false, "cost": { "input": 0.287, "output": 0.861 }, "description": "Qwen2.5 32B Instruct is an AI model provided by alibaba-cn.", "family": "qwen", "id": "qwen2-5-32b-instruct", "knowledge": "2024-04", "last_updated": "2024-09", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen2.5 32B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-09", "temperature": true, "tool_call": true }, "qwen2-5-72b-instruct": { "attachment": false, "cost": { "input": 0.574, "output": 1.721 }, "description": "Qwen2.5 72B Instruct is an AI model provided by alibaba-cn.", "family": "qwen", "id": "qwen2-5-72b-instruct", "knowledge": "2024-04", "last_updated": "2024-09", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen2.5 72B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-09", "temperature": true, "tool_call": true }, "qwen2-5-7b-instruct": { "attachment": false, "cost": { "input": 0.072, "output": 0.144 }, "description": "Qwen2.5 7B Instruct is an AI model provided by alibaba-cn.", "family": "qwen", "id": "qwen2-5-7b-instruct", "knowledge": "2024-04", "last_updated": "2024-09", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen2.5 7B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-09", "temperature": true, "tool_call": true }, "qwen2-5-coder-32b-instruct": { "attachment": false, "cost": { "input": 0.287, "output": 0.861 }, "description": "Qwen2.5-Coder 32B Instruct is an AI model provided by alibaba-cn.", "family": "qwen", "id": "qwen2-5-coder-32b-instruct", "knowledge": "2024-04", "last_updated": "2024-11", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen2.5-Coder 32B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-11", "temperature": true, "tool_call": true }, "qwen2-5-coder-7b-instruct": { "attachment": false, "cost": { "input": 0.144, "output": 0.287 }, "description": "Qwen2.5-Coder 7B Instruct is an AI model provided by alibaba-cn.", "family": "qwen", "id": "qwen2-5-coder-7b-instruct", "knowledge": "2024-04", "last_updated": "2024-11", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen2.5-Coder 7B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-11", "temperature": true, "tool_call": true }, "qwen2-5-math-72b-instruct": { "attachment": false, "cost": { "input": 0.574, "output": 1.721 }, "description": "Qwen2.5-Math 72B Instruct is an AI model provided by alibaba-cn.", "family": "qwen", "id": "qwen2-5-math-72b-instruct", "knowledge": "2024-04", "last_updated": "2024-09", "limit": { "context": 4096, "output": 3072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen2.5-Math 72B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-09", "temperature": true, "tool_call": true }, "qwen2-5-math-7b-instruct": { "attachment": false, "cost": { "input": 0.144, "output": 0.287 }, "description": "Qwen2.5-Math 7B Instruct is an AI model provided by alibaba-cn.", "family": "qwen", "id": "qwen2-5-math-7b-instruct", "knowledge": "2024-04", "last_updated": "2024-09", "limit": { "context": 4096, "output": 3072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen2.5-Math 7B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-09", "temperature": true, "tool_call": true }, "qwen2-5-omni-7b": { "attachment": false, "cost": { "input": 0.087, "input_audio": 5.448, "output": 0.345 }, "description": "Qwen2.5-Omni 7B is an AI model provided by alibaba-cn.", "family": "qwen", "id": "qwen2-5-omni-7b", "knowledge": "2024-04", "last_updated": "2024-12", "limit": { "context": 32768, "output": 2048 }, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text", "audio" ] }, "name": "Qwen2.5-Omni 7B", "open_weights": true, "reasoning": false, "release_date": "2024-12", "temperature": true, "tool_call": true }, "qwen2-5-vl-72b-instruct": { "attachment": false, "cost": { "input": 2.294, "output": 6.881 }, "description": "Qwen2.5-VL 72B Instruct is an AI model provided by alibaba-cn.", "family": "qwen", "id": "qwen2-5-vl-72b-instruct", "knowledge": "2024-04", "last_updated": "2024-09", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen2.5-VL 72B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-09", "temperature": true, "tool_call": true }, "qwen2-5-vl-7b-instruct": { "attachment": false, "cost": { "input": 0.287, "output": 0.717 }, "description": "Qwen2.5-VL 7B Instruct is an AI model provided by alibaba-cn.", "family": "qwen", "id": "qwen2-5-vl-7b-instruct", "knowledge": "2024-04", "last_updated": "2024-09", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen2.5-VL 7B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-09", "temperature": true, "tool_call": true }, "qwen3-14b": { "attachment": false, "cost": { "input": 0.144, "output": 0.574, "reasoning": 1.434 }, "description": "Qwen3 14B is an AI model provided by alibaba-cn.", "family": "qwen", "id": "qwen3-14b", "knowledge": "2025-04", "last_updated": "2025-04", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 14B", "open_weights": true, "reasoning": true, "release_date": "2025-04", "temperature": true, "tool_call": true }, "qwen3-235b-a22b": { "attachment": false, "cost": { "input": 0.287, "output": 1.147, "reasoning": 2.868 }, "description": "Qwen3 235B-A22B is an AI model provided by alibaba-cn.", "family": "qwen", "id": "qwen3-235b-a22b", "knowledge": "2025-04", "last_updated": "2025-04", "limit": { "context": 131072, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 235B-A22B", "open_weights": true, "reasoning": true, "release_date": "2025-04", "temperature": true, "tool_call": true }, "qwen3-32b": { "attachment": false, "cost": { "input": 0.287, "output": 1.147, "reasoning": 2.868 }, "description": "Qwen3 32B is an AI model provided by alibaba-cn.", "family": "qwen", "id": "qwen3-32b", "knowledge": "2025-04", "last_updated": "2025-04", "limit": { "context": 131072, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 32B", "open_weights": true, "reasoning": true, "release_date": "2025-04", "temperature": true, "tool_call": true }, "qwen3-8b": { "attachment": false, "cost": { "input": 0.072, "output": 0.287, "reasoning": 0.717 }, "description": "Qwen3 8B is an AI model provided by alibaba-cn.", "family": "qwen", "id": "qwen3-8b", "knowledge": "2025-04", "last_updated": "2025-04", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 8B", "open_weights": true, "reasoning": true, "release_date": "2025-04", "temperature": true, "tool_call": true }, "qwen3-asr-flash": { "attachment": false, "cost": { "input": 0.032, "output": 0.032 }, "description": "Qwen3-ASR Flash is an AI model provided by alibaba-cn.", "family": "qwen", "id": "qwen3-asr-flash", "knowledge": "2024-04", "last_updated": "2025-09-08", "limit": { "context": 53248, "output": 4096 }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "name": "Qwen3-ASR Flash", "open_weights": false, "reasoning": false, "release_date": "2025-09-08", "temperature": false, "tool_call": false }, "qwen3-coder-30b-a3b-instruct": { "attachment": false, "cost": { "input": 0.216, "output": 0.861 }, "description": "Qwen3-Coder 30B-A3B Instruct is an AI model provided by alibaba-cn.", "family": "qwen", "id": "qwen3-coder-30b-a3b-instruct", "knowledge": "2025-04", "last_updated": "2025-04", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3-Coder 30B-A3B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-04", "temperature": true, "tool_call": true }, "qwen3-coder-480b-a35b-instruct": { "attachment": false, "cost": { "input": 0.861, "output": 3.441 }, "description": "Qwen3-Coder 480B-A35B Instruct is an AI model provided by alibaba-cn.", "family": "qwen", "id": "qwen3-coder-480b-a35b-instruct", "knowledge": "2025-04", "last_updated": "2025-04", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3-Coder 480B-A35B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-04", "temperature": true, "tool_call": true }, "qwen3-coder-flash": { "attachment": false, "cost": { "input": 0.144, "output": 0.574 }, "description": "Qwen3 Coder Flash is an AI model provided by alibaba-cn.", "family": "qwen", "id": "qwen3-coder-flash", "knowledge": "2025-04", "last_updated": "2025-07-28", "limit": { "context": 1000000, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Coder Flash", "open_weights": false, "reasoning": false, "release_date": "2025-07-28", "temperature": true, "tool_call": true }, "qwen3-coder-plus": { "attachment": false, "cost": { "input": 1, "output": 5 }, "description": "Qwen3 Coder Plus is an AI model provided by alibaba-cn.", "family": "qwen", "id": "qwen3-coder-plus", "knowledge": "2025-04", "last_updated": "2025-07-23", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Coder Plus", "open_weights": true, "reasoning": false, "release_date": "2025-07-23", "temperature": true, "tool_call": true }, "qwen3-max": { "attachment": false, "cost": { "input": 0.861, "output": 3.441 }, "description": "Qwen3 Max is an AI model provided by alibaba-cn.", "family": "qwen", "id": "qwen3-max", "knowledge": "2025-04", "last_updated": "2025-09-23", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Max", "open_weights": false, "reasoning": false, "release_date": "2025-09-23", "temperature": true, "tool_call": true }, "qwen3-next-80b-a3b-instruct": { "attachment": false, "cost": { "input": 0.144, "output": 0.574 }, "description": "Qwen3-Next 80B-A3B Instruct is an AI model provided by alibaba-cn.", "family": "qwen", "id": "qwen3-next-80b-a3b-instruct", "knowledge": "2025-04", "last_updated": "2025-09", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3-Next 80B-A3B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-09", "temperature": true, "tool_call": true }, "qwen3-next-80b-a3b-thinking": { "attachment": false, "cost": { "input": 0.144, "output": 1.434 }, "description": "Qwen3-Next 80B-A3B (Thinking) is an AI model provided by alibaba-cn.", "family": "qwen", "id": "qwen3-next-80b-a3b-thinking", "knowledge": "2025-04", "last_updated": "2025-09", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3-Next 80B-A3B (Thinking)", "open_weights": true, "reasoning": true, "release_date": "2025-09", "temperature": true, "tool_call": true }, "qwen3-omni-flash": { "attachment": false, "cost": { "input": 0.058, "input_audio": 3.584, "output": 0.23, "output_audio": 7.168 }, "description": "Qwen3-Omni Flash is an AI model provided by alibaba-cn.", "family": "qwen", "id": "qwen3-omni-flash", "knowledge": "2024-04", "last_updated": "2025-09-15", "limit": { "context": 65536, "output": 16384 }, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text", "audio" ] }, "name": "Qwen3-Omni Flash", "open_weights": false, "reasoning": true, "release_date": "2025-09-15", "temperature": true, "tool_call": true }, "qwen3-omni-flash-realtime": { "attachment": false, "cost": { "input": 0.23, "input_audio": 3.584, "output": 0.918, "output_audio": 7.168 }, "description": "Qwen3-Omni Flash Realtime is an AI model provided by alibaba-cn.", "family": "qwen", "id": "qwen3-omni-flash-realtime", "knowledge": "2024-04", "last_updated": "2025-09-15", "limit": { "context": 65536, "output": 16384 }, "modalities": { "input": [ "text", "image", "audio" ], "output": [ "text", "audio" ] }, "name": "Qwen3-Omni Flash Realtime", "open_weights": false, "reasoning": false, "release_date": "2025-09-15", "temperature": true, "tool_call": true }, "qwen3-vl-235b-a22b": { "attachment": false, "cost": { "input": 0.286705, "output": 1.14682, "reasoning": 2.867051 }, "description": "Qwen3-VL 235B-A22B is an AI model provided by alibaba-cn.", "family": "qwen", "id": "qwen3-vl-235b-a22b", "knowledge": "2025-04", "last_updated": "2025-04", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen3-VL 235B-A22B", "open_weights": true, "reasoning": true, "release_date": "2025-04", "temperature": true, "tool_call": true }, "qwen3-vl-30b-a3b": { "attachment": false, "cost": { "input": 0.108, "output": 0.431, "reasoning": 1.076 }, "description": "Qwen3-VL 30B-A3B is an AI model provided by alibaba-cn.", "family": "qwen", "id": "qwen3-vl-30b-a3b", "knowledge": "2025-04", "last_updated": "2025-04", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen3-VL 30B-A3B", "open_weights": true, "reasoning": true, "release_date": "2025-04", "temperature": true, "tool_call": true }, "qwen3-vl-plus": { "attachment": false, "cost": { "input": 0.143353, "output": 1.433525, "reasoning": 4.300576 }, "description": "Qwen3-VL Plus is an AI model provided by alibaba-cn.", "family": "qwen", "id": "qwen3-vl-plus", "knowledge": "2025-04", "last_updated": "2025-09-23", "limit": { "context": 262144, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen3-VL Plus", "open_weights": false, "reasoning": true, "release_date": "2025-09-23", "temperature": true, "tool_call": true }, "qwen3.5-397b-a17b": { "attachment": false, "cost": { "input": 0.43, "output": 2.58, "reasoning": 2.58 }, "description": "Qwen3.5 397B-A17B is an AI model provided by alibaba-cn.", "family": "qwen", "id": "qwen3.5-397b-a17b", "knowledge": "2025-04", "last_updated": "2026-02-16", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen3.5 397B-A17B", "open_weights": true, "reasoning": true, "release_date": "2026-02-16", "temperature": true, "tool_call": true }, "qwen3.5-flash": { "attachment": true, "cost": { "input": 0.172, "output": 1.72, "reasoning": 1.72 }, "description": "Qwen3.5 Flash is an AI model provided by alibaba-cn.", "family": "qwen", "id": "qwen3.5-flash", "knowledge": "2025-04", "last_updated": "2026-02-23", "limit": { "context": 1000000, "output": 65536 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen3.5 Flash", "open_weights": false, "reasoning": true, "release_date": "2026-02-23", "structured_output": true, "temperature": true, "tool_call": true }, "qwen3.5-plus": { "attachment": false, "cost": { "input": 0.573, "output": 3.44, "reasoning": 3.44 }, "description": "Qwen3.5 Plus is an AI model provided by alibaba-cn.", "family": "qwen", "id": "qwen3.5-plus", "knowledge": "2025-04", "last_updated": "2026-02-16", "limit": { "context": 1000000, "output": 65536 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen3.5 Plus", "open_weights": false, "reasoning": true, "release_date": "2026-02-16", "temperature": true, "tool_call": true }, "qwen3.6-max-preview": { "attachment": false, "cost": { "cache_read": 0.132, "input": 1.32, "output": 7.9 }, "description": "Qwen3.6 Max Preview is an AI model provided by alibaba-cn.", "family": "qwen", "id": "qwen3.6-max-preview", "last_updated": "2026-04-21", "limit": { "context": 245800, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3.6 Max Preview", "open_weights": false, "reasoning": true, "release_date": "2026-04-20", "structured_output": true, "temperature": true, "tool_call": true }, "qwen3.6-plus": { "attachment": false, "cost": { "cache_read": 0.05, "cache_write": 0.625, "context_over_200k": { "cache_read": 0.2, "cache_write": 2.5, "input": 2, "output": 6 }, "input": 0.5, "output": 3, "tiers": [ { "cache_read": 0.2, "cache_write": 2.5, "input": 2, "output": 6, "tier": { "size": 256000, "type": "context" } } ] }, "description": "Qwen3.6 Plus is an AI model provided by alibaba-cn.", "family": "qwen", "id": "qwen3.6-plus", "knowledge": "2025-04", "last_updated": "2026-04-02", "limit": { "context": 1000000, "output": 65536 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen3.6 Plus", "open_weights": false, "reasoning": true, "release_date": "2026-04-02", "temperature": true, "tool_call": true }, "qwq-32b": { "attachment": false, "cost": { "input": 0.287, "output": 0.861 }, "description": "QwQ 32B is an AI model provided by alibaba-cn.", "family": "qwen", "id": "qwq-32b", "knowledge": "2024-04", "last_updated": "2024-12", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "QwQ 32B", "open_weights": true, "reasoning": true, "release_date": "2024-12", "temperature": true, "tool_call": true }, "qwq-plus": { "attachment": false, "cost": { "input": 0.23, "output": 0.574 }, "description": "QwQ Plus is an AI model provided by alibaba-cn.", "family": "qwen", "id": "qwq-plus", "knowledge": "2024-04", "last_updated": "2025-03-05", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "QwQ Plus", "open_weights": false, "reasoning": true, "release_date": "2025-03-05", "temperature": true, "tool_call": true }, "siliconflow/deepseek-r1-0528": { "attachment": false, "cost": { "input": 0.5, "output": 2.18 }, "description": "siliconflow/deepseek-r1-0528 is an AI model provided by alibaba-cn.", "family": "deepseek-thinking", "id": "siliconflow/deepseek-r1-0528", "last_updated": "2025-11-25", "limit": { "context": 163840, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "siliconflow/deepseek-r1-0528", "open_weights": false, "reasoning": true, "release_date": "2025-05-28", "structured_output": true, "temperature": true, "tool_call": true }, "siliconflow/deepseek-v3-0324": { "attachment": false, "cost": { "input": 0.25, "output": 1 }, "description": "siliconflow/deepseek-v3-0324 is an AI model provided by alibaba-cn.", "family": "deepseek", "id": "siliconflow/deepseek-v3-0324", "last_updated": "2025-11-25", "limit": { "context": 163840, "output": 163840 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "siliconflow/deepseek-v3-0324", "open_weights": false, "reasoning": false, "release_date": "2024-12-26", "structured_output": true, "temperature": true, "tool_call": true }, "siliconflow/deepseek-v3.1-terminus": { "attachment": false, "cost": { "input": 0.27, "output": 1 }, "description": "siliconflow/deepseek-v3.1-terminus is an AI model provided by alibaba-cn.", "family": "deepseek", "id": "siliconflow/deepseek-v3.1-terminus", "last_updated": "2025-11-25", "limit": { "context": 163840, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "siliconflow/deepseek-v3.1-terminus", "open_weights": false, "reasoning": true, "release_date": "2025-09-29", "structured_output": true, "temperature": true, "tool_call": true }, "siliconflow/deepseek-v3.2": { "attachment": false, "cost": { "input": 0.27, "output": 0.42 }, "description": "siliconflow/deepseek-v3.2 is an AI model provided by alibaba-cn.", "family": "deepseek", "id": "siliconflow/deepseek-v3.2", "last_updated": "2025-12-03", "limit": { "context": 163840, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "siliconflow/deepseek-v3.2", "open_weights": false, "reasoning": true, "release_date": "2025-12-03", "structured_output": true, "temperature": true, "tool_call": true }, "tongyi-intent-detect-v3": { "attachment": false, "cost": { "input": 0.058, "output": 0.144 }, "description": "Tongyi Intent Detect V3 is an AI model provided by alibaba-cn.", "family": "yi", "id": "tongyi-intent-detect-v3", "knowledge": "2024-04", "last_updated": "2024-01", "limit": { "context": 8192, "output": 1024 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Tongyi Intent Detect V3", "open_weights": false, "reasoning": false, "release_date": "2024-01", "temperature": true, "tool_call": false } }, "name": "Alibaba (China)", "npm": "@ai-sdk/openai-compatible" }, "alibaba-coding-plan": { "api": "https://coding-intl.dashscope.aliyuncs.com/v1", "doc": "https://www.alibabacloud.com/help/en/model-studio/coding-plan", "env": [ "ALIBABA_CODING_PLAN_API_KEY" ], "iconURL": "https://models.dev/logos/alibaba-coding-plan.svg", "id": "alibaba-coding-plan", "models": { "MiniMax-M2.5": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "MiniMax-M2.5 is an AI model provided by alibaba-coding-plan.", "family": "minimax", "id": "MiniMax-M2.5", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-02-12", "limit": { "context": 196608, "input": 196601, "output": 24576 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.5", "open_weights": true, "reasoning": true, "release_date": "2026-02-12", "temperature": true, "tool_call": true }, "glm-4.7": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "GLM-4.7 is an AI model provided by alibaba-coding-plan.", "family": "glm", "id": "glm-4.7", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-04", "last_updated": "2025-12-22", "limit": { "context": 202752, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.7", "open_weights": true, "reasoning": true, "release_date": "2025-12-22", "temperature": true, "tool_call": true }, "glm-5": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "GLM-5 is an AI model provided by alibaba-coding-plan.", "family": "glm", "id": "glm-5", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-02-11", "limit": { "context": 202752, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5", "open_weights": false, "reasoning": true, "release_date": "2026-02-11", "temperature": true, "tool_call": true }, "kimi-k2.5": { "attachment": true, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "Kimi K2.5 is an AI model provided by alibaba-coding-plan.", "family": "kimi", "id": "kimi-k2.5", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-01", "last_updated": "2026-01-27", "limit": { "context": 262144, "output": 32768 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Kimi K2.5", "open_weights": true, "reasoning": true, "release_date": "2026-01-27", "temperature": true, "tool_call": true }, "qwen3-coder-next": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "Qwen3 Coder Next is an AI model provided by alibaba-coding-plan.", "family": "qwen", "id": "qwen3-coder-next", "last_updated": "2026-02-03", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Coder Next", "open_weights": true, "reasoning": false, "release_date": "2026-02-03", "structured_output": true, "temperature": true, "tool_call": true }, "qwen3-coder-plus": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "Qwen3 Coder Plus is an AI model provided by alibaba-coding-plan.", "family": "qwen", "id": "qwen3-coder-plus", "knowledge": "2025-04", "last_updated": "2025-07-23", "limit": { "context": 1000000, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Coder Plus", "open_weights": true, "reasoning": false, "release_date": "2025-07-23", "temperature": true, "tool_call": true }, "qwen3-max-2026-01-23": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "Qwen3 Max is an AI model provided by alibaba-coding-plan.", "family": "qwen", "id": "qwen3-max-2026-01-23", "knowledge": "2025-04", "last_updated": "2026-01-23", "limit": { "context": 262144, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Max", "open_weights": false, "reasoning": false, "release_date": "2026-01-23", "temperature": true, "tool_call": true }, "qwen3.5-plus": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "Qwen3.5 Plus is an AI model provided by alibaba-coding-plan.", "family": "qwen", "id": "qwen3.5-plus", "knowledge": "2025-04", "last_updated": "2026-02-16", "limit": { "context": 1000000, "output": 65536 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen3.5 Plus", "open_weights": false, "reasoning": true, "release_date": "2026-02-16", "temperature": true, "tool_call": true }, "qwen3.6-plus": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "Qwen3.6 Plus is an AI model provided by alibaba-coding-plan.", "family": "qwen", "id": "qwen3.6-plus", "knowledge": "2025-04", "last_updated": "2026-04-02", "limit": { "context": 1000000, "output": 65536 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen3.6 Plus", "open_weights": false, "reasoning": true, "release_date": "2026-04-02", "temperature": true, "tool_call": true } }, "name": "Alibaba Coding Plan", "npm": "@ai-sdk/openai-compatible" }, "alibaba-coding-plan-cn": { "api": "https://coding.dashscope.aliyuncs.com/v1", "doc": "https://help.aliyun.com/zh/model-studio/coding-plan", "env": [ "ALIBABA_CODING_PLAN_API_KEY" ], "iconURL": "https://models.dev/logos/alibaba-coding-plan-cn.svg", "id": "alibaba-coding-plan-cn", "models": { "MiniMax-M2.5": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "MiniMax-M2.5 is an AI model provided by alibaba-coding-plan-cn.", "family": "minimax", "id": "MiniMax-M2.5", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-02-12", "limit": { "context": 196608, "output": 24576 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.5", "open_weights": true, "reasoning": true, "release_date": "2026-02-12", "temperature": true, "tool_call": true }, "glm-4.7": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "GLM-4.7 is an AI model provided by alibaba-coding-plan-cn.", "family": "glm", "id": "glm-4.7", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-04", "last_updated": "2025-12-22", "limit": { "context": 202752, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.7", "open_weights": true, "reasoning": true, "release_date": "2025-12-22", "temperature": true, "tool_call": true }, "glm-5": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "GLM-5 is an AI model provided by alibaba-coding-plan-cn.", "family": "glm", "id": "glm-5", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-02-11", "limit": { "context": 202752, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5", "open_weights": false, "reasoning": true, "release_date": "2026-02-11", "temperature": true, "tool_call": true }, "kimi-k2.5": { "attachment": true, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "Kimi K2.5 is an AI model provided by alibaba-coding-plan-cn.", "family": "kimi", "id": "kimi-k2.5", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-01", "last_updated": "2026-01-27", "limit": { "context": 262144, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Kimi K2.5", "open_weights": true, "reasoning": true, "release_date": "2026-01-27", "temperature": true, "tool_call": true }, "qwen3-coder-next": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "Qwen3 Coder Next is an AI model provided by alibaba-coding-plan-cn.", "family": "qwen", "id": "qwen3-coder-next", "last_updated": "2026-02-03", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Coder Next", "open_weights": true, "reasoning": false, "release_date": "2026-02-03", "structured_output": true, "temperature": true, "tool_call": true }, "qwen3-coder-plus": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "Qwen3 Coder Plus is an AI model provided by alibaba-coding-plan-cn.", "family": "qwen", "id": "qwen3-coder-plus", "knowledge": "2025-04", "last_updated": "2025-07-23", "limit": { "context": 1000000, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Coder Plus", "open_weights": true, "reasoning": false, "release_date": "2025-07-23", "temperature": true, "tool_call": true }, "qwen3-max-2026-01-23": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "Qwen3 Max is an AI model provided by alibaba-coding-plan-cn.", "family": "qwen", "id": "qwen3-max-2026-01-23", "knowledge": "2025-04", "last_updated": "2026-01-23", "limit": { "context": 262144, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Max", "open_weights": false, "reasoning": false, "release_date": "2026-01-23", "temperature": true, "tool_call": true }, "qwen3.5-plus": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "Qwen3.5 Plus is an AI model provided by alibaba-coding-plan-cn.", "family": "qwen", "id": "qwen3.5-plus", "knowledge": "2025-04", "last_updated": "2026-02-16", "limit": { "context": 1000000, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen3.5 Plus", "open_weights": false, "reasoning": true, "release_date": "2026-02-16", "temperature": true, "tool_call": true }, "qwen3.6-plus": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "Qwen3.6 Plus is an AI model provided by alibaba-coding-plan-cn.", "family": "qwen", "id": "qwen3.6-plus", "knowledge": "2025-04", "last_updated": "2026-04-02", "limit": { "context": 1000000, "output": 65536 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen3.6 Plus", "open_weights": false, "reasoning": true, "release_date": "2026-04-02", "temperature": true, "tool_call": true } }, "name": "Alibaba Coding Plan (China)", "npm": "@ai-sdk/openai-compatible" }, "aliyun-bailian": { "api": "https://bailian.console.aliyun.com/?tab=api#/api", "id": "aliyun-bailian", "models": { "animate-anyone-gen2": { "cost": { "currency": "CNY", "per_second_standard": 0.08 }, "description": "animate-anyone-gen2 is an AI model provided by aliyun-bailian.", "id": "animate-anyone-gen2", "name": "animate-anyone-gen2" }, "animate-anyone-template-gen2": { "cost": { "currency": "CNY", "per_second_standard": 0.08 }, "description": "animate-anyone-template-gen2 is an AI model provided by aliyun-bailian.", "id": "animate-anyone-template-gen2", "name": "animate-anyone-template-gen2" }, "cosyvoice-v1": { "cost": { "currency": "CNY", "per_10k_chars": 2 }, "description": "cosyvoice-v1 is an AI model provided by aliyun-bailian.", "id": "cosyvoice-v1", "name": "cosyvoice-v1" }, "cosyvoice-v2": { "cost": { "currency": "CNY", "per_10k_chars": 2 }, "description": "cosyvoice-v2 is an AI model provided by aliyun-bailian.", "id": "cosyvoice-v2", "name": "cosyvoice-v2" }, "cosyvoice-v3": { "cost": { "currency": "CNY", "per_10k_chars": 0.4 }, "description": "cosyvoice-v3 is an AI model provided by aliyun-bailian.", "id": "cosyvoice-v3", "name": "cosyvoice-v3" }, "cosyvoice-v3-plus": { "cost": { "currency": "CNY", "per_10k_chars": 2 }, "description": "cosyvoice-v3-plus is an AI model provided by aliyun-bailian.", "id": "cosyvoice-v3-plus", "name": "cosyvoice-v3-plus" }, "fun-asr": { "cost": { "currency": "CNY", "per_second": 0.00022 }, "description": "fun-asr is an AI model provided by aliyun-bailian.", "id": "fun-asr", "name": "fun-asr" }, "fun-asr-2025-08-25": { "cost": { "currency": "CNY", "per_second": 0.00022 }, "description": "fun-asr-2025-08-25 is an AI model provided by aliyun-bailian.", "id": "fun-asr-2025-08-25", "name": "fun-asr-2025-08-25" }, "fun-asr-mtl": { "cost": { "currency": "CNY", "per_second": 0.00022 }, "description": "fun-asr-mtl is an AI model provided by aliyun-bailian.", "id": "fun-asr-mtl", "name": "fun-asr-mtl" }, "fun-asr-mtl-2025-08-25": { "cost": { "currency": "CNY", "per_second": 0.00022 }, "description": "fun-asr-mtl-2025-08-25 is an AI model provided by aliyun-bailian.", "id": "fun-asr-mtl-2025-08-25", "name": "fun-asr-mtl-2025-08-25" }, "fun-asr-realtime": { "cost": { "currency": "CNY", "per_second": 0.00033 }, "description": "fun-asr-realtime is an AI model provided by aliyun-bailian.", "id": "fun-asr-realtime", "name": "fun-asr-realtime" }, "fun-asr-realtime-2025-09-15": { "cost": { "currency": "CNY", "per_second": 0.00033 }, "description": "fun-asr-realtime-2025-09-15 is an AI model provided by aliyun-bailian.", "id": "fun-asr-realtime-2025-09-15", "name": "fun-asr-realtime-2025-09-15" }, "gte-rerank-v2": { "cost": { "currency": "CNY", "input": 0.8 }, "description": "gte-rerank-v2 is an AI model provided by aliyun-bailian.", "id": "gte-rerank-v2", "name": "gte-rerank-v2" }, "image-out-painting": { "cost": { "currency": "CNY", "per_image": 0.18 }, "description": "image-out-painting is an AI model provided by aliyun-bailian.", "id": "image-out-painting", "name": "image-out-painting" }, "multimodal-embedding-v1": { "cost": { "currency": "CNY", "embedding_image": 0.9, "embedding_text": 0.7 }, "description": "multimodal-embedding-v1 is an AI model provided by aliyun-bailian.", "id": "multimodal-embedding-v1", "name": "multimodal-embedding-v1" }, "paraformer-8k-v2": { "cost": { "currency": "CNY", "per_second": 0.00008 }, "description": "paraformer-8k-v2 is an AI model provided by aliyun-bailian.", "id": "paraformer-8k-v2", "name": "paraformer-8k-v2" }, "paraformer-realtime-8k-v2": { "cost": { "currency": "CNY", "per_second": 0.00024 }, "description": "paraformer-realtime-8k-v2 is an AI model provided by aliyun-bailian.", "id": "paraformer-realtime-8k-v2", "name": "paraformer-realtime-8k-v2" }, "paraformer-realtime-v2": { "cost": { "currency": "CNY", "per_second": 0.00024 }, "description": "paraformer-realtime-v2 is an AI model provided by aliyun-bailian.", "id": "paraformer-realtime-v2", "name": "paraformer-realtime-v2" }, "paraformer-v2": { "cost": { "currency": "CNY", "per_second": 0.00008 }, "description": "paraformer-v2 is an AI model provided by aliyun-bailian.", "id": "paraformer-v2", "name": "paraformer-v2" }, "qvq-max-2025-03-25": { "cost": { "currency": "CNY", "input": 8, "output": 32 }, "description": "qvq-max-2025-03-25 is an AI model provided by aliyun-bailian.", "id": "qvq-max-2025-03-25", "name": "qvq-max-2025-03-25" }, "qwen-coder-turbo-2024-09-19": { "cost": { "currency": "CNY", "input": 2, "output": 6 }, "description": "qwen-coder-turbo-2024-09-19 is an AI model provided by aliyun-bailian.", "id": "qwen-coder-turbo-2024-09-19", "name": "qwen-coder-turbo-2024-09-19" }, "qwen-coder-turbo-latest": { "cost": { "currency": "CNY", "input": 2, "output": 6 }, "description": "qwen-coder-turbo-latest is an AI model provided by aliyun-bailian.", "id": "qwen-coder-turbo-latest", "name": "qwen-coder-turbo-latest" }, "qwen-flash": { "cost": { "cache_read": 0.015, "cache_read_128k_256k": 0.06, "cache_read_256k_1m": 0.12, "cache_write": 0.188, "cache_write_128k_256k": 0.75, "cache_write_256k_1m": 1.5, "currency": "CNY", "input": 0.15, "input_128k_256k": 0.6, "input_256k_1m": 1.2, "output": 1.5, "output_128k_256k": 6, "output_256k_1m": 12 }, "description": "qwen-flash is an AI model provided by aliyun-bailian.", "id": "qwen-flash", "name": "qwen-flash" }, "qwen-flash-2025-07-28": { "cost": { "currency": "CNY", "input": 0.15, "input_128k_256k": 0.6, "input_256k_1m": 1.2, "output": 1.5, "output_128k_256k": 6, "output_256k_1m": 12 }, "description": "qwen-flash-2025-07-28 is an AI model provided by aliyun-bailian.", "id": "qwen-flash-2025-07-28", "name": "qwen-flash-2025-07-28" }, "qwen-image": { "cost": { "currency": "CNY", "per_image": 0.25 }, "description": "qwen-image is an AI model provided by aliyun-bailian.", "id": "qwen-image", "name": "qwen-image" }, "qwen-image-edit": { "cost": { "currency": "CNY", "per_image": 0.3 }, "description": "qwen-image-edit is an AI model provided by aliyun-bailian.", "id": "qwen-image-edit", "name": "qwen-image-edit" }, "qwen-image-plus": { "cost": { "currency": "CNY", "per_image": 0.2 }, "description": "qwen-image-plus is an AI model provided by aliyun-bailian.", "id": "qwen-image-plus", "name": "qwen-image-plus" }, "qwen-long": { "cost": { "currency": "CNY", "input": 0.5, "output": 2 }, "description": "qwen-long is an AI model provided by aliyun-bailian.", "id": "qwen-long", "name": "qwen-long" }, "qwen-long-latest": { "cost": { "currency": "CNY", "input": 0.5, "output": 2 }, "description": "qwen-long-latest is an AI model provided by aliyun-bailian.", "id": "qwen-long-latest", "name": "qwen-long-latest" }, "qwen-max": { "cost": { "cache_read": 0.48, "currency": "CNY", "input": 2.4, "output": 9.6 }, "description": "qwen-max is an AI model provided by aliyun-bailian.", "id": "qwen-max", "name": "qwen-max" }, "qwen-max-latest": { "cost": { "currency": "CNY", "input": 2.4, "output": 9.6 }, "description": "qwen-max-latest is an AI model provided by aliyun-bailian.", "id": "qwen-max-latest", "name": "qwen-max-latest" }, "qwen-mt-image": { "cost": { "currency": "CNY", "per_image": 0.003 }, "description": "qwen-mt-image is an AI model provided by aliyun-bailian.", "id": "qwen-mt-image", "name": "qwen-mt-image" }, "qwen-mt-plus": { "cost": { "currency": "CNY", "input": 1.8, "output": 5.4 }, "description": "qwen-mt-plus is an AI model provided by aliyun-bailian.", "id": "qwen-mt-plus", "name": "qwen-mt-plus" }, "qwen-mt-turbo": { "cost": { "currency": "CNY", "input": 0.7, "output": 1.95 }, "description": "qwen-mt-turbo is an AI model provided by aliyun-bailian.", "id": "qwen-mt-turbo", "name": "qwen-mt-turbo" }, "qwen-omni-turbo": { "cost": { "audio_input": 25, "audio_input_cache": 5, "currency": "CNY", "multi_output": 50, "multiin_text_output": 4.5, "purein_text_output": 1.6, "text_input": 0.4, "text_input_cache": 0.08, "vision_input": 1.5, "vision_input_cache": 0.3 }, "description": "qwen-omni-turbo is an AI model provided by aliyun-bailian.", "id": "qwen-omni-turbo", "name": "qwen-omni-turbo" }, "qwen-omni-turbo-latest": { "cost": { "audio_input": 25, "currency": "CNY", "multi_output": 50, "multiin_text_output": 4.5, "purein_text_output": 1.6, "text_input": 0.4, "vision_input": 1.5 }, "description": "qwen-omni-turbo-latest is an AI model provided by aliyun-bailian.", "id": "qwen-omni-turbo-latest", "name": "qwen-omni-turbo-latest" }, "qwen-omni-turbo-realtime": { "cost": { "audio_input": 25, "currency": "CNY", "multi_output": 50, "multiin_text_output": 18, "purein_text_output": 6.4, "text_input": 1.6, "vision_input": 6 }, "description": "qwen-omni-turbo-realtime is an AI model provided by aliyun-bailian.", "id": "qwen-omni-turbo-realtime", "name": "qwen-omni-turbo-realtime" }, "qwen-omni-turbo-realtime-latest": { "cost": { "audio_input": 25, "currency": "CNY", "multi_output": 50, "multiin_text_output": 18, "purein_text_output": 6.4, "text_input": 1.6, "vision_input": 6 }, "description": "qwen-omni-turbo-realtime-latest is an AI model provided by aliyun-bailian.", "id": "qwen-omni-turbo-realtime-latest", "name": "qwen-omni-turbo-realtime-latest" }, "qwen-plus": { "cost": { "cache_read": 0.08, "cache_read_128k_256k": 0.24, "cache_read_256k_1m": 0.48, "cache_write": 1, "cache_write_128k_256k": 3, "cache_write_256k_1m": 6, "currency": "CNY", "input": 0.8, "input_128k_256k": 2.4, "input_256k_1m": 4.8, "output": 2, "output_128k_256k": 20, "output_256k_1m": 48, "thinking_cache_read": 0.08, "thinking_cache_read_128k_256k": 0.24, "thinking_cache_read_256k_1m": 0.48, "thinking_cache_write": 1, "thinking_cache_write_128k_256k": 3, "thinking_cache_write_256k_1m": 6, "thinking_input": 0.8, "thinking_input_128k_256k": 2.4, "thinking_input_256k_1m": 4.8, "thinking_output": 8, "thinking_output_128k_256k": 24, "thinking_output_256k_1m": 64 }, "description": "qwen-plus is an AI model provided by aliyun-bailian.", "id": "qwen-plus", "name": "qwen-plus" }, "qwen-plus-2024-09-19": { "cost": { "currency": "CNY", "input": 0.8, "output": 2 }, "description": "qwen-plus-2024-09-19 is an AI model provided by aliyun-bailian.", "id": "qwen-plus-2024-09-19", "name": "qwen-plus-2024-09-19" }, "qwen-plus-latest": { "cost": { "currency": "CNY", "input": 0.8, "input_128k_256k": 2.4, "input_256k_1m": 4.8, "output": 2, "output_128k_256k": 20, "output_256k_1m": 48, "thinking_input": 0.8, "thinking_input_128k_256k": 2.4, "thinking_input_256k_1m": 4.8, "thinking_output": 8, "thinking_output_128k_256k": 24, "thinking_output_256k_1m": 64 }, "description": "qwen-plus-latest is an AI model provided by aliyun-bailian.", "id": "qwen-plus-latest", "name": "qwen-plus-latest" }, "qwen-turbo": { "cost": { "cache_read": 0.06, "currency": "CNY", "input": 0.3, "output": 0.6, "text": 2, "thinking_cache_read": 0.06, "thinking_input": 0.3, "thinking_output": 3 }, "description": "qwen-turbo is an AI model provided by aliyun-bailian.", "id": "qwen-turbo", "name": "qwen-turbo" }, "qwen-turbo-latest": { "cost": { "currency": "CNY", "input": 0.3, "output": 0.6, "thinking_input": 0.3, "thinking_output": 3 }, "description": "qwen-turbo-latest is an AI model provided by aliyun-bailian.", "id": "qwen-turbo-latest", "name": "qwen-turbo-latest" }, "qwen-vl-max": { "cost": { "cache_read": 0.32, "currency": "CNY", "input": 1.6, "output": 4 }, "description": "qwen-vl-max is an AI model provided by aliyun-bailian.", "id": "qwen-vl-max", "name": "qwen-vl-max" }, "qwen-vl-max-latest": { "cost": { "currency": "CNY", "input": 1.6, "output": 4 }, "description": "qwen-vl-max-latest is an AI model provided by aliyun-bailian.", "id": "qwen-vl-max-latest", "name": "qwen-vl-max-latest" }, "qwen-vl-ocr": { "cost": { "currency": "CNY", "vl": 5 }, "description": "qwen-vl-ocr is an AI model provided by aliyun-bailian.", "id": "qwen-vl-ocr", "name": "qwen-vl-ocr" }, "qwen-vl-ocr-latest": { "cost": { "currency": "CNY", "vl": 5 }, "description": "qwen-vl-ocr-latest is an AI model provided by aliyun-bailian.", "id": "qwen-vl-ocr-latest", "name": "qwen-vl-ocr-latest" }, "qwen-vl-plus": { "cost": { "cache_read": 0.16, "currency": "CNY", "input": 0.8, "output": 2 }, "description": "qwen-vl-plus is an AI model provided by aliyun-bailian.", "id": "qwen-vl-plus", "name": "qwen-vl-plus" }, "qwen-vl-plus-latest": { "cost": { "currency": "CNY", "input": 0.8, "output": 2 }, "description": "qwen-vl-plus-latest is an AI model provided by aliyun-bailian.", "id": "qwen-vl-plus-latest", "name": "qwen-vl-plus-latest" }, "qwen2.5-14b-instruct": { "cost": { "currency": "CNY", "input": 1, "output": 3 }, "description": "qwen2.5-14b-instruct is an AI model provided by aliyun-bailian.", "id": "qwen2.5-14b-instruct", "name": "qwen2.5-14b-instruct" }, "qwen2.5-14b-instruct-1m": { "cost": { "currency": "CNY", "input": 1, "output": 3 }, "description": "qwen2.5-14b-instruct-1m is an AI model provided by aliyun-bailian.", "id": "qwen2.5-14b-instruct-1m", "name": "qwen2.5-14b-instruct-1m" }, "qwen2.5-32b-instruct": { "cost": { "currency": "CNY", "input": 2, "output": 6 }, "description": "qwen2.5-32b-instruct is an AI model provided by aliyun-bailian.", "id": "qwen2.5-32b-instruct", "name": "qwen2.5-32b-instruct" }, "qwen2.5-3b-instruct": { "cost": { "currency": "CNY", "input": 0.3, "output": 0.9 }, "description": "qwen2.5-3b-instruct is an AI model provided by aliyun-bailian.", "id": "qwen2.5-3b-instruct", "name": "qwen2.5-3b-instruct" }, "qwen2.5-72b-instruct": { "cost": { "currency": "CNY", "input": 4, "output": 12 }, "description": "qwen2.5-72b-instruct is an AI model provided by aliyun-bailian.", "id": "qwen2.5-72b-instruct", "name": "qwen2.5-72b-instruct" }, "qwen2.5-7b-instruct": { "cost": { "currency": "CNY", "input": 0.5, "output": 1 }, "description": "qwen2.5-7b-instruct is an AI model provided by aliyun-bailian.", "id": "qwen2.5-7b-instruct", "name": "qwen2.5-7b-instruct" }, "qwen2.5-7b-instruct-1m": { "cost": { "currency": "CNY", "input": 0.5, "output": 1 }, "description": "qwen2.5-7b-instruct-1m is an AI model provided by aliyun-bailian.", "id": "qwen2.5-7b-instruct-1m", "name": "qwen2.5-7b-instruct-1m" }, "qwen2.5-coder-14b-instruct": { "cost": { "currency": "CNY", "input": 2, "output": 6 }, "description": "qwen2.5-coder-14b-instruct is an AI model provided by aliyun-bailian.", "id": "qwen2.5-coder-14b-instruct", "name": "qwen2.5-coder-14b-instruct" }, "qwen2.5-coder-32b-instruct": { "cost": { "currency": "CNY", "input": 2, "output": 6 }, "description": "qwen2.5-coder-32b-instruct is an AI model provided by aliyun-bailian.", "id": "qwen2.5-coder-32b-instruct", "name": "qwen2.5-coder-32b-instruct" }, "qwen2.5-coder-7b-instruct": { "cost": { "currency": "CNY", "input": 1, "output": 2 }, "description": "qwen2.5-coder-7b-instruct is an AI model provided by aliyun-bailian.", "id": "qwen2.5-coder-7b-instruct", "name": "qwen2.5-coder-7b-instruct" }, "qwen2.5-omni-7b": { "cost": { "audio_input": 38, "currency": "CNY", "multi_output": 76, "multiin_text_output": 6, "purein_text_output": 2.4, "text_input": 0.6, "vision_input": 2 }, "description": "qwen2.5-omni-7b is an AI model provided by aliyun-bailian.", "id": "qwen2.5-omni-7b", "name": "qwen2.5-omni-7b" }, "qwen2.5-vl-32b-instruct": { "cost": { "currency": "CNY", "input": 8, "output": 24 }, "description": "qwen2.5-vl-32b-instruct is an AI model provided by aliyun-bailian.", "id": "qwen2.5-vl-32b-instruct", "name": "qwen2.5-vl-32b-instruct" }, "qwen2.5-vl-3b-instruct": { "cost": { "currency": "CNY", "input": 1.2, "output": 3.6 }, "description": "qwen2.5-vl-3b-instruct is an AI model provided by aliyun-bailian.", "id": "qwen2.5-vl-3b-instruct", "name": "qwen2.5-vl-3b-instruct" }, "qwen2.5-vl-72b-instruct": { "cost": { "currency": "CNY", "input": 16, "output": 48 }, "description": "qwen2.5-vl-72b-instruct is an AI model provided by aliyun-bailian.", "id": "qwen2.5-vl-72b-instruct", "name": "qwen2.5-vl-72b-instruct" }, "qwen2.5-vl-7b-instruct": { "cost": { "currency": "CNY", "input": 2, "output": 5 }, "description": "qwen2.5-vl-7b-instruct is an AI model provided by aliyun-bailian.", "id": "qwen2.5-vl-7b-instruct", "name": "qwen2.5-vl-7b-instruct" }, "qwen3-0.6b": { "cost": { "currency": "CNY", "input": 0.3, "output": 1.2, "thinking_input": 0.3, "thinking_output": 3 }, "description": "qwen3-0.6b is an AI model provided by aliyun-bailian.", "id": "qwen3-0.6b", "name": "qwen3-0.6b" }, "qwen3-1.7b": { "cost": { "currency": "CNY", "input": 0.3, "output": 1.2, "thinking_input": 0.3, "thinking_output": 3 }, "description": "qwen3-1.7b is an AI model provided by aliyun-bailian.", "id": "qwen3-1.7b", "name": "qwen3-1.7b" }, "qwen3-14b": { "cost": { "currency": "CNY", "input": 1, "output": 4, "thinking_input": 1, "thinking_output": 10 }, "description": "qwen3-14b is an AI model provided by aliyun-bailian.", "id": "qwen3-14b", "name": "qwen3-14b" }, "qwen3-235b-a22b": { "cost": { "currency": "CNY", "input": 2, "output": 8, "thinking_input": 2, "thinking_output": 20 }, "description": "qwen3-235b-a22b is an AI model provided by aliyun-bailian.", "id": "qwen3-235b-a22b", "name": "qwen3-235b-a22b" }, "qwen3-235b-a22b-instruct-2507": { "cost": { "currency": "CNY", "input": 2, "output": 8 }, "description": "qwen3-235b-a22b-instruct-2507 is an AI model provided by aliyun-bailian.", "id": "qwen3-235b-a22b-instruct-2507", "name": "qwen3-235b-a22b-instruct-2507" }, "qwen3-235b-a22b-thinking-2507": { "cost": { "currency": "CNY", "thinking_input": 2, "thinking_output": 20 }, "description": "qwen3-235b-a22b-thinking-2507 is an AI model provided by aliyun-bailian.", "id": "qwen3-235b-a22b-thinking-2507", "name": "qwen3-235b-a22b-thinking-2507" }, "qwen3-30b-a3b": { "cost": { "currency": "CNY", "input": 0.75, "output": 3, "thinking_input": 0.75, "thinking_output": 7.5 }, "description": "qwen3-30b-a3b is an AI model provided by aliyun-bailian.", "id": "qwen3-30b-a3b", "name": "qwen3-30b-a3b" }, "qwen3-32b": { "cost": { "currency": "CNY", "input": 2, "output": 8, "thinking_input": 2, "thinking_output": 20 }, "description": "qwen3-32b is an AI model provided by aliyun-bailian.", "id": "qwen3-32b", "name": "qwen3-32b" }, "qwen3-4b": { "cost": { "currency": "CNY", "input": 0.3, "output": 1.2, "thinking_input": 0.3, "thinking_output": 3 }, "description": "qwen3-4b is an AI model provided by aliyun-bailian.", "id": "qwen3-4b", "name": "qwen3-4b" }, "qwen3-8b": { "cost": { "currency": "CNY", "input": 0.5, "output": 2, "thinking_input": 0.5, "thinking_output": 5 }, "description": "qwen3-8b is an AI model provided by aliyun-bailian.", "id": "qwen3-8b", "name": "qwen3-8b" }, "qwen3-asr-flash": { "cost": { "currency": "CNY", "per_second": 0.00022 }, "description": "qwen3-asr-flash is an AI model provided by aliyun-bailian.", "id": "qwen3-asr-flash", "name": "qwen3-asr-flash" }, "qwen3-asr-flash-2025-09-08": { "cost": { "currency": "CNY", "per_second": 0.00022 }, "description": "qwen3-asr-flash-2025-09-08 is an AI model provided by aliyun-bailian.", "id": "qwen3-asr-flash-2025-09-08", "name": "qwen3-asr-flash-2025-09-08" }, "qwen3-coder-30b-a3b-instruct": { "cost": { "currency": "CNY", "input": 1.5, "input_128k_256k": 3.75, "input_256k_1m": 7.5, "input_32k_128k": 2.25, "output": 6, "output_128k_256k": 15, "output_256k_1m": 37.5, "output_32k_128k": 9 }, "description": "qwen3-coder-30b-a3b-instruct is an AI model provided by aliyun-bailian.", "id": "qwen3-coder-30b-a3b-instruct", "name": "qwen3-coder-30b-a3b-instruct" }, "qwen3-coder-480b-a35b-instruct": { "cost": { "currency": "CNY", "input": 6, "input_128k_256k": 15, "input_256k_1m": 30, "input_32k_128k": 9, "output": 24, "output_128k_256k": 60, "output_256k_1m": 300, "output_32k_128k": 36 }, "description": "qwen3-coder-480b-a35b-instruct is an AI model provided by aliyun-bailian.", "id": "qwen3-coder-480b-a35b-instruct", "name": "qwen3-coder-480b-a35b-instruct" }, "qwen3-coder-flash": { "cost": { "cache_read": 0.1, "cache_read_128k_256k": 0.25, "cache_read_256k_1m": 0.5, "cache_read_32k_128k": 0.15, "cache_write": 1.25, "cache_write_128k_256k": 3.125, "cache_write_256k_1m": 6.25, "cache_write_32k_128k": 1.875, "currency": "CNY", "input": 1, "input_128k_256k": 2.5, "input_256k_1m": 5, "input_32k_128k": 1.5, "output": 4, "output_128k_256k": 10, "output_256k_1m": 25, "output_32k_128k": 6 }, "description": "qwen3-coder-flash is an AI model provided by aliyun-bailian.", "id": "qwen3-coder-flash", "name": "qwen3-coder-flash" }, "qwen3-coder-plus": { "cost": { "cache_read": 0.4, "cache_read_128k_256k": 1, "cache_read_256k_1m": 2, "cache_read_32k_128k": 0.6, "cache_write": 5, "cache_write_128k_256k": 12.5, "cache_write_256k_1m": 25, "cache_write_32k_128k": 7.5, "currency": "CNY", "input": 4, "input_128k_256k": 10, "input_256k_1m": 20, "input_32k_128k": 6, "output": 16, "output_128k_256k": 40, "output_256k_1m": 200, "output_32k_128k": 24 }, "description": "qwen3-coder-plus is an AI model provided by aliyun-bailian.", "id": "qwen3-coder-plus", "name": "qwen3-coder-plus" }, "qwen3-coder-plus-2025-07-22": { "cost": { "currency": "CNY", "input": 4, "input_128k_256k": 10, "input_256k_1m": 20, "input_32k_128k": 6, "output": 16, "output_128k_256k": 40, "output_256k_1m": 200, "output_32k_128k": 24 }, "description": "qwen3-coder-plus-2025-07-22 is an AI model provided by aliyun-bailian.", "id": "qwen3-coder-plus-2025-07-22", "name": "qwen3-coder-plus-2025-07-22" }, "qwen3-coder-plus-2025-09-23": { "cost": { "currency": "CNY", "input": 4, "input_128k_256k": 10, "input_256k_1m": 20, "input_32k_128k": 6, "output": 16, "output_128k_256k": 40, "output_256k_1m": 200, "output_32k_128k": 24 }, "description": "qwen3-coder-plus-2025-09-23 is an AI model provided by aliyun-bailian.", "id": "qwen3-coder-plus-2025-09-23", "name": "qwen3-coder-plus-2025-09-23" }, "qwen3-max": { "cost": { "cache_read": 0.6, "cache_read_128k_256k": 1.5, "cache_read_32k_128k": 1, "cache_write": 7.5, "cache_write_128k_256k": 18.75, "cache_write_32k_128k": 12.5, "currency": "CNY", "input": 6, "input_128k_256k": 15, "input_32k_128k": 10, "output": 24, "output_128k_256k": 60, "output_32k_128k": 40 }, "description": "qwen3-max is an AI model provided by aliyun-bailian.", "id": "qwen3-max", "name": "qwen3-max" }, "qwen3-max-2025-09-23": { "cost": { "currency": "CNY", "input": 6, "input_128k_256k": 15, "input_32k_128k": 10, "output": 24, "output_128k_256k": 60, "output_32k_128k": 40 }, "description": "qwen3-max-2025-09-23 is an AI model provided by aliyun-bailian.", "id": "qwen3-max-2025-09-23", "name": "qwen3-max-2025-09-23" }, "qwen3-max-preview": { "cost": { "cache_read": 1.2, "cache_read_128k_256k": 3, "cache_read_32k_128k": 2, "currency": "CNY", "input": 6, "input_128k_256k": 15, "input_32k_128k": 10, "output": 24, "output_128k_256k": 60, "output_32k_128k": 40 }, "description": "qwen3-max-preview is an AI model provided by aliyun-bailian.", "id": "qwen3-max-preview", "name": "qwen3-max-preview" }, "qwen3-omni-30b-a3b-captioner": { "cost": { "audio_input": 15.8, "currency": "CNY", "multiin_text_output": 12.7 }, "description": "qwen3-omni-30b-a3b-captioner is an AI model provided by aliyun-bailian.", "id": "qwen3-omni-30b-a3b-captioner", "name": "qwen3-omni-30b-a3b-captioner" }, "qwen3-omni-flash": { "cost": { "audio_input": 15.8, "currency": "CNY", "multi_output": 62.6, "multiin_text_output": 12.7, "purein_text_output": 6.9, "text_input": 1.8, "thinking_audio_input": 15.8, "thinking_multiin_text_output": 12.7, "thinking_purein_text_output": 6.9, "thinking_text_input": 1.8, "thinking_vision_input": 3.3, "vision_input": 3.3 }, "description": "qwen3-omni-flash is an AI model provided by aliyun-bailian.", "id": "qwen3-omni-flash", "name": "qwen3-omni-flash" }, "qwen3-omni-flash-2025-09-15": { "cost": { "audio_input": 15.8, "currency": "CNY", "multi_output": 62.6, "multiin_text_output": 12.7, "purein_text_output": 6.9, "text_input": 1.8, "thinking_audio_input": 15.8, "thinking_multiin_text_output": 12.7, "thinking_purein_text_output": 6.9, "thinking_text_input": 1.8, "thinking_vision_input": 3.3, "vision_input": 3.3 }, "description": "qwen3-omni-flash-2025-09-15 is an AI model provided by aliyun-bailian.", "id": "qwen3-omni-flash-2025-09-15", "name": "qwen3-omni-flash-2025-09-15" }, "qwen3-omni-flash-realtime": { "cost": { "audio_input": 18.9, "currency": "CNY", "multi_output": 75.1, "multiin_text_output": 15.2, "purein_text_output": 8.3, "text_input": 2.2, "vision_input": 3.9 }, "description": "qwen3-omni-flash-realtime is an AI model provided by aliyun-bailian.", "id": "qwen3-omni-flash-realtime", "name": "qwen3-omni-flash-realtime" }, "qwen3-omni-flash-realtime-2025-09-15": { "cost": { "audio_input": 18.9, "currency": "CNY", "multi_output": 75.1, "multiin_text_output": 15.2, "purein_text_output": 8.3, "text_input": 2.2, "vision_input": 3.9 }, "description": "qwen3-omni-flash-realtime-2025-09-15 is an AI model provided by aliyun-bailian.", "id": "qwen3-omni-flash-realtime-2025-09-15", "name": "qwen3-omni-flash-realtime-2025-09-15" }, "qwen3-tts-flash": { "cost": { "currency": "CNY", "per_10k_chars": 0.8 }, "description": "qwen3-tts-flash is an AI model provided by aliyun-bailian.", "id": "qwen3-tts-flash", "name": "qwen3-tts-flash" }, "qwen3-tts-flash-2025-09-18": { "cost": { "currency": "CNY", "per_10k_chars": 0.8 }, "description": "qwen3-tts-flash-2025-09-18 is an AI model provided by aliyun-bailian.", "id": "qwen3-tts-flash-2025-09-18", "name": "qwen3-tts-flash-2025-09-18" }, "qwen3-tts-flash-realtime": { "cost": { "currency": "CNY", "per_10k_chars": 1 }, "description": "qwen3-tts-flash-realtime is an AI model provided by aliyun-bailian.", "id": "qwen3-tts-flash-realtime", "name": "qwen3-tts-flash-realtime" }, "qwen3-tts-flash-realtime-2025-09-18": { "cost": { "currency": "CNY", "per_10k_chars": 1 }, "description": "qwen3-tts-flash-realtime-2025-09-18 is an AI model provided by aliyun-bailian.", "id": "qwen3-tts-flash-realtime-2025-09-18", "name": "qwen3-tts-flash-realtime-2025-09-18" }, "qwen3-vl-plus": { "cost": { "cache_read": 0.2, "cache_read_128k_256k": 0.6, "cache_read_32k_128k": 0.3, "currency": "CNY", "input": 1, "input_128k_256k": 3, "input_32k_128k": 1.5, "output": 10, "output_128k_256k": 30, "output_32k_128k": 15 }, "description": "qwen3-vl-plus is an AI model provided by aliyun-bailian.", "id": "qwen3-vl-plus", "name": "qwen3-vl-plus" }, "qwen3-vl-plus-2025-09-23": { "cost": { "currency": "CNY", "input": 1, "input_128k_256k": 3, "input_32k_128k": 1.5, "output": 10, "output_128k_256k": 30, "output_32k_128k": 15 }, "description": "qwen3-vl-plus-2025-09-23 is an AI model provided by aliyun-bailian.", "id": "qwen3-vl-plus-2025-09-23", "name": "qwen3-vl-plus-2025-09-23" }, "qwq-32b": { "cost": { "currency": "CNY", "input": 2, "output": 6 }, "description": "qwq-32b is an AI model provided by aliyun-bailian.", "id": "qwq-32b", "name": "qwq-32b" }, "qwq-32b-preview": { "cost": { "currency": "CNY", "input": 2, "output": 6 }, "description": "qwq-32b-preview is an AI model provided by aliyun-bailian.", "id": "qwq-32b-preview", "name": "qwq-32b-preview" }, "qwq-plus": { "cost": { "currency": "CNY", "input": 1.6, "output": 4 }, "description": "qwq-plus is an AI model provided by aliyun-bailian.", "id": "qwq-plus", "name": "qwq-plus" }, "qwq-plus-latest": { "cost": { "currency": "CNY", "input": 1.6, "output": 4 }, "description": "qwq-plus-latest is an AI model provided by aliyun-bailian.", "id": "qwq-plus-latest", "name": "qwq-plus-latest" }, "text-embedding-async-v2": { "cost": { "currency": "CNY", "input": 0.7 }, "description": "text-embedding-async-v2 is an AI model provided by aliyun-bailian.", "id": "text-embedding-async-v2", "name": "text-embedding-async-v2" }, "text-embedding-v1": { "cost": { "currency": "CNY", "input": 0.7 }, "description": "text-embedding-v1 is an AI model provided by aliyun-bailian.", "id": "text-embedding-v1", "name": "text-embedding-v1" }, "text-embedding-v2": { "cost": { "currency": "CNY", "input": 0.7 }, "description": "text-embedding-v2 is an AI model provided by aliyun-bailian.", "id": "text-embedding-v2", "name": "text-embedding-v2" }, "text-embedding-v3": { "cost": { "currency": "CNY", "input": 0.5 }, "description": "text-embedding-v3 is an AI model provided by aliyun-bailian.", "id": "text-embedding-v3", "name": "text-embedding-v3" }, "text-embedding-v4": { "cost": { "currency": "CNY", "input": 0.5 }, "description": "text-embedding-v4 is an AI model provided by aliyun-bailian.", "id": "text-embedding-v4", "name": "text-embedding-v4" }, "tongyi-embedding-vision-flash": { "cost": { "currency": "CNY", "embedding_image": 0.5, "embedding_text": 0.2 }, "description": "tongyi-embedding-vision-flash is an AI model provided by aliyun-bailian.", "id": "tongyi-embedding-vision-flash", "name": "tongyi-embedding-vision-flash" }, "tongyi-embedding-vision-plus": { "cost": { "currency": "CNY", "embedding_image": 0.5, "embedding_text": 0.5 }, "description": "tongyi-embedding-vision-plus is an AI model provided by aliyun-bailian.", "id": "tongyi-embedding-vision-plus", "name": "tongyi-embedding-vision-plus" }, "tongyi-intent-detect-v3": { "cost": { "currency": "CNY", "input": 0.4, "output": 1 }, "description": "tongyi-intent-detect-v3 is an AI model provided by aliyun-bailian.", "id": "tongyi-intent-detect-v3", "name": "tongyi-intent-detect-v3" }, "wan2.2-animate-mix": { "cost": { "currency": "CNY", "per_second_pro": 0.9, "per_second_standard": 0.6 }, "description": "wan2.2-animate-mix is an AI model provided by aliyun-bailian.", "id": "wan2.2-animate-mix", "name": "wan2.2-animate-mix" }, "wan2.2-animate-move": { "cost": { "currency": "CNY", "per_second_pro": 0.6, "per_second_standard": 0.4 }, "description": "wan2.2-animate-move is an AI model provided by aliyun-bailian.", "id": "wan2.2-animate-move", "name": "wan2.2-animate-move" }, "wan2.2-i2v-flash": { "cost": { "currency": "CNY", "per_second_1080p": 0.48, "per_second_480p": 0.1, "per_second_720p": 0.2 }, "description": "wan2.2-i2v-flash is an AI model provided by aliyun-bailian.", "id": "wan2.2-i2v-flash", "name": "wan2.2-i2v-flash" }, "wan2.2-i2v-plus": { "cost": { "currency": "CNY", "per_second_1080p": 0.7, "per_second_480p": 0.14 }, "description": "wan2.2-i2v-plus is an AI model provided by aliyun-bailian.", "id": "wan2.2-i2v-plus", "name": "wan2.2-i2v-plus" }, "wan2.2-kf2v-flash": { "cost": { "currency": "CNY", "per_second_1080p": 0.48, "per_second_480p": 0.1, "per_second_720p": 0.2 }, "description": "wan2.2-kf2v-flash is an AI model provided by aliyun-bailian.", "id": "wan2.2-kf2v-flash", "name": "wan2.2-kf2v-flash" }, "wan2.2-s2v": { "cost": { "currency": "CNY", "per_second_480p": 0.5, "per_second_720p": 0.9 }, "description": "wan2.2-s2v is an AI model provided by aliyun-bailian.", "id": "wan2.2-s2v", "name": "wan2.2-s2v" }, "wan2.2-t2i-flash": { "cost": { "currency": "CNY", "per_image": 0.14 }, "description": "wan2.2-t2i-flash is an AI model provided by aliyun-bailian.", "id": "wan2.2-t2i-flash", "name": "wan2.2-t2i-flash" }, "wan2.2-t2i-plus": { "cost": { "currency": "CNY", "per_image": 0.2 }, "description": "wan2.2-t2i-plus is an AI model provided by aliyun-bailian.", "id": "wan2.2-t2i-plus", "name": "wan2.2-t2i-plus" }, "wan2.2-t2v-plus": { "cost": { "currency": "CNY", "per_second_1080x1920": 0.7, "per_second_1248x1632": 0.7, "per_second_1440x1440": 0.7, "per_second_1632x1248": 0.7, "per_second_1920x1080": 0.7, "per_second_480x832": 0.14, "per_second_624x624": 0.14, "per_second_832x480": 0.14 }, "description": "wan2.2-t2v-plus is an AI model provided by aliyun-bailian.", "id": "wan2.2-t2v-plus", "name": "wan2.2-t2v-plus" }, "wan2.5-i2i-preview": { "cost": { "currency": "CNY", "per_image": 0.2 }, "description": "wan2.5-i2i-preview is an AI model provided by aliyun-bailian.", "id": "wan2.5-i2i-preview", "name": "wan2.5-i2i-preview" }, "wan2.5-i2v-preview": { "cost": { "currency": "CNY", "per_second_1080p": 1, "per_second_480p": 0.3, "per_second_720p": 0.6 }, "description": "wan2.5-i2v-preview is an AI model provided by aliyun-bailian.", "id": "wan2.5-i2v-preview", "name": "wan2.5-i2v-preview" }, "wan2.5-t2i-preview": { "cost": { "currency": "CNY", "per_image": 0.2 }, "description": "wan2.5-t2i-preview is an AI model provided by aliyun-bailian.", "id": "wan2.5-t2i-preview", "name": "wan2.5-t2i-preview" }, "wan2.5-t2v-preview": { "cost": { "currency": "CNY", "per_second_1080x1920": 1, "per_second_1088x832": 0.6, "per_second_1248x1632": 1, "per_second_1280x720": 0.6, "per_second_1440x1440": 1, "per_second_1632x1248": 1, "per_second_1920x1080": 1, "per_second_480x832": 0.3, "per_second_624x624": 0.3, "per_second_720x1280": 0.6, "per_second_832x1088": 0.6, "per_second_832x480": 0.3, "per_second_960x960": 0.6 }, "description": "wan2.5-t2v-preview is an AI model provided by aliyun-bailian.", "id": "wan2.5-t2v-preview", "name": "wan2.5-t2v-preview" }, "wanx-background-generation-v2": { "cost": { "currency": "CNY", "per_image": 0.08 }, "description": "wanx-background-generation-v2 is an AI model provided by aliyun-bailian.", "id": "wanx-background-generation-v2", "name": "wanx-background-generation-v2" }, "wanx-sketch-to-image-lite": { "cost": { "currency": "CNY", "per_image": 0.06 }, "description": "wanx-sketch-to-image-lite is an AI model provided by aliyun-bailian.", "id": "wanx-sketch-to-image-lite", "name": "wanx-sketch-to-image-lite" }, "wanx-style-repaint-v1": { "cost": { "currency": "CNY", "per_image": 0.12 }, "description": "wanx-style-repaint-v1 is an AI model provided by aliyun-bailian.", "id": "wanx-style-repaint-v1", "name": "wanx-style-repaint-v1" }, "wanx-v1": { "cost": { "currency": "CNY", "per_image": 0.16 }, "description": "wanx-v1 is an AI model provided by aliyun-bailian.", "id": "wanx-v1", "name": "wanx-v1" }, "wanx2.0-t2i-turbo": { "cost": { "currency": "CNY", "per_image": 0.04 }, "description": "wanx2.0-t2i-turbo is an AI model provided by aliyun-bailian.", "id": "wanx2.0-t2i-turbo", "name": "wanx2.0-t2i-turbo" }, "wanx2.1-i2v-plus": { "cost": { "currency": "CNY", "per_second_standard": 0.7 }, "description": "wanx2.1-i2v-plus is an AI model provided by aliyun-bailian.", "id": "wanx2.1-i2v-plus", "name": "wanx2.1-i2v-plus" }, "wanx2.1-i2v-turbo": { "cost": { "currency": "CNY", "per_second_standard": 0.24 }, "description": "wanx2.1-i2v-turbo is an AI model provided by aliyun-bailian.", "id": "wanx2.1-i2v-turbo", "name": "wanx2.1-i2v-turbo" }, "wanx2.1-imageedit": { "cost": { "currency": "CNY", "per_image": 0.14 }, "description": "wanx2.1-imageedit is an AI model provided by aliyun-bailian.", "id": "wanx2.1-imageedit", "name": "wanx2.1-imageedit" }, "wanx2.1-kf2v-plus": { "cost": { "currency": "CNY", "per_second_standard": 0.7 }, "description": "wanx2.1-kf2v-plus is an AI model provided by aliyun-bailian.", "id": "wanx2.1-kf2v-plus", "name": "wanx2.1-kf2v-plus" }, "wanx2.1-t2i-plus": { "cost": { "currency": "CNY", "per_image": 0.2 }, "description": "wanx2.1-t2i-plus is an AI model provided by aliyun-bailian.", "id": "wanx2.1-t2i-plus", "name": "wanx2.1-t2i-plus" }, "wanx2.1-t2i-turbo": { "cost": { "currency": "CNY", "per_image": 0.14 }, "description": "wanx2.1-t2i-turbo is an AI model provided by aliyun-bailian.", "id": "wanx2.1-t2i-turbo", "name": "wanx2.1-t2i-turbo" }, "wanx2.1-t2v-plus": { "cost": { "currency": "CNY", "per_second_1088x832": 0.7, "per_second_1280x720": 0.7, "per_second_720x1280": 0.7, "per_second_832x1088": 0.7, "per_second_960x960": 0.7 }, "description": "wanx2.1-t2v-plus is an AI model provided by aliyun-bailian.", "id": "wanx2.1-t2v-plus", "name": "wanx2.1-t2v-plus" }, "wanx2.1-t2v-turbo": { "cost": { "currency": "CNY", "per_second_1088x832": 0.24, "per_second_1280x720": 0.24, "per_second_480x832": 0.24, "per_second_624x624": 0.24, "per_second_720x1280": 0.24, "per_second_832x1088": 0.24, "per_second_832x480": 0.24, "per_second_960x960": 0.24 }, "description": "wanx2.1-t2v-turbo is an AI model provided by aliyun-bailian.", "id": "wanx2.1-t2v-turbo", "name": "wanx2.1-t2v-turbo" }, "wanx2.1-vace-plus": { "cost": { "currency": "CNY", "per_second_standard": 0.7 }, "description": "wanx2.1-vace-plus is an AI model provided by aliyun-bailian.", "id": "wanx2.1-vace-plus", "name": "wanx2.1-vace-plus" } } }, "amazon-bedrock": { "doc": "https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html", "env": [ "AWS_ACCESS_KEY_ID", "AWS_SECRET_ACCESS_KEY", "AWS_REGION", "AWS_BEARER_TOKEN_BEDROCK" ], "iconURL": "https://models.dev/logos/amazon-bedrock.svg", "id": "amazon-bedrock", "lobeIcon": "AmazonBedrock.Color", "models": { "amazon.nova-2-lite-v1:0": { "attachment": false, "cost": { "input": 0.33, "output": 2.75 }, "description": "Nova 2 Lite is an AI model provided by amazon-bedrock.", "family": "nova", "id": "amazon.nova-2-lite-v1:0", "last_updated": "2024-12-01", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Nova 2 Lite", "open_weights": false, "reasoning": false, "release_date": "2024-12-01", "temperature": true, "tool_call": true }, "amazon.nova-lite-v1:0": { "attachment": true, "cost": { "cache_read": 0.015, "input": 0.06, "output": 0.24 }, "description": "Nova Lite is an AI model provided by amazon-bedrock.", "family": "nova-lite", "id": "amazon.nova-lite-v1:0", "knowledge": "2024-10", "last_updated": "2024-12-03", "limit": { "context": 300000, "output": 8192 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Nova Lite", "open_weights": false, "reasoning": false, "release_date": "2024-12-03", "temperature": true, "tool_call": true }, "amazon.nova-micro-v1:0": { "attachment": false, "cost": { "cache_read": 0.00875, "input": 0.035, "output": 0.14 }, "description": "Nova Micro is an AI model provided by amazon-bedrock.", "family": "nova-micro", "id": "amazon.nova-micro-v1:0", "knowledge": "2024-10", "last_updated": "2024-12-03", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Nova Micro", "open_weights": false, "reasoning": false, "release_date": "2024-12-03", "temperature": true, "tool_call": true }, "amazon.nova-pro-v1:0": { "attachment": true, "cost": { "cache_read": 0.2, "input": 0.8, "output": 3.2 }, "description": "Nova Pro is an AI model provided by amazon-bedrock.", "family": "nova-pro", "id": "amazon.nova-pro-v1:0", "knowledge": "2024-10", "last_updated": "2024-12-03", "limit": { "context": 300000, "output": 8192 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Nova Pro", "open_weights": false, "reasoning": false, "release_date": "2024-12-03", "temperature": true, "tool_call": true }, "anthropic.claude-haiku-4-5-20251001-v1:0": { "attachment": true, "cost": { "cache_read": 0.1, "cache_write": 1.25, "input": 1, "output": 5 }, "description": "Claude Haiku 4.5 is an AI model provided by amazon-bedrock.", "family": "claude-haiku", "id": "anthropic.claude-haiku-4-5-20251001-v1:0", "knowledge": "2025-02-28", "last_updated": "2025-10-15", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Haiku 4.5", "open_weights": false, "reasoning": true, "release_date": "2025-10-15", "structured_output": true, "temperature": true, "tool_call": true }, "anthropic.claude-opus-4-1-20250805-v1:0": { "attachment": true, "cost": { "cache_read": 1.5, "cache_write": 18.75, "input": 15, "output": 75 }, "description": "Claude Opus 4.1 is an AI model provided by amazon-bedrock.", "family": "claude-opus", "id": "anthropic.claude-opus-4-1-20250805-v1:0", "knowledge": "2025-03-31", "last_updated": "2025-08-05", "limit": { "context": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.1", "open_weights": false, "reasoning": true, "release_date": "2025-08-05", "temperature": true, "tool_call": true }, "anthropic.claude-opus-4-5-20251101-v1:0": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "input": 5, "output": 25 }, "description": "Claude Opus 4.5 is an AI model provided by amazon-bedrock.", "family": "claude-opus", "id": "anthropic.claude-opus-4-5-20251101-v1:0", "knowledge": "2025-03-31", "last_updated": "2025-08-01", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.5", "open_weights": false, "reasoning": true, "release_date": "2025-11-24", "structured_output": true, "temperature": true, "tool_call": true }, "anthropic.claude-opus-4-6-v1": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "input": 5, "output": 25 }, "description": "Claude Opus 4.6 is an AI model provided by amazon-bedrock.", "family": "claude-opus", "id": "anthropic.claude-opus-4-6-v1", "knowledge": "2025-05-31", "last_updated": "2026-03-13", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.6", "open_weights": false, "reasoning": true, "release_date": "2026-02-05", "structured_output": true, "temperature": true, "tool_call": true }, "anthropic.claude-opus-4-7": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "input": 5, "output": 25 }, "description": "Claude Opus 4.7 is an AI model provided by amazon-bedrock.", "family": "claude-opus", "id": "anthropic.claude-opus-4-7", "knowledge": "2026-01-31", "last_updated": "2026-04-16", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.7", "open_weights": false, "reasoning": true, "release_date": "2026-04-16", "temperature": false, "tool_call": true }, "anthropic.claude-sonnet-4-5-20250929-v1:0": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 4.5 is an AI model provided by amazon-bedrock.", "family": "claude-sonnet", "id": "anthropic.claude-sonnet-4-5-20250929-v1:0", "knowledge": "2025-07-31", "last_updated": "2025-09-29", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.5", "open_weights": false, "reasoning": true, "release_date": "2025-09-29", "structured_output": true, "temperature": true, "tool_call": true }, "anthropic.claude-sonnet-4-6": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 4.6 is an AI model provided by amazon-bedrock.", "family": "claude-sonnet", "id": "anthropic.claude-sonnet-4-6", "knowledge": "2025-08-31", "last_updated": "2026-03-13", "limit": { "context": 1000000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.6", "open_weights": false, "reasoning": true, "release_date": "2026-02-17", "structured_output": true, "temperature": true, "tool_call": true }, "au.anthropic.claude-haiku-4-5-20251001-v1:0": { "attachment": true, "cost": { "cache_read": 0.1, "cache_write": 1.25, "input": 1, "output": 5 }, "description": "Claude Haiku 4.5 (AU) is an AI model provided by amazon-bedrock.", "family": "claude-haiku", "id": "au.anthropic.claude-haiku-4-5-20251001-v1:0", "knowledge": "2025-02-28", "last_updated": "2025-10-15", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Haiku 4.5 (AU)", "open_weights": false, "reasoning": true, "release_date": "2025-10-15", "structured_output": true, "temperature": true, "tool_call": true }, "au.anthropic.claude-opus-4-6-v1": { "attachment": true, "cost": { "cache_read": 1.65, "cache_write": 20.625, "input": 16.5, "output": 82.5 }, "description": "AU Anthropic Claude Opus 4.6 is an AI model provided by amazon-bedrock.", "family": "claude-opus", "id": "au.anthropic.claude-opus-4-6-v1", "knowledge": "2025-05", "last_updated": "2026-02-05", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "AU Anthropic Claude Opus 4.6", "open_weights": false, "reasoning": true, "release_date": "2026-02-05", "structured_output": true, "temperature": true, "tool_call": true }, "au.anthropic.claude-sonnet-4-5-20250929-v1:0": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 4.5 (AU) is an AI model provided by amazon-bedrock.", "family": "claude-sonnet", "id": "au.anthropic.claude-sonnet-4-5-20250929-v1:0", "knowledge": "2025-07-31", "last_updated": "2025-09-29", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.5 (AU)", "open_weights": false, "reasoning": true, "release_date": "2025-09-29", "structured_output": true, "temperature": true, "tool_call": true }, "au.anthropic.claude-sonnet-4-6": { "attachment": true, "cost": { "cache_read": 0.33, "cache_write": 4.125, "input": 3.3, "output": 16.5 }, "description": "AU Anthropic Claude Sonnet 4.6 is an AI model provided by amazon-bedrock.", "family": "claude-sonnet", "id": "au.anthropic.claude-sonnet-4-6", "knowledge": "2025-08", "last_updated": "2026-02-17", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "AU Anthropic Claude Sonnet 4.6", "open_weights": false, "reasoning": true, "release_date": "2026-02-17", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek.r1-v1:0": { "attachment": false, "cost": { "input": 1.35, "output": 5.4 }, "description": "DeepSeek-R1 is an AI model provided by amazon-bedrock.", "family": "deepseek-thinking", "id": "deepseek.r1-v1:0", "knowledge": "2024-07", "last_updated": "2025-05-29", "limit": { "context": 128000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek-R1", "open_weights": false, "reasoning": true, "release_date": "2025-01-20", "temperature": true, "tool_call": true }, "deepseek.v3-v1:0": { "attachment": false, "cost": { "input": 0.58, "output": 1.68 }, "description": "DeepSeek-V3.1 is an AI model provided by amazon-bedrock.", "family": "deepseek", "id": "deepseek.v3-v1:0", "knowledge": "2024-07", "last_updated": "2025-09-18", "limit": { "context": 163840, "output": 81920 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek-V3.1", "open_weights": true, "reasoning": true, "release_date": "2025-09-18", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek.v3.2": { "attachment": false, "cost": { "input": 0.62, "output": 1.85 }, "description": "DeepSeek-V3.2 is an AI model provided by amazon-bedrock.", "family": "deepseek", "id": "deepseek.v3.2", "knowledge": "2024-07", "last_updated": "2026-02-06", "limit": { "context": 163840, "output": 81920 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek-V3.2", "open_weights": true, "reasoning": true, "release_date": "2026-02-06", "structured_output": true, "temperature": true, "tool_call": true }, "eu.anthropic.claude-haiku-4-5-20251001-v1:0": { "attachment": true, "cost": { "cache_read": 0.1, "cache_write": 1.25, "input": 1, "output": 5 }, "description": "Claude Haiku 4.5 (EU) is an AI model provided by amazon-bedrock.", "family": "claude-haiku", "id": "eu.anthropic.claude-haiku-4-5-20251001-v1:0", "knowledge": "2025-02-28", "last_updated": "2025-10-15", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Haiku 4.5 (EU)", "open_weights": false, "reasoning": true, "release_date": "2025-10-15", "structured_output": true, "temperature": true, "tool_call": true }, "eu.anthropic.claude-opus-4-5-20251101-v1:0": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "input": 5, "output": 25 }, "description": "Claude Opus 4.5 (EU) is an AI model provided by amazon-bedrock.", "family": "claude-opus", "id": "eu.anthropic.claude-opus-4-5-20251101-v1:0", "knowledge": "2025-03-31", "last_updated": "2025-08-01", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.5 (EU)", "open_weights": false, "reasoning": true, "release_date": "2025-11-24", "structured_output": true, "temperature": true, "tool_call": true }, "eu.anthropic.claude-opus-4-6-v1": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "input": 5, "output": 25 }, "description": "Claude Opus 4.6 (EU) is an AI model provided by amazon-bedrock.", "family": "claude-opus", "id": "eu.anthropic.claude-opus-4-6-v1", "knowledge": "2025-05-31", "last_updated": "2026-03-13", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.6 (EU)", "open_weights": false, "reasoning": true, "release_date": "2026-02-05", "structured_output": true, "temperature": true, "tool_call": true }, "eu.anthropic.claude-opus-4-7": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "input": 5, "output": 25 }, "description": "Claude Opus 4.7 (EU) is an AI model provided by amazon-bedrock.", "family": "claude-opus", "id": "eu.anthropic.claude-opus-4-7", "knowledge": "2026-01-31", "last_updated": "2026-04-16", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.7 (EU)", "open_weights": false, "reasoning": true, "release_date": "2026-04-16", "temperature": false, "tool_call": true }, "eu.anthropic.claude-sonnet-4-5-20250929-v1:0": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 4.5 (EU) is an AI model provided by amazon-bedrock.", "family": "claude-sonnet", "id": "eu.anthropic.claude-sonnet-4-5-20250929-v1:0", "knowledge": "2025-07-31", "last_updated": "2025-09-29", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.5 (EU)", "open_weights": false, "reasoning": true, "release_date": "2025-09-29", "structured_output": true, "temperature": true, "tool_call": true }, "eu.anthropic.claude-sonnet-4-6": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 4.6 (EU) is an AI model provided by amazon-bedrock.", "family": "claude-sonnet", "id": "eu.anthropic.claude-sonnet-4-6", "knowledge": "2025-08-31", "last_updated": "2026-03-13", "limit": { "context": 1000000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.6 (EU)", "open_weights": false, "reasoning": true, "release_date": "2026-02-17", "structured_output": true, "temperature": true, "tool_call": true }, "global.anthropic.claude-haiku-4-5-20251001-v1:0": { "attachment": true, "cost": { "cache_read": 0.1, "cache_write": 1.25, "input": 1, "output": 5 }, "description": "Claude Haiku 4.5 (Global) is an AI model provided by amazon-bedrock.", "family": "claude-haiku", "id": "global.anthropic.claude-haiku-4-5-20251001-v1:0", "knowledge": "2025-02-28", "last_updated": "2025-10-15", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Haiku 4.5 (Global)", "open_weights": false, "reasoning": true, "release_date": "2025-10-15", "structured_output": true, "temperature": true, "tool_call": true }, "global.anthropic.claude-opus-4-5-20251101-v1:0": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "input": 5, "output": 25 }, "description": "Claude Opus 4.5 (Global) is an AI model provided by amazon-bedrock.", "family": "claude-opus", "id": "global.anthropic.claude-opus-4-5-20251101-v1:0", "knowledge": "2025-03-31", "last_updated": "2025-08-01", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.5 (Global)", "open_weights": false, "reasoning": true, "release_date": "2025-11-24", "structured_output": true, "temperature": true, "tool_call": true }, "global.anthropic.claude-opus-4-6-v1": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "input": 5, "output": 25 }, "description": "Claude Opus 4.6 (Global) is an AI model provided by amazon-bedrock.", "family": "claude-opus", "id": "global.anthropic.claude-opus-4-6-v1", "knowledge": "2025-05-31", "last_updated": "2026-03-13", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.6 (Global)", "open_weights": false, "reasoning": true, "release_date": "2026-02-05", "structured_output": true, "temperature": true, "tool_call": true }, "global.anthropic.claude-opus-4-7": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "input": 5, "output": 25 }, "description": "Claude Opus 4.7 (Global) is an AI model provided by amazon-bedrock.", "family": "claude-opus", "id": "global.anthropic.claude-opus-4-7", "knowledge": "2026-01-31", "last_updated": "2026-04-16", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.7 (Global)", "open_weights": false, "reasoning": true, "release_date": "2026-04-16", "temperature": false, "tool_call": true }, "global.anthropic.claude-sonnet-4-5-20250929-v1:0": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 4.5 (Global) is an AI model provided by amazon-bedrock.", "family": "claude-sonnet", "id": "global.anthropic.claude-sonnet-4-5-20250929-v1:0", "knowledge": "2025-07-31", "last_updated": "2025-09-29", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.5 (Global)", "open_weights": false, "reasoning": true, "release_date": "2025-09-29", "structured_output": true, "temperature": true, "tool_call": true }, "global.anthropic.claude-sonnet-4-6": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 4.6 (Global) is an AI model provided by amazon-bedrock.", "family": "claude-sonnet", "id": "global.anthropic.claude-sonnet-4-6", "knowledge": "2025-08-31", "last_updated": "2026-03-13", "limit": { "context": 1000000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.6 (Global)", "open_weights": false, "reasoning": true, "release_date": "2026-02-17", "structured_output": true, "temperature": true, "tool_call": true }, "google.gemma-3-12b-it": { "attachment": false, "cost": { "input": 0.049999999999999996, "output": 0.09999999999999999 }, "description": "Google Gemma 3 12B is an AI model provided by amazon-bedrock.", "family": "gemma", "id": "google.gemma-3-12b-it", "knowledge": "2024-12", "last_updated": "2024-12-01", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Google Gemma 3 12B", "open_weights": false, "reasoning": false, "release_date": "2024-12-01", "structured_output": true, "temperature": true, "tool_call": false }, "google.gemma-3-27b-it": { "attachment": true, "cost": { "input": 0.12, "output": 0.2 }, "description": "Google Gemma 3 27B Instruct is an AI model provided by amazon-bedrock.", "family": "gemma", "id": "google.gemma-3-27b-it", "knowledge": "2025-07", "last_updated": "2025-07-27", "limit": { "context": 202752, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Google Gemma 3 27B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-07-27", "structured_output": true, "temperature": true, "tool_call": true }, "google.gemma-3-4b-it": { "attachment": false, "cost": { "input": 0.04, "output": 0.08 }, "description": "Gemma 3 4B IT is an AI model provided by amazon-bedrock.", "family": "gemma", "id": "google.gemma-3-4b-it", "last_updated": "2024-12-01", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemma 3 4B IT", "open_weights": false, "reasoning": false, "release_date": "2024-12-01", "temperature": true, "tool_call": true }, "jp.anthropic.claude-opus-4-7": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "input": 5, "output": 25 }, "description": "Claude Opus 4.7 (JP) is an AI model provided by amazon-bedrock.", "family": "claude-opus", "id": "jp.anthropic.claude-opus-4-7", "knowledge": "2026-01-31", "last_updated": "2026-04-16", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.7 (JP)", "open_weights": false, "reasoning": true, "release_date": "2026-04-16", "temperature": false, "tool_call": true }, "jp.anthropic.claude-sonnet-4-5-20250929-v1:0": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 4.5 (JP) is an AI model provided by amazon-bedrock.", "family": "claude-sonnet", "id": "jp.anthropic.claude-sonnet-4-5-20250929-v1:0", "knowledge": "2025-07-31", "last_updated": "2025-09-29", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.5 (JP)", "open_weights": false, "reasoning": true, "release_date": "2025-09-29", "structured_output": true, "temperature": true, "tool_call": true }, "jp.anthropic.claude-sonnet-4-6": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 4.6 (JP) is an AI model provided by amazon-bedrock.", "family": "claude-sonnet", "id": "jp.anthropic.claude-sonnet-4-6", "knowledge": "2025-08-31", "last_updated": "2026-03-13", "limit": { "context": 1000000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.6 (JP)", "open_weights": false, "reasoning": true, "release_date": "2026-02-17", "structured_output": true, "temperature": true, "tool_call": true }, "meta.llama3-1-70b-instruct-v1:0": { "attachment": false, "cost": { "input": 0.72, "output": 0.72 }, "description": "Llama 3.1 70B Instruct is an AI model provided by amazon-bedrock.", "family": "llama", "id": "meta.llama3-1-70b-instruct-v1:0", "knowledge": "2023-12", "last_updated": "2024-07-23", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.1 70B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-07-23", "temperature": true, "tool_call": true }, "meta.llama3-1-8b-instruct-v1:0": { "attachment": false, "cost": { "input": 0.22, "output": 0.22 }, "description": "Llama 3.1 8B Instruct is an AI model provided by amazon-bedrock.", "family": "llama", "id": "meta.llama3-1-8b-instruct-v1:0", "knowledge": "2023-12", "last_updated": "2024-07-23", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.1 8B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-07-23", "temperature": true, "tool_call": true }, "meta.llama3-3-70b-instruct-v1:0": { "attachment": false, "cost": { "input": 0.72, "output": 0.72 }, "description": "Llama 3.3 70B Instruct is an AI model provided by amazon-bedrock.", "family": "llama", "id": "meta.llama3-3-70b-instruct-v1:0", "knowledge": "2023-12", "last_updated": "2024-12-06", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-12-06", "temperature": true, "tool_call": true }, "meta.llama4-maverick-17b-instruct-v1:0": { "attachment": true, "cost": { "input": 0.24, "output": 0.97 }, "description": "Llama 4 Maverick 17B Instruct is an AI model provided by amazon-bedrock.", "family": "llama", "id": "meta.llama4-maverick-17b-instruct-v1:0", "knowledge": "2024-08", "last_updated": "2025-04-05", "limit": { "context": 1000000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Llama 4 Maverick 17B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-04-05", "temperature": true, "tool_call": true }, "meta.llama4-scout-17b-instruct-v1:0": { "attachment": true, "cost": { "input": 0.17, "output": 0.66 }, "description": "Llama 4 Scout 17B Instruct is an AI model provided by amazon-bedrock.", "family": "llama", "id": "meta.llama4-scout-17b-instruct-v1:0", "knowledge": "2024-08", "last_updated": "2025-04-05", "limit": { "context": 3500000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Llama 4 Scout 17B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-04-05", "temperature": true, "tool_call": true }, "minimax.minimax-m2": { "attachment": false, "cost": { "input": 0.3, "output": 1.2 }, "description": "MiniMax M2 is an AI model provided by amazon-bedrock.", "family": "minimax", "id": "minimax.minimax-m2", "last_updated": "2025-10-27", "limit": { "context": 204608, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M2", "open_weights": true, "reasoning": true, "release_date": "2025-10-27", "structured_output": false, "temperature": true, "tool_call": true }, "minimax.minimax-m2.1": { "attachment": false, "cost": { "input": 0.3, "output": 1.2 }, "description": "MiniMax M2.1 is an AI model provided by amazon-bedrock.", "family": "minimax", "id": "minimax.minimax-m2.1", "last_updated": "2025-12-23", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M2.1", "open_weights": true, "reasoning": true, "release_date": "2025-12-23", "structured_output": false, "temperature": true, "tool_call": true }, "minimax.minimax-m2.5": { "attachment": false, "cost": { "input": 0.3, "output": 1.2 }, "description": "MiniMax M2.5 is an AI model provided by amazon-bedrock.", "family": "minimax", "id": "minimax.minimax-m2.5", "last_updated": "2026-03-18", "limit": { "context": 196608, "output": 98304 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M2.5", "open_weights": true, "reasoning": true, "release_date": "2026-03-18", "structured_output": false, "temperature": true, "tool_call": true }, "mistral.devstral-2-123b": { "attachment": false, "cost": { "input": 0.4, "output": 2 }, "description": "Devstral 2 123B is an AI model provided by amazon-bedrock.", "family": "devstral", "id": "mistral.devstral-2-123b", "last_updated": "2026-02-17", "limit": { "context": 256000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Devstral 2 123B", "open_weights": true, "reasoning": false, "release_date": "2026-02-17", "structured_output": true, "temperature": true, "tool_call": true }, "mistral.magistral-small-2509": { "attachment": false, "cost": { "input": 0.5, "output": 1.5 }, "description": "Magistral Small 1.2 is an AI model provided by amazon-bedrock.", "family": "magistral", "id": "mistral.magistral-small-2509", "last_updated": "2025-12-02", "limit": { "context": 128000, "output": 40000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Magistral Small 1.2", "open_weights": true, "reasoning": true, "release_date": "2025-12-02", "structured_output": true, "temperature": true, "tool_call": true }, "mistral.ministral-3-14b-instruct": { "attachment": false, "cost": { "input": 0.2, "output": 0.2 }, "description": "Ministral 14B 3.0 is an AI model provided by amazon-bedrock.", "family": "ministral", "id": "mistral.ministral-3-14b-instruct", "last_updated": "2024-12-01", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Ministral 14B 3.0", "open_weights": false, "reasoning": false, "release_date": "2024-12-01", "structured_output": true, "temperature": true, "tool_call": true }, "mistral.ministral-3-3b-instruct": { "attachment": false, "cost": { "input": 0.1, "output": 0.1 }, "description": "Ministral 3 3B is an AI model provided by amazon-bedrock.", "family": "ministral", "id": "mistral.ministral-3-3b-instruct", "last_updated": "2025-12-02", "limit": { "context": 256000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Ministral 3 3B", "open_weights": true, "reasoning": false, "release_date": "2025-12-02", "structured_output": true, "temperature": true, "tool_call": true }, "mistral.ministral-3-8b-instruct": { "attachment": false, "cost": { "input": 0.15, "output": 0.15 }, "description": "Ministral 3 8B is an AI model provided by amazon-bedrock.", "family": "ministral", "id": "mistral.ministral-3-8b-instruct", "last_updated": "2024-12-01", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Ministral 3 8B", "open_weights": false, "reasoning": false, "release_date": "2024-12-01", "structured_output": true, "temperature": true, "tool_call": true }, "mistral.mistral-large-3-675b-instruct": { "attachment": false, "cost": { "input": 0.5, "output": 1.5 }, "description": "Mistral Large 3 is an AI model provided by amazon-bedrock.", "family": "mistral", "id": "mistral.mistral-large-3-675b-instruct", "last_updated": "2025-12-02", "limit": { "context": 256000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Mistral Large 3", "open_weights": true, "reasoning": false, "release_date": "2025-12-02", "structured_output": true, "temperature": true, "tool_call": true }, "mistral.pixtral-large-2502-v1:0": { "attachment": false, "cost": { "input": 2, "output": 6 }, "description": "Pixtral Large (25.02) is an AI model provided by amazon-bedrock.", "family": "mistral", "id": "mistral.pixtral-large-2502-v1:0", "last_updated": "2025-04-08", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Pixtral Large (25.02)", "open_weights": false, "reasoning": false, "release_date": "2025-04-08", "temperature": true, "tool_call": true }, "mistral.voxtral-mini-3b-2507": { "attachment": false, "cost": { "input": 0.04, "output": 0.04 }, "description": "Voxtral Mini 3B 2507 is an AI model provided by amazon-bedrock.", "family": "mistral", "id": "mistral.voxtral-mini-3b-2507", "last_updated": "2024-12-01", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "audio", "text" ], "output": [ "text" ] }, "name": "Voxtral Mini 3B 2507", "open_weights": false, "reasoning": false, "release_date": "2024-12-01", "structured_output": true, "temperature": true, "tool_call": true }, "mistral.voxtral-small-24b-2507": { "attachment": true, "cost": { "input": 0.15, "output": 0.35 }, "description": "Voxtral Small 24B 2507 is an AI model provided by amazon-bedrock.", "family": "mistral", "id": "mistral.voxtral-small-24b-2507", "last_updated": "2025-07-01", "limit": { "context": 32000, "output": 8192 }, "modalities": { "input": [ "text", "audio" ], "output": [ "text" ] }, "name": "Voxtral Small 24B 2507", "open_weights": true, "reasoning": false, "release_date": "2025-07-01", "structured_output": true, "temperature": true, "tool_call": true }, "moonshot.kimi-k2-thinking": { "attachment": false, "cost": { "input": 0.6, "output": 2.5 }, "description": "Kimi K2 Thinking is an AI model provided by amazon-bedrock.", "family": "kimi-thinking", "id": "moonshot.kimi-k2-thinking", "interleaved": true, "last_updated": "2025-12-02", "limit": { "context": 256000, "output": 256000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 Thinking", "open_weights": true, "reasoning": true, "release_date": "2025-12-02", "structured_output": true, "temperature": true, "tool_call": true }, "moonshotai.kimi-k2.5": { "attachment": false, "cost": { "input": 0.6, "output": 3 }, "description": "Kimi K2.5 is an AI model provided by amazon-bedrock.", "family": "kimi", "id": "moonshotai.kimi-k2.5", "interleaved": true, "last_updated": "2026-02-06", "limit": { "context": 256000, "output": 256000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Kimi K2.5", "open_weights": true, "reasoning": true, "release_date": "2026-02-06", "structured_output": true, "temperature": true, "tool_call": true }, "nvidia.nemotron-nano-12b-v2": { "attachment": false, "cost": { "input": 0.2, "output": 0.6 }, "description": "NVIDIA Nemotron Nano 12B v2 VL BF16 is an AI model provided by amazon-bedrock.", "family": "nemotron", "id": "nvidia.nemotron-nano-12b-v2", "last_updated": "2024-12-01", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "NVIDIA Nemotron Nano 12B v2 VL BF16", "open_weights": false, "reasoning": false, "release_date": "2024-12-01", "structured_output": true, "temperature": true, "tool_call": true }, "nvidia.nemotron-nano-3-30b": { "attachment": false, "cost": { "input": 0.06, "output": 0.24 }, "description": "NVIDIA Nemotron Nano 3 30B is an AI model provided by amazon-bedrock.", "family": "nemotron", "id": "nvidia.nemotron-nano-3-30b", "last_updated": "2025-12-23", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "NVIDIA Nemotron Nano 3 30B", "open_weights": true, "reasoning": true, "release_date": "2025-12-23", "structured_output": true, "temperature": true, "tool_call": true }, "nvidia.nemotron-nano-9b-v2": { "attachment": false, "cost": { "input": 0.06, "output": 0.23 }, "description": "NVIDIA Nemotron Nano 9B v2 is an AI model provided by amazon-bedrock.", "family": "nemotron", "id": "nvidia.nemotron-nano-9b-v2", "last_updated": "2024-12-01", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "NVIDIA Nemotron Nano 9B v2", "open_weights": false, "reasoning": false, "release_date": "2024-12-01", "structured_output": true, "temperature": true, "tool_call": true }, "nvidia.nemotron-super-3-120b": { "attachment": false, "cost": { "input": 0.15, "output": 0.65 }, "description": "NVIDIA Nemotron 3 Super 120B A12B is an AI model provided by amazon-bedrock.", "family": "nemotron", "id": "nvidia.nemotron-super-3-120b", "last_updated": "2026-03-11", "limit": { "context": 262144, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "NVIDIA Nemotron 3 Super 120B A12B", "open_weights": true, "reasoning": true, "release_date": "2026-03-11", "structured_output": true, "temperature": true, "tool_call": true }, "openai.gpt-oss-120b-1:0": { "attachment": false, "cost": { "input": 0.15, "output": 0.6 }, "description": "gpt-oss-120b is an AI model provided by amazon-bedrock.", "family": "gpt-oss", "id": "openai.gpt-oss-120b-1:0", "last_updated": "2025-08-05", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "gpt-oss-120b", "open_weights": false, "reasoning": false, "release_date": "2025-08-05", "structured_output": true, "temperature": true, "tool_call": true }, "openai.gpt-oss-20b-1:0": { "attachment": false, "cost": { "input": 0.07, "output": 0.3 }, "description": "gpt-oss-20b is an AI model provided by amazon-bedrock.", "family": "gpt-oss", "id": "openai.gpt-oss-20b-1:0", "last_updated": "2025-08-05", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "gpt-oss-20b", "open_weights": false, "reasoning": false, "release_date": "2025-08-05", "structured_output": true, "temperature": true, "tool_call": true }, "openai.gpt-oss-safeguard-120b": { "attachment": false, "cost": { "input": 0.15, "output": 0.6 }, "description": "GPT OSS Safeguard 120B is an AI model provided by amazon-bedrock.", "family": "gpt-oss", "id": "openai.gpt-oss-safeguard-120b", "last_updated": "2025-10-29", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT OSS Safeguard 120B", "open_weights": false, "reasoning": false, "release_date": "2025-10-29", "structured_output": true, "temperature": true, "tool_call": true }, "openai.gpt-oss-safeguard-20b": { "attachment": false, "cost": { "input": 0.07, "output": 0.2 }, "description": "GPT OSS Safeguard 20B is an AI model provided by amazon-bedrock.", "family": "gpt-oss", "id": "openai.gpt-oss-safeguard-20b", "last_updated": "2025-10-29", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT OSS Safeguard 20B", "open_weights": false, "reasoning": false, "release_date": "2025-10-29", "structured_output": true, "temperature": true, "tool_call": true }, "qwen.qwen3-235b-a22b-2507-v1:0": { "attachment": false, "cost": { "input": 0.22, "output": 0.88 }, "description": "Qwen3 235B A22B 2507 is an AI model provided by amazon-bedrock.", "family": "qwen", "id": "qwen.qwen3-235b-a22b-2507-v1:0", "knowledge": "2024-04", "last_updated": "2025-09-18", "limit": { "context": 262144, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 235B A22B 2507", "open_weights": true, "reasoning": false, "release_date": "2025-09-18", "structured_output": true, "temperature": true, "tool_call": true }, "qwen.qwen3-32b-v1:0": { "attachment": false, "cost": { "input": 0.15, "output": 0.6 }, "description": "Qwen3 32B (dense) is an AI model provided by amazon-bedrock.", "family": "qwen", "id": "qwen.qwen3-32b-v1:0", "knowledge": "2024-04", "last_updated": "2025-09-18", "limit": { "context": 16384, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 32B (dense)", "open_weights": true, "reasoning": true, "release_date": "2025-09-18", "structured_output": true, "temperature": true, "tool_call": true }, "qwen.qwen3-coder-30b-a3b-v1:0": { "attachment": false, "cost": { "input": 0.15, "output": 0.6 }, "description": "Qwen3 Coder 30B A3B Instruct is an AI model provided by amazon-bedrock.", "family": "qwen", "id": "qwen.qwen3-coder-30b-a3b-v1:0", "knowledge": "2024-04", "last_updated": "2025-09-18", "limit": { "context": 262144, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Coder 30B A3B Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-09-18", "structured_output": true, "temperature": true, "tool_call": true }, "qwen.qwen3-coder-480b-a35b-v1:0": { "attachment": false, "cost": { "input": 0.22, "output": 1.8 }, "description": "Qwen3 Coder 480B A35B Instruct is an AI model provided by amazon-bedrock.", "family": "qwen", "id": "qwen.qwen3-coder-480b-a35b-v1:0", "knowledge": "2024-04", "last_updated": "2025-09-18", "limit": { "context": 131072, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Coder 480B A35B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-09-18", "structured_output": true, "temperature": true, "tool_call": true }, "qwen.qwen3-coder-next": { "attachment": false, "cost": { "input": 0.22, "output": 1.8 }, "description": "Qwen3 Coder Next is an AI model provided by amazon-bedrock.", "family": "qwen", "id": "qwen.qwen3-coder-next", "last_updated": "2026-02-06", "limit": { "context": 131072, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Coder Next", "open_weights": true, "reasoning": true, "release_date": "2026-02-06", "structured_output": true, "temperature": true, "tool_call": true }, "qwen.qwen3-next-80b-a3b": { "attachment": false, "cost": { "input": 0.14, "output": 1.4 }, "description": "Qwen/Qwen3-Next-80B-A3B-Instruct is an AI model provided by amazon-bedrock.", "family": "qwen", "id": "qwen.qwen3-next-80b-a3b", "last_updated": "2025-11-25", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen/Qwen3-Next-80B-A3B-Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-09-18", "structured_output": true, "temperature": true, "tool_call": true }, "qwen.qwen3-vl-235b-a22b": { "attachment": true, "cost": { "input": 0.3, "output": 1.5 }, "description": "Qwen/Qwen3-VL-235B-A22B-Instruct is an AI model provided by amazon-bedrock.", "family": "qwen", "id": "qwen.qwen3-vl-235b-a22b", "last_updated": "2025-11-25", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen/Qwen3-VL-235B-A22B-Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-10-04", "structured_output": true, "temperature": true, "tool_call": true }, "us.anthropic.claude-haiku-4-5-20251001-v1:0": { "attachment": true, "cost": { "cache_read": 0.1, "cache_write": 1.25, "input": 1, "output": 5 }, "description": "Claude Haiku 4.5 (US) is an AI model provided by amazon-bedrock.", "family": "claude-haiku", "id": "us.anthropic.claude-haiku-4-5-20251001-v1:0", "knowledge": "2025-02-28", "last_updated": "2025-10-15", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Haiku 4.5 (US)", "open_weights": false, "reasoning": true, "release_date": "2025-10-15", "structured_output": true, "temperature": true, "tool_call": true }, "us.anthropic.claude-opus-4-1-20250805-v1:0": { "attachment": true, "cost": { "cache_read": 1.5, "cache_write": 18.75, "input": 15, "output": 75 }, "description": "Claude Opus 4.1 (US) is an AI model provided by amazon-bedrock.", "family": "claude-opus", "id": "us.anthropic.claude-opus-4-1-20250805-v1:0", "knowledge": "2025-03-31", "last_updated": "2025-08-05", "limit": { "context": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.1 (US)", "open_weights": false, "reasoning": true, "release_date": "2025-08-05", "temperature": true, "tool_call": true }, "us.anthropic.claude-opus-4-5-20251101-v1:0": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "input": 5, "output": 25 }, "description": "Claude Opus 4.5 (US) is an AI model provided by amazon-bedrock.", "family": "claude-opus", "id": "us.anthropic.claude-opus-4-5-20251101-v1:0", "knowledge": "2025-03-31", "last_updated": "2025-08-01", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.5 (US)", "open_weights": false, "reasoning": true, "release_date": "2025-11-24", "structured_output": true, "temperature": true, "tool_call": true }, "us.anthropic.claude-opus-4-6-v1": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "input": 5, "output": 25 }, "description": "Claude Opus 4.6 (US) is an AI model provided by amazon-bedrock.", "family": "claude-opus", "id": "us.anthropic.claude-opus-4-6-v1", "knowledge": "2025-05-31", "last_updated": "2026-03-13", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.6 (US)", "open_weights": false, "reasoning": true, "release_date": "2026-02-05", "structured_output": true, "temperature": true, "tool_call": true }, "us.anthropic.claude-opus-4-7": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "input": 5, "output": 25 }, "description": "Claude Opus 4.7 (US) is an AI model provided by amazon-bedrock.", "family": "claude-opus", "id": "us.anthropic.claude-opus-4-7", "knowledge": "2026-01-31", "last_updated": "2026-04-16", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.7 (US)", "open_weights": false, "reasoning": true, "release_date": "2026-04-16", "temperature": false, "tool_call": true }, "us.anthropic.claude-sonnet-4-5-20250929-v1:0": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 4.5 (US) is an AI model provided by amazon-bedrock.", "family": "claude-sonnet", "id": "us.anthropic.claude-sonnet-4-5-20250929-v1:0", "knowledge": "2025-07-31", "last_updated": "2025-09-29", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.5 (US)", "open_weights": false, "reasoning": true, "release_date": "2025-09-29", "structured_output": true, "temperature": true, "tool_call": true }, "us.anthropic.claude-sonnet-4-6": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 4.6 (US) is an AI model provided by amazon-bedrock.", "family": "claude-sonnet", "id": "us.anthropic.claude-sonnet-4-6", "knowledge": "2025-08-31", "last_updated": "2026-03-13", "limit": { "context": 1000000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.6 (US)", "open_weights": false, "reasoning": true, "release_date": "2026-02-17", "structured_output": true, "temperature": true, "tool_call": true }, "us.deepseek.r1-v1:0": { "attachment": false, "cost": { "input": 1.35, "output": 5.4 }, "description": "DeepSeek-R1 (US) is an AI model provided by amazon-bedrock.", "family": "deepseek-thinking", "id": "us.deepseek.r1-v1:0", "knowledge": "2024-07", "last_updated": "2025-05-29", "limit": { "context": 128000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek-R1 (US)", "open_weights": false, "reasoning": true, "release_date": "2025-01-20", "temperature": true, "tool_call": true }, "us.meta.llama4-maverick-17b-instruct-v1:0": { "attachment": true, "cost": { "input": 0.24, "output": 0.97 }, "description": "Llama 4 Maverick 17B Instruct (US) is an AI model provided by amazon-bedrock.", "family": "llama", "id": "us.meta.llama4-maverick-17b-instruct-v1:0", "knowledge": "2024-08", "last_updated": "2025-04-05", "limit": { "context": 1000000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Llama 4 Maverick 17B Instruct (US)", "open_weights": true, "reasoning": false, "release_date": "2025-04-05", "temperature": true, "tool_call": true }, "us.meta.llama4-scout-17b-instruct-v1:0": { "attachment": true, "cost": { "input": 0.17, "output": 0.66 }, "description": "Llama 4 Scout 17B Instruct (US) is an AI model provided by amazon-bedrock.", "family": "llama", "id": "us.meta.llama4-scout-17b-instruct-v1:0", "knowledge": "2024-08", "last_updated": "2025-04-05", "limit": { "context": 3500000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Llama 4 Scout 17B Instruct (US)", "open_weights": true, "reasoning": false, "release_date": "2025-04-05", "temperature": true, "tool_call": true }, "writer.palmyra-x4-v1:0": { "attachment": false, "cost": { "input": 2.5, "output": 10 }, "description": "Palmyra X4 is an AI model provided by amazon-bedrock.", "family": "palmyra", "id": "writer.palmyra-x4-v1:0", "last_updated": "2025-04-28", "limit": { "context": 122880, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Palmyra X4", "open_weights": false, "reasoning": true, "release_date": "2025-04-28", "temperature": true, "tool_call": true }, "writer.palmyra-x5-v1:0": { "attachment": false, "cost": { "input": 0.6, "output": 6 }, "description": "Palmyra X5 is an AI model provided by amazon-bedrock.", "family": "palmyra", "id": "writer.palmyra-x5-v1:0", "last_updated": "2025-04-28", "limit": { "context": 1040000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Palmyra X5", "open_weights": false, "reasoning": true, "release_date": "2025-04-28", "temperature": true, "tool_call": true }, "zai.glm-4.7": { "attachment": false, "cost": { "input": 0.6, "output": 2.2 }, "description": "GLM-4.7 is an AI model provided by amazon-bedrock.", "family": "glm", "id": "zai.glm-4.7", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-04", "last_updated": "2025-12-22", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.7", "open_weights": true, "reasoning": true, "release_date": "2025-12-22", "structured_output": true, "temperature": true, "tool_call": true }, "zai.glm-4.7-flash": { "attachment": false, "cost": { "input": 0.07, "output": 0.4 }, "description": "GLM-4.7-Flash is an AI model provided by amazon-bedrock.", "family": "glm-flash", "id": "zai.glm-4.7-flash", "knowledge": "2025-04", "last_updated": "2026-01-19", "limit": { "context": 200000, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.7-Flash", "open_weights": true, "reasoning": true, "release_date": "2026-01-19", "structured_output": true, "temperature": true, "tool_call": true }, "zai.glm-5": { "attachment": false, "cost": { "input": 1, "output": 3.2 }, "description": "GLM-5 is an AI model provided by amazon-bedrock.", "family": "glm", "id": "zai.glm-5", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-03-18", "limit": { "context": 202752, "output": 101376 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5", "open_weights": true, "reasoning": true, "release_date": "2026-03-18", "structured_output": true, "temperature": true, "tool_call": true } }, "name": "Amazon Bedrock", "npm": "@ai-sdk/amazon-bedrock" }, "ambient": { "api": "https://api.ambient.xyz/v1", "doc": "https://ambient.xyz", "env": [ "AMBIENT_API_KEY" ], "iconURL": "https://models.dev/logos/ambient.svg", "id": "ambient", "models": { "moonshotai/kimi-k2.6": { "attachment": true, "cost": { "cache_read": 0.2, "cache_write": 0, "input": 0.95, "output": 4 }, "description": "Kimi K2.6 is an AI model provided by ambient.", "family": "kimi-k2.6", "id": "moonshotai/kimi-k2.6", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-01", "last_updated": "2026-04-21", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Kimi K2.6", "open_weights": true, "reasoning": true, "release_date": "2026-04-21", "structured_output": true, "temperature": true, "tool_call": true }, "zai-org/GLM-5.1-FP8": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 1.4, "output": 4.4 }, "description": "GLM-5.1 is an AI model provided by ambient.", "family": "glm", "id": "zai-org/GLM-5.1-FP8", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-03-27", "limit": { "context": 202752, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5.1", "open_weights": false, "reasoning": true, "release_date": "2026-03-27", "structured_output": true, "temperature": true, "tool_call": true } }, "name": "Ambient", "npm": "@ai-sdk/openai-compatible" }, "anthropic": { "doc": "https://docs.anthropic.com/en/docs/about-claude/models", "env": [ "ANTHROPIC_API_KEY" ], "iconURL": "https://models.dev/logos/anthropic.svg", "id": "anthropic", "lobeIcon": "Claude.Color", "models": { "claude-3-5-haiku-20241022": { "attachment": true, "cost": { "cache_read": 0.08, "cache_write": 1, "input": 0.8, "output": 4 }, "description": "Claude Haiku 3.5 is an AI model provided by anthropic.", "family": "claude-haiku", "id": "claude-3-5-haiku-20241022", "knowledge": "2024-07-31", "last_updated": "2024-10-22", "limit": { "context": 200000, "output": 8192 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Haiku 3.5", "open_weights": false, "reasoning": false, "release_date": "2024-10-22", "temperature": true, "tool_call": true }, "claude-3-5-haiku-latest": { "attachment": true, "cost": { "cache_read": 0.08, "cache_write": 1, "input": 0.8, "output": 4 }, "description": "Claude Haiku 3.5 (latest) is an AI model provided by anthropic.", "family": "claude-haiku", "id": "claude-3-5-haiku-latest", "knowledge": "2024-07-31", "last_updated": "2024-10-22", "limit": { "context": 200000, "output": 8192 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Haiku 3.5 (latest)", "open_weights": false, "reasoning": false, "release_date": "2024-10-22", "temperature": true, "tool_call": true }, "claude-3-5-sonnet-20240620": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 3.5 is an AI model provided by anthropic.", "family": "claude-sonnet", "id": "claude-3-5-sonnet-20240620", "knowledge": "2024-04-30", "last_updated": "2024-06-20", "limit": { "context": 200000, "output": 8192 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 3.5", "open_weights": false, "reasoning": false, "release_date": "2024-06-20", "temperature": true, "tool_call": true }, "claude-3-5-sonnet-20241022": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 3.5 v2 is an AI model provided by anthropic.", "family": "claude-sonnet", "id": "claude-3-5-sonnet-20241022", "knowledge": "2024-04-30", "last_updated": "2024-10-22", "limit": { "context": 200000, "output": 8192 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 3.5 v2", "open_weights": false, "reasoning": false, "release_date": "2024-10-22", "temperature": true, "tool_call": true }, "claude-3-7-sonnet-20250219": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 3.7 is an AI model provided by anthropic.", "family": "claude-sonnet", "id": "claude-3-7-sonnet-20250219", "knowledge": "2024-10-31", "last_updated": "2025-02-19", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 3.7", "open_weights": false, "reasoning": true, "release_date": "2025-02-19", "temperature": true, "tool_call": true }, "claude-3-haiku-20240307": { "attachment": true, "cost": { "cache_read": 0.03, "cache_write": 0.3, "input": 0.25, "output": 1.25 }, "description": "Claude Haiku 3 is an AI model provided by anthropic.", "family": "claude-haiku", "id": "claude-3-haiku-20240307", "knowledge": "2023-08-31", "last_updated": "2024-03-13", "limit": { "context": 200000, "output": 4096 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Haiku 3", "open_weights": false, "reasoning": false, "release_date": "2024-03-13", "temperature": true, "tool_call": true }, "claude-3-opus-20240229": { "attachment": true, "cost": { "cache_read": 1.5, "cache_write": 18.75, "input": 15, "output": 75 }, "description": "Claude Opus 3 is an AI model provided by anthropic.", "family": "claude-opus", "id": "claude-3-opus-20240229", "knowledge": "2023-08-31", "last_updated": "2024-02-29", "limit": { "context": 200000, "output": 4096 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 3", "open_weights": false, "reasoning": false, "release_date": "2024-02-29", "temperature": true, "tool_call": true }, "claude-3-sonnet-20240229": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 0.3, "input": 3, "output": 15 }, "description": "Claude Sonnet 3 is an AI model provided by anthropic.", "family": "claude-sonnet", "id": "claude-3-sonnet-20240229", "knowledge": "2023-08-31", "last_updated": "2024-03-04", "limit": { "context": 200000, "output": 4096 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 3", "open_weights": false, "reasoning": false, "release_date": "2024-03-04", "temperature": true, "tool_call": true }, "claude-haiku-4-5": { "attachment": true, "cost": { "cache_read": 0.1, "cache_write": 1.25, "input": 1, "output": 5 }, "description": "Claude Haiku 4.5 (latest) is an AI model provided by anthropic.", "family": "claude-haiku", "id": "claude-haiku-4-5", "knowledge": "2025-02-28", "last_updated": "2025-10-15", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Haiku 4.5 (latest)", "open_weights": false, "reasoning": true, "release_date": "2025-10-15", "temperature": true, "tool_call": true }, "claude-haiku-4-5-20251001": { "attachment": true, "cost": { "cache_read": 0.1, "cache_write": 1.25, "input": 1, "output": 5 }, "description": "Claude Haiku 4.5 is an AI model provided by anthropic.", "family": "claude-haiku", "id": "claude-haiku-4-5-20251001", "knowledge": "2025-02-28", "last_updated": "2025-10-15", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Haiku 4.5", "open_weights": false, "reasoning": true, "release_date": "2025-10-15", "temperature": true, "tool_call": true }, "claude-opus-4-0": { "attachment": true, "cost": { "cache_read": 1.5, "cache_write": 18.75, "input": 15, "output": 75 }, "description": "Claude Opus 4 (latest) is an AI model provided by anthropic.", "family": "claude-opus", "id": "claude-opus-4-0", "knowledge": "2025-03-31", "last_updated": "2025-05-22", "limit": { "context": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4 (latest)", "open_weights": false, "reasoning": true, "release_date": "2025-05-22", "temperature": true, "tool_call": true }, "claude-opus-4-1": { "attachment": true, "cost": { "cache_read": 1.5, "cache_write": 18.75, "input": 15, "output": 75 }, "description": "Claude Opus 4.1 (latest) is an AI model provided by anthropic.", "family": "claude-opus", "id": "claude-opus-4-1", "knowledge": "2025-03-31", "last_updated": "2025-08-05", "limit": { "context": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.1 (latest)", "open_weights": false, "reasoning": true, "release_date": "2025-08-05", "temperature": true, "tool_call": true }, "claude-opus-4-1-20250805": { "attachment": true, "cost": { "cache_read": 1.5, "cache_write": 18.75, "input": 15, "output": 75 }, "description": "Claude Opus 4.1 is an AI model provided by anthropic.", "family": "claude-opus", "id": "claude-opus-4-1-20250805", "knowledge": "2025-03-31", "last_updated": "2025-08-05", "limit": { "context": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.1", "open_weights": false, "reasoning": true, "release_date": "2025-08-05", "temperature": true, "tool_call": true }, "claude-opus-4-20250514": { "attachment": true, "cost": { "cache_read": 1.5, "cache_write": 18.75, "input": 15, "output": 75 }, "description": "Claude Opus 4 is an AI model provided by anthropic.", "family": "claude-opus", "id": "claude-opus-4-20250514", "knowledge": "2025-03-31", "last_updated": "2025-05-22", "limit": { "context": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4", "open_weights": false, "reasoning": true, "release_date": "2025-05-22", "temperature": true, "tool_call": true }, "claude-opus-4-5": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "input": 5, "output": 25 }, "description": "Claude Opus 4.5 (latest) is an AI model provided by anthropic.", "family": "claude-opus", "id": "claude-opus-4-5", "knowledge": "2025-03-31", "last_updated": "2025-11-24", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.5 (latest)", "open_weights": false, "reasoning": true, "release_date": "2025-11-24", "temperature": true, "tool_call": true }, "claude-opus-4-5-20251101": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "input": 5, "output": 25 }, "description": "Claude Opus 4.5 is an AI model provided by anthropic.", "family": "claude-opus", "id": "claude-opus-4-5-20251101", "knowledge": "2025-03-31", "last_updated": "2025-11-01", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.5", "open_weights": false, "reasoning": true, "release_date": "2025-11-01", "temperature": true, "tool_call": true }, "claude-opus-4-6": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "input": 5, "output": 25 }, "description": "Claude Opus 4.6 is an AI model provided by anthropic.", "experimental": { "modes": { "fast": { "cost": { "cache_read": 3, "cache_write": 37.5, "input": 30, "output": 150 }, "provider": { "body": { "speed": "fast" }, "headers": { "anthropic-beta": "fast-mode-2026-02-01" } } } } }, "family": "claude-opus", "id": "claude-opus-4-6", "knowledge": "2025-05-31", "last_updated": "2026-03-13", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.6", "open_weights": false, "reasoning": true, "release_date": "2026-02-05", "temperature": true, "tool_call": true }, "claude-opus-4-7": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "input": 5, "output": 25 }, "description": "Claude Opus 4.7 is an AI model provided by anthropic.", "experimental": { "modes": { "fast": { "cost": { "cache_read": 3, "cache_write": 37.5, "input": 30, "output": 150 }, "provider": { "body": { "speed": "fast" }, "headers": { "anthropic-beta": "fast-mode-2026-02-01" } } } } }, "family": "claude-opus", "id": "claude-opus-4-7", "knowledge": "2026-01-31", "last_updated": "2026-04-16", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.7", "open_weights": false, "reasoning": true, "release_date": "2026-04-16", "temperature": false, "tool_call": true }, "claude-sonnet-4-0": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 4 (latest) is an AI model provided by anthropic.", "family": "claude-sonnet", "id": "claude-sonnet-4-0", "knowledge": "2025-03-31", "last_updated": "2025-05-22", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4 (latest)", "open_weights": false, "reasoning": true, "release_date": "2025-05-22", "temperature": true, "tool_call": true }, "claude-sonnet-4-20250514": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 4 is an AI model provided by anthropic.", "family": "claude-sonnet", "id": "claude-sonnet-4-20250514", "knowledge": "2025-03-31", "last_updated": "2025-05-22", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4", "open_weights": false, "reasoning": true, "release_date": "2025-05-22", "temperature": true, "tool_call": true }, "claude-sonnet-4-5": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 4.5 (latest) is an AI model provided by anthropic.", "family": "claude-sonnet", "id": "claude-sonnet-4-5", "knowledge": "2025-07-31", "last_updated": "2025-09-29", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.5 (latest)", "open_weights": false, "reasoning": true, "release_date": "2025-09-29", "temperature": true, "tool_call": true }, "claude-sonnet-4-5-20250929": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 4.5 is an AI model provided by anthropic.", "family": "claude-sonnet", "id": "claude-sonnet-4-5-20250929", "knowledge": "2025-07-31", "last_updated": "2025-09-29", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.5", "open_weights": false, "reasoning": true, "release_date": "2025-09-29", "temperature": true, "tool_call": true }, "claude-sonnet-4-6": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 4.6 is an AI model provided by anthropic.", "family": "claude-sonnet", "id": "claude-sonnet-4-6", "knowledge": "2025-08-31", "last_updated": "2026-03-13", "limit": { "context": 1000000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.6", "open_weights": false, "reasoning": true, "release_date": "2026-02-17", "temperature": true, "tool_call": true } }, "name": "Anthropic", "npm": "@ai-sdk/anthropic" }, "auriko": { "api": "https://api.auriko.ai/v1", "doc": "https://docs.auriko.ai", "env": [ "AURIKO_API_KEY" ], "iconURL": "https://models.dev/logos/auriko.svg", "id": "auriko", "models": { "claude-opus-4-6": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "input": 5, "output": 25 }, "description": "Claude Opus 4.6 is an AI model provided by auriko.", "family": "claude-opus", "id": "claude-opus-4-6", "knowledge": "2025-05-31", "last_updated": "2026-03-13", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.6", "open_weights": false, "reasoning": true, "release_date": "2026-02-05", "temperature": true, "tool_call": true }, "claude-opus-4-7": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "input": 5, "output": 25 }, "description": "Claude Opus 4.7 is an AI model provided by auriko.", "experimental": { "modes": { "fast": { "cost": { "cache_read": 3, "cache_write": 37.5, "input": 30, "output": 150 }, "provider": { "body": { "speed": "fast" }, "headers": { "anthropic-beta": "fast-mode-2026-02-01" } } } } }, "family": "claude-opus", "id": "claude-opus-4-7", "knowledge": "2026-01-31", "last_updated": "2026-04-16", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.7", "open_weights": false, "reasoning": true, "release_date": "2026-04-16", "temperature": false, "tool_call": true }, "claude-sonnet-4-6": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 4.6 is an AI model provided by auriko.", "family": "claude-sonnet", "id": "claude-sonnet-4-6", "knowledge": "2025-08-31", "last_updated": "2026-03-13", "limit": { "context": 1000000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.6", "open_weights": false, "reasoning": true, "release_date": "2026-02-17", "temperature": true, "tool_call": true }, "deepseek-v4-flash": { "attachment": false, "cost": { "cache_read": 0.0028, "input": 0.14, "output": 0.28 }, "description": "DeepSeek V4 Flash is an AI model provided by auriko.", "family": "deepseek-flash", "id": "deepseek-v4-flash", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-05", "last_updated": "2026-04-24", "limit": { "context": 1000000, "output": 384000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V4 Flash", "open_weights": true, "reasoning": true, "release_date": "2026-04-24", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek-v4-pro": { "attachment": false, "cost": { "cache_read": 0.003625, "input": 0.435, "output": 0.87 }, "description": "DeepSeek V4 Pro is an AI model provided by auriko.", "family": "deepseek-thinking", "id": "deepseek-v4-pro", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-05", "last_updated": "2026-04-24", "limit": { "context": 1000000, "output": 384000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V4 Pro", "open_weights": true, "reasoning": true, "release_date": "2026-04-24", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-2.5-flash": { "attachment": true, "cost": { "cache_read": 0.03, "input": 0.3, "output": 2.5 }, "description": "Gemini 2.5 Flash is an AI model provided by auriko.", "family": "gemini-flash", "id": "gemini-2.5-flash", "knowledge": "2025-01", "last_updated": "2025-06-05", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Flash", "open_weights": false, "reasoning": true, "release_date": "2025-03-20", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-2.5-pro": { "attachment": true, "cost": { "cache_read": 0.125, "context_over_200k": { "cache_read": 0.25, "input": 2.5, "output": 15 }, "input": 1.25, "output": 10, "tiers": [ { "cache_read": 0.25, "input": 2.5, "output": 15, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Gemini 2.5 Pro is an AI model provided by auriko.", "family": "gemini-pro", "id": "gemini-2.5-pro", "knowledge": "2025-01", "last_updated": "2025-06-05", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Pro", "open_weights": false, "reasoning": true, "release_date": "2025-03-20", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-3.1-pro-preview": { "attachment": true, "cost": { "cache_read": 0.2, "context_over_200k": { "cache_read": 0.4, "input": 4, "output": 18 }, "input": 2, "output": 12, "tiers": [ { "cache_read": 0.4, "input": 4, "output": 18, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Gemini 3.1 Pro Preview is an AI model provided by auriko.", "family": "gemini-pro", "id": "gemini-3.1-pro-preview", "knowledge": "2025-01", "last_updated": "2026-02-19", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "name": "Gemini 3.1 Pro Preview", "open_weights": false, "reasoning": true, "release_date": "2026-02-19", "structured_output": true, "temperature": true, "tool_call": true }, "glm-5.1": { "attachment": false, "cost": { "cache_read": 0.26, "input": 1.4, "output": 4.4 }, "description": "GLM-5.1 is an AI model provided by auriko.", "family": "glm", "id": "glm-5.1", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-03-27", "limit": { "context": 200000, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5.1", "open_weights": false, "reasoning": true, "release_date": "2026-03-27", "structured_output": true, "temperature": true, "tool_call": true }, "grok-4.3": { "attachment": true, "cost": { "cache_read": 0.2, "context_over_200k": { "cache_read": 0.4, "input": 2.5, "output": 5 }, "input": 1.25, "output": 2.5, "tiers": [ { "cache_read": 0.4, "input": 2.5, "output": 5, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Grok 4.3 is an AI model provided by auriko.", "family": "grok", "id": "grok-4.3", "last_updated": "2026-05-01", "limit": { "context": 1000000, "output": 30000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 4.3", "open_weights": false, "reasoning": true, "release_date": "2026-05-01", "temperature": true, "tool_call": true }, "kimi-k2.5": { "attachment": false, "cost": { "input": 0.5, "output": 2.8 }, "description": "Kimi K2.5 is an AI model provided by auriko.", "family": "kimi-k2.5", "id": "kimi-k2.5", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-01", "last_updated": "2026-01", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Kimi K2.5", "open_weights": true, "reasoning": true, "release_date": "2026-01", "structured_output": true, "temperature": false, "tool_call": true }, "kimi-k2.6": { "attachment": true, "cost": { "cache_read": 0.16, "input": 0.95, "output": 4 }, "description": "Kimi K2.6 is an AI model provided by auriko.", "family": "kimi-k2.6", "id": "kimi-k2.6", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-01", "last_updated": "2026-04-21", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Kimi K2.6", "open_weights": true, "reasoning": true, "release_date": "2026-04-21", "structured_output": true, "temperature": true, "tool_call": true }, "minimax-m2-7": { "attachment": false, "cost": { "cache_write": 0.375, "input": 0.3, "output": 1.2 }, "description": "MiniMax-M2.7 is an AI model provided by auriko.", "family": "minimax", "id": "minimax-m2-7", "last_updated": "2026-03-18", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.7", "open_weights": true, "reasoning": true, "release_date": "2026-03-18", "temperature": true, "tool_call": true }, "minimax-m2-7-highspeed": { "attachment": false, "cost": { "cache_write": 0.375, "input": 0.6, "output": 2.4 }, "description": "MiniMax-M2.7-highspeed is an AI model provided by auriko.", "family": "minimax", "id": "minimax-m2-7-highspeed", "last_updated": "2026-03-18", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.7-highspeed", "open_weights": true, "reasoning": true, "release_date": "2026-03-18", "temperature": true, "tool_call": true }, "qwen-3.6-plus": { "attachment": false, "cost": { "cache_read": 0.1, "context_over_200k": { "cache_read": 0.2, "cache_write": 2.5, "input": 2, "output": 6 }, "input": 0.5, "output": 3, "tiers": [ { "cache_read": 0.2, "cache_write": 2.5, "input": 2, "output": 6, "tier": { "size": 256000, "type": "context" } } ] }, "description": "Qwen3.6 Plus is an AI model provided by auriko.", "family": "qwen", "id": "qwen-3.6-plus", "knowledge": "2025-04", "last_updated": "2026-04-02", "limit": { "context": 1000000, "output": 65536 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen3.6 Plus", "open_weights": false, "reasoning": true, "release_date": "2026-04-02", "temperature": true, "tool_call": true } }, "name": "Auriko", "npm": "@ai-sdk/openai-compatible" }, "azure": { "doc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "env": [ "AZURE_RESOURCE_NAME", "AZURE_API_KEY" ], "iconURL": "https://models.dev/logos/azure.svg", "id": "azure", "lobeIcon": "AzureAI.Color", "models": { "claude-haiku-4-5": { "attachment": true, "cost": { "cache_read": 0.1, "cache_write": 1.25, "input": 1, "output": 5 }, "description": "Claude Haiku 4.5 is an AI model provided by azure.", "family": "claude-haiku", "id": "claude-haiku-4-5", "knowledge": "2025-02-31", "last_updated": "2025-11-18", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Haiku 4.5", "open_weights": false, "provider": { "api": "https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1", "npm": "@ai-sdk/anthropic" }, "reasoning": true, "release_date": "2025-11-18", "structured_output": true, "temperature": true, "tool_call": true }, "claude-opus-4-1": { "attachment": true, "cost": { "cache_read": 1.5, "cache_write": 18.75, "input": 15, "output": 75 }, "description": "Claude Opus 4.1 is an AI model provided by azure.", "family": "claude-opus", "id": "claude-opus-4-1", "knowledge": "2025-03-31", "last_updated": "2025-11-18", "limit": { "context": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.1", "open_weights": false, "provider": { "api": "https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1", "npm": "@ai-sdk/anthropic" }, "reasoning": true, "release_date": "2025-11-18", "structured_output": true, "temperature": true, "tool_call": true }, "claude-opus-4-5": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "input": 5, "output": 25 }, "description": "Claude Opus 4.5 is an AI model provided by azure.", "family": "claude-opus", "id": "claude-opus-4-5", "knowledge": "2025-03-31", "last_updated": "2025-08-01", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.5", "open_weights": false, "provider": { "api": "https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1", "npm": "@ai-sdk/anthropic" }, "reasoning": true, "release_date": "2025-11-24", "temperature": true, "tool_call": true }, "claude-opus-4-6": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "context_over_200k": { "cache_read": 1, "cache_write": 12.5, "input": 10, "output": 37.5 }, "input": 5, "output": 25, "tiers": [ { "cache_read": 1, "cache_write": 12.5, "input": 10, "output": 37.5, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Claude Opus 4.6 is an AI model provided by azure.", "family": "claude-opus", "id": "claude-opus-4-6", "knowledge": "2025-05-31", "last_updated": "2026-02-05", "limit": { "context": 200000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.6", "open_weights": false, "provider": { "api": "https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1", "npm": "@ai-sdk/anthropic" }, "reasoning": true, "release_date": "2026-02-05", "temperature": true, "tool_call": true }, "claude-sonnet-4-5": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 4.5 is an AI model provided by azure.", "family": "claude-sonnet", "id": "claude-sonnet-4-5", "knowledge": "2025-07-31", "last_updated": "2025-11-18", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.5", "open_weights": false, "provider": { "api": "https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1", "npm": "@ai-sdk/anthropic" }, "reasoning": true, "release_date": "2025-11-18", "structured_output": true, "temperature": true, "tool_call": true }, "claude-sonnet-4-6": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 4.6 is an AI model provided by azure.", "family": "claude-sonnet", "id": "claude-sonnet-4-6", "knowledge": "2025-08-31", "last_updated": "2026-03-13", "limit": { "context": 1000000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.6", "open_weights": false, "provider": { "api": "https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1", "npm": "@ai-sdk/anthropic" }, "reasoning": true, "release_date": "2026-02-17", "structured_output": true, "temperature": true, "tool_call": true }, "codestral-2501": { "attachment": false, "cost": { "input": 0.3, "output": 0.9 }, "description": "Codestral 25.01 is an AI model provided by azure.", "family": "codestral", "id": "codestral-2501", "knowledge": "2024-03", "last_updated": "2025-01-01", "limit": { "context": 256000, "output": 256000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Codestral 25.01", "open_weights": false, "reasoning": false, "release_date": "2025-01-01", "temperature": true, "tool_call": true }, "codex-mini": { "attachment": true, "cost": { "cache_read": 0.375, "input": 1.5, "output": 6 }, "description": "Codex Mini is an AI model provided by azure.", "family": "gpt-codex-mini", "id": "codex-mini", "knowledge": "2024-04", "last_updated": "2025-05-16", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Codex Mini", "open_weights": false, "reasoning": true, "release_date": "2025-05-16", "temperature": false, "tool_call": true }, "cohere-command-a": { "attachment": false, "cost": { "input": 2.5, "output": 10 }, "description": "Command A is an AI model provided by azure.", "family": "command-a", "id": "cohere-command-a", "knowledge": "2024-06-01", "last_updated": "2025-03-13", "limit": { "context": 256000, "output": 8000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Command A", "open_weights": true, "reasoning": true, "release_date": "2025-03-13", "temperature": true, "tool_call": true }, "cohere-command-r-08-2024": { "attachment": false, "cost": { "input": 0.15, "output": 0.6 }, "description": "Command R is an AI model provided by azure.", "family": "command-r", "id": "cohere-command-r-08-2024", "knowledge": "2024-06-01", "last_updated": "2024-08-30", "limit": { "context": 128000, "output": 4000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Command R", "open_weights": true, "reasoning": false, "release_date": "2024-08-30", "temperature": true, "tool_call": true }, "cohere-command-r-plus-08-2024": { "attachment": false, "cost": { "input": 2.5, "output": 10 }, "description": "Command R+ is an AI model provided by azure.", "family": "command-r", "id": "cohere-command-r-plus-08-2024", "knowledge": "2024-06-01", "last_updated": "2024-08-30", "limit": { "context": 128000, "output": 4000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Command R+", "open_weights": true, "reasoning": false, "release_date": "2024-08-30", "temperature": true, "tool_call": true }, "cohere-embed-v-4-0": { "attachment": true, "cost": { "input": 0.12, "output": 0 }, "description": "Embed v4 is an AI model provided by azure.", "family": "cohere-embed", "id": "cohere-embed-v-4-0", "last_updated": "2025-04-15", "limit": { "context": 128000, "output": 1536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Embed v4", "open_weights": true, "reasoning": false, "release_date": "2025-04-15", "temperature": false, "tool_call": false }, "cohere-embed-v3-english": { "attachment": false, "cost": { "input": 0.1, "output": 0 }, "description": "Embed v3 English is an AI model provided by azure.", "family": "cohere-embed", "id": "cohere-embed-v3-english", "last_updated": "2023-11-07", "limit": { "context": 512, "output": 1024 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Embed v3 English", "open_weights": true, "reasoning": false, "release_date": "2023-11-07", "temperature": false, "tool_call": false }, "cohere-embed-v3-multilingual": { "attachment": false, "cost": { "input": 0.1, "output": 0 }, "description": "Embed v3 Multilingual is an AI model provided by azure.", "family": "cohere-embed", "id": "cohere-embed-v3-multilingual", "last_updated": "2023-11-07", "limit": { "context": 512, "output": 1024 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Embed v3 Multilingual", "open_weights": true, "reasoning": false, "release_date": "2023-11-07", "temperature": false, "tool_call": false }, "deepseek-r1": { "attachment": false, "cost": { "input": 1.35, "output": 5.4 }, "description": "DeepSeek-R1 is an AI model provided by azure.", "family": "deepseek-thinking", "id": "deepseek-r1", "knowledge": "2024-07", "last_updated": "2025-01-20", "limit": { "context": 163840, "output": 163840 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek-R1", "open_weights": true, "reasoning": true, "release_date": "2025-01-20", "temperature": true, "tool_call": false }, "deepseek-r1-0528": { "attachment": false, "cost": { "input": 1.35, "output": 5.4 }, "description": "DeepSeek-R1-0528 is an AI model provided by azure.", "family": "deepseek-thinking", "id": "deepseek-r1-0528", "knowledge": "2024-07", "last_updated": "2025-05-28", "limit": { "context": 163840, "output": 163840 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek-R1-0528", "open_weights": true, "reasoning": true, "release_date": "2025-05-28", "temperature": true, "tool_call": true }, "deepseek-v3-0324": { "attachment": false, "cost": { "input": 1.14, "output": 4.56 }, "description": "DeepSeek-V3-0324 is an AI model provided by azure.", "family": "deepseek", "id": "deepseek-v3-0324", "knowledge": "2024-07", "last_updated": "2025-03-24", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek-V3-0324", "open_weights": true, "reasoning": false, "release_date": "2025-03-24", "temperature": true, "tool_call": true }, "deepseek-v3.1": { "attachment": false, "cost": { "input": 0.56, "output": 1.68 }, "description": "DeepSeek-V3.1 is an AI model provided by azure.", "family": "deepseek", "id": "deepseek-v3.1", "knowledge": "2024-07", "last_updated": "2025-08-21", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek-V3.1", "open_weights": true, "reasoning": true, "release_date": "2025-08-21", "temperature": true, "tool_call": true }, "deepseek-v3.2": { "attachment": false, "cost": { "input": 0.58, "output": 1.68 }, "description": "DeepSeek-V3.2 is an AI model provided by azure.", "family": "deepseek", "id": "deepseek-v3.2", "knowledge": "2024-07", "last_updated": "2025-12-01", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek-V3.2", "open_weights": true, "reasoning": true, "release_date": "2025-12-01", "temperature": true, "tool_call": true }, "deepseek-v3.2-speciale": { "attachment": false, "cost": { "input": 0.58, "output": 1.68 }, "description": "DeepSeek-V3.2-Speciale is an AI model provided by azure.", "family": "deepseek", "id": "deepseek-v3.2-speciale", "knowledge": "2024-07", "last_updated": "2025-12-01", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek-V3.2-Speciale", "open_weights": true, "reasoning": true, "release_date": "2025-12-01", "temperature": true, "tool_call": false }, "gpt-3.5-turbo-0125": { "attachment": false, "cost": { "input": 0.5, "output": 1.5 }, "description": "GPT-3.5 Turbo 0125 is an AI model provided by azure.", "family": "gpt", "id": "gpt-3.5-turbo-0125", "knowledge": "2021-08", "last_updated": "2024-01-25", "limit": { "context": 16384, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT-3.5 Turbo 0125", "open_weights": false, "reasoning": false, "release_date": "2024-01-25", "temperature": true, "tool_call": false }, "gpt-3.5-turbo-0301": { "attachment": false, "cost": { "input": 1.5, "output": 2 }, "description": "GPT-3.5 Turbo 0301 is an AI model provided by azure.", "family": "gpt", "id": "gpt-3.5-turbo-0301", "knowledge": "2021-08", "last_updated": "2023-03-01", "limit": { "context": 4096, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT-3.5 Turbo 0301", "open_weights": false, "reasoning": false, "release_date": "2023-03-01", "temperature": true, "tool_call": false }, "gpt-3.5-turbo-0613": { "attachment": false, "cost": { "input": 3, "output": 4 }, "description": "GPT-3.5 Turbo 0613 is an AI model provided by azure.", "family": "gpt", "id": "gpt-3.5-turbo-0613", "knowledge": "2021-08", "last_updated": "2023-06-13", "limit": { "context": 16384, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT-3.5 Turbo 0613", "open_weights": false, "reasoning": false, "release_date": "2023-06-13", "temperature": true, "tool_call": false }, "gpt-3.5-turbo-1106": { "attachment": false, "cost": { "input": 1, "output": 2 }, "description": "GPT-3.5 Turbo 1106 is an AI model provided by azure.", "family": "gpt", "id": "gpt-3.5-turbo-1106", "knowledge": "2021-08", "last_updated": "2023-11-06", "limit": { "context": 16384, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT-3.5 Turbo 1106", "open_weights": false, "reasoning": false, "release_date": "2023-11-06", "temperature": true, "tool_call": false }, "gpt-3.5-turbo-instruct": { "attachment": false, "cost": { "input": 1.5, "output": 2 }, "description": "GPT-3.5 Turbo Instruct is an AI model provided by azure.", "family": "gpt", "id": "gpt-3.5-turbo-instruct", "knowledge": "2021-08", "last_updated": "2023-09-21", "limit": { "context": 4096, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT-3.5 Turbo Instruct", "open_weights": false, "reasoning": false, "release_date": "2023-09-21", "temperature": true, "tool_call": false }, "gpt-4": { "attachment": false, "cost": { "input": 60, "output": 120 }, "description": "GPT-4 is an AI model provided by azure.", "family": "gpt", "id": "gpt-4", "knowledge": "2023-11", "last_updated": "2023-03-14", "limit": { "context": 8192, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT-4", "open_weights": false, "reasoning": false, "release_date": "2023-03-14", "temperature": true, "tool_call": true }, "gpt-4-32k": { "attachment": false, "cost": { "input": 60, "output": 120 }, "description": "GPT-4 32K is an AI model provided by azure.", "family": "gpt", "id": "gpt-4-32k", "knowledge": "2023-11", "last_updated": "2023-03-14", "limit": { "context": 32768, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT-4 32K", "open_weights": false, "reasoning": false, "release_date": "2023-03-14", "temperature": true, "tool_call": true }, "gpt-4-turbo": { "attachment": true, "cost": { "input": 10, "output": 30 }, "description": "GPT-4 Turbo is an AI model provided by azure.", "family": "gpt", "id": "gpt-4-turbo", "knowledge": "2023-12", "last_updated": "2024-04-09", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4 Turbo", "open_weights": false, "reasoning": false, "release_date": "2023-11-06", "temperature": true, "tool_call": true }, "gpt-4-turbo-vision": { "attachment": true, "cost": { "input": 10, "output": 30 }, "description": "GPT-4 Turbo Vision is an AI model provided by azure.", "family": "gpt", "id": "gpt-4-turbo-vision", "knowledge": "2023-11", "last_updated": "2024-04-09", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4 Turbo Vision", "open_weights": false, "reasoning": false, "release_date": "2023-11-06", "temperature": true, "tool_call": true }, "gpt-4.1": { "attachment": true, "cost": { "cache_read": 0.5, "input": 2, "output": 8 }, "description": "GPT-4.1 is an AI model provided by azure.", "family": "gpt", "id": "gpt-4.1", "knowledge": "2024-04", "last_updated": "2025-04-14", "limit": { "context": 1047576, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4.1", "open_weights": false, "reasoning": false, "release_date": "2025-04-14", "temperature": true, "tool_call": true }, "gpt-4.1-mini": { "attachment": true, "cost": { "cache_read": 0.1, "input": 0.4, "output": 1.6 }, "description": "GPT-4.1 mini is an AI model provided by azure.", "family": "gpt-mini", "id": "gpt-4.1-mini", "knowledge": "2024-04", "last_updated": "2025-04-14", "limit": { "context": 1047576, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4.1 mini", "open_weights": false, "reasoning": false, "release_date": "2025-04-14", "temperature": true, "tool_call": true }, "gpt-4.1-nano": { "attachment": true, "cost": { "cache_read": 0.03, "input": 0.1, "output": 0.4 }, "description": "GPT-4.1 nano is an AI model provided by azure.", "family": "gpt-nano", "id": "gpt-4.1-nano", "knowledge": "2024-04", "last_updated": "2025-04-14", "limit": { "context": 1047576, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4.1 nano", "open_weights": false, "reasoning": false, "release_date": "2025-04-14", "temperature": true, "tool_call": true }, "gpt-4o": { "attachment": true, "cost": { "cache_read": 1.25, "input": 2.5, "output": 10 }, "description": "GPT-4o is an AI model provided by azure.", "family": "gpt", "id": "gpt-4o", "knowledge": "2023-09", "last_updated": "2024-08-06", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4o", "open_weights": false, "reasoning": false, "release_date": "2024-05-13", "temperature": true, "tool_call": true }, "gpt-4o-mini": { "attachment": true, "cost": { "cache_read": 0.08, "input": 0.15, "output": 0.6 }, "description": "GPT-4o mini is an AI model provided by azure.", "family": "gpt-mini", "id": "gpt-4o-mini", "knowledge": "2023-09", "last_updated": "2024-07-18", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4o mini", "open_weights": false, "reasoning": false, "release_date": "2024-07-18", "temperature": true, "tool_call": true }, "gpt-5": { "attachment": true, "cost": { "cache_read": 0.13, "input": 1.25, "output": 10 }, "description": "GPT-5 is an AI model provided by azure.", "family": "gpt", "id": "gpt-5", "knowledge": "2024-09-30", "last_updated": "2025-08-07", "limit": { "context": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "temperature": false, "tool_call": true }, "gpt-5-chat": { "attachment": true, "cost": { "cache_read": 0.13, "input": 1.25, "output": 10 }, "description": "GPT-5 Chat is an AI model provided by azure.", "family": "gpt-codex", "id": "gpt-5-chat", "knowledge": "2024-10-24", "last_updated": "2025-08-07", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5 Chat", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "temperature": false, "tool_call": false }, "gpt-5-codex": { "attachment": false, "cost": { "cache_read": 0.13, "input": 1.25, "output": 10 }, "description": "GPT-5-Codex is an AI model provided by azure.", "family": "gpt-codex", "id": "gpt-5-codex", "knowledge": "2024-09-30", "last_updated": "2025-09-15", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5-Codex", "open_weights": false, "reasoning": true, "release_date": "2025-09-15", "temperature": false, "tool_call": true }, "gpt-5-mini": { "attachment": true, "cost": { "cache_read": 0.03, "input": 0.25, "output": 2 }, "description": "GPT-5 Mini is an AI model provided by azure.", "family": "gpt-mini", "id": "gpt-5-mini", "knowledge": "2024-05-30", "last_updated": "2025-08-07", "limit": { "context": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5 Mini", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "temperature": false, "tool_call": true }, "gpt-5-nano": { "attachment": true, "cost": { "cache_read": 0.01, "input": 0.05, "output": 0.4 }, "description": "GPT-5 Nano is an AI model provided by azure.", "family": "gpt-nano", "id": "gpt-5-nano", "knowledge": "2024-05-30", "last_updated": "2025-08-07", "limit": { "context": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5 Nano", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "temperature": false, "tool_call": true }, "gpt-5-pro": { "attachment": true, "cost": { "input": 15, "output": 120 }, "description": "GPT-5 Pro is an AI model provided by azure.", "family": "gpt-pro", "id": "gpt-5-pro", "knowledge": "2024-09-30", "last_updated": "2025-10-06", "limit": { "context": 400000, "output": 272000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5 Pro", "open_weights": false, "reasoning": true, "release_date": "2025-10-06", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.1": { "attachment": true, "cost": { "cache_read": 0.125, "input": 1.25, "output": 10 }, "description": "GPT-5.1 is an AI model provided by azure.", "family": "gpt", "id": "gpt-5.1", "knowledge": "2024-09-30", "last_updated": "2025-11-14", "limit": { "context": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image", "audio" ], "output": [ "text", "image", "audio" ] }, "name": "GPT-5.1", "open_weights": false, "reasoning": true, "release_date": "2025-11-14", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.1-chat": { "attachment": true, "cost": { "cache_read": 0.125, "input": 1.25, "output": 10 }, "description": "GPT-5.1 Chat is an AI model provided by azure.", "family": "gpt-codex", "id": "gpt-5.1-chat", "knowledge": "2024-09-30", "last_updated": "2025-11-14", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image", "audio" ], "output": [ "text", "image", "audio" ] }, "name": "GPT-5.1 Chat", "open_weights": false, "reasoning": true, "release_date": "2025-11-14", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.1-codex": { "attachment": false, "cost": { "cache_read": 0.125, "input": 1.25, "output": 10 }, "description": "GPT-5.1 Codex is an AI model provided by azure.", "family": "gpt-codex", "id": "gpt-5.1-codex", "knowledge": "2024-09-30", "last_updated": "2025-11-14", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image", "audio" ], "output": [ "text", "image", "audio" ] }, "name": "GPT-5.1 Codex", "open_weights": false, "reasoning": true, "release_date": "2025-11-14", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.1-codex-max": { "attachment": true, "cost": { "cache_read": 0.125, "input": 1.25, "output": 10 }, "description": "GPT-5.1 Codex Max is an AI model provided by azure.", "family": "gpt-codex", "id": "gpt-5.1-codex-max", "knowledge": "2024-09-30", "last_updated": "2025-11-13", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.1 Codex Max", "open_weights": false, "reasoning": true, "release_date": "2025-11-13", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.1-codex-mini": { "attachment": false, "cost": { "cache_read": 0.025, "input": 0.25, "output": 2 }, "description": "GPT-5.1 Codex Mini is an AI model provided by azure.", "family": "gpt-codex", "id": "gpt-5.1-codex-mini", "knowledge": "2024-09-30", "last_updated": "2025-11-14", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.1 Codex Mini", "open_weights": false, "reasoning": true, "release_date": "2025-11-14", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.2": { "attachment": true, "cost": { "cache_read": 0.125, "input": 1.75, "output": 14 }, "description": "GPT-5.2 is an AI model provided by azure.", "family": "gpt", "id": "gpt-5.2", "knowledge": "2025-08-31", "last_updated": "2025-12-11", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.2", "open_weights": false, "reasoning": true, "release_date": "2025-12-11", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.2-chat": { "attachment": true, "cost": { "cache_read": 0.175, "input": 1.75, "output": 14 }, "description": "GPT-5.2 Chat is an AI model provided by azure.", "family": "gpt-codex", "id": "gpt-5.2-chat", "knowledge": "2025-08-31", "last_updated": "2025-12-11", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.2 Chat", "open_weights": false, "reasoning": true, "release_date": "2025-12-11", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.2-codex": { "attachment": false, "cost": { "cache_read": 0.175, "input": 1.75, "output": 14 }, "description": "GPT-5.2 Codex is an AI model provided by azure.", "family": "gpt-codex", "id": "gpt-5.2-codex", "knowledge": "2025-08-31", "last_updated": "2026-01-14", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.2 Codex", "open_weights": false, "reasoning": true, "release_date": "2026-01-14", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.3-chat": { "attachment": true, "cost": { "cache_read": 0.175, "input": 1.75, "output": 14 }, "description": "GPT-5.3 Chat is an AI model provided by azure.", "family": "gpt-codex", "id": "gpt-5.3-chat", "knowledge": "2025-08-31", "last_updated": "2026-03-03", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.3 Chat", "open_weights": false, "reasoning": true, "release_date": "2026-03-03", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.3-codex": { "attachment": false, "cost": { "cache_read": 0.175, "input": 1.75, "output": 14 }, "description": "GPT-5.3 Codex is an AI model provided by azure.", "family": "gpt-codex", "id": "gpt-5.3-codex", "knowledge": "2025-08-31", "last_updated": "2026-02-24", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.3 Codex", "open_weights": false, "reasoning": true, "release_date": "2026-02-24", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.4": { "attachment": true, "cost": { "cache_read": 0.25, "context_over_200k": { "cache_read": 0.5, "input": 5, "output": 22.5 }, "input": 2.5, "output": 15, "tiers": [ { "cache_read": 0.5, "input": 5, "output": 22.5, "tier": { "size": 272000, "type": "context" } } ] }, "description": "GPT-5.4 is an AI model provided by azure.", "family": "gpt", "id": "gpt-5.4", "knowledge": "2025-08-31", "last_updated": "2026-03-05", "limit": { "context": 1050000, "input": 922000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.4", "open_weights": false, "reasoning": true, "release_date": "2026-03-05", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.4-mini": { "attachment": true, "cost": { "cache_read": 0.075, "input": 0.75, "output": 4.5 }, "description": "GPT-5.4 Mini is an AI model provided by azure.", "family": "gpt-mini", "id": "gpt-5.4-mini", "knowledge": "2025-08-31", "last_updated": "2026-03-17", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.4 Mini", "open_weights": false, "reasoning": true, "release_date": "2026-03-17", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.4-nano": { "attachment": true, "cost": { "cache_read": 0.02, "input": 0.2, "output": 1.25 }, "description": "GPT-5.4 Nano is an AI model provided by azure.", "family": "gpt-nano", "id": "gpt-5.4-nano", "knowledge": "2025-08-31", "last_updated": "2026-03-17", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.4 Nano", "open_weights": false, "reasoning": true, "release_date": "2026-03-17", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.4-pro": { "attachment": true, "cost": { "context_over_200k": { "input": 60, "output": 270 }, "input": 30, "output": 180, "tiers": [ { "input": 60, "output": 270, "tier": { "size": 272000, "type": "context" } } ] }, "description": "GPT-5.4 Pro is an AI model provided by azure.", "family": "gpt-pro", "id": "gpt-5.4-pro", "knowledge": "2025-08-31", "last_updated": "2026-03-05", "limit": { "context": 1050000, "input": 922000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.4 Pro", "open_weights": false, "reasoning": true, "release_date": "2026-03-05", "structured_output": false, "temperature": false, "tool_call": true }, "gpt-5.5": { "attachment": true, "cost": { "cache_read": 0.5, "context_over_200k": { "cache_read": 1, "input": 10, "output": 45 }, "input": 5, "output": 30, "tiers": [ { "cache_read": 1, "input": 10, "output": 45, "tier": { "size": 272000, "type": "context" } } ] }, "description": "GPT-5.5 is an AI model provided by azure.", "family": "gpt", "id": "gpt-5.5", "knowledge": "2025-12-01", "last_updated": "2026-04-24", "limit": { "context": 1050000, "input": 922000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.5", "open_weights": false, "reasoning": true, "release_date": "2026-04-24", "structured_output": true, "temperature": false, "tool_call": true }, "grok-3": { "attachment": false, "cost": { "cache_read": 0.75, "input": 3, "output": 15 }, "description": "Grok 3 is an AI model provided by azure.", "family": "grok", "id": "grok-3", "knowledge": "2024-11", "last_updated": "2025-02-17", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok 3", "open_weights": false, "reasoning": false, "release_date": "2025-02-17", "temperature": true, "tool_call": true }, "grok-3-mini": { "attachment": false, "cost": { "cache_read": 0.075, "input": 0.3, "output": 0.5, "reasoning": 0.5 }, "description": "Grok 3 Mini is an AI model provided by azure.", "family": "grok", "id": "grok-3-mini", "knowledge": "2024-11", "last_updated": "2025-02-17", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok 3 Mini", "open_weights": false, "reasoning": true, "release_date": "2025-02-17", "temperature": true, "tool_call": true }, "grok-4": { "attachment": false, "cost": { "cache_read": 0.75, "input": 3, "output": 15, "reasoning": 15 }, "description": "Grok 4 is an AI model provided by azure.", "family": "grok", "id": "grok-4", "knowledge": "2025-07", "last_updated": "2025-07-09", "limit": { "context": 256000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok 4", "open_weights": false, "reasoning": true, "release_date": "2025-07-09", "temperature": true, "tool_call": true }, "grok-4-1-fast-non-reasoning": { "attachment": true, "cost": { "cache_read": 0.05, "input": 0.2, "output": 0.5 }, "description": "Grok 4.1 Fast (Non-Reasoning) is an AI model provided by azure.", "family": "grok", "id": "grok-4-1-fast-non-reasoning", "last_updated": "2025-06-27", "limit": { "context": 128000, "input": 128000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 4.1 Fast (Non-Reasoning)", "open_weights": false, "reasoning": false, "release_date": "2025-06-27", "status": "beta", "temperature": true, "tool_call": true }, "grok-4-1-fast-reasoning": { "attachment": true, "cost": { "cache_read": 0.05, "input": 0.2, "output": 0.5 }, "description": "Grok 4.1 Fast (Reasoning) is an AI model provided by azure.", "family": "grok", "id": "grok-4-1-fast-reasoning", "last_updated": "2025-06-27", "limit": { "context": 128000, "input": 128000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 4.1 Fast (Reasoning)", "open_weights": false, "reasoning": true, "release_date": "2025-06-27", "status": "beta", "temperature": true, "tool_call": true }, "grok-4-20-non-reasoning": { "attachment": false, "cost": { "input": 2, "output": 6 }, "description": "Grok 4.20 (Non-Reasoning) is an AI model provided by azure.", "family": "grok", "id": "grok-4-20-non-reasoning", "knowledge": "2025-09", "last_updated": "2026-04-08", "limit": { "context": 262000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok 4.20 (Non-Reasoning)", "open_weights": false, "reasoning": false, "release_date": "2026-04-08", "status": "beta", "temperature": true, "tool_call": true }, "grok-4-20-reasoning": { "attachment": false, "cost": { "input": 2, "output": 6 }, "description": "Grok 4.20 (Reasoning) is an AI model provided by azure.", "family": "grok", "id": "grok-4-20-reasoning", "knowledge": "2025-09", "last_updated": "2026-04-08", "limit": { "context": 262000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok 4.20 (Reasoning)", "open_weights": false, "reasoning": true, "release_date": "2026-04-08", "status": "beta", "temperature": true, "tool_call": true }, "grok-4-fast-non-reasoning": { "attachment": true, "cost": { "cache_read": 0.05, "input": 0.2, "output": 0.5 }, "description": "Grok 4 Fast (Non-Reasoning) is an AI model provided by azure.", "family": "grok", "id": "grok-4-fast-non-reasoning", "knowledge": "2025-07", "last_updated": "2025-09-19", "limit": { "context": 2000000, "output": 30000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 4 Fast (Non-Reasoning)", "open_weights": false, "reasoning": false, "release_date": "2025-09-19", "temperature": true, "tool_call": true }, "grok-4-fast-reasoning": { "attachment": true, "cost": { "cache_read": 0.05, "input": 0.2, "output": 0.5 }, "description": "Grok 4 Fast (Reasoning) is an AI model provided by azure.", "family": "grok", "id": "grok-4-fast-reasoning", "knowledge": "2025-07", "last_updated": "2025-09-19", "limit": { "context": 2000000, "output": 30000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 4 Fast (Reasoning)", "open_weights": false, "reasoning": true, "release_date": "2025-09-19", "temperature": true, "tool_call": true }, "grok-code-fast-1": { "attachment": false, "cost": { "cache_read": 0.02, "input": 0.2, "output": 1.5 }, "description": "Grok Code Fast 1 is an AI model provided by azure.", "family": "grok", "id": "grok-code-fast-1", "knowledge": "2023-10", "last_updated": "2025-08-28", "limit": { "context": 256000, "output": 10000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok Code Fast 1", "open_weights": false, "reasoning": true, "release_date": "2025-08-28", "temperature": true, "tool_call": true }, "kimi-k2-thinking": { "attachment": false, "cost": { "cache_read": 0.15, "input": 0.6, "output": 2.5 }, "description": "Kimi K2 Thinking is an AI model provided by azure.", "family": "kimi-thinking", "id": "kimi-k2-thinking", "interleaved": true, "knowledge": "2024-08", "last_updated": "2025-12-02", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 Thinking", "open_weights": true, "reasoning": true, "release_date": "2025-11-06", "temperature": true, "tool_call": true }, "kimi-k2.5": { "attachment": false, "cost": { "input": 0.6, "output": 3 }, "description": "Kimi K2.5 is an AI model provided by azure.", "family": "kimi", "id": "kimi-k2.5", "interleaved": true, "knowledge": "2025-01", "last_updated": "2026-02-06", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Kimi K2.5", "open_weights": true, "provider": { "api": "https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/models", "npm": "@ai-sdk/openai-compatible", "shape": "completions" }, "reasoning": true, "release_date": "2026-02-06", "structured_output": true, "temperature": true, "tool_call": true }, "kimi-k2.6": { "attachment": false, "cost": { "input": 0.95, "output": 4 }, "description": "Kimi K2.6 is an AI model provided by azure.", "family": "kimi", "id": "kimi-k2.6", "interleaved": true, "knowledge": "2025-01", "last_updated": "2026-04-22", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Kimi K2.6", "open_weights": true, "provider": { "api": "https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/models", "npm": "@ai-sdk/openai-compatible", "shape": "completions" }, "reasoning": true, "release_date": "2026-04-22", "structured_output": true, "temperature": true, "tool_call": true }, "llama-3.2-11b-vision-instruct": { "attachment": true, "cost": { "input": 0.37, "output": 0.37 }, "description": "Llama-3.2-11B-Vision-Instruct is an AI model provided by azure.", "family": "llama", "id": "llama-3.2-11b-vision-instruct", "knowledge": "2023-12", "last_updated": "2024-09-25", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Llama-3.2-11B-Vision-Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-09-25", "temperature": true, "tool_call": true }, "llama-3.2-90b-vision-instruct": { "attachment": true, "cost": { "input": 2.04, "output": 2.04 }, "description": "Llama-3.2-90B-Vision-Instruct is an AI model provided by azure.", "family": "llama", "id": "llama-3.2-90b-vision-instruct", "knowledge": "2023-12", "last_updated": "2024-09-25", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Llama-3.2-90B-Vision-Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-09-25", "temperature": true, "tool_call": true }, "llama-3.3-70b-instruct": { "attachment": false, "cost": { "input": 0.71, "output": 0.71 }, "description": "Llama-3.3-70B-Instruct is an AI model provided by azure.", "family": "llama", "id": "llama-3.3-70b-instruct", "knowledge": "2023-12", "last_updated": "2024-12-06", "limit": { "context": 128000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama-3.3-70B-Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-12-06", "temperature": true, "tool_call": true }, "llama-4-maverick-17b-128e-instruct-fp8": { "attachment": true, "cost": { "input": 0.25, "output": 1 }, "description": "Llama 4 Maverick 17B 128E Instruct FP8 is an AI model provided by azure.", "family": "llama", "id": "llama-4-maverick-17b-128e-instruct-fp8", "knowledge": "2024-08", "last_updated": "2025-04-05", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Llama 4 Maverick 17B 128E Instruct FP8", "open_weights": true, "reasoning": false, "release_date": "2025-04-05", "temperature": true, "tool_call": true }, "llama-4-scout-17b-16e-instruct": { "attachment": true, "cost": { "input": 0.2, "output": 0.78 }, "description": "Llama 4 Scout 17B 16E Instruct is an AI model provided by azure.", "family": "llama", "id": "llama-4-scout-17b-16e-instruct", "knowledge": "2024-08", "last_updated": "2025-04-05", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Llama 4 Scout 17B 16E Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-04-05", "temperature": true, "tool_call": true }, "mai-ds-r1": { "attachment": false, "cost": { "input": 1.35, "output": 5.4 }, "description": "MAI-DS-R1 is an AI model provided by azure.", "family": "mai", "id": "mai-ds-r1", "knowledge": "2024-06", "last_updated": "2025-01-20", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MAI-DS-R1", "open_weights": false, "reasoning": true, "release_date": "2025-01-20", "temperature": true, "tool_call": false }, "meta-llama-3-70b-instruct": { "attachment": false, "cost": { "input": 2.68, "output": 3.54 }, "description": "Meta-Llama-3-70B-Instruct is an AI model provided by azure.", "family": "llama", "id": "meta-llama-3-70b-instruct", "knowledge": "2023-12", "last_updated": "2024-04-18", "limit": { "context": 8192, "output": 2048 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Meta-Llama-3-70B-Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-04-18", "temperature": true, "tool_call": false }, "meta-llama-3-8b-instruct": { "attachment": false, "cost": { "input": 0.3, "output": 0.61 }, "description": "Meta-Llama-3-8B-Instruct is an AI model provided by azure.", "family": "llama", "id": "meta-llama-3-8b-instruct", "knowledge": "2023-12", "last_updated": "2024-04-18", "limit": { "context": 8192, "output": 2048 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Meta-Llama-3-8B-Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-04-18", "temperature": true, "tool_call": false }, "meta-llama-3.1-405b-instruct": { "attachment": false, "cost": { "input": 5.33, "output": 16 }, "description": "Meta-Llama-3.1-405B-Instruct is an AI model provided by azure.", "family": "llama", "id": "meta-llama-3.1-405b-instruct", "knowledge": "2023-12", "last_updated": "2024-07-23", "limit": { "context": 128000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Meta-Llama-3.1-405B-Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-07-23", "temperature": true, "tool_call": true }, "meta-llama-3.1-70b-instruct": { "attachment": false, "cost": { "input": 2.68, "output": 3.54 }, "description": "Meta-Llama-3.1-70B-Instruct is an AI model provided by azure.", "family": "llama", "id": "meta-llama-3.1-70b-instruct", "knowledge": "2023-12", "last_updated": "2024-07-23", "limit": { "context": 128000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Meta-Llama-3.1-70B-Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-07-23", "temperature": true, "tool_call": true }, "meta-llama-3.1-8b-instruct": { "attachment": false, "cost": { "input": 0.3, "output": 0.61 }, "description": "Meta-Llama-3.1-8B-Instruct is an AI model provided by azure.", "family": "llama", "id": "meta-llama-3.1-8b-instruct", "knowledge": "2023-12", "last_updated": "2024-07-23", "limit": { "context": 128000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Meta-Llama-3.1-8B-Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-07-23", "temperature": true, "tool_call": true }, "ministral-3b": { "attachment": false, "cost": { "input": 0.04, "output": 0.04 }, "description": "Ministral 3B is an AI model provided by azure.", "family": "ministral", "id": "ministral-3b", "knowledge": "2024-03", "last_updated": "2024-10-22", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Ministral 3B", "open_weights": true, "reasoning": false, "release_date": "2024-10-22", "temperature": true, "tool_call": true }, "mistral-large-2411": { "attachment": false, "cost": { "input": 2, "output": 6 }, "description": "Mistral Large 24.11 is an AI model provided by azure.", "family": "mistral-large", "id": "mistral-large-2411", "knowledge": "2024-09", "last_updated": "2024-11-01", "limit": { "context": 128000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral Large 24.11", "open_weights": false, "reasoning": false, "release_date": "2024-11-01", "temperature": true, "tool_call": true }, "mistral-medium-2505": { "attachment": true, "cost": { "input": 0.4, "output": 2 }, "description": "Mistral Medium 3 is an AI model provided by azure.", "family": "mistral-medium", "id": "mistral-medium-2505", "knowledge": "2025-05", "last_updated": "2025-05-07", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Mistral Medium 3", "open_weights": false, "reasoning": false, "release_date": "2025-05-07", "temperature": true, "tool_call": true }, "mistral-nemo": { "attachment": false, "cost": { "input": 0.15, "output": 0.15 }, "description": "Mistral Nemo is an AI model provided by azure.", "family": "mistral-nemo", "id": "mistral-nemo", "knowledge": "2024-07", "last_updated": "2024-07-18", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral Nemo", "open_weights": true, "reasoning": false, "release_date": "2024-07-18", "temperature": true, "tool_call": true }, "mistral-small-2503": { "attachment": true, "cost": { "input": 0.1, "output": 0.3 }, "description": "Mistral Small 3.1 is an AI model provided by azure.", "family": "mistral-small", "id": "mistral-small-2503", "knowledge": "2024-09", "last_updated": "2025-03-01", "limit": { "context": 128000, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Mistral Small 3.1", "open_weights": false, "reasoning": false, "release_date": "2025-03-01", "temperature": true, "tool_call": true }, "model-router": { "attachment": true, "cost": { "input": 0.14, "output": 0 }, "description": "Model Router is an AI model provided by azure.", "family": "model-router", "id": "model-router", "last_updated": "2025-11-18", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Model Router", "open_weights": false, "reasoning": false, "release_date": "2025-05-19", "tool_call": true }, "o1": { "attachment": false, "cost": { "cache_read": 7.5, "input": 15, "output": 60 }, "description": "o1 is an AI model provided by azure.", "family": "o", "id": "o1", "knowledge": "2023-09", "last_updated": "2024-12-05", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "o1", "open_weights": false, "reasoning": true, "release_date": "2024-12-05", "temperature": false, "tool_call": true }, "o1-mini": { "attachment": false, "cost": { "cache_read": 0.55, "input": 1.1, "output": 4.4 }, "description": "o1-mini is an AI model provided by azure.", "family": "o-mini", "id": "o1-mini", "knowledge": "2023-09", "last_updated": "2024-09-12", "limit": { "context": 128000, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "o1-mini", "open_weights": false, "reasoning": true, "release_date": "2024-09-12", "temperature": false, "tool_call": true }, "o1-preview": { "attachment": false, "cost": { "cache_read": 8.25, "input": 16.5, "output": 66 }, "description": "o1-preview is an AI model provided by azure.", "family": "o", "id": "o1-preview", "knowledge": "2023-09", "last_updated": "2024-09-12", "limit": { "context": 128000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "o1-preview", "open_weights": false, "reasoning": true, "release_date": "2024-09-12", "temperature": false, "tool_call": true }, "o3": { "attachment": true, "cost": { "cache_read": 0.5, "input": 2, "output": 8 }, "description": "o3 is an AI model provided by azure.", "family": "o", "id": "o3", "knowledge": "2024-05", "last_updated": "2025-04-16", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "o3", "open_weights": false, "reasoning": true, "release_date": "2025-04-16", "temperature": false, "tool_call": true }, "o3-mini": { "attachment": false, "cost": { "cache_read": 0.55, "input": 1.1, "output": 4.4 }, "description": "o3-mini is an AI model provided by azure.", "family": "o-mini", "id": "o3-mini", "knowledge": "2024-05", "last_updated": "2025-01-29", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "o3-mini", "open_weights": false, "reasoning": true, "release_date": "2024-12-20", "temperature": false, "tool_call": true }, "o4-mini": { "attachment": true, "cost": { "cache_read": 0.28, "input": 1.1, "output": 4.4 }, "description": "o4-mini is an AI model provided by azure.", "family": "o-mini", "id": "o4-mini", "knowledge": "2024-05", "last_updated": "2025-04-16", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "o4-mini", "open_weights": false, "reasoning": true, "release_date": "2025-04-16", "temperature": false, "tool_call": true }, "phi-3-medium-128k-instruct": { "attachment": false, "cost": { "input": 0.17, "output": 0.68 }, "description": "Phi-3-medium-instruct (128k) is an AI model provided by azure.", "family": "phi", "id": "phi-3-medium-128k-instruct", "knowledge": "2023-10", "last_updated": "2024-04-23", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Phi-3-medium-instruct (128k)", "open_weights": true, "reasoning": false, "release_date": "2024-04-23", "temperature": true, "tool_call": false }, "phi-3-medium-4k-instruct": { "attachment": false, "cost": { "input": 0.17, "output": 0.68 }, "description": "Phi-3-medium-instruct (4k) is an AI model provided by azure.", "family": "phi", "id": "phi-3-medium-4k-instruct", "knowledge": "2023-10", "last_updated": "2024-04-23", "limit": { "context": 4096, "output": 1024 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Phi-3-medium-instruct (4k)", "open_weights": true, "reasoning": false, "release_date": "2024-04-23", "temperature": true, "tool_call": false }, "phi-3-mini-128k-instruct": { "attachment": false, "cost": { "input": 0.13, "output": 0.52 }, "description": "Phi-3-mini-instruct (128k) is an AI model provided by azure.", "family": "phi", "id": "phi-3-mini-128k-instruct", "knowledge": "2023-10", "last_updated": "2024-04-23", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Phi-3-mini-instruct (128k)", "open_weights": true, "reasoning": false, "release_date": "2024-04-23", "temperature": true, "tool_call": false }, "phi-3-mini-4k-instruct": { "attachment": false, "cost": { "input": 0.13, "output": 0.52 }, "description": "Phi-3-mini-instruct (4k) is an AI model provided by azure.", "family": "phi", "id": "phi-3-mini-4k-instruct", "knowledge": "2023-10", "last_updated": "2024-04-23", "limit": { "context": 4096, "output": 1024 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Phi-3-mini-instruct (4k)", "open_weights": true, "reasoning": false, "release_date": "2024-04-23", "temperature": true, "tool_call": false }, "phi-3-small-128k-instruct": { "attachment": false, "cost": { "input": 0.15, "output": 0.6 }, "description": "Phi-3-small-instruct (128k) is an AI model provided by azure.", "family": "phi", "id": "phi-3-small-128k-instruct", "knowledge": "2023-10", "last_updated": "2024-04-23", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Phi-3-small-instruct (128k)", "open_weights": true, "reasoning": false, "release_date": "2024-04-23", "temperature": true, "tool_call": false }, "phi-3-small-8k-instruct": { "attachment": false, "cost": { "input": 0.15, "output": 0.6 }, "description": "Phi-3-small-instruct (8k) is an AI model provided by azure.", "family": "phi", "id": "phi-3-small-8k-instruct", "knowledge": "2023-10", "last_updated": "2024-04-23", "limit": { "context": 8192, "output": 2048 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Phi-3-small-instruct (8k)", "open_weights": true, "reasoning": false, "release_date": "2024-04-23", "temperature": true, "tool_call": false }, "phi-3.5-mini-instruct": { "attachment": false, "cost": { "input": 0.13, "output": 0.52 }, "description": "Phi-3.5-mini-instruct is an AI model provided by azure.", "family": "phi", "id": "phi-3.5-mini-instruct", "knowledge": "2023-10", "last_updated": "2024-08-20", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Phi-3.5-mini-instruct", "open_weights": true, "reasoning": false, "release_date": "2024-08-20", "temperature": true, "tool_call": false }, "phi-3.5-moe-instruct": { "attachment": false, "cost": { "input": 0.16, "output": 0.64 }, "description": "Phi-3.5-MoE-instruct is an AI model provided by azure.", "family": "phi", "id": "phi-3.5-moe-instruct", "knowledge": "2023-10", "last_updated": "2024-08-20", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Phi-3.5-MoE-instruct", "open_weights": true, "reasoning": false, "release_date": "2024-08-20", "temperature": true, "tool_call": false }, "phi-4": { "attachment": false, "cost": { "input": 0.125, "output": 0.5 }, "description": "Phi-4 is an AI model provided by azure.", "family": "phi", "id": "phi-4", "knowledge": "2023-10", "last_updated": "2024-12-11", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Phi-4", "open_weights": true, "reasoning": false, "release_date": "2024-12-11", "temperature": true, "tool_call": false }, "phi-4-mini": { "attachment": false, "cost": { "input": 0.075, "output": 0.3 }, "description": "Phi-4-mini is an AI model provided by azure.", "family": "phi", "id": "phi-4-mini", "knowledge": "2023-10", "last_updated": "2024-12-11", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Phi-4-mini", "open_weights": true, "reasoning": false, "release_date": "2024-12-11", "temperature": true, "tool_call": true }, "phi-4-mini-reasoning": { "attachment": false, "cost": { "input": 0.075, "output": 0.3 }, "description": "Phi-4-mini-reasoning is an AI model provided by azure.", "family": "phi", "id": "phi-4-mini-reasoning", "knowledge": "2023-10", "last_updated": "2024-12-11", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Phi-4-mini-reasoning", "open_weights": true, "reasoning": true, "release_date": "2024-12-11", "temperature": true, "tool_call": true }, "phi-4-multimodal": { "attachment": true, "cost": { "input": 0.08, "input_audio": 4, "output": 0.32 }, "description": "Phi-4-multimodal is an AI model provided by azure.", "family": "phi", "id": "phi-4-multimodal", "knowledge": "2023-10", "last_updated": "2024-12-11", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text", "image", "audio" ], "output": [ "text" ] }, "name": "Phi-4-multimodal", "open_weights": true, "reasoning": false, "release_date": "2024-12-11", "temperature": true, "tool_call": false }, "phi-4-reasoning": { "attachment": false, "cost": { "input": 0.125, "output": 0.5 }, "description": "Phi-4-reasoning is an AI model provided by azure.", "family": "phi", "id": "phi-4-reasoning", "knowledge": "2023-10", "last_updated": "2024-12-11", "limit": { "context": 32000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Phi-4-reasoning", "open_weights": true, "reasoning": true, "release_date": "2024-12-11", "temperature": true, "tool_call": false }, "phi-4-reasoning-plus": { "attachment": false, "cost": { "input": 0.125, "output": 0.5 }, "description": "Phi-4-reasoning-plus is an AI model provided by azure.", "family": "phi", "id": "phi-4-reasoning-plus", "knowledge": "2023-10", "last_updated": "2024-12-11", "limit": { "context": 32000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Phi-4-reasoning-plus", "open_weights": true, "reasoning": true, "release_date": "2024-12-11", "temperature": true, "tool_call": false }, "text-embedding-3-large": { "attachment": false, "cost": { "input": 0.13, "output": 0 }, "description": "text-embedding-3-large is an AI model provided by azure.", "family": "text-embedding", "id": "text-embedding-3-large", "last_updated": "2024-01-25", "limit": { "context": 8191, "output": 3072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "text-embedding-3-large", "open_weights": false, "reasoning": false, "release_date": "2024-01-25", "tool_call": false }, "text-embedding-3-small": { "attachment": false, "cost": { "input": 0.02, "output": 0 }, "description": "text-embedding-3-small is an AI model provided by azure.", "family": "text-embedding", "id": "text-embedding-3-small", "last_updated": "2024-01-25", "limit": { "context": 8191, "output": 1536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "text-embedding-3-small", "open_weights": false, "reasoning": false, "release_date": "2024-01-25", "tool_call": false }, "text-embedding-ada-002": { "attachment": false, "cost": { "input": 0.1, "output": 0 }, "description": "text-embedding-ada-002 is an AI model provided by azure.", "family": "text-embedding", "id": "text-embedding-ada-002", "last_updated": "2022-12-15", "limit": { "context": 8192, "output": 1536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "text-embedding-ada-002", "open_weights": false, "reasoning": false, "release_date": "2022-12-15", "tool_call": false } }, "name": "Azure", "npm": "@ai-sdk/azure" }, "azure-cognitive-services": { "doc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models", "env": [ "AZURE_COGNITIVE_SERVICES_RESOURCE_NAME", "AZURE_COGNITIVE_SERVICES_API_KEY" ], "iconURL": "https://models.dev/logos/azure-cognitive-services.svg", "id": "azure-cognitive-services", "models": { "claude-haiku-4-5": { "attachment": true, "cost": { "cache_read": 0.1, "cache_write": 1.25, "input": 1, "output": 5 }, "description": "Claude Haiku 4.5 is an AI model provided by azure-cognitive-services.", "family": "claude-haiku", "id": "claude-haiku-4-5", "knowledge": "2025-02-31", "last_updated": "2025-11-18", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Haiku 4.5", "open_weights": false, "provider": { "api": "https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1", "npm": "@ai-sdk/anthropic" }, "reasoning": true, "release_date": "2025-11-18", "structured_output": true, "temperature": true, "tool_call": true }, "claude-opus-4-1": { "attachment": true, "cost": { "cache_read": 1.5, "cache_write": 18.75, "input": 15, "output": 75 }, "description": "Claude Opus 4.1 is an AI model provided by azure-cognitive-services.", "family": "claude-opus", "id": "claude-opus-4-1", "knowledge": "2025-03-31", "last_updated": "2025-11-18", "limit": { "context": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.1", "open_weights": false, "provider": { "api": "https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1", "npm": "@ai-sdk/anthropic" }, "reasoning": true, "release_date": "2025-11-18", "structured_output": true, "temperature": true, "tool_call": true }, "claude-opus-4-5": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "input": 5, "output": 25 }, "description": "Claude Opus 4.5 is an AI model provided by azure-cognitive-services.", "family": "claude-opus", "id": "claude-opus-4-5", "knowledge": "2025-03-31", "last_updated": "2025-08-01", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.5", "open_weights": false, "provider": { "api": "https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1", "npm": "@ai-sdk/anthropic" }, "reasoning": true, "release_date": "2025-11-24", "temperature": true, "tool_call": true }, "claude-opus-4-6": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "context_over_200k": { "cache_read": 1, "cache_write": 12.5, "input": 10, "output": 37.5 }, "input": 5, "output": 25, "tiers": [ { "cache_read": 1, "cache_write": 12.5, "input": 10, "output": 37.5, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Claude Opus 4.6 is an AI model provided by azure-cognitive-services.", "family": "claude-opus", "id": "claude-opus-4-6", "knowledge": "2025-05-31", "last_updated": "2026-02-05", "limit": { "context": 200000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.6", "open_weights": false, "provider": { "api": "https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1", "npm": "@ai-sdk/anthropic" }, "reasoning": true, "release_date": "2026-02-05", "temperature": true, "tool_call": true }, "claude-sonnet-4-5": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 4.5 is an AI model provided by azure-cognitive-services.", "family": "claude-sonnet", "id": "claude-sonnet-4-5", "knowledge": "2025-07-31", "last_updated": "2025-11-18", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.5", "open_weights": false, "provider": { "api": "https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1", "npm": "@ai-sdk/anthropic" }, "reasoning": true, "release_date": "2025-11-18", "structured_output": true, "temperature": true, "tool_call": true }, "codestral-2501": { "attachment": false, "cost": { "input": 0.3, "output": 0.9 }, "description": "Codestral 25.01 is an AI model provided by azure-cognitive-services.", "family": "codestral", "id": "codestral-2501", "knowledge": "2024-03", "last_updated": "2025-01-01", "limit": { "context": 256000, "output": 256000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Codestral 25.01", "open_weights": false, "reasoning": false, "release_date": "2025-01-01", "temperature": true, "tool_call": true }, "codex-mini": { "attachment": true, "cost": { "cache_read": 0.375, "input": 1.5, "output": 6 }, "description": "Codex Mini is an AI model provided by azure-cognitive-services.", "family": "gpt-codex-mini", "id": "codex-mini", "knowledge": "2024-04", "last_updated": "2025-05-16", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Codex Mini", "open_weights": false, "reasoning": true, "release_date": "2025-05-16", "temperature": false, "tool_call": true }, "cohere-command-a": { "attachment": false, "cost": { "input": 2.5, "output": 10 }, "description": "Command A is an AI model provided by azure-cognitive-services.", "family": "command-a", "id": "cohere-command-a", "knowledge": "2024-06-01", "last_updated": "2025-03-13", "limit": { "context": 256000, "output": 8000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Command A", "open_weights": true, "reasoning": true, "release_date": "2025-03-13", "temperature": true, "tool_call": true }, "cohere-command-r-08-2024": { "attachment": false, "cost": { "input": 0.15, "output": 0.6 }, "description": "Command R is an AI model provided by azure-cognitive-services.", "family": "command-r", "id": "cohere-command-r-08-2024", "knowledge": "2024-06-01", "last_updated": "2024-08-30", "limit": { "context": 128000, "output": 4000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Command R", "open_weights": true, "reasoning": false, "release_date": "2024-08-30", "temperature": true, "tool_call": true }, "cohere-command-r-plus-08-2024": { "attachment": false, "cost": { "input": 2.5, "output": 10 }, "description": "Command R+ is an AI model provided by azure-cognitive-services.", "family": "command-r", "id": "cohere-command-r-plus-08-2024", "knowledge": "2024-06-01", "last_updated": "2024-08-30", "limit": { "context": 128000, "output": 4000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Command R+", "open_weights": true, "reasoning": false, "release_date": "2024-08-30", "temperature": true, "tool_call": true }, "cohere-embed-v-4-0": { "attachment": true, "cost": { "input": 0.12, "output": 0 }, "description": "Embed v4 is an AI model provided by azure-cognitive-services.", "family": "cohere-embed", "id": "cohere-embed-v-4-0", "last_updated": "2025-04-15", "limit": { "context": 128000, "output": 1536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Embed v4", "open_weights": true, "reasoning": false, "release_date": "2025-04-15", "temperature": false, "tool_call": false }, "cohere-embed-v3-english": { "attachment": false, "cost": { "input": 0.1, "output": 0 }, "description": "Embed v3 English is an AI model provided by azure-cognitive-services.", "family": "cohere-embed", "id": "cohere-embed-v3-english", "last_updated": "2023-11-07", "limit": { "context": 512, "output": 1024 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Embed v3 English", "open_weights": true, "reasoning": false, "release_date": "2023-11-07", "temperature": false, "tool_call": false }, "cohere-embed-v3-multilingual": { "attachment": false, "cost": { "input": 0.1, "output": 0 }, "description": "Embed v3 Multilingual is an AI model provided by azure-cognitive-services.", "family": "cohere-embed", "id": "cohere-embed-v3-multilingual", "last_updated": "2023-11-07", "limit": { "context": 512, "output": 1024 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Embed v3 Multilingual", "open_weights": true, "reasoning": false, "release_date": "2023-11-07", "temperature": false, "tool_call": false }, "deepseek-r1": { "attachment": false, "cost": { "input": 1.35, "output": 5.4 }, "description": "DeepSeek-R1 is an AI model provided by azure-cognitive-services.", "family": "deepseek-thinking", "id": "deepseek-r1", "knowledge": "2024-07", "last_updated": "2025-01-20", "limit": { "context": 163840, "output": 163840 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek-R1", "open_weights": true, "reasoning": true, "release_date": "2025-01-20", "temperature": true, "tool_call": false }, "deepseek-r1-0528": { "attachment": false, "cost": { "input": 1.35, "output": 5.4 }, "description": "DeepSeek-R1-0528 is an AI model provided by azure-cognitive-services.", "family": "deepseek-thinking", "id": "deepseek-r1-0528", "knowledge": "2024-07", "last_updated": "2025-05-28", "limit": { "context": 163840, "output": 163840 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek-R1-0528", "open_weights": true, "reasoning": true, "release_date": "2025-05-28", "temperature": true, "tool_call": true }, "deepseek-v3-0324": { "attachment": false, "cost": { "input": 1.14, "output": 4.56 }, "description": "DeepSeek-V3-0324 is an AI model provided by azure-cognitive-services.", "family": "deepseek", "id": "deepseek-v3-0324", "knowledge": "2024-07", "last_updated": "2025-03-24", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek-V3-0324", "open_weights": true, "reasoning": false, "release_date": "2025-03-24", "temperature": true, "tool_call": true }, "deepseek-v3.1": { "attachment": false, "cost": { "input": 0.56, "output": 1.68 }, "description": "DeepSeek-V3.1 is an AI model provided by azure-cognitive-services.", "family": "deepseek", "id": "deepseek-v3.1", "knowledge": "2024-07", "last_updated": "2025-08-21", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek-V3.1", "open_weights": true, "reasoning": true, "release_date": "2025-08-21", "temperature": true, "tool_call": true }, "deepseek-v3.2": { "attachment": false, "cost": { "input": 0.58, "output": 1.68 }, "description": "DeepSeek-V3.2 is an AI model provided by azure-cognitive-services.", "family": "deepseek", "id": "deepseek-v3.2", "knowledge": "2024-07", "last_updated": "2025-12-01", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek-V3.2", "open_weights": true, "reasoning": true, "release_date": "2025-12-01", "temperature": true, "tool_call": true }, "deepseek-v3.2-speciale": { "attachment": false, "cost": { "input": 0.58, "output": 1.68 }, "description": "DeepSeek-V3.2-Speciale is an AI model provided by azure-cognitive-services.", "family": "deepseek", "id": "deepseek-v3.2-speciale", "knowledge": "2024-07", "last_updated": "2025-12-01", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek-V3.2-Speciale", "open_weights": true, "reasoning": true, "release_date": "2025-12-01", "temperature": true, "tool_call": false }, "gpt-3.5-turbo-0125": { "attachment": false, "cost": { "input": 0.5, "output": 1.5 }, "description": "GPT-3.5 Turbo 0125 is an AI model provided by azure-cognitive-services.", "family": "gpt", "id": "gpt-3.5-turbo-0125", "knowledge": "2021-08", "last_updated": "2024-01-25", "limit": { "context": 16384, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT-3.5 Turbo 0125", "open_weights": false, "reasoning": false, "release_date": "2024-01-25", "temperature": true, "tool_call": false }, "gpt-3.5-turbo-0301": { "attachment": false, "cost": { "input": 1.5, "output": 2 }, "description": "GPT-3.5 Turbo 0301 is an AI model provided by azure-cognitive-services.", "family": "gpt", "id": "gpt-3.5-turbo-0301", "knowledge": "2021-08", "last_updated": "2023-03-01", "limit": { "context": 4096, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT-3.5 Turbo 0301", "open_weights": false, "reasoning": false, "release_date": "2023-03-01", "temperature": true, "tool_call": false }, "gpt-3.5-turbo-0613": { "attachment": false, "cost": { "input": 3, "output": 4 }, "description": "GPT-3.5 Turbo 0613 is an AI model provided by azure-cognitive-services.", "family": "gpt", "id": "gpt-3.5-turbo-0613", "knowledge": "2021-08", "last_updated": "2023-06-13", "limit": { "context": 16384, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT-3.5 Turbo 0613", "open_weights": false, "reasoning": false, "release_date": "2023-06-13", "temperature": true, "tool_call": false }, "gpt-3.5-turbo-1106": { "attachment": false, "cost": { "input": 1, "output": 2 }, "description": "GPT-3.5 Turbo 1106 is an AI model provided by azure-cognitive-services.", "family": "gpt", "id": "gpt-3.5-turbo-1106", "knowledge": "2021-08", "last_updated": "2023-11-06", "limit": { "context": 16384, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT-3.5 Turbo 1106", "open_weights": false, "reasoning": false, "release_date": "2023-11-06", "temperature": true, "tool_call": false }, "gpt-3.5-turbo-instruct": { "attachment": false, "cost": { "input": 1.5, "output": 2 }, "description": "GPT-3.5 Turbo Instruct is an AI model provided by azure-cognitive-services.", "family": "gpt", "id": "gpt-3.5-turbo-instruct", "knowledge": "2021-08", "last_updated": "2023-09-21", "limit": { "context": 4096, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT-3.5 Turbo Instruct", "open_weights": false, "reasoning": false, "release_date": "2023-09-21", "temperature": true, "tool_call": false }, "gpt-4": { "attachment": false, "cost": { "input": 60, "output": 120 }, "description": "GPT-4 is an AI model provided by azure-cognitive-services.", "family": "gpt", "id": "gpt-4", "knowledge": "2023-11", "last_updated": "2023-03-14", "limit": { "context": 8192, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT-4", "open_weights": false, "reasoning": false, "release_date": "2023-03-14", "temperature": true, "tool_call": true }, "gpt-4-32k": { "attachment": false, "cost": { "input": 60, "output": 120 }, "description": "GPT-4 32K is an AI model provided by azure-cognitive-services.", "family": "gpt", "id": "gpt-4-32k", "knowledge": "2023-11", "last_updated": "2023-03-14", "limit": { "context": 32768, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT-4 32K", "open_weights": false, "reasoning": false, "release_date": "2023-03-14", "temperature": true, "tool_call": true }, "gpt-4-turbo": { "attachment": true, "cost": { "input": 10, "output": 30 }, "description": "GPT-4 Turbo is an AI model provided by azure-cognitive-services.", "family": "gpt", "id": "gpt-4-turbo", "knowledge": "2023-12", "last_updated": "2024-04-09", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4 Turbo", "open_weights": false, "reasoning": false, "release_date": "2023-11-06", "temperature": true, "tool_call": true }, "gpt-4-turbo-vision": { "attachment": true, "cost": { "input": 10, "output": 30 }, "description": "GPT-4 Turbo Vision is an AI model provided by azure-cognitive-services.", "family": "gpt", "id": "gpt-4-turbo-vision", "knowledge": "2023-11", "last_updated": "2024-04-09", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4 Turbo Vision", "open_weights": false, "reasoning": false, "release_date": "2023-11-06", "temperature": true, "tool_call": true }, "gpt-4.1": { "attachment": true, "cost": { "cache_read": 0.5, "input": 2, "output": 8 }, "description": "GPT-4.1 is an AI model provided by azure-cognitive-services.", "family": "gpt", "id": "gpt-4.1", "knowledge": "2024-04", "last_updated": "2025-04-14", "limit": { "context": 1047576, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4.1", "open_weights": false, "reasoning": false, "release_date": "2025-04-14", "temperature": true, "tool_call": true }, "gpt-4.1-mini": { "attachment": true, "cost": { "cache_read": 0.1, "input": 0.4, "output": 1.6 }, "description": "GPT-4.1 mini is an AI model provided by azure-cognitive-services.", "family": "gpt-mini", "id": "gpt-4.1-mini", "knowledge": "2024-04", "last_updated": "2025-04-14", "limit": { "context": 1047576, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4.1 mini", "open_weights": false, "reasoning": false, "release_date": "2025-04-14", "temperature": true, "tool_call": true }, "gpt-4.1-nano": { "attachment": true, "cost": { "cache_read": 0.03, "input": 0.1, "output": 0.4 }, "description": "GPT-4.1 nano is an AI model provided by azure-cognitive-services.", "family": "gpt-nano", "id": "gpt-4.1-nano", "knowledge": "2024-04", "last_updated": "2025-04-14", "limit": { "context": 1047576, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4.1 nano", "open_weights": false, "reasoning": false, "release_date": "2025-04-14", "temperature": true, "tool_call": true }, "gpt-4o": { "attachment": true, "cost": { "cache_read": 1.25, "input": 2.5, "output": 10 }, "description": "GPT-4o is an AI model provided by azure-cognitive-services.", "family": "gpt", "id": "gpt-4o", "knowledge": "2023-09", "last_updated": "2024-08-06", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4o", "open_weights": false, "reasoning": false, "release_date": "2024-05-13", "temperature": true, "tool_call": true }, "gpt-4o-mini": { "attachment": true, "cost": { "cache_read": 0.08, "input": 0.15, "output": 0.6 }, "description": "GPT-4o mini is an AI model provided by azure-cognitive-services.", "family": "gpt-mini", "id": "gpt-4o-mini", "knowledge": "2023-09", "last_updated": "2024-07-18", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4o mini", "open_weights": false, "reasoning": false, "release_date": "2024-07-18", "temperature": true, "tool_call": true }, "gpt-5": { "attachment": true, "cost": { "cache_read": 0.13, "input": 1.25, "output": 10 }, "description": "GPT-5 is an AI model provided by azure-cognitive-services.", "family": "gpt", "id": "gpt-5", "knowledge": "2024-09-30", "last_updated": "2025-08-07", "limit": { "context": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "temperature": false, "tool_call": true }, "gpt-5-chat": { "attachment": true, "cost": { "cache_read": 0.13, "input": 1.25, "output": 10 }, "description": "GPT-5 Chat is an AI model provided by azure-cognitive-services.", "family": "gpt-codex", "id": "gpt-5-chat", "knowledge": "2024-10-24", "last_updated": "2025-08-07", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5 Chat", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "temperature": false, "tool_call": false }, "gpt-5-codex": { "attachment": false, "cost": { "cache_read": 0.13, "input": 1.25, "output": 10 }, "description": "GPT-5-Codex is an AI model provided by azure-cognitive-services.", "family": "gpt-codex", "id": "gpt-5-codex", "knowledge": "2024-09-30", "last_updated": "2025-09-15", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5-Codex", "open_weights": false, "reasoning": true, "release_date": "2025-09-15", "temperature": false, "tool_call": true }, "gpt-5-mini": { "attachment": true, "cost": { "cache_read": 0.03, "input": 0.25, "output": 2 }, "description": "GPT-5 Mini is an AI model provided by azure-cognitive-services.", "family": "gpt-mini", "id": "gpt-5-mini", "knowledge": "2024-05-30", "last_updated": "2025-08-07", "limit": { "context": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5 Mini", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "temperature": false, "tool_call": true }, "gpt-5-nano": { "attachment": true, "cost": { "cache_read": 0.01, "input": 0.05, "output": 0.4 }, "description": "GPT-5 Nano is an AI model provided by azure-cognitive-services.", "family": "gpt-nano", "id": "gpt-5-nano", "knowledge": "2024-05-30", "last_updated": "2025-08-07", "limit": { "context": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5 Nano", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "temperature": false, "tool_call": true }, "gpt-5-pro": { "attachment": true, "cost": { "input": 15, "output": 120 }, "description": "GPT-5 Pro is an AI model provided by azure-cognitive-services.", "family": "gpt-pro", "id": "gpt-5-pro", "knowledge": "2024-09-30", "last_updated": "2025-10-06", "limit": { "context": 400000, "output": 272000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5 Pro", "open_weights": false, "reasoning": true, "release_date": "2025-10-06", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.1": { "attachment": true, "cost": { "cache_read": 0.125, "input": 1.25, "output": 10 }, "description": "GPT-5.1 is an AI model provided by azure-cognitive-services.", "family": "gpt", "id": "gpt-5.1", "knowledge": "2024-09-30", "last_updated": "2025-11-14", "limit": { "context": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image", "audio" ], "output": [ "text", "image", "audio" ] }, "name": "GPT-5.1", "open_weights": false, "reasoning": true, "release_date": "2025-11-14", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.1-chat": { "attachment": true, "cost": { "cache_read": 0.125, "input": 1.25, "output": 10 }, "description": "GPT-5.1 Chat is an AI model provided by azure-cognitive-services.", "family": "gpt-codex", "id": "gpt-5.1-chat", "knowledge": "2024-09-30", "last_updated": "2025-11-14", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image", "audio" ], "output": [ "text", "image", "audio" ] }, "name": "GPT-5.1 Chat", "open_weights": false, "reasoning": true, "release_date": "2025-11-14", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.1-codex": { "attachment": false, "cost": { "cache_read": 0.125, "input": 1.25, "output": 10 }, "description": "GPT-5.1 Codex is an AI model provided by azure-cognitive-services.", "family": "gpt-codex", "id": "gpt-5.1-codex", "knowledge": "2024-09-30", "last_updated": "2025-11-14", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image", "audio" ], "output": [ "text", "image", "audio" ] }, "name": "GPT-5.1 Codex", "open_weights": false, "reasoning": true, "release_date": "2025-11-14", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.1-codex-mini": { "attachment": false, "cost": { "cache_read": 0.025, "input": 0.25, "output": 2 }, "description": "GPT-5.1 Codex Mini is an AI model provided by azure-cognitive-services.", "family": "gpt-codex", "id": "gpt-5.1-codex-mini", "knowledge": "2024-09-30", "last_updated": "2025-11-14", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.1 Codex Mini", "open_weights": false, "reasoning": true, "release_date": "2025-11-14", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.2": { "attachment": true, "cost": { "cache_read": 0.125, "input": 1.75, "output": 14 }, "description": "GPT-5.2 is an AI model provided by azure-cognitive-services.", "family": "gpt", "id": "gpt-5.2", "knowledge": "2025-08-31", "last_updated": "2025-12-11", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.2", "open_weights": false, "reasoning": true, "release_date": "2025-12-11", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.2-chat": { "attachment": true, "cost": { "cache_read": 0.175, "input": 1.75, "output": 14 }, "description": "GPT-5.2 Chat is an AI model provided by azure-cognitive-services.", "family": "gpt-codex", "id": "gpt-5.2-chat", "knowledge": "2025-08-31", "last_updated": "2025-12-11", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.2 Chat", "open_weights": false, "reasoning": true, "release_date": "2025-12-11", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.2-codex": { "attachment": false, "cost": { "cache_read": 0.175, "input": 1.75, "output": 14 }, "description": "GPT-5.2 Codex is an AI model provided by azure-cognitive-services.", "family": "gpt-codex", "id": "gpt-5.2-codex", "knowledge": "2025-08-31", "last_updated": "2026-01-14", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.2 Codex", "open_weights": false, "reasoning": true, "release_date": "2026-01-14", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.3-codex": { "attachment": false, "cost": { "cache_read": 0.175, "input": 1.75, "output": 14 }, "description": "GPT-5.3 Codex is an AI model provided by azure-cognitive-services.", "family": "gpt-codex", "id": "gpt-5.3-codex", "knowledge": "2025-08-31", "last_updated": "2026-02-24", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.3 Codex", "open_weights": false, "reasoning": true, "release_date": "2026-02-24", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.4": { "attachment": true, "cost": { "cache_read": 0.25, "context_over_200k": { "cache_read": 0.5, "input": 5, "output": 22.5 }, "input": 2.5, "output": 15, "tiers": [ { "cache_read": 0.5, "input": 5, "output": 22.5, "tier": { "size": 272000, "type": "context" } } ] }, "description": "GPT-5.4 is an AI model provided by azure-cognitive-services.", "family": "gpt", "id": "gpt-5.4", "knowledge": "2025-08-31", "last_updated": "2026-03-05", "limit": { "context": 1050000, "input": 922000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.4", "open_weights": false, "reasoning": true, "release_date": "2026-03-05", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.4-mini": { "attachment": true, "cost": { "cache_read": 0.075, "input": 0.75, "output": 4.5 }, "description": "GPT-5.4 Mini is an AI model provided by azure-cognitive-services.", "family": "gpt-mini", "id": "gpt-5.4-mini", "knowledge": "2025-08-31", "last_updated": "2026-03-17", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.4 Mini", "open_weights": false, "reasoning": true, "release_date": "2026-03-17", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.4-nano": { "attachment": true, "cost": { "cache_read": 0.02, "input": 0.2, "output": 1.25 }, "description": "GPT-5.4 Nano is an AI model provided by azure-cognitive-services.", "family": "gpt-nano", "id": "gpt-5.4-nano", "knowledge": "2025-08-31", "last_updated": "2026-03-17", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.4 Nano", "open_weights": false, "reasoning": true, "release_date": "2026-03-17", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.4-pro": { "attachment": true, "cost": { "context_over_200k": { "input": 60, "output": 270 }, "input": 30, "output": 180, "tiers": [ { "input": 60, "output": 270, "tier": { "size": 272000, "type": "context" } } ] }, "description": "GPT-5.4 Pro is an AI model provided by azure-cognitive-services.", "family": "gpt-pro", "id": "gpt-5.4-pro", "knowledge": "2025-08-31", "last_updated": "2026-03-05", "limit": { "context": 1050000, "input": 922000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.4 Pro", "open_weights": false, "reasoning": true, "release_date": "2026-03-05", "structured_output": false, "temperature": false, "tool_call": true }, "gpt-5.5": { "attachment": true, "cost": { "cache_read": 0.5, "context_over_200k": { "cache_read": 1, "input": 10, "output": 45 }, "input": 5, "output": 30, "tiers": [ { "cache_read": 1, "input": 10, "output": 45, "tier": { "size": 272000, "type": "context" } } ] }, "description": "GPT-5.5 is an AI model provided by azure-cognitive-services.", "family": "gpt", "id": "gpt-5.5", "knowledge": "2025-12-01", "last_updated": "2026-04-24", "limit": { "context": 1050000, "input": 922000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.5", "open_weights": false, "reasoning": true, "release_date": "2026-04-24", "structured_output": true, "temperature": false, "tool_call": true }, "grok-3": { "attachment": false, "cost": { "cache_read": 0.75, "input": 3, "output": 15 }, "description": "Grok 3 is an AI model provided by azure-cognitive-services.", "family": "grok", "id": "grok-3", "knowledge": "2024-11", "last_updated": "2025-02-17", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok 3", "open_weights": false, "reasoning": false, "release_date": "2025-02-17", "temperature": true, "tool_call": true }, "grok-3-mini": { "attachment": false, "cost": { "cache_read": 0.075, "input": 0.3, "output": 0.5, "reasoning": 0.5 }, "description": "Grok 3 Mini is an AI model provided by azure-cognitive-services.", "family": "grok", "id": "grok-3-mini", "knowledge": "2024-11", "last_updated": "2025-02-17", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok 3 Mini", "open_weights": false, "reasoning": true, "release_date": "2025-02-17", "temperature": true, "tool_call": true }, "grok-4": { "attachment": false, "cost": { "cache_read": 0.75, "input": 3, "output": 15, "reasoning": 15 }, "description": "Grok 4 is an AI model provided by azure-cognitive-services.", "family": "grok", "id": "grok-4", "knowledge": "2025-07", "last_updated": "2025-07-09", "limit": { "context": 256000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok 4", "open_weights": false, "reasoning": true, "release_date": "2025-07-09", "temperature": true, "tool_call": true }, "grok-4-fast-non-reasoning": { "attachment": true, "cost": { "cache_read": 0.05, "input": 0.2, "output": 0.5 }, "description": "Grok 4 Fast (Non-Reasoning) is an AI model provided by azure-cognitive-services.", "family": "grok", "id": "grok-4-fast-non-reasoning", "knowledge": "2025-07", "last_updated": "2025-09-19", "limit": { "context": 2000000, "output": 30000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 4 Fast (Non-Reasoning)", "open_weights": false, "reasoning": false, "release_date": "2025-09-19", "temperature": true, "tool_call": true }, "grok-4-fast-reasoning": { "attachment": true, "cost": { "cache_read": 0.05, "input": 0.2, "output": 0.5 }, "description": "Grok 4 Fast (Reasoning) is an AI model provided by azure-cognitive-services.", "family": "grok", "id": "grok-4-fast-reasoning", "knowledge": "2025-07", "last_updated": "2025-09-19", "limit": { "context": 2000000, "output": 30000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 4 Fast (Reasoning)", "open_weights": false, "reasoning": true, "release_date": "2025-09-19", "temperature": true, "tool_call": true }, "grok-code-fast-1": { "attachment": false, "cost": { "cache_read": 0.02, "input": 0.2, "output": 1.5 }, "description": "Grok Code Fast 1 is an AI model provided by azure-cognitive-services.", "family": "grok", "id": "grok-code-fast-1", "knowledge": "2023-10", "last_updated": "2025-08-28", "limit": { "context": 256000, "output": 10000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok Code Fast 1", "open_weights": false, "reasoning": true, "release_date": "2025-08-28", "temperature": true, "tool_call": true }, "kimi-k2-thinking": { "attachment": false, "cost": { "cache_read": 0.15, "input": 0.6, "output": 2.5 }, "description": "Kimi K2 Thinking is an AI model provided by azure-cognitive-services.", "family": "kimi-thinking", "id": "kimi-k2-thinking", "interleaved": true, "knowledge": "2024-08", "last_updated": "2025-12-02", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 Thinking", "open_weights": true, "reasoning": true, "release_date": "2025-11-06", "temperature": true, "tool_call": true }, "kimi-k2.5": { "attachment": false, "cost": { "input": 0.6, "output": 3 }, "description": "Kimi K2.5 is an AI model provided by azure-cognitive-services.", "family": "kimi", "id": "kimi-k2.5", "interleaved": true, "knowledge": "2025-01", "last_updated": "2026-02-06", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Kimi K2.5", "open_weights": true, "provider": { "api": "https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/models", "npm": "@ai-sdk/openai-compatible", "shape": "completions" }, "reasoning": true, "release_date": "2026-02-06", "structured_output": true, "temperature": true, "tool_call": true }, "kimi-k2.6": { "attachment": false, "cost": { "input": 0.95, "output": 4 }, "description": "Kimi K2.6 is an AI model provided by azure-cognitive-services.", "family": "kimi", "id": "kimi-k2.6", "interleaved": true, "knowledge": "2025-01", "last_updated": "2026-04-22", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Kimi K2.6", "open_weights": true, "provider": { "api": "https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/models", "npm": "@ai-sdk/openai-compatible", "shape": "completions" }, "reasoning": true, "release_date": "2026-04-22", "structured_output": true, "temperature": true, "tool_call": true }, "llama-3.2-11b-vision-instruct": { "attachment": true, "cost": { "input": 0.37, "output": 0.37 }, "description": "Llama-3.2-11B-Vision-Instruct is an AI model provided by azure-cognitive-services.", "family": "llama", "id": "llama-3.2-11b-vision-instruct", "knowledge": "2023-12", "last_updated": "2024-09-25", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Llama-3.2-11B-Vision-Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-09-25", "temperature": true, "tool_call": true }, "llama-3.2-90b-vision-instruct": { "attachment": true, "cost": { "input": 2.04, "output": 2.04 }, "description": "Llama-3.2-90B-Vision-Instruct is an AI model provided by azure-cognitive-services.", "family": "llama", "id": "llama-3.2-90b-vision-instruct", "knowledge": "2023-12", "last_updated": "2024-09-25", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Llama-3.2-90B-Vision-Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-09-25", "temperature": true, "tool_call": true }, "llama-3.3-70b-instruct": { "attachment": false, "cost": { "input": 0.71, "output": 0.71 }, "description": "Llama-3.3-70B-Instruct is an AI model provided by azure-cognitive-services.", "family": "llama", "id": "llama-3.3-70b-instruct", "knowledge": "2023-12", "last_updated": "2024-12-06", "limit": { "context": 128000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama-3.3-70B-Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-12-06", "temperature": true, "tool_call": true }, "llama-4-maverick-17b-128e-instruct-fp8": { "attachment": true, "cost": { "input": 0.25, "output": 1 }, "description": "Llama 4 Maverick 17B 128E Instruct FP8 is an AI model provided by azure-cognitive-services.", "family": "llama", "id": "llama-4-maverick-17b-128e-instruct-fp8", "knowledge": "2024-08", "last_updated": "2025-04-05", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Llama 4 Maverick 17B 128E Instruct FP8", "open_weights": true, "reasoning": false, "release_date": "2025-04-05", "temperature": true, "tool_call": true }, "llama-4-scout-17b-16e-instruct": { "attachment": true, "cost": { "input": 0.2, "output": 0.78 }, "description": "Llama 4 Scout 17B 16E Instruct is an AI model provided by azure-cognitive-services.", "family": "llama", "id": "llama-4-scout-17b-16e-instruct", "knowledge": "2024-08", "last_updated": "2025-04-05", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Llama 4 Scout 17B 16E Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-04-05", "temperature": true, "tool_call": true }, "mai-ds-r1": { "attachment": false, "cost": { "input": 1.35, "output": 5.4 }, "description": "MAI-DS-R1 is an AI model provided by azure-cognitive-services.", "family": "mai", "id": "mai-ds-r1", "knowledge": "2024-06", "last_updated": "2025-01-20", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MAI-DS-R1", "open_weights": false, "reasoning": true, "release_date": "2025-01-20", "temperature": true, "tool_call": false }, "meta-llama-3-70b-instruct": { "attachment": false, "cost": { "input": 2.68, "output": 3.54 }, "description": "Meta-Llama-3-70B-Instruct is an AI model provided by azure-cognitive-services.", "family": "llama", "id": "meta-llama-3-70b-instruct", "knowledge": "2023-12", "last_updated": "2024-04-18", "limit": { "context": 8192, "output": 2048 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Meta-Llama-3-70B-Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-04-18", "temperature": true, "tool_call": false }, "meta-llama-3-8b-instruct": { "attachment": false, "cost": { "input": 0.3, "output": 0.61 }, "description": "Meta-Llama-3-8B-Instruct is an AI model provided by azure-cognitive-services.", "family": "llama", "id": "meta-llama-3-8b-instruct", "knowledge": "2023-12", "last_updated": "2024-04-18", "limit": { "context": 8192, "output": 2048 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Meta-Llama-3-8B-Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-04-18", "temperature": true, "tool_call": false }, "meta-llama-3.1-405b-instruct": { "attachment": false, "cost": { "input": 5.33, "output": 16 }, "description": "Meta-Llama-3.1-405B-Instruct is an AI model provided by azure-cognitive-services.", "family": "llama", "id": "meta-llama-3.1-405b-instruct", "knowledge": "2023-12", "last_updated": "2024-07-23", "limit": { "context": 128000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Meta-Llama-3.1-405B-Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-07-23", "temperature": true, "tool_call": true }, "meta-llama-3.1-70b-instruct": { "attachment": false, "cost": { "input": 2.68, "output": 3.54 }, "description": "Meta-Llama-3.1-70B-Instruct is an AI model provided by azure-cognitive-services.", "family": "llama", "id": "meta-llama-3.1-70b-instruct", "knowledge": "2023-12", "last_updated": "2024-07-23", "limit": { "context": 128000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Meta-Llama-3.1-70B-Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-07-23", "temperature": true, "tool_call": true }, "meta-llama-3.1-8b-instruct": { "attachment": false, "cost": { "input": 0.3, "output": 0.61 }, "description": "Meta-Llama-3.1-8B-Instruct is an AI model provided by azure-cognitive-services.", "family": "llama", "id": "meta-llama-3.1-8b-instruct", "knowledge": "2023-12", "last_updated": "2024-07-23", "limit": { "context": 128000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Meta-Llama-3.1-8B-Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-07-23", "temperature": true, "tool_call": true }, "ministral-3b": { "attachment": false, "cost": { "input": 0.04, "output": 0.04 }, "description": "Ministral 3B is an AI model provided by azure-cognitive-services.", "family": "ministral", "id": "ministral-3b", "knowledge": "2024-03", "last_updated": "2024-10-22", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Ministral 3B", "open_weights": true, "reasoning": false, "release_date": "2024-10-22", "temperature": true, "tool_call": true }, "mistral-large-2411": { "attachment": false, "cost": { "input": 2, "output": 6 }, "description": "Mistral Large 24.11 is an AI model provided by azure-cognitive-services.", "family": "mistral-large", "id": "mistral-large-2411", "knowledge": "2024-09", "last_updated": "2024-11-01", "limit": { "context": 128000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral Large 24.11", "open_weights": false, "reasoning": false, "release_date": "2024-11-01", "temperature": true, "tool_call": true }, "mistral-medium-2505": { "attachment": true, "cost": { "input": 0.4, "output": 2 }, "description": "Mistral Medium 3 is an AI model provided by azure-cognitive-services.", "family": "mistral-medium", "id": "mistral-medium-2505", "knowledge": "2025-05", "last_updated": "2025-05-07", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Mistral Medium 3", "open_weights": false, "reasoning": false, "release_date": "2025-05-07", "temperature": true, "tool_call": true }, "mistral-nemo": { "attachment": false, "cost": { "input": 0.15, "output": 0.15 }, "description": "Mistral Nemo is an AI model provided by azure-cognitive-services.", "family": "mistral-nemo", "id": "mistral-nemo", "knowledge": "2024-07", "last_updated": "2024-07-18", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral Nemo", "open_weights": true, "reasoning": false, "release_date": "2024-07-18", "temperature": true, "tool_call": true }, "mistral-small-2503": { "attachment": true, "cost": { "input": 0.1, "output": 0.3 }, "description": "Mistral Small 3.1 is an AI model provided by azure-cognitive-services.", "family": "mistral-small", "id": "mistral-small-2503", "knowledge": "2024-09", "last_updated": "2025-03-01", "limit": { "context": 128000, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Mistral Small 3.1", "open_weights": false, "reasoning": false, "release_date": "2025-03-01", "temperature": true, "tool_call": true }, "model-router": { "attachment": true, "cost": { "input": 0.14, "output": 0 }, "description": "Model Router is an AI model provided by azure-cognitive-services.", "family": "model-router", "id": "model-router", "last_updated": "2025-11-18", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Model Router", "open_weights": false, "reasoning": false, "release_date": "2025-05-19", "tool_call": true }, "o1": { "attachment": false, "cost": { "cache_read": 7.5, "input": 15, "output": 60 }, "description": "o1 is an AI model provided by azure-cognitive-services.", "family": "o", "id": "o1", "knowledge": "2023-09", "last_updated": "2024-12-05", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "o1", "open_weights": false, "reasoning": true, "release_date": "2024-12-05", "temperature": false, "tool_call": true }, "o1-mini": { "attachment": false, "cost": { "cache_read": 0.55, "input": 1.1, "output": 4.4 }, "description": "o1-mini is an AI model provided by azure-cognitive-services.", "family": "o-mini", "id": "o1-mini", "knowledge": "2023-09", "last_updated": "2024-09-12", "limit": { "context": 128000, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "o1-mini", "open_weights": false, "reasoning": true, "release_date": "2024-09-12", "temperature": false, "tool_call": true }, "o1-preview": { "attachment": false, "cost": { "cache_read": 8.25, "input": 16.5, "output": 66 }, "description": "o1-preview is an AI model provided by azure-cognitive-services.", "family": "o", "id": "o1-preview", "knowledge": "2023-09", "last_updated": "2024-09-12", "limit": { "context": 128000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "o1-preview", "open_weights": false, "reasoning": true, "release_date": "2024-09-12", "temperature": false, "tool_call": true }, "o3": { "attachment": true, "cost": { "cache_read": 0.5, "input": 2, "output": 8 }, "description": "o3 is an AI model provided by azure-cognitive-services.", "family": "o", "id": "o3", "knowledge": "2024-05", "last_updated": "2025-04-16", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "o3", "open_weights": false, "reasoning": true, "release_date": "2025-04-16", "temperature": false, "tool_call": true }, "o3-mini": { "attachment": false, "cost": { "cache_read": 0.55, "input": 1.1, "output": 4.4 }, "description": "o3-mini is an AI model provided by azure-cognitive-services.", "family": "o-mini", "id": "o3-mini", "knowledge": "2024-05", "last_updated": "2025-01-29", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "o3-mini", "open_weights": false, "reasoning": true, "release_date": "2024-12-20", "temperature": false, "tool_call": true }, "o4-mini": { "attachment": true, "cost": { "cache_read": 0.28, "input": 1.1, "output": 4.4 }, "description": "o4-mini is an AI model provided by azure-cognitive-services.", "family": "o-mini", "id": "o4-mini", "knowledge": "2024-05", "last_updated": "2025-04-16", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "o4-mini", "open_weights": false, "reasoning": true, "release_date": "2025-04-16", "temperature": false, "tool_call": true }, "phi-3-medium-128k-instruct": { "attachment": false, "cost": { "input": 0.17, "output": 0.68 }, "description": "Phi-3-medium-instruct (128k) is an AI model provided by azure-cognitive-services.", "family": "phi", "id": "phi-3-medium-128k-instruct", "knowledge": "2023-10", "last_updated": "2024-04-23", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Phi-3-medium-instruct (128k)", "open_weights": true, "reasoning": false, "release_date": "2024-04-23", "temperature": true, "tool_call": false }, "phi-3-medium-4k-instruct": { "attachment": false, "cost": { "input": 0.17, "output": 0.68 }, "description": "Phi-3-medium-instruct (4k) is an AI model provided by azure-cognitive-services.", "family": "phi", "id": "phi-3-medium-4k-instruct", "knowledge": "2023-10", "last_updated": "2024-04-23", "limit": { "context": 4096, "output": 1024 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Phi-3-medium-instruct (4k)", "open_weights": true, "reasoning": false, "release_date": "2024-04-23", "temperature": true, "tool_call": false }, "phi-3-mini-128k-instruct": { "attachment": false, "cost": { "input": 0.13, "output": 0.52 }, "description": "Phi-3-mini-instruct (128k) is an AI model provided by azure-cognitive-services.", "family": "phi", "id": "phi-3-mini-128k-instruct", "knowledge": "2023-10", "last_updated": "2024-04-23", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Phi-3-mini-instruct (128k)", "open_weights": true, "reasoning": false, "release_date": "2024-04-23", "temperature": true, "tool_call": false }, "phi-3-mini-4k-instruct": { "attachment": false, "cost": { "input": 0.13, "output": 0.52 }, "description": "Phi-3-mini-instruct (4k) is an AI model provided by azure-cognitive-services.", "family": "phi", "id": "phi-3-mini-4k-instruct", "knowledge": "2023-10", "last_updated": "2024-04-23", "limit": { "context": 4096, "output": 1024 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Phi-3-mini-instruct (4k)", "open_weights": true, "reasoning": false, "release_date": "2024-04-23", "temperature": true, "tool_call": false }, "phi-3-small-128k-instruct": { "attachment": false, "cost": { "input": 0.15, "output": 0.6 }, "description": "Phi-3-small-instruct (128k) is an AI model provided by azure-cognitive-services.", "family": "phi", "id": "phi-3-small-128k-instruct", "knowledge": "2023-10", "last_updated": "2024-04-23", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Phi-3-small-instruct (128k)", "open_weights": true, "reasoning": false, "release_date": "2024-04-23", "temperature": true, "tool_call": false }, "phi-3-small-8k-instruct": { "attachment": false, "cost": { "input": 0.15, "output": 0.6 }, "description": "Phi-3-small-instruct (8k) is an AI model provided by azure-cognitive-services.", "family": "phi", "id": "phi-3-small-8k-instruct", "knowledge": "2023-10", "last_updated": "2024-04-23", "limit": { "context": 8192, "output": 2048 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Phi-3-small-instruct (8k)", "open_weights": true, "reasoning": false, "release_date": "2024-04-23", "temperature": true, "tool_call": false }, "phi-3.5-mini-instruct": { "attachment": false, "cost": { "input": 0.13, "output": 0.52 }, "description": "Phi-3.5-mini-instruct is an AI model provided by azure-cognitive-services.", "family": "phi", "id": "phi-3.5-mini-instruct", "knowledge": "2023-10", "last_updated": "2024-08-20", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Phi-3.5-mini-instruct", "open_weights": true, "reasoning": false, "release_date": "2024-08-20", "temperature": true, "tool_call": false }, "phi-3.5-moe-instruct": { "attachment": false, "cost": { "input": 0.16, "output": 0.64 }, "description": "Phi-3.5-MoE-instruct is an AI model provided by azure-cognitive-services.", "family": "phi", "id": "phi-3.5-moe-instruct", "knowledge": "2023-10", "last_updated": "2024-08-20", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Phi-3.5-MoE-instruct", "open_weights": true, "reasoning": false, "release_date": "2024-08-20", "temperature": true, "tool_call": false }, "phi-4": { "attachment": false, "cost": { "input": 0.125, "output": 0.5 }, "description": "Phi-4 is an AI model provided by azure-cognitive-services.", "family": "phi", "id": "phi-4", "knowledge": "2023-10", "last_updated": "2024-12-11", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Phi-4", "open_weights": true, "reasoning": false, "release_date": "2024-12-11", "temperature": true, "tool_call": false }, "phi-4-mini": { "attachment": false, "cost": { "input": 0.075, "output": 0.3 }, "description": "Phi-4-mini is an AI model provided by azure-cognitive-services.", "family": "phi", "id": "phi-4-mini", "knowledge": "2023-10", "last_updated": "2024-12-11", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Phi-4-mini", "open_weights": true, "reasoning": false, "release_date": "2024-12-11", "temperature": true, "tool_call": true }, "phi-4-mini-reasoning": { "attachment": false, "cost": { "input": 0.075, "output": 0.3 }, "description": "Phi-4-mini-reasoning is an AI model provided by azure-cognitive-services.", "family": "phi", "id": "phi-4-mini-reasoning", "knowledge": "2023-10", "last_updated": "2024-12-11", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Phi-4-mini-reasoning", "open_weights": true, "reasoning": true, "release_date": "2024-12-11", "temperature": true, "tool_call": true }, "phi-4-multimodal": { "attachment": true, "cost": { "input": 0.08, "input_audio": 4, "output": 0.32 }, "description": "Phi-4-multimodal is an AI model provided by azure-cognitive-services.", "family": "phi", "id": "phi-4-multimodal", "knowledge": "2023-10", "last_updated": "2024-12-11", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text", "image", "audio" ], "output": [ "text" ] }, "name": "Phi-4-multimodal", "open_weights": true, "reasoning": false, "release_date": "2024-12-11", "temperature": true, "tool_call": false }, "phi-4-reasoning": { "attachment": false, "cost": { "input": 0.125, "output": 0.5 }, "description": "Phi-4-reasoning is an AI model provided by azure-cognitive-services.", "family": "phi", "id": "phi-4-reasoning", "knowledge": "2023-10", "last_updated": "2024-12-11", "limit": { "context": 32000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Phi-4-reasoning", "open_weights": true, "reasoning": true, "release_date": "2024-12-11", "temperature": true, "tool_call": false }, "phi-4-reasoning-plus": { "attachment": false, "cost": { "input": 0.125, "output": 0.5 }, "description": "Phi-4-reasoning-plus is an AI model provided by azure-cognitive-services.", "family": "phi", "id": "phi-4-reasoning-plus", "knowledge": "2023-10", "last_updated": "2024-12-11", "limit": { "context": 32000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Phi-4-reasoning-plus", "open_weights": true, "reasoning": true, "release_date": "2024-12-11", "temperature": true, "tool_call": false }, "text-embedding-3-large": { "attachment": false, "cost": { "input": 0.13, "output": 0 }, "description": "text-embedding-3-large is an AI model provided by azure-cognitive-services.", "family": "text-embedding", "id": "text-embedding-3-large", "last_updated": "2024-01-25", "limit": { "context": 8191, "output": 3072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "text-embedding-3-large", "open_weights": false, "reasoning": false, "release_date": "2024-01-25", "tool_call": false }, "text-embedding-3-small": { "attachment": false, "cost": { "input": 0.02, "output": 0 }, "description": "text-embedding-3-small is an AI model provided by azure-cognitive-services.", "family": "text-embedding", "id": "text-embedding-3-small", "last_updated": "2024-01-25", "limit": { "context": 8191, "output": 1536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "text-embedding-3-small", "open_weights": false, "reasoning": false, "release_date": "2024-01-25", "tool_call": false }, "text-embedding-ada-002": { "attachment": false, "cost": { "input": 0.1, "output": 0 }, "description": "text-embedding-ada-002 is an AI model provided by azure-cognitive-services.", "family": "text-embedding", "id": "text-embedding-ada-002", "last_updated": "2022-12-15", "limit": { "context": 8192, "output": 1536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "text-embedding-ada-002", "open_weights": false, "reasoning": false, "release_date": "2022-12-15", "tool_call": false } }, "name": "Azure Cognitive Services", "npm": "@ai-sdk/azure" }, "bailing": { "api": "https://api.tbox.cn/api/llm/v1/chat/completions", "doc": "https://alipaytbox.yuque.com/sxs0ba/ling/intro", "env": [ "BAILING_API_TOKEN" ], "iconURL": "https://models.dev/logos/bailing.svg", "id": "bailing", "models": { "Ling-1T": { "attachment": false, "cost": { "input": 0.57, "output": 2.29 }, "description": "Ling-1T is an AI model provided by bailing.", "family": "ling", "id": "Ling-1T", "knowledge": "2024-06", "last_updated": "2025-10", "limit": { "context": 128000, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Ling-1T", "open_weights": true, "reasoning": false, "release_date": "2025-10", "temperature": true, "tool_call": true }, "Ring-1T": { "attachment": false, "cost": { "input": 0.57, "output": 2.29 }, "description": "Ring-1T is an AI model provided by bailing.", "family": "ring", "id": "Ring-1T", "knowledge": "2024-06", "last_updated": "2025-10", "limit": { "context": 128000, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Ring-1T", "open_weights": true, "reasoning": true, "release_date": "2025-10", "temperature": true, "tool_call": false } }, "name": "Bailing", "npm": "@ai-sdk/openai-compatible" }, "baseten": { "api": "https://inference.baseten.co/v1", "doc": "https://docs.baseten.co/development/model-apis/overview", "env": [ "BASETEN_API_KEY" ], "iconURL": "https://models.dev/logos/baseten.svg", "id": "baseten", "models": { "MiniMaxAI/MiniMax-M2.5": { "attachment": false, "cost": { "input": 0.3, "output": 1.2 }, "description": "MiniMax-M2.5 is an AI model provided by baseten.", "family": "minimax", "id": "MiniMaxAI/MiniMax-M2.5", "interleaved": { "field": "reasoning_content" }, "knowledge": "2026-01", "last_updated": "2026-02-12", "limit": { "context": 204000, "output": 204000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.5", "open_weights": true, "reasoning": true, "release_date": "2026-02-12", "temperature": true, "tool_call": true }, "deepseek-ai/DeepSeek-V3-0324": { "attachment": false, "cost": { "input": 0.77, "output": 0.77 }, "description": "DeepSeek V3 0324 is an AI model provided by baseten.", "family": "deepseek", "id": "deepseek-ai/DeepSeek-V3-0324", "knowledge": "2024-12", "last_updated": "2025-03-24", "limit": { "context": 164000, "output": 131000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3 0324", "open_weights": true, "reasoning": false, "release_date": "2025-03-24", "temperature": true, "tool_call": true }, "deepseek-ai/DeepSeek-V3.1": { "attachment": false, "cost": { "input": 0.5, "output": 1.5 }, "description": "DeepSeek V3.1 is an AI model provided by baseten.", "family": "deepseek", "id": "deepseek-ai/DeepSeek-V3.1", "last_updated": "2025-08-25", "limit": { "context": 164000, "output": 131000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3.1", "open_weights": true, "reasoning": true, "release_date": "2025-08-25", "temperature": true, "tool_call": true }, "deepseek-ai/DeepSeek-V3.2": { "attachment": false, "cost": { "input": 0.3, "output": 0.45 }, "description": "DeepSeek V3.2 is an AI model provided by baseten.", "family": "deepseek", "id": "deepseek-ai/DeepSeek-V3.2", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-10", "last_updated": "2026-03-06", "limit": { "context": 163800, "output": 131100 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3.2", "open_weights": true, "reasoning": true, "release_date": "2025-12-01", "status": "deprecated", "temperature": true, "tool_call": true }, "deepseek-ai/DeepSeek-V4-Pro": { "attachment": false, "cost": { "cache_read": 0.15, "input": 1.74, "output": 3.48 }, "description": "DeepSeek V4 Pro is an AI model provided by baseten.", "family": "deepseek-thinking", "id": "deepseek-ai/DeepSeek-V4-Pro", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-05", "last_updated": "2026-04-24", "limit": { "context": 1000000, "output": 384000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V4 Pro", "open_weights": true, "reasoning": true, "release_date": "2026-04-24", "structured_output": true, "temperature": true, "tool_call": true }, "moonshotai/Kimi-K2-Instruct-0905": { "attachment": false, "cost": { "input": 0.6, "output": 2.5 }, "description": "Kimi K2 Instruct 0905 is an AI model provided by baseten.", "family": "kimi", "id": "moonshotai/Kimi-K2-Instruct-0905", "knowledge": "2025-08", "last_updated": "2026-03-06", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 Instruct 0905", "open_weights": true, "reasoning": false, "release_date": "2025-09-05", "status": "deprecated", "temperature": true, "tool_call": true }, "moonshotai/Kimi-K2-Thinking": { "attachment": false, "cost": { "input": 0.6, "output": 2.5 }, "description": "Kimi K2 Thinking is an AI model provided by baseten.", "family": "kimi-thinking", "id": "moonshotai/Kimi-K2-Thinking", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-08", "last_updated": "2026-03-06", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 Thinking", "open_weights": true, "reasoning": true, "release_date": "2025-11-06", "status": "deprecated", "temperature": true, "tool_call": true }, "moonshotai/Kimi-K2.5": { "attachment": true, "cost": { "input": 0.6, "output": 3 }, "description": "Kimi K2.5 is an AI model provided by baseten.", "family": "kimi", "id": "moonshotai/Kimi-K2.5", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-12", "last_updated": "2026-02-12", "limit": { "context": 262144, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2.5", "open_weights": true, "reasoning": true, "release_date": "2026-01-30", "temperature": true, "tool_call": true }, "moonshotai/Kimi-K2.6": { "attachment": true, "cost": { "cache_read": 0.16, "input": 0.95, "output": 4 }, "description": "Kimi K2.6 is an AI model provided by baseten.", "family": "kimi-k2.6", "id": "moonshotai/Kimi-K2.6", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-01", "last_updated": "2026-04-21", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Kimi K2.6", "open_weights": true, "reasoning": true, "release_date": "2026-04-21", "structured_output": true, "temperature": true, "tool_call": true }, "nvidia/Nemotron-120B-A12B": { "attachment": false, "cost": { "input": 0.3, "output": 0.75 }, "description": "Nemotron 3 Super is an AI model provided by baseten.", "family": "nemotron", "id": "nvidia/Nemotron-120B-A12B", "interleaved": { "field": "reasoning_content" }, "knowledge": "2026-02", "last_updated": "2026-03-11", "limit": { "context": 262144, "output": 32678 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Nemotron 3 Super", "open_weights": true, "reasoning": true, "release_date": "2026-03-11", "temperature": true, "tool_call": true }, "openai/gpt-oss-120b": { "attachment": false, "cost": { "input": 0.1, "output": 0.5 }, "description": "GPT OSS 120B is an AI model provided by baseten.", "family": "gpt-oss", "id": "openai/gpt-oss-120b", "knowledge": "2025-08", "last_updated": "2025-08-05", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT OSS 120B", "open_weights": true, "reasoning": true, "release_date": "2025-08-05", "temperature": true, "tool_call": true }, "zai-org/GLM-4.6": { "attachment": false, "cost": { "input": 0.6, "output": 2.2 }, "description": "GLM 4.6 is an AI model provided by baseten.", "family": "glm", "id": "zai-org/GLM-4.6", "knowledge": "2025-08-31", "last_updated": "2025-09-16", "limit": { "context": 200000, "output": 200000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.6", "open_weights": true, "reasoning": false, "release_date": "2025-09-16", "temperature": true, "tool_call": true }, "zai-org/GLM-4.7": { "attachment": false, "cost": { "input": 0.6, "output": 2.2 }, "description": "GLM-4.7 is an AI model provided by baseten.", "family": "glm", "id": "zai-org/GLM-4.7", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-04", "last_updated": "2025-12-22", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.7", "open_weights": true, "reasoning": true, "release_date": "2025-12-22", "temperature": true, "tool_call": true }, "zai-org/GLM-5": { "attachment": false, "cost": { "input": 0.95, "output": 3.15 }, "description": "GLM-5 is an AI model provided by baseten.", "family": "glm", "id": "zai-org/GLM-5", "interleaved": { "field": "reasoning_content" }, "knowledge": "2026-01", "last_updated": "2026-02-12", "limit": { "context": 202752, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5", "open_weights": true, "reasoning": true, "release_date": "2026-02-12", "temperature": true, "tool_call": true } }, "name": "Baseten", "npm": "@ai-sdk/openai-compatible" }, "berget": { "api": "https://api.berget.ai/v1", "doc": "https://api.berget.ai", "env": [ "BERGET_API_KEY" ], "iconURL": "https://models.dev/logos/berget.svg", "id": "berget", "models": { "google/gemma-4-31B-it": { "attachment": true, "cost": { "input": 0.275, "output": 0.55 }, "description": "Gemma 4 31B Instruct is an AI model provided by berget.", "family": "gemma", "id": "google/gemma-4-31B-it", "knowledge": "2025-12", "last_updated": "2026-04-02", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "audio", "image", "text", "video" ], "output": [ "text" ] }, "name": "Gemma 4 31B Instruct", "open_weights": true, "reasoning": true, "release_date": "2026-04-02", "structured_output": true, "temperature": true, "tool_call": true }, "meta-llama/Llama-3.3-70B-Instruct": { "attachment": false, "cost": { "input": 0.99, "output": 0.99 }, "description": "Llama 3.3 70B Instruct is an AI model provided by berget.", "family": "llama", "id": "meta-llama/Llama-3.3-70B-Instruct", "knowledge": "2023-12", "last_updated": "2025-04-27", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B Instruct", "open_weights": true, "reasoning": true, "release_date": "2025-04-27", "structured_output": true, "temperature": true, "tool_call": true }, "mistralai/Mistral-Medium-3.5-128B": { "attachment": true, "cost": { "input": 1.65, "output": 5.5 }, "description": "Mistral Medium 3.5 128B is an AI model provided by berget.", "family": "mistral-medium", "id": "mistralai/Mistral-Medium-3.5-128B", "knowledge": "2026-04", "last_updated": "2026-04-29", "limit": { "context": 262144, "output": 131072 }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "name": "Mistral Medium 3.5 128B", "open_weights": true, "reasoning": true, "release_date": "2026-04-29", "structured_output": true, "temperature": true, "tool_call": true }, "mistralai/Mistral-Small-3.2-24B-Instruct-2506": { "attachment": false, "cost": { "input": 0.33, "output": 0.33 }, "description": "Mistral Small 3.2 24B Instruct 2506 is an AI model provided by berget.", "family": "mistral-small", "id": "mistralai/Mistral-Small-3.2-24B-Instruct-2506", "knowledge": "2025-09", "last_updated": "2025-10-01", "limit": { "context": 32000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral Small 3.2 24B Instruct 2506", "open_weights": true, "reasoning": true, "release_date": "2025-10-01", "structured_output": true, "temperature": true, "tool_call": true }, "openai/gpt-oss-120b": { "attachment": false, "cost": { "input": 0.44, "output": 0.99 }, "description": "GPT-OSS-120B is an AI model provided by berget.", "family": "gpt-oss", "id": "openai/gpt-oss-120b", "knowledge": "2025-08", "last_updated": "2025-08-05", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT-OSS-120B", "open_weights": true, "reasoning": true, "release_date": "2025-08-05", "structured_output": true, "temperature": true, "tool_call": true }, "zai-org/GLM-4.7": { "attachment": false, "cost": { "input": 0.77, "output": 2.75 }, "description": "GLM 4.7 is an AI model provided by berget.", "family": "glm", "id": "zai-org/GLM-4.7", "knowledge": "2025-12", "last_updated": "2026-01-19", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.7", "open_weights": true, "reasoning": true, "release_date": "2026-01-19", "structured_output": true, "temperature": true, "tool_call": true } }, "name": "Berget.AI", "npm": "@ai-sdk/openai-compatible" }, "cerebras": { "doc": "https://inference-docs.cerebras.ai/models/overview", "env": [ "CEREBRAS_API_KEY" ], "iconURL": "https://models.dev/logos/cerebras.svg", "id": "cerebras", "lobeIcon": "Cerebras", "models": { "gpt-oss-120b": { "attachment": false, "cost": { "input": 0.25, "output": 0.69 }, "description": "GPT OSS 120B is an AI model provided by cerebras.", "family": "gpt-oss", "id": "gpt-oss-120b", "last_updated": "2025-08-05", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT OSS 120B", "open_weights": true, "reasoning": true, "release_date": "2025-08-05", "temperature": true, "tool_call": true }, "llama3.1-8b": { "attachment": false, "cost": { "input": 0.1, "output": 0.1 }, "description": "Llama 3.1 8B is an AI model provided by cerebras.", "family": "llama", "id": "llama3.1-8b", "knowledge": "2023-12", "last_updated": "2025-01-01", "limit": { "context": 32000, "output": 8000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.1 8B", "open_weights": true, "reasoning": false, "release_date": "2025-01-01", "temperature": true, "tool_call": true }, "qwen-3-235b-a22b-instruct-2507": { "attachment": false, "cost": { "input": 0.6, "output": 1.2 }, "description": "Qwen 3 235B Instruct is an AI model provided by cerebras.", "family": "qwen", "id": "qwen-3-235b-a22b-instruct-2507", "knowledge": "2025-04", "last_updated": "2025-07-22", "limit": { "context": 131000, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen 3 235B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-07-22", "temperature": true, "tool_call": true }, "zai-glm-4.7": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 2.25, "output": 2.75 }, "description": "Z.AI GLM-4.7 is an AI model provided by cerebras.", "id": "zai-glm-4.7", "last_updated": "2026-01-10", "limit": { "context": 131072, "output": 40000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Z.AI GLM-4.7", "open_weights": true, "reasoning": false, "release_date": "2026-01-10", "temperature": true, "tool_call": true } }, "name": "Cerebras", "npm": "@ai-sdk/cerebras" }, "chutes": { "api": "https://llm.chutes.ai/v1", "doc": "https://llm.chutes.ai/v1/models", "env": [ "CHUTES_API_KEY" ], "iconURL": "https://models.dev/logos/chutes.svg", "id": "chutes", "lobeIcon": "Chutes", "models": { "MiniMaxAI/MiniMax-M2.5-TEE": { "attachment": false, "cost": { "cache_read": 0.075, "input": 0.15, "output": 1.2 }, "description": "MiniMax M2.5 TEE is an AI model provided by chutes.", "family": "minimax", "id": "MiniMaxAI/MiniMax-M2.5-TEE", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-25", "limit": { "context": 196608, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M2.5 TEE", "open_weights": true, "reasoning": true, "release_date": "2026-02-15", "structured_output": true, "temperature": true, "tool_call": true }, "NousResearch/DeepHermes-3-Mistral-24B-Preview": { "attachment": false, "cost": { "cache_read": 0.01225, "input": 0.0245, "output": 0.0978 }, "description": "DeepHermes 3 Mistral 24B Preview is an AI model provided by chutes.", "family": "nousresearch", "id": "NousResearch/DeepHermes-3-Mistral-24B-Preview", "last_updated": "2026-04-25", "limit": { "context": 32768, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepHermes 3 Mistral 24B Preview", "open_weights": true, "reasoning": false, "release_date": "2025-12-29", "structured_output": true, "temperature": true, "tool_call": true }, "NousResearch/Hermes-4-14B": { "attachment": false, "cost": { "cache_read": 0.0068, "input": 0.0136, "output": 0.0543 }, "description": "Hermes 4 14B is an AI model provided by chutes.", "family": "nousresearch", "id": "NousResearch/Hermes-4-14B", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-25", "limit": { "context": 40960, "output": 40960 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Hermes 4 14B", "open_weights": true, "reasoning": true, "release_date": "2025-12-29", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen2.5-72B-Instruct": { "attachment": false, "cost": { "cache_read": 0.14945, "input": 0.2989, "output": 1.1957 }, "description": "Qwen2.5 72B Instruct is an AI model provided by chutes.", "family": "qwen", "id": "Qwen/Qwen2.5-72B-Instruct", "last_updated": "2026-04-25", "limit": { "context": 32768, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen2.5 72B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-12-29", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen2.5-Coder-32B-Instruct": { "attachment": false, "cost": { "cache_read": 0.0136, "input": 0.0272, "output": 0.1087 }, "description": "Qwen2.5 Coder 32B Instruct is an AI model provided by chutes.", "family": "qwen", "id": "Qwen/Qwen2.5-Coder-32B-Instruct", "last_updated": "2026-04-25", "limit": { "context": 32768, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen2.5 Coder 32B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-12-29", "structured_output": true, "temperature": true, "tool_call": false }, "Qwen/Qwen2.5-VL-32B-Instruct": { "attachment": true, "cost": { "cache_read": 0.02715, "input": 0.0543, "output": 0.2174 }, "description": "Qwen2.5 VL 32B Instruct is an AI model provided by chutes.", "family": "qwen", "id": "Qwen/Qwen2.5-VL-32B-Instruct", "last_updated": "2026-04-25", "limit": { "context": 16384, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen2.5 VL 32B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-12-29", "structured_output": true, "temperature": true, "tool_call": false }, "Qwen/Qwen3-235B-A22B-Instruct-2507-TEE": { "attachment": false, "cost": { "cache_read": 0.05, "input": 0.1, "output": 0.6 }, "description": "Qwen3 235B A22B Instruct 2507 TEE is an AI model provided by chutes.", "family": "qwen", "id": "Qwen/Qwen3-235B-A22B-Instruct-2507-TEE", "last_updated": "2026-04-25", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 235B A22B Instruct 2507 TEE", "open_weights": true, "reasoning": false, "release_date": "2025-12-29", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-235B-A22B-Thinking-2507": { "attachment": false, "cost": { "cache_read": 0.055, "input": 0.11, "output": 0.6 }, "description": "Qwen3 235B A22B Thinking 2507 is an AI model provided by chutes.", "family": "qwen", "id": "Qwen/Qwen3-235B-A22B-Thinking-2507", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-25", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 235B A22B Thinking 2507", "open_weights": true, "reasoning": true, "release_date": "2025-12-29", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-30B-A3B": { "attachment": false, "cost": { "cache_read": 0.03, "input": 0.06, "output": 0.22 }, "description": "Qwen3 30B A3B is an AI model provided by chutes.", "family": "qwen", "id": "Qwen/Qwen3-30B-A3B", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-25", "limit": { "context": 40960, "output": 40960 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 30B A3B", "open_weights": true, "reasoning": true, "release_date": "2025-12-29", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-32B-TEE": { "attachment": false, "cost": { "cache_read": 0.04, "input": 0.08, "output": 0.24 }, "description": "Qwen3 32B TEE is an AI model provided by chutes.", "family": "qwen", "id": "Qwen/Qwen3-32B-TEE", "last_updated": "2026-04-25", "limit": { "context": 40960, "output": 40960 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 32B TEE", "open_weights": true, "reasoning": true, "release_date": "2026-04-25", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-Coder-Next-TEE": { "attachment": false, "cost": { "cache_read": 0.06, "input": 0.12, "output": 0.75 }, "description": "Qwen3 Coder Next TEE is an AI model provided by chutes.", "family": "qwen", "id": "Qwen/Qwen3-Coder-Next-TEE", "last_updated": "2026-04-25", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Coder Next TEE", "open_weights": true, "reasoning": false, "release_date": "2026-04-25", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-Next-80B-A3B-Instruct": { "attachment": false, "cost": { "cache_read": 0.05, "input": 0.1, "output": 0.8 }, "description": "Qwen3 Next 80B A3B Instruct is an AI model provided by chutes.", "family": "qwen", "id": "Qwen/Qwen3-Next-80B-A3B-Instruct", "last_updated": "2026-04-25", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Next 80B A3B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-12-29", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3.5-397B-A17B-TEE": { "attachment": true, "cost": { "cache_read": 0.195, "input": 0.39, "output": 2.34 }, "description": "Qwen3.5 397B A17B TEE is an AI model provided by chutes.", "family": "qwen", "id": "Qwen/Qwen3.5-397B-A17B-TEE", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-25", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen3.5 397B A17B TEE", "open_weights": true, "reasoning": true, "release_date": "2026-02-18", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3.6-27B-TEE": { "attachment": true, "cost": { "cache_read": 0.0975, "input": 0.195, "output": 1.56 }, "description": "Qwen3.6 27B TEE is an AI model provided by chutes.", "family": "qwen", "id": "Qwen/Qwen3.6-27B-TEE", "last_updated": "2026-04-25", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen3.6 27B TEE", "open_weights": true, "reasoning": true, "release_date": "2026-04-25", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3Guard-Gen-0.6B": { "attachment": false, "cost": { "cache_read": 0.005, "input": 0.01, "output": 0.0109 }, "description": "Qwen3Guard Gen 0.6B is an AI model provided by chutes.", "family": "qwen", "id": "Qwen/Qwen3Guard-Gen-0.6B", "last_updated": "2026-04-25", "limit": { "context": 32768, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3Guard Gen 0.6B", "open_weights": true, "reasoning": false, "release_date": "2025-12-29", "temperature": true, "tool_call": false }, "XiaomiMiMo/MiMo-V2-Flash-TEE": { "attachment": false, "cost": { "cache_read": 0.045, "input": 0.09, "output": 0.29 }, "description": "MiMo V2 Flash TEE is an AI model provided by chutes.", "family": "mimo", "id": "XiaomiMiMo/MiMo-V2-Flash-TEE", "last_updated": "2026-04-25", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiMo V2 Flash TEE", "open_weights": true, "reasoning": false, "release_date": "2026-04-25", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek-ai/DeepSeek-R1-0528-TEE": { "attachment": false, "cost": { "cache_read": 0.225, "input": 0.45, "output": 2.15 }, "description": "DeepSeek R1 0528 TEE is an AI model provided by chutes.", "family": "deepseek-thinking", "id": "deepseek-ai/DeepSeek-R1-0528-TEE", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-25", "limit": { "context": 163840, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek R1 0528 TEE", "open_weights": true, "reasoning": true, "release_date": "2025-12-29", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { "attachment": false, "cost": { "cache_read": 0.0136, "input": 0.0272, "output": 0.1087 }, "description": "DeepSeek R1 Distill Llama 70B is an AI model provided by chutes.", "family": "deepseek-thinking", "id": "deepseek-ai/DeepSeek-R1-Distill-Llama-70B", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-25", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek R1 Distill Llama 70B", "open_weights": true, "reasoning": true, "release_date": "2025-12-29", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek-ai/DeepSeek-V3-0324-TEE": { "attachment": false, "cost": { "cache_read": 0.125, "input": 0.25, "output": 1 }, "description": "DeepSeek V3 0324 TEE is an AI model provided by chutes.", "family": "deepseek", "id": "deepseek-ai/DeepSeek-V3-0324-TEE", "last_updated": "2026-04-25", "limit": { "context": 163840, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3 0324 TEE", "open_weights": true, "reasoning": false, "release_date": "2025-12-29", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek-ai/DeepSeek-V3.1-TEE": { "attachment": false, "cost": { "cache_read": 0.135, "input": 0.27, "output": 1 }, "description": "DeepSeek V3.1 TEE is an AI model provided by chutes.", "family": "deepseek", "id": "deepseek-ai/DeepSeek-V3.1-TEE", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-25", "limit": { "context": 163840, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3.1 TEE", "open_weights": true, "reasoning": true, "release_date": "2025-12-29", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek-ai/DeepSeek-V3.2-TEE": { "attachment": false, "cost": { "cache_read": 0.14, "input": 0.28, "output": 0.42 }, "description": "DeepSeek V3.2 TEE is an AI model provided by chutes.", "family": "deepseek", "id": "deepseek-ai/DeepSeek-V3.2-TEE", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-25", "limit": { "context": 131072, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3.2 TEE", "open_weights": true, "reasoning": true, "release_date": "2025-12-29", "structured_output": true, "temperature": true, "tool_call": true }, "google/gemma-4-31B-turbo-TEE": { "attachment": true, "cost": { "cache_read": 0.065, "input": 0.13, "output": 0.38 }, "description": "gemma 4 31B turbo TEE is an AI model provided by chutes.", "family": "gemma", "id": "google/gemma-4-31B-turbo-TEE", "last_updated": "2026-04-25", "limit": { "context": 131072, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "gemma 4 31B turbo TEE", "open_weights": true, "reasoning": true, "release_date": "2026-04-25", "structured_output": true, "temperature": true, "tool_call": true }, "moonshotai/Kimi-K2.5-TEE": { "attachment": true, "cost": { "cache_read": 0.22, "input": 0.44, "output": 2 }, "description": "Kimi K2.5 TEE is an AI model provided by chutes.", "family": "kimi", "id": "moonshotai/Kimi-K2.5-TEE", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-10", "last_updated": "2026-04-25", "limit": { "context": 262144, "output": 65535 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Kimi K2.5 TEE", "open_weights": true, "reasoning": true, "release_date": "2026-01-27", "structured_output": true, "temperature": true, "tool_call": true }, "moonshotai/Kimi-K2.6-TEE": { "attachment": true, "cost": { "cache_read": 0.475, "input": 0.95, "output": 4 }, "description": "Kimi K2.6 TEE is an AI model provided by chutes.", "family": "kimi", "id": "moonshotai/Kimi-K2.6-TEE", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-12", "last_updated": "2026-04-25", "limit": { "context": 262144, "output": 65535 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Kimi K2.6 TEE", "open_weights": true, "reasoning": true, "release_date": "2026-04-20", "structured_output": true, "temperature": true, "tool_call": true }, "openai/gpt-oss-120b-TEE": { "attachment": false, "cost": { "cache_read": 0.045, "input": 0.09, "output": 0.36 }, "description": "gpt oss 120b TEE is an AI model provided by chutes.", "family": "gpt-oss", "id": "openai/gpt-oss-120b-TEE", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-25", "limit": { "context": 131072, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "gpt oss 120b TEE", "open_weights": true, "reasoning": true, "release_date": "2025-12-29", "structured_output": true, "temperature": true, "tool_call": true }, "rednote-hilab/dots.ocr": { "attachment": true, "cost": { "cache_read": 0.005, "input": 0.01, "output": 0.0109 }, "description": "dots.ocr is an AI model provided by chutes.", "family": "rednote", "id": "rednote-hilab/dots.ocr", "last_updated": "2026-04-25", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "dots.ocr", "open_weights": true, "reasoning": false, "release_date": "2025-12-29", "structured_output": true, "temperature": true, "tool_call": false }, "tngtech/DeepSeek-TNG-R1T2-Chimera-TEE": { "attachment": false, "cost": { "cache_read": 0.15, "input": 0.3, "output": 1.1 }, "description": "DeepSeek TNG R1T2 Chimera TEE is an AI model provided by chutes.", "family": "deepseek", "id": "tngtech/DeepSeek-TNG-R1T2-Chimera-TEE", "last_updated": "2026-04-25", "limit": { "context": 163840, "output": 163840 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek TNG R1T2 Chimera TEE", "open_weights": true, "reasoning": true, "release_date": "2026-04-25", "structured_output": true, "temperature": true, "tool_call": true }, "unsloth/Llama-3.2-1B-Instruct": { "attachment": false, "cost": { "cache_read": 0.005, "input": 0.01, "output": 0.0109 }, "description": "Llama 3.2 1B Instruct is an AI model provided by chutes.", "family": "unsloth", "id": "unsloth/Llama-3.2-1B-Instruct", "last_updated": "2026-04-25", "limit": { "context": 16384, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.2 1B Instruct", "open_weights": true, "reasoning": false, "release_date": "2026-01-27", "temperature": true, "tool_call": false }, "unsloth/Llama-3.2-3B-Instruct": { "attachment": false, "cost": { "cache_read": 0.005, "input": 0.01, "output": 0.0136 }, "description": "Llama 3.2 3B Instruct is an AI model provided by chutes.", "family": "unsloth", "id": "unsloth/Llama-3.2-3B-Instruct", "last_updated": "2026-04-25", "limit": { "context": 16384, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.2 3B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-02-12", "temperature": true, "tool_call": false }, "unsloth/Mistral-Nemo-Instruct-2407": { "attachment": false, "cost": { "cache_read": 0.01, "input": 0.02, "output": 0.04 }, "description": "Mistral Nemo Instruct 2407 is an AI model provided by chutes.", "family": "unsloth", "id": "unsloth/Mistral-Nemo-Instruct-2407", "last_updated": "2026-04-25", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral Nemo Instruct 2407", "open_weights": true, "reasoning": false, "release_date": "2025-12-29", "structured_output": true, "temperature": true, "tool_call": false }, "unsloth/gemma-3-12b-it": { "attachment": true, "cost": { "cache_read": 0.015, "input": 0.03, "output": 0.1 }, "description": "gemma 3 12b it is an AI model provided by chutes.", "family": "unsloth", "id": "unsloth/gemma-3-12b-it", "last_updated": "2026-04-25", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "gemma 3 12b it", "open_weights": true, "reasoning": false, "release_date": "2025-12-29", "temperature": true, "tool_call": false }, "unsloth/gemma-3-27b-it": { "attachment": true, "cost": { "cache_read": 0.0136, "input": 0.0272, "output": 0.1087 }, "description": "gemma 3 27b it is an AI model provided by chutes.", "family": "unsloth", "id": "unsloth/gemma-3-27b-it", "last_updated": "2026-04-25", "limit": { "context": 128000, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "gemma 3 27b it", "open_weights": true, "reasoning": false, "release_date": "2025-12-29", "structured_output": true, "temperature": true, "tool_call": true }, "unsloth/gemma-3-4b-it": { "attachment": true, "cost": { "cache_read": 0.005, "input": 0.01, "output": 0.0272 }, "description": "gemma 3 4b it is an AI model provided by chutes.", "family": "unsloth", "id": "unsloth/gemma-3-4b-it", "last_updated": "2026-04-25", "limit": { "context": 96000, "output": 96000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "gemma 3 4b it", "open_weights": true, "reasoning": false, "release_date": "2025-12-29", "structured_output": true, "temperature": true, "tool_call": false }, "zai-org/GLM-4.6V": { "attachment": true, "cost": { "cache_read": 0.15, "input": 0.3, "output": 0.9 }, "description": "GLM 4.6V is an AI model provided by chutes.", "family": "glm", "id": "zai-org/GLM-4.6V", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-25", "limit": { "context": 131072, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GLM 4.6V", "open_weights": true, "reasoning": true, "release_date": "2025-12-29", "structured_output": true, "temperature": true, "tool_call": true }, "zai-org/GLM-4.7-FP8": { "attachment": false, "cost": { "cache_read": 0.14945, "input": 0.2989, "output": 1.1957 }, "description": "GLM 4.7 FP8 is an AI model provided by chutes.", "family": "glm", "id": "zai-org/GLM-4.7-FP8", "last_updated": "2026-04-25", "limit": { "context": 202752, "output": 65535 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.7 FP8", "open_weights": true, "reasoning": true, "release_date": "2026-01-27", "structured_output": true, "temperature": true, "tool_call": true }, "zai-org/GLM-4.7-TEE": { "attachment": false, "cost": { "cache_read": 0.195, "input": 0.39, "output": 1.75 }, "description": "GLM 4.7 TEE is an AI model provided by chutes.", "family": "glm", "id": "zai-org/GLM-4.7-TEE", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-25", "limit": { "context": 202752, "output": 65535 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.7 TEE", "open_weights": true, "reasoning": true, "release_date": "2025-12-29", "structured_output": true, "temperature": true, "tool_call": true }, "zai-org/GLM-5-TEE": { "attachment": false, "cost": { "cache_read": 0.475, "input": 0.95, "output": 2.55 }, "description": "GLM 5 TEE is an AI model provided by chutes.", "family": "glm", "id": "zai-org/GLM-5-TEE", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-25", "limit": { "context": 202752, "output": 65535 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 5 TEE", "open_weights": true, "reasoning": true, "release_date": "2026-02-14", "structured_output": true, "temperature": true, "tool_call": true }, "zai-org/GLM-5-Turbo": { "attachment": false, "cost": { "cache_read": 0.24455, "input": 0.4891, "output": 1.9565 }, "description": "GLM 5 Turbo is an AI model provided by chutes.", "family": "glm", "id": "zai-org/GLM-5-Turbo", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-25", "limit": { "context": 202752, "output": 65535 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 5 Turbo", "open_weights": true, "reasoning": true, "release_date": "2026-03-11", "structured_output": true, "temperature": true, "tool_call": true }, "zai-org/GLM-5.1-TEE": { "attachment": false, "cost": { "cache_read": 0.525, "input": 1.05, "output": 3.5 }, "description": "GLM 5.1 TEE is an AI model provided by chutes.", "family": "glm", "id": "zai-org/GLM-5.1-TEE", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-25", "limit": { "context": 202752, "output": 65535 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 5.1 TEE", "open_weights": true, "reasoning": true, "release_date": "2026-04-08", "structured_output": true, "temperature": true, "tool_call": true } }, "name": "Chutes", "npm": "@ai-sdk/openai-compatible" }, "clarifai": { "api": "https://api.clarifai.com/v2/ext/openai/v1", "doc": "https://docs.clarifai.com/compute/inference/", "env": [ "CLARIFAI_PAT" ], "iconURL": "https://models.dev/logos/clarifai.svg", "id": "clarifai", "models": { "arcee_ai/AFM/models/trinity-mini": { "attachment": false, "cost": { "input": 0.045, "output": 0.15 }, "description": "Trinity Mini is an AI model provided by clarifai.", "family": "trinity-mini", "id": "arcee_ai/AFM/models/trinity-mini", "knowledge": "2024-10", "last_updated": "2026-02-25", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Trinity Mini", "open_weights": true, "reasoning": true, "release_date": "2025-12", "temperature": true, "tool_call": true }, "clarifai/main/models/mm-poly-8b": { "attachment": true, "cost": { "input": 0.658, "output": 1.11 }, "description": "MM Poly 8B is an AI model provided by clarifai.", "family": "mm-poly", "id": "clarifai/main/models/mm-poly-8b", "last_updated": "2026-02-25", "limit": { "context": 32768, "output": 4096 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "MM Poly 8B", "open_weights": false, "reasoning": false, "release_date": "2025-06", "temperature": true, "tool_call": false }, "deepseek-ai/deepseek-ocr/models/DeepSeek-OCR": { "attachment": true, "cost": { "input": 0.2, "output": 0.7 }, "description": "DeepSeek OCR is an AI model provided by clarifai.", "family": "deepseek", "id": "deepseek-ai/deepseek-ocr/models/DeepSeek-OCR", "last_updated": "2026-02-25", "limit": { "context": 8192, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "DeepSeek OCR", "open_weights": true, "reasoning": false, "release_date": "2025-10-20", "temperature": true, "tool_call": false }, "minimaxai/chat-completion/models/MiniMax-M2_5-high-throughput": { "attachment": false, "cost": { "input": 0.3, "output": 1.2 }, "description": "MiniMax-M2.5 High Throughput is an AI model provided by clarifai.", "family": "minimax", "id": "minimaxai/chat-completion/models/MiniMax-M2_5-high-throughput", "last_updated": "2026-02-25", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.5 High Throughput", "open_weights": true, "reasoning": true, "release_date": "2026-02-12", "temperature": true, "tool_call": true }, "mistralai/completion/models/Ministral-3-14B-Reasoning-2512": { "attachment": true, "cost": { "input": 2.5, "output": 1.7 }, "description": "Ministral 3 14B Reasoning 2512 is an AI model provided by clarifai.", "family": "ministral", "id": "mistralai/completion/models/Ministral-3-14B-Reasoning-2512", "knowledge": "2025-12", "last_updated": "2025-12-12", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Ministral 3 14B Reasoning 2512", "open_weights": true, "reasoning": true, "release_date": "2025-12-01", "temperature": true, "tool_call": true }, "mistralai/completion/models/Ministral-3-3B-Reasoning-2512": { "attachment": true, "cost": { "input": 1.039, "output": 0.54825 }, "description": "Ministral 3 3B Reasoning 2512 is an AI model provided by clarifai.", "family": "ministral", "id": "mistralai/completion/models/Ministral-3-3B-Reasoning-2512", "last_updated": "2026-02-25", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Ministral 3 3B Reasoning 2512", "open_weights": true, "reasoning": true, "release_date": "2025-12", "temperature": true, "tool_call": true }, "moonshotai/chat-completion/models/Kimi-K2_6": { "attachment": true, "cost": { "input": 0.95, "output": 4 }, "description": "Kimi K2.6 is an AI model provided by clarifai.", "family": "kimi-k2.6", "id": "moonshotai/chat-completion/models/Kimi-K2_6", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-01", "last_updated": "2026-04-21", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Kimi K2.6", "open_weights": true, "reasoning": true, "release_date": "2026-04-21", "structured_output": true, "temperature": true, "tool_call": true }, "openai/chat-completion/models/gpt-oss-120b-high-throughput": { "attachment": false, "cost": { "input": 0.09, "output": 0.36 }, "description": "GPT OSS 120B High Throughput is an AI model provided by clarifai.", "family": "gpt-oss", "id": "openai/chat-completion/models/gpt-oss-120b-high-throughput", "last_updated": "2026-02-25", "limit": { "context": 131072, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT OSS 120B High Throughput", "open_weights": true, "reasoning": true, "release_date": "2025-08-05", "temperature": true, "tool_call": true }, "openai/chat-completion/models/gpt-oss-20b": { "attachment": false, "cost": { "input": 0.045, "output": 0.18 }, "description": "GPT OSS 20B is an AI model provided by clarifai.", "family": "gpt-oss", "id": "openai/chat-completion/models/gpt-oss-20b", "last_updated": "2025-12-12", "limit": { "context": 131072, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT OSS 20B", "open_weights": true, "reasoning": true, "release_date": "2025-08-05", "temperature": true, "tool_call": true }, "qwen/qwenCoder/models/Qwen3-Coder-30B-A3B-Instruct": { "attachment": false, "cost": { "input": 0.11458, "output": 0.74812 }, "description": "Qwen3 Coder 30B A3B Instruct is an AI model provided by clarifai.", "family": "qwen", "id": "qwen/qwenCoder/models/Qwen3-Coder-30B-A3B-Instruct", "knowledge": "2025-04", "last_updated": "2026-02-12", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Coder 30B A3B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-07-31", "temperature": true, "tool_call": true }, "qwen/qwenLM/models/Qwen3-30B-A3B-Instruct-2507": { "attachment": false, "cost": { "input": 0.3, "output": 0.5 }, "description": "Qwen3 30B A3B Instruct 2507 is an AI model provided by clarifai.", "family": "qwen", "id": "qwen/qwenLM/models/Qwen3-30B-A3B-Instruct-2507", "last_updated": "2026-02-25", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 30B A3B Instruct 2507", "open_weights": true, "reasoning": false, "release_date": "2025-07-30", "structured_output": true, "temperature": true, "tool_call": true }, "qwen/qwenLM/models/Qwen3-30B-A3B-Thinking-2507": { "attachment": false, "cost": { "input": 0.36, "output": 1.3 }, "description": "Qwen3 30B A3B Thinking 2507 is an AI model provided by clarifai.", "family": "qwen", "id": "qwen/qwenLM/models/Qwen3-30B-A3B-Thinking-2507", "last_updated": "2026-02-25", "limit": { "context": 262144, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 30B A3B Thinking 2507", "open_weights": true, "reasoning": true, "release_date": "2025-07-31", "structured_output": true, "temperature": true, "tool_call": true } }, "name": "Clarifai", "npm": "@ai-sdk/openai-compatible" }, "claudinio": { "api": "https://api.claudin.io/v1", "doc": "https://claudin.io", "env": [ "CLAUDINIO_API_KEY" ], "iconURL": "https://models.dev/logos/claudinio.svg", "id": "claudinio", "models": { "claudinio": { "attachment": true, "cost": { "cache_read": 0.05, "input": 0.5, "output": 2 }, "description": "Claudinio is an AI model provided by claudinio.", "id": "claudinio", "knowledge": "2026-05", "last_updated": "2026-05-12", "limit": { "context": 256000, "output": 64000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Claudinio", "open_weights": false, "reasoning": true, "release_date": "2026-05-12", "tool_call": true } }, "name": "Claudinio", "npm": "@ai-sdk/openai-compatible" }, "cloudferro-sherlock": { "api": "https://api-sherlock.cloudferro.com/openai/v1/", "doc": "https://docs.sherlock.cloudferro.com/", "env": [ "CLOUDFERRO_SHERLOCK_API_KEY" ], "iconURL": "https://models.dev/logos/cloudferro-sherlock.svg", "id": "cloudferro-sherlock", "models": { "MiniMaxAI/MiniMax-M2.5": { "attachment": false, "cost": { "input": 0.3, "output": 1.2 }, "description": "MiniMax-M2.5 is an AI model provided by cloudferro-sherlock.", "family": "minimax", "id": "MiniMaxAI/MiniMax-M2.5", "knowledge": "2026-01", "last_updated": "2026-03-05", "limit": { "context": 196000, "input": 180000, "output": 16000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.5", "open_weights": true, "reasoning": true, "release_date": "2026-03-05", "structured_output": true, "temperature": true, "tool_call": true }, "meta-llama/Llama-3.3-70B-Instruct": { "attachment": false, "cost": { "input": 2.92, "output": 2.92 }, "description": "Llama 3.3 70B Instruct is an AI model provided by cloudferro-sherlock.", "family": "llama", "id": "meta-llama/Llama-3.3-70B-Instruct", "knowledge": "2024-10-09", "last_updated": "2024-12-06", "limit": { "context": 70000, "output": 70000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-12-06", "temperature": true, "tool_call": true }, "openai/gpt-oss-120b": { "attachment": false, "cost": { "input": 2.92, "output": 2.92 }, "description": "OpenAI GPT OSS 120B is an AI model provided by cloudferro-sherlock.", "family": "gpt-oss", "id": "openai/gpt-oss-120b", "last_updated": "2025-08-28", "limit": { "context": 131000, "output": 131000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "OpenAI GPT OSS 120B", "open_weights": true, "reasoning": true, "release_date": "2025-08-28", "structured_output": true, "temperature": true, "tool_call": true }, "speakleash/Bielik-11B-v2.6-Instruct": { "attachment": false, "cost": { "input": 0.67, "output": 0.67 }, "description": "Bielik 11B v2.6 Instruct is an AI model provided by cloudferro-sherlock.", "id": "speakleash/Bielik-11B-v2.6-Instruct", "knowledge": "2025-03", "last_updated": "2025-03-13", "limit": { "context": 32000, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Bielik 11B v2.6 Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-03-13", "structured_output": true, "temperature": true, "tool_call": true }, "speakleash/Bielik-11B-v3.0-Instruct": { "attachment": false, "cost": { "input": 0.67, "output": 0.67 }, "description": "Bielik 11B v3.0 Instruct is an AI model provided by cloudferro-sherlock.", "id": "speakleash/Bielik-11B-v3.0-Instruct", "knowledge": "2025-03", "last_updated": "2025-03-13", "limit": { "context": 32000, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Bielik 11B v3.0 Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-03-13", "structured_output": true, "temperature": true, "tool_call": true } }, "name": "CloudFerro Sherlock", "npm": "@ai-sdk/openai-compatible" }, "cloudflare-ai-gateway": { "doc": "https://developers.cloudflare.com/ai-gateway/", "env": [ "CLOUDFLARE_API_TOKEN", "CLOUDFLARE_ACCOUNT_ID", "CLOUDFLARE_GATEWAY_ID" ], "iconURL": "https://models.dev/logos/cloudflare-ai-gateway.svg", "id": "cloudflare-ai-gateway", "models": { "anthropic/claude-3-5-haiku": { "attachment": true, "cost": { "cache_read": 0.08, "cache_write": 1, "input": 0.8, "output": 4 }, "description": "Claude Haiku 3.5 (latest) is an AI model provided by cloudflare-ai-gateway.", "family": "claude-haiku", "id": "anthropic/claude-3-5-haiku", "knowledge": "2024-07-31", "last_updated": "2024-10-22", "limit": { "context": 200000, "output": 8192 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Haiku 3.5 (latest)", "open_weights": false, "reasoning": false, "release_date": "2024-10-22", "temperature": true, "tool_call": true }, "anthropic/claude-3-haiku": { "attachment": true, "cost": { "cache_read": 0.03, "cache_write": 0.3, "input": 0.25, "output": 1.25 }, "description": "Claude Haiku 3 is an AI model provided by cloudflare-ai-gateway.", "family": "claude-haiku", "id": "anthropic/claude-3-haiku", "knowledge": "2023-08-31", "last_updated": "2024-03-13", "limit": { "context": 200000, "output": 4096 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Haiku 3", "open_weights": false, "reasoning": false, "release_date": "2024-03-13", "temperature": true, "tool_call": true }, "anthropic/claude-3-opus": { "attachment": true, "cost": { "cache_read": 1.5, "cache_write": 18.75, "input": 15, "output": 75 }, "description": "Claude Opus 3 is an AI model provided by cloudflare-ai-gateway.", "family": "claude-opus", "id": "anthropic/claude-3-opus", "knowledge": "2023-08-31", "last_updated": "2024-02-29", "limit": { "context": 200000, "output": 4096 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 3", "open_weights": false, "reasoning": false, "release_date": "2024-02-29", "temperature": true, "tool_call": true }, "anthropic/claude-3-sonnet": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 0.3, "input": 3, "output": 15 }, "description": "Claude Sonnet 3 is an AI model provided by cloudflare-ai-gateway.", "family": "claude-sonnet", "id": "anthropic/claude-3-sonnet", "knowledge": "2023-08-31", "last_updated": "2024-03-04", "limit": { "context": 200000, "output": 4096 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 3", "open_weights": false, "reasoning": false, "release_date": "2024-03-04", "temperature": true, "tool_call": true }, "anthropic/claude-3.5-haiku": { "attachment": true, "cost": { "cache_read": 0.08, "cache_write": 1, "input": 0.8, "output": 4 }, "description": "Claude Haiku 3.5 (latest) is an AI model provided by cloudflare-ai-gateway.", "family": "claude-haiku", "id": "anthropic/claude-3.5-haiku", "knowledge": "2024-07-31", "last_updated": "2024-10-22", "limit": { "context": 200000, "output": 8192 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Haiku 3.5 (latest)", "open_weights": false, "reasoning": false, "release_date": "2024-10-22", "temperature": true, "tool_call": true }, "anthropic/claude-3.5-sonnet": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 3.5 v2 is an AI model provided by cloudflare-ai-gateway.", "family": "claude-sonnet", "id": "anthropic/claude-3.5-sonnet", "knowledge": "2024-04-30", "last_updated": "2024-10-22", "limit": { "context": 200000, "output": 8192 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 3.5 v2", "open_weights": false, "reasoning": false, "release_date": "2024-10-22", "temperature": true, "tool_call": true }, "anthropic/claude-haiku-4-5": { "attachment": true, "cost": { "cache_read": 0.1, "cache_write": 1.25, "input": 1, "output": 5 }, "description": "Claude Haiku 4.5 (latest) is an AI model provided by cloudflare-ai-gateway.", "family": "claude-haiku", "id": "anthropic/claude-haiku-4-5", "knowledge": "2025-02-28", "last_updated": "2025-10-15", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Haiku 4.5 (latest)", "open_weights": false, "reasoning": true, "release_date": "2025-10-15", "temperature": true, "tool_call": true }, "anthropic/claude-opus-4": { "attachment": true, "cost": { "cache_read": 1.5, "cache_write": 18.75, "input": 15, "output": 75 }, "description": "Claude Opus 4 (latest) is an AI model provided by cloudflare-ai-gateway.", "family": "claude-opus", "id": "anthropic/claude-opus-4", "knowledge": "2025-03-31", "last_updated": "2025-05-22", "limit": { "context": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4 (latest)", "open_weights": false, "reasoning": true, "release_date": "2025-05-22", "temperature": true, "tool_call": true }, "anthropic/claude-opus-4-1": { "attachment": true, "cost": { "cache_read": 1.5, "cache_write": 18.75, "input": 15, "output": 75 }, "description": "Claude Opus 4.1 (latest) is an AI model provided by cloudflare-ai-gateway.", "family": "claude-opus", "id": "anthropic/claude-opus-4-1", "knowledge": "2025-03-31", "last_updated": "2025-08-05", "limit": { "context": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.1 (latest)", "open_weights": false, "reasoning": true, "release_date": "2025-08-05", "temperature": true, "tool_call": true }, "anthropic/claude-opus-4-5": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "input": 5, "output": 25 }, "description": "Claude Opus 4.5 (latest) is an AI model provided by cloudflare-ai-gateway.", "family": "claude-opus", "id": "anthropic/claude-opus-4-5", "knowledge": "2025-03-31", "last_updated": "2025-11-24", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.5 (latest)", "open_weights": false, "reasoning": true, "release_date": "2025-11-24", "temperature": true, "tool_call": true }, "anthropic/claude-opus-4-6": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "context_over_200k": { "cache_read": 1, "cache_write": 12.5, "input": 10, "output": 37.5 }, "input": 5, "output": 25, "tiers": [ { "cache_read": 1, "cache_write": 12.5, "input": 10, "output": 37.5, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Claude Opus 4.6 (latest) is an AI model provided by cloudflare-ai-gateway.", "family": "claude-opus", "id": "anthropic/claude-opus-4-6", "knowledge": "2025-05-31", "last_updated": "2026-02-05", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.6 (latest)", "open_weights": false, "reasoning": true, "release_date": "2026-02-05", "temperature": true, "tool_call": true }, "anthropic/claude-opus-4-7": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "input": 5, "output": 25 }, "description": "Claude Opus 4.7 is an AI model provided by cloudflare-ai-gateway.", "family": "claude-opus", "id": "anthropic/claude-opus-4-7", "knowledge": "2026-01", "last_updated": "2026-04-16", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.7", "open_weights": false, "provider": { "npm": "@ai-sdk/anthropic" }, "reasoning": true, "release_date": "2026-04-16", "temperature": false, "tool_call": true }, "anthropic/claude-sonnet-4": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 4 (latest) is an AI model provided by cloudflare-ai-gateway.", "family": "claude-sonnet", "id": "anthropic/claude-sonnet-4", "knowledge": "2025-03-31", "last_updated": "2025-05-22", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4 (latest)", "open_weights": false, "reasoning": true, "release_date": "2025-05-22", "temperature": true, "tool_call": true }, "anthropic/claude-sonnet-4-5": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 4.5 (latest) is an AI model provided by cloudflare-ai-gateway.", "family": "claude-sonnet", "id": "anthropic/claude-sonnet-4-5", "knowledge": "2025-07-31", "last_updated": "2025-09-29", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.5 (latest)", "open_weights": false, "reasoning": true, "release_date": "2025-09-29", "temperature": true, "tool_call": true }, "anthropic/claude-sonnet-4-6": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "context_over_200k": { "cache_read": 0.6, "cache_write": 7.5, "input": 6, "output": 22.5 }, "input": 3, "output": 15, "tiers": [ { "cache_read": 0.6, "cache_write": 7.5, "input": 6, "output": 22.5, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Claude Sonnet 4.6 is an AI model provided by cloudflare-ai-gateway.", "family": "claude-sonnet", "id": "anthropic/claude-sonnet-4-6", "interleaved": true, "knowledge": "2025-08-31", "last_updated": "2026-02-17", "limit": { "context": 1000000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.6", "open_weights": false, "provider": { "npm": "ai-gateway-provider" }, "reasoning": true, "release_date": "2026-02-17", "temperature": true, "tool_call": true }, "openai/gpt-3.5-turbo": { "attachment": false, "cost": { "cache_read": 1.25, "input": 0.5, "output": 1.5 }, "description": "GPT-3.5-turbo is an AI model provided by cloudflare-ai-gateway.", "family": "gpt", "id": "openai/gpt-3.5-turbo", "knowledge": "2021-09-01", "last_updated": "2023-11-06", "limit": { "context": 16385, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT-3.5-turbo", "open_weights": false, "reasoning": false, "release_date": "2023-03-01", "structured_output": false, "temperature": true, "tool_call": false }, "openai/gpt-4": { "attachment": true, "cost": { "input": 30, "output": 60 }, "description": "GPT-4 is an AI model provided by cloudflare-ai-gateway.", "family": "gpt", "id": "openai/gpt-4", "knowledge": "2023-11", "last_updated": "2024-04-09", "limit": { "context": 8192, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT-4", "open_weights": false, "reasoning": false, "release_date": "2023-11-06", "structured_output": false, "temperature": true, "tool_call": true }, "openai/gpt-4-turbo": { "attachment": true, "cost": { "input": 10, "output": 30 }, "description": "GPT-4 Turbo is an AI model provided by cloudflare-ai-gateway.", "family": "gpt", "id": "openai/gpt-4-turbo", "knowledge": "2023-12", "last_updated": "2024-04-09", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4 Turbo", "open_weights": false, "reasoning": false, "release_date": "2023-11-06", "structured_output": false, "temperature": true, "tool_call": true }, "openai/gpt-4o": { "attachment": true, "cost": { "cache_read": 1.25, "input": 2.5, "output": 10 }, "description": "GPT-4o is an AI model provided by cloudflare-ai-gateway.", "family": "gpt", "id": "openai/gpt-4o", "knowledge": "2023-09", "last_updated": "2024-08-06", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4o", "open_weights": false, "reasoning": false, "release_date": "2024-05-13", "structured_output": true, "temperature": true, "tool_call": true }, "openai/gpt-4o-mini": { "attachment": true, "cost": { "cache_read": 0.08, "input": 0.15, "output": 0.6 }, "description": "GPT-4o mini is an AI model provided by cloudflare-ai-gateway.", "family": "gpt-mini", "id": "openai/gpt-4o-mini", "knowledge": "2023-09", "last_updated": "2024-07-18", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4o mini", "open_weights": false, "reasoning": false, "release_date": "2024-07-18", "structured_output": true, "temperature": true, "tool_call": true }, "openai/gpt-5.1": { "attachment": true, "cost": { "cache_read": 0.13, "input": 1.25, "output": 10 }, "description": "GPT-5.1 is an AI model provided by cloudflare-ai-gateway.", "family": "gpt", "id": "openai/gpt-5.1", "knowledge": "2024-09-30", "last_updated": "2025-11-13", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.1", "open_weights": false, "reasoning": true, "release_date": "2025-11-13", "temperature": false, "tool_call": true }, "openai/gpt-5.1-codex": { "attachment": true, "cost": { "cache_read": 0.125, "input": 1.25, "output": 10 }, "description": "GPT-5.1 Codex is an AI model provided by cloudflare-ai-gateway.", "family": "gpt-codex", "id": "openai/gpt-5.1-codex", "knowledge": "2024-09-30", "last_updated": "2025-11-13", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.1 Codex", "open_weights": false, "reasoning": true, "release_date": "2025-11-13", "structured_output": true, "temperature": false, "tool_call": true }, "openai/gpt-5.2": { "attachment": true, "cost": { "cache_read": 0.175, "input": 1.75, "output": 14 }, "description": "GPT-5.2 is an AI model provided by cloudflare-ai-gateway.", "family": "gpt", "id": "openai/gpt-5.2", "knowledge": "2025-08-31", "last_updated": "2025-12-11", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.2", "open_weights": false, "reasoning": true, "release_date": "2025-12-11", "temperature": false, "tool_call": true }, "openai/gpt-5.2-codex": { "attachment": true, "cost": { "cache_read": 0.175, "input": 1.75, "output": 14 }, "description": "GPT-5.2 Codex is an AI model provided by cloudflare-ai-gateway.", "family": "gpt-codex", "id": "openai/gpt-5.2-codex", "knowledge": "2025-08-31", "last_updated": "2025-12-11", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.2 Codex", "open_weights": false, "provider": { "npm": "ai-gateway-provider" }, "reasoning": true, "release_date": "2025-12-11", "structured_output": true, "temperature": false, "tool_call": true }, "openai/gpt-5.3-codex": { "attachment": true, "cost": { "cache_read": 0.175, "input": 1.75, "output": 14 }, "description": "GPT-5.3 Codex is an AI model provided by cloudflare-ai-gateway.", "family": "gpt-codex", "id": "openai/gpt-5.3-codex", "knowledge": "2025-08-31", "last_updated": "2026-02-05", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.3 Codex", "open_weights": false, "provider": { "npm": "ai-gateway-provider" }, "reasoning": true, "release_date": "2026-02-05", "structured_output": true, "temperature": false, "tool_call": true }, "openai/gpt-5.4": { "attachment": true, "cost": { "cache_read": 0.25, "input": 2.5, "output": 15 }, "description": "GPT-5.4 is an AI model provided by cloudflare-ai-gateway.", "family": "gpt", "id": "openai/gpt-5.4", "knowledge": "2025-08-31", "last_updated": "2026-03-05", "limit": { "context": 1050000, "input": 922000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.4", "open_weights": false, "provider": { "npm": "ai-gateway-provider" }, "reasoning": true, "release_date": "2026-03-05", "structured_output": true, "temperature": false, "tool_call": true }, "openai/gpt-5.5": { "attachment": true, "cost": { "cache_read": 0.5, "context_over_200k": { "cache_read": 1, "input": 10, "output": 45 }, "input": 5, "output": 30, "tiers": [ { "cache_read": 1, "input": 10, "output": 45, "tier": { "size": 272000, "type": "context" } } ] }, "description": "GPT-5.5 is an AI model provided by cloudflare-ai-gateway.", "family": "gpt", "id": "openai/gpt-5.5", "knowledge": "2025-12-01", "last_updated": "2026-04-23", "limit": { "context": 1050000, "input": 922000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.5", "open_weights": false, "reasoning": true, "release_date": "2026-04-23", "structured_output": true, "temperature": false, "tool_call": true }, "openai/o1": { "attachment": true, "cost": { "cache_read": 7.5, "input": 15, "output": 60 }, "description": "o1 is an AI model provided by cloudflare-ai-gateway.", "family": "o", "id": "openai/o1", "knowledge": "2023-09", "last_updated": "2024-12-05", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "o1", "open_weights": false, "reasoning": true, "release_date": "2024-12-05", "structured_output": true, "temperature": false, "tool_call": true }, "openai/o3": { "attachment": true, "cost": { "cache_read": 0.5, "input": 2, "output": 8 }, "description": "o3 is an AI model provided by cloudflare-ai-gateway.", "family": "o", "id": "openai/o3", "knowledge": "2024-05", "last_updated": "2025-04-16", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "o3", "open_weights": false, "reasoning": true, "release_date": "2025-04-16", "structured_output": true, "temperature": false, "tool_call": true }, "openai/o3-mini": { "attachment": false, "cost": { "cache_read": 0.55, "input": 1.1, "output": 4.4 }, "description": "o3-mini is an AI model provided by cloudflare-ai-gateway.", "family": "o-mini", "id": "openai/o3-mini", "knowledge": "2024-05", "last_updated": "2025-01-29", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "o3-mini", "open_weights": false, "reasoning": true, "release_date": "2024-12-20", "structured_output": true, "temperature": false, "tool_call": true }, "openai/o3-pro": { "attachment": true, "cost": { "input": 20, "output": 80 }, "description": "o3-pro is an AI model provided by cloudflare-ai-gateway.", "family": "o-pro", "id": "openai/o3-pro", "knowledge": "2024-05", "last_updated": "2025-06-10", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "o3-pro", "open_weights": false, "reasoning": true, "release_date": "2025-06-10", "structured_output": true, "temperature": false, "tool_call": true }, "openai/o4-mini": { "attachment": true, "cost": { "cache_read": 0.28, "input": 1.1, "output": 4.4 }, "description": "o4-mini is an AI model provided by cloudflare-ai-gateway.", "family": "o-mini", "id": "openai/o4-mini", "knowledge": "2024-05", "last_updated": "2025-04-16", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "o4-mini", "open_weights": false, "reasoning": true, "release_date": "2025-04-16", "structured_output": true, "temperature": false, "tool_call": true }, "workers-ai/@cf/ai4bharat/indictrans2-en-indic-1B": { "attachment": false, "cost": { "input": 0.34, "output": 0.34 }, "description": "IndicTrans2 EN-Indic 1B is an AI model provided by cloudflare-ai-gateway.", "family": "indictrans", "id": "workers-ai/@cf/ai4bharat/indictrans2-en-indic-1B", "last_updated": "2025-09-25", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "IndicTrans2 EN-Indic 1B", "open_weights": false, "reasoning": false, "release_date": "2025-09-25", "temperature": true, "tool_call": false }, "workers-ai/@cf/aisingapore/gemma-sea-lion-v4-27b-it": { "attachment": false, "cost": { "input": 0.35, "output": 0.56 }, "description": "Gemma SEA-LION v4 27B IT is an AI model provided by cloudflare-ai-gateway.", "family": "gemma", "id": "workers-ai/@cf/aisingapore/gemma-sea-lion-v4-27b-it", "last_updated": "2025-09-25", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Gemma SEA-LION v4 27B IT", "open_weights": false, "reasoning": false, "release_date": "2025-09-25", "temperature": true, "tool_call": false }, "workers-ai/@cf/baai/bge-base-en-v1.5": { "attachment": false, "cost": { "input": 0.067, "output": 0 }, "description": "BGE Base EN v1.5 is an AI model provided by cloudflare-ai-gateway.", "family": "bge", "id": "workers-ai/@cf/baai/bge-base-en-v1.5", "last_updated": "2025-04-03", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "BGE Base EN v1.5", "open_weights": false, "reasoning": false, "release_date": "2025-04-03", "temperature": true, "tool_call": false }, "workers-ai/@cf/baai/bge-large-en-v1.5": { "attachment": false, "cost": { "input": 0.2, "output": 0 }, "description": "BGE Large EN v1.5 is an AI model provided by cloudflare-ai-gateway.", "family": "bge", "id": "workers-ai/@cf/baai/bge-large-en-v1.5", "last_updated": "2025-04-03", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "BGE Large EN v1.5", "open_weights": false, "reasoning": false, "release_date": "2025-04-03", "temperature": true, "tool_call": false }, "workers-ai/@cf/baai/bge-m3": { "attachment": false, "cost": { "input": 0.012, "output": 0 }, "description": "BGE M3 is an AI model provided by cloudflare-ai-gateway.", "family": "bge", "id": "workers-ai/@cf/baai/bge-m3", "last_updated": "2025-04-03", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "BGE M3", "open_weights": false, "reasoning": false, "release_date": "2025-04-03", "temperature": true, "tool_call": false }, "workers-ai/@cf/baai/bge-reranker-base": { "attachment": false, "cost": { "input": 0.0031, "output": 0 }, "description": "BGE Reranker Base is an AI model provided by cloudflare-ai-gateway.", "family": "bge", "id": "workers-ai/@cf/baai/bge-reranker-base", "last_updated": "2025-04-09", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "BGE Reranker Base", "open_weights": false, "reasoning": false, "release_date": "2025-04-09", "temperature": true, "tool_call": false }, "workers-ai/@cf/baai/bge-small-en-v1.5": { "attachment": false, "cost": { "input": 0.02, "output": 0 }, "description": "BGE Small EN v1.5 is an AI model provided by cloudflare-ai-gateway.", "family": "bge", "id": "workers-ai/@cf/baai/bge-small-en-v1.5", "last_updated": "2025-04-03", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "BGE Small EN v1.5", "open_weights": false, "reasoning": false, "release_date": "2025-04-03", "temperature": true, "tool_call": false }, "workers-ai/@cf/deepgram/aura-2-en": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Deepgram Aura 2 (EN) is an AI model provided by cloudflare-ai-gateway.", "family": "aura", "id": "workers-ai/@cf/deepgram/aura-2-en", "last_updated": "2025-11-14", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Deepgram Aura 2 (EN)", "open_weights": false, "reasoning": false, "release_date": "2025-11-14", "temperature": true, "tool_call": false }, "workers-ai/@cf/deepgram/aura-2-es": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Deepgram Aura 2 (ES) is an AI model provided by cloudflare-ai-gateway.", "family": "aura", "id": "workers-ai/@cf/deepgram/aura-2-es", "last_updated": "2025-11-14", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Deepgram Aura 2 (ES)", "open_weights": false, "reasoning": false, "release_date": "2025-11-14", "temperature": true, "tool_call": false }, "workers-ai/@cf/deepgram/nova-3": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Deepgram Nova 3 is an AI model provided by cloudflare-ai-gateway.", "family": "nova", "id": "workers-ai/@cf/deepgram/nova-3", "last_updated": "2025-11-14", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Deepgram Nova 3", "open_weights": false, "reasoning": false, "release_date": "2025-11-14", "temperature": true, "tool_call": false }, "workers-ai/@cf/deepseek-ai/deepseek-r1-distill-qwen-32b": { "attachment": false, "cost": { "input": 0.5, "output": 4.88 }, "description": "DeepSeek R1 Distill Qwen 32B is an AI model provided by cloudflare-ai-gateway.", "family": "deepseek-thinking", "id": "workers-ai/@cf/deepseek-ai/deepseek-r1-distill-qwen-32b", "last_updated": "2025-04-03", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek R1 Distill Qwen 32B", "open_weights": false, "reasoning": false, "release_date": "2025-04-03", "temperature": true, "tool_call": false }, "workers-ai/@cf/facebook/bart-large-cnn": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "BART Large CNN is an AI model provided by cloudflare-ai-gateway.", "family": "bart", "id": "workers-ai/@cf/facebook/bart-large-cnn", "last_updated": "2025-04-09", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "BART Large CNN", "open_weights": false, "reasoning": false, "release_date": "2025-04-09", "temperature": true, "tool_call": false }, "workers-ai/@cf/google/gemma-3-12b-it": { "attachment": false, "cost": { "input": 0.35, "output": 0.56 }, "description": "Gemma 3 12B IT is an AI model provided by cloudflare-ai-gateway.", "family": "gemma", "id": "workers-ai/@cf/google/gemma-3-12b-it", "last_updated": "2025-04-11", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Gemma 3 12B IT", "open_weights": false, "reasoning": false, "release_date": "2025-04-11", "temperature": true, "tool_call": false }, "workers-ai/@cf/huggingface/distilbert-sst-2-int8": { "attachment": false, "cost": { "input": 0.026, "output": 0 }, "description": "DistilBERT SST-2 INT8 is an AI model provided by cloudflare-ai-gateway.", "family": "distilbert", "id": "workers-ai/@cf/huggingface/distilbert-sst-2-int8", "last_updated": "2025-04-03", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DistilBERT SST-2 INT8", "open_weights": false, "reasoning": false, "release_date": "2025-04-03", "temperature": true, "tool_call": false }, "workers-ai/@cf/ibm-granite/granite-4.0-h-micro": { "attachment": false, "cost": { "input": 0.017, "output": 0.11 }, "description": "IBM Granite 4.0 H Micro is an AI model provided by cloudflare-ai-gateway.", "family": "granite", "id": "workers-ai/@cf/ibm-granite/granite-4.0-h-micro", "last_updated": "2025-10-15", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "IBM Granite 4.0 H Micro", "open_weights": false, "reasoning": false, "release_date": "2025-10-15", "temperature": true, "tool_call": false }, "workers-ai/@cf/meta/llama-2-7b-chat-fp16": { "attachment": false, "cost": { "input": 0.56, "output": 6.67 }, "description": "Llama 2 7B Chat FP16 is an AI model provided by cloudflare-ai-gateway.", "family": "llama", "id": "workers-ai/@cf/meta/llama-2-7b-chat-fp16", "last_updated": "2025-04-03", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 2 7B Chat FP16", "open_weights": false, "reasoning": false, "release_date": "2025-04-03", "temperature": true, "tool_call": false }, "workers-ai/@cf/meta/llama-3-8b-instruct": { "attachment": false, "cost": { "input": 0.28, "output": 0.83 }, "description": "Llama 3 8B Instruct is an AI model provided by cloudflare-ai-gateway.", "family": "llama", "id": "workers-ai/@cf/meta/llama-3-8b-instruct", "last_updated": "2025-04-03", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3 8B Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-04-03", "temperature": true, "tool_call": false }, "workers-ai/@cf/meta/llama-3-8b-instruct-awq": { "attachment": false, "cost": { "input": 0.12, "output": 0.27 }, "description": "Llama 3 8B Instruct AWQ is an AI model provided by cloudflare-ai-gateway.", "family": "llama", "id": "workers-ai/@cf/meta/llama-3-8b-instruct-awq", "last_updated": "2025-04-03", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3 8B Instruct AWQ", "open_weights": false, "reasoning": false, "release_date": "2025-04-03", "temperature": true, "tool_call": false }, "workers-ai/@cf/meta/llama-3.1-8b-instruct": { "attachment": false, "cost": { "input": 0.28, "output": 0.8299999999999998 }, "description": "Llama 3.1 8B Instruct is an AI model provided by cloudflare-ai-gateway.", "family": "llama", "id": "workers-ai/@cf/meta/llama-3.1-8b-instruct", "last_updated": "2025-04-03", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.1 8B Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-04-03", "temperature": true, "tool_call": false }, "workers-ai/@cf/meta/llama-3.1-8b-instruct-awq": { "attachment": false, "cost": { "input": 0.12, "output": 0.27 }, "description": "Llama 3.1 8B Instruct AWQ is an AI model provided by cloudflare-ai-gateway.", "family": "llama", "id": "workers-ai/@cf/meta/llama-3.1-8b-instruct-awq", "last_updated": "2025-04-03", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.1 8B Instruct AWQ", "open_weights": false, "reasoning": false, "release_date": "2025-04-03", "temperature": true, "tool_call": false }, "workers-ai/@cf/meta/llama-3.1-8b-instruct-fp8": { "attachment": false, "cost": { "input": 0.15, "output": 0.29 }, "description": "Llama 3.1 8B Instruct FP8 is an AI model provided by cloudflare-ai-gateway.", "family": "llama", "id": "workers-ai/@cf/meta/llama-3.1-8b-instruct-fp8", "last_updated": "2025-04-03", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.1 8B Instruct FP8", "open_weights": false, "reasoning": false, "release_date": "2025-04-03", "temperature": true, "tool_call": false }, "workers-ai/@cf/meta/llama-3.2-11b-vision-instruct": { "attachment": false, "cost": { "input": 0.049, "output": 0.68 }, "description": "Llama 3.2 11B Vision Instruct is an AI model provided by cloudflare-ai-gateway.", "family": "llama", "id": "workers-ai/@cf/meta/llama-3.2-11b-vision-instruct", "last_updated": "2025-04-03", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.2 11B Vision Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-04-03", "temperature": true, "tool_call": false }, "workers-ai/@cf/meta/llama-3.2-1b-instruct": { "attachment": false, "cost": { "input": 0.027, "output": 0.2 }, "description": "Llama 3.2 1B Instruct is an AI model provided by cloudflare-ai-gateway.", "family": "llama", "id": "workers-ai/@cf/meta/llama-3.2-1b-instruct", "last_updated": "2025-04-03", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.2 1B Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-04-03", "temperature": true, "tool_call": false }, "workers-ai/@cf/meta/llama-3.2-3b-instruct": { "attachment": false, "cost": { "input": 0.051, "output": 0.34 }, "description": "Llama 3.2 3B Instruct is an AI model provided by cloudflare-ai-gateway.", "family": "llama", "id": "workers-ai/@cf/meta/llama-3.2-3b-instruct", "last_updated": "2025-04-03", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.2 3B Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-04-03", "temperature": true, "tool_call": false }, "workers-ai/@cf/meta/llama-3.3-70b-instruct-fp8-fast": { "attachment": false, "cost": { "input": 0.29, "output": 2.25 }, "description": "Llama 3.3 70B Instruct FP8 Fast is an AI model provided by cloudflare-ai-gateway.", "family": "llama", "id": "workers-ai/@cf/meta/llama-3.3-70b-instruct-fp8-fast", "last_updated": "2025-04-03", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B Instruct FP8 Fast", "open_weights": false, "reasoning": false, "release_date": "2025-04-03", "temperature": true, "tool_call": false }, "workers-ai/@cf/meta/llama-4-scout-17b-16e-instruct": { "attachment": false, "cost": { "input": 0.27, "output": 0.85 }, "description": "Llama 4 Scout 17B 16E Instruct is an AI model provided by cloudflare-ai-gateway.", "family": "llama", "id": "workers-ai/@cf/meta/llama-4-scout-17b-16e-instruct", "last_updated": "2025-04-16", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 4 Scout 17B 16E Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-04-16", "temperature": true, "tool_call": false }, "workers-ai/@cf/meta/llama-guard-3-8b": { "attachment": false, "cost": { "input": 0.48, "output": 0.03 }, "description": "Llama Guard 3 8B is an AI model provided by cloudflare-ai-gateway.", "family": "llama", "id": "workers-ai/@cf/meta/llama-guard-3-8b", "last_updated": "2025-04-03", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama Guard 3 8B", "open_weights": false, "reasoning": false, "release_date": "2025-04-03", "temperature": true, "tool_call": false }, "workers-ai/@cf/meta/m2m100-1.2b": { "attachment": false, "cost": { "input": 0.34, "output": 0.34 }, "description": "M2M100 1.2B is an AI model provided by cloudflare-ai-gateway.", "family": "m2m", "id": "workers-ai/@cf/meta/m2m100-1.2b", "last_updated": "2025-04-03", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "M2M100 1.2B", "open_weights": false, "reasoning": false, "release_date": "2025-04-03", "temperature": true, "tool_call": false }, "workers-ai/@cf/mistral/mistral-7b-instruct-v0.1": { "attachment": false, "cost": { "input": 0.11, "output": 0.19 }, "description": "Mistral 7B Instruct v0.1 is an AI model provided by cloudflare-ai-gateway.", "family": "mistral", "id": "workers-ai/@cf/mistral/mistral-7b-instruct-v0.1", "last_updated": "2025-04-03", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral 7B Instruct v0.1", "open_weights": false, "reasoning": false, "release_date": "2025-04-03", "temperature": true, "tool_call": false }, "workers-ai/@cf/mistralai/mistral-small-3.1-24b-instruct": { "attachment": false, "cost": { "input": 0.35, "output": 0.56 }, "description": "Mistral Small 3.1 24B Instruct is an AI model provided by cloudflare-ai-gateway.", "family": "mistral-small", "id": "workers-ai/@cf/mistralai/mistral-small-3.1-24b-instruct", "last_updated": "2025-04-11", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral Small 3.1 24B Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-04-11", "temperature": true, "tool_call": false }, "workers-ai/@cf/moonshotai/kimi-k2.5": { "attachment": true, "cost": { "cache_read": 0.1, "input": 0.6, "output": 3 }, "description": "Kimi K2.5 is an AI model provided by cloudflare-ai-gateway.", "family": "kimi", "id": "workers-ai/@cf/moonshotai/kimi-k2.5", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-01", "last_updated": "2026-01-27", "limit": { "context": 256000, "output": 256000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Kimi K2.5", "open_weights": true, "reasoning": true, "release_date": "2026-01-27", "structured_output": true, "temperature": true, "tool_call": true }, "workers-ai/@cf/moonshotai/kimi-k2.6": { "attachment": true, "cost": { "cache_read": 0.16, "input": 0.95, "output": 4 }, "description": "Kimi K2.6 is an AI model provided by cloudflare-ai-gateway.", "family": "kimi", "id": "workers-ai/@cf/moonshotai/kimi-k2.6", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-01", "last_updated": "2026-04-20", "limit": { "context": 256000, "output": 256000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Kimi K2.6", "open_weights": true, "reasoning": true, "release_date": "2026-04-20", "structured_output": true, "temperature": true, "tool_call": true }, "workers-ai/@cf/myshell-ai/melotts": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "MyShell MeloTTS is an AI model provided by cloudflare-ai-gateway.", "family": "melotts", "id": "workers-ai/@cf/myshell-ai/melotts", "last_updated": "2025-11-14", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MyShell MeloTTS", "open_weights": false, "reasoning": false, "release_date": "2025-11-14", "temperature": true, "tool_call": false }, "workers-ai/@cf/nvidia/nemotron-3-120b-a12b": { "attachment": false, "cost": { "input": 0.5, "output": 1.5 }, "description": "Nemotron 3 Super 120B is an AI model provided by cloudflare-ai-gateway.", "family": "nemotron", "id": "workers-ai/@cf/nvidia/nemotron-3-120b-a12b", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-03-11", "limit": { "context": 256000, "output": 256000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Nemotron 3 Super 120B", "open_weights": true, "reasoning": true, "release_date": "2026-03-11", "temperature": true, "tool_call": true }, "workers-ai/@cf/openai/gpt-oss-120b": { "attachment": false, "cost": { "input": 0.35, "output": 0.75 }, "description": "GPT OSS 120B is an AI model provided by cloudflare-ai-gateway.", "id": "workers-ai/@cf/openai/gpt-oss-120b", "last_updated": "2025-08-05", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT OSS 120B", "open_weights": false, "reasoning": false, "release_date": "2025-08-05", "temperature": true, "tool_call": false }, "workers-ai/@cf/openai/gpt-oss-20b": { "attachment": false, "cost": { "input": 0.2, "output": 0.3 }, "description": "GPT OSS 20B is an AI model provided by cloudflare-ai-gateway.", "id": "workers-ai/@cf/openai/gpt-oss-20b", "last_updated": "2025-08-05", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT OSS 20B", "open_weights": false, "reasoning": false, "release_date": "2025-08-05", "temperature": true, "tool_call": false }, "workers-ai/@cf/pfnet/plamo-embedding-1b": { "attachment": false, "cost": { "input": 0.019, "output": 0 }, "description": "PLaMo Embedding 1B is an AI model provided by cloudflare-ai-gateway.", "family": "plamo", "id": "workers-ai/@cf/pfnet/plamo-embedding-1b", "last_updated": "2025-09-25", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "PLaMo Embedding 1B", "open_weights": false, "reasoning": false, "release_date": "2025-09-25", "temperature": true, "tool_call": false }, "workers-ai/@cf/pipecat-ai/smart-turn-v2": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Pipecat Smart Turn v2 is an AI model provided by cloudflare-ai-gateway.", "family": "smart-turn", "id": "workers-ai/@cf/pipecat-ai/smart-turn-v2", "last_updated": "2025-11-14", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Pipecat Smart Turn v2", "open_weights": false, "reasoning": false, "release_date": "2025-11-14", "temperature": true, "tool_call": false }, "workers-ai/@cf/qwen/qwen2.5-coder-32b-instruct": { "attachment": false, "cost": { "input": 0.66, "output": 1 }, "description": "Qwen 2.5 Coder 32B Instruct is an AI model provided by cloudflare-ai-gateway.", "family": "qwen", "id": "workers-ai/@cf/qwen/qwen2.5-coder-32b-instruct", "last_updated": "2025-04-11", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen 2.5 Coder 32B Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-04-11", "temperature": true, "tool_call": false }, "workers-ai/@cf/qwen/qwen3-30b-a3b-fp8": { "attachment": false, "cost": { "input": 0.051, "output": 0.34 }, "description": "Qwen3 30B A3B FP8 is an AI model provided by cloudflare-ai-gateway.", "family": "qwen", "id": "workers-ai/@cf/qwen/qwen3-30b-a3b-fp8", "last_updated": "2025-11-14", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 30B A3B FP8", "open_weights": false, "reasoning": false, "release_date": "2025-11-14", "temperature": true, "tool_call": false }, "workers-ai/@cf/qwen/qwen3-embedding-0.6b": { "attachment": false, "cost": { "input": 0.012, "output": 0 }, "description": "Qwen3 Embedding 0.6B is an AI model provided by cloudflare-ai-gateway.", "family": "qwen", "id": "workers-ai/@cf/qwen/qwen3-embedding-0.6b", "last_updated": "2025-11-14", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Embedding 0.6B", "open_weights": false, "reasoning": false, "release_date": "2025-11-14", "temperature": true, "tool_call": false }, "workers-ai/@cf/qwen/qwq-32b": { "attachment": false, "cost": { "input": 0.66, "output": 1 }, "description": "QwQ 32B is an AI model provided by cloudflare-ai-gateway.", "family": "qwen", "id": "workers-ai/@cf/qwen/qwq-32b", "last_updated": "2025-04-11", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "QwQ 32B", "open_weights": false, "reasoning": false, "release_date": "2025-04-11", "temperature": true, "tool_call": false }, "workers-ai/@cf/zai-org/glm-4.7-flash": { "attachment": false, "cost": { "input": 0.06, "output": 0.4 }, "description": "GLM-4.7-Flash is an AI model provided by cloudflare-ai-gateway.", "family": "glm-flash", "id": "workers-ai/@cf/zai-org/glm-4.7-flash", "knowledge": "2025-04", "last_updated": "2026-01-19", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.7-Flash", "open_weights": true, "reasoning": true, "release_date": "2026-01-19", "temperature": true, "tool_call": true } }, "name": "Cloudflare AI Gateway", "npm": "ai-gateway-provider" }, "cloudflare-workers-ai": { "api": "https://api.cloudflare.com/client/v4/accounts/${CLOUDFLARE_ACCOUNT_ID}/ai/v1", "doc": "https://developers.cloudflare.com/workers-ai/models/", "env": [ "CLOUDFLARE_ACCOUNT_ID", "CLOUDFLARE_API_KEY" ], "iconURL": "https://models.dev/logos/cloudflare-workers-ai.svg", "id": "cloudflare-workers-ai", "lobeIcon": "Cloudflare.Color", "models": { "@cf/google/gemma-4-26b-a4b-it": { "attachment": true, "cost": { "input": 0.1, "output": 0.3 }, "description": "Gemma 4 26B A4B IT is an AI model provided by cloudflare-workers-ai.", "family": "gemma", "id": "@cf/google/gemma-4-26b-a4b-it", "last_updated": "2025-12-15", "limit": { "context": 256000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemma 4 26B A4B IT", "open_weights": true, "reasoning": true, "release_date": "2025-12-15", "temperature": true, "tool_call": true }, "@cf/meta/llama-4-scout-17b-16e-instruct": { "attachment": true, "cost": { "input": 0.27, "output": 0.85 }, "description": "Llama 4 Scout 17B 16E Instruct is an AI model provided by cloudflare-workers-ai.", "family": "llama", "id": "@cf/meta/llama-4-scout-17b-16e-instruct", "last_updated": "2025-04-16", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Llama 4 Scout 17B 16E Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-04-16", "temperature": true, "tool_call": true }, "@cf/moonshotai/kimi-k2.5": { "attachment": true, "cost": { "cache_read": 0.1, "input": 0.6, "output": 3 }, "description": "Kimi K2.5 is an AI model provided by cloudflare-workers-ai.", "family": "kimi", "id": "@cf/moonshotai/kimi-k2.5", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-01", "last_updated": "2026-01-27", "limit": { "context": 256000, "output": 256000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Kimi K2.5", "open_weights": true, "reasoning": true, "release_date": "2026-01-27", "structured_output": true, "temperature": true, "tool_call": true }, "@cf/moonshotai/kimi-k2.6": { "attachment": true, "cost": { "cache_read": 0.16, "input": 0.95, "output": 4 }, "description": "Kimi K2.6 is an AI model provided by cloudflare-workers-ai.", "family": "kimi", "id": "@cf/moonshotai/kimi-k2.6", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-01", "last_updated": "2026-04-20", "limit": { "context": 256000, "output": 256000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Kimi K2.6", "open_weights": true, "reasoning": true, "release_date": "2026-04-20", "structured_output": true, "temperature": true, "tool_call": true }, "@cf/nvidia/nemotron-3-120b-a12b": { "attachment": false, "cost": { "input": 0.5, "output": 1.5 }, "description": "Nemotron 3 Super 120B is an AI model provided by cloudflare-workers-ai.", "family": "nemotron", "id": "@cf/nvidia/nemotron-3-120b-a12b", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-03-11", "limit": { "context": 256000, "output": 256000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Nemotron 3 Super 120B", "open_weights": true, "reasoning": true, "release_date": "2026-03-11", "temperature": true, "tool_call": true }, "@cf/openai/gpt-oss-120b": { "attachment": false, "cost": { "input": 0.35, "output": 0.75 }, "description": "GPT OSS 120B is an AI model provided by cloudflare-workers-ai.", "id": "@cf/openai/gpt-oss-120b", "last_updated": "2025-08-05", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT OSS 120B", "open_weights": true, "reasoning": true, "release_date": "2025-08-05", "temperature": true, "tool_call": true }, "@cf/openai/gpt-oss-20b": { "attachment": false, "cost": { "input": 0.2, "output": 0.3 }, "description": "GPT OSS 20B is an AI model provided by cloudflare-workers-ai.", "id": "@cf/openai/gpt-oss-20b", "last_updated": "2025-08-05", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT OSS 20B", "open_weights": true, "reasoning": true, "release_date": "2025-08-05", "temperature": true, "tool_call": true }, "@cf/zai-org/glm-4.7-flash": { "attachment": false, "cost": { "input": 0.06, "output": 0.4 }, "description": "GLM-4.7-Flash is an AI model provided by cloudflare-workers-ai.", "family": "glm-flash", "id": "@cf/zai-org/glm-4.7-flash", "knowledge": "2025-04", "last_updated": "2026-01-19", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.7-Flash", "open_weights": true, "reasoning": true, "release_date": "2026-01-19", "temperature": true, "tool_call": true } }, "name": "Cloudflare Workers AI", "npm": "@ai-sdk/openai-compatible" }, "cohere": { "doc": "https://docs.cohere.com/docs/models", "env": [ "COHERE_API_KEY" ], "iconURL": "https://models.dev/logos/cohere.svg", "id": "cohere", "models": { "c4ai-aya-expanse-32b": { "attachment": false, "description": "Aya Expanse 32B is an AI model provided by cohere.", "id": "c4ai-aya-expanse-32b", "last_updated": "2024-10-24", "limit": { "context": 128000, "output": 4000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Aya Expanse 32B", "open_weights": true, "reasoning": false, "release_date": "2024-10-24", "temperature": true, "tool_call": false }, "c4ai-aya-expanse-8b": { "attachment": false, "description": "Aya Expanse 8B is an AI model provided by cohere.", "id": "c4ai-aya-expanse-8b", "last_updated": "2024-10-24", "limit": { "context": 8000, "output": 4000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Aya Expanse 8B", "open_weights": true, "reasoning": false, "release_date": "2024-10-24", "temperature": true, "tool_call": false }, "c4ai-aya-vision-32b": { "attachment": true, "description": "Aya Vision 32B is an AI model provided by cohere.", "id": "c4ai-aya-vision-32b", "last_updated": "2025-05-14", "limit": { "context": 16000, "output": 4000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Aya Vision 32B", "open_weights": true, "reasoning": false, "release_date": "2025-03-04", "temperature": true, "tool_call": false }, "c4ai-aya-vision-8b": { "attachment": true, "description": "Aya Vision 8B is an AI model provided by cohere.", "id": "c4ai-aya-vision-8b", "last_updated": "2025-05-14", "limit": { "context": 16000, "output": 4000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Aya Vision 8B", "open_weights": true, "reasoning": false, "release_date": "2025-03-04", "temperature": true, "tool_call": false }, "command-a-03-2025": { "attachment": false, "cost": { "input": 2.5, "output": 10 }, "description": "Command A is an AI model provided by cohere.", "family": "command-a", "id": "command-a-03-2025", "knowledge": "2024-06-01", "last_updated": "2025-03-13", "limit": { "context": 256000, "output": 8000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Command A", "open_weights": true, "reasoning": false, "release_date": "2025-03-13", "temperature": true, "tool_call": true }, "command-a-reasoning-08-2025": { "attachment": false, "cost": { "input": 2.5, "output": 10 }, "description": "Command A Reasoning is an AI model provided by cohere.", "family": "command-a", "id": "command-a-reasoning-08-2025", "knowledge": "2024-06-01", "last_updated": "2025-08-21", "limit": { "context": 256000, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Command A Reasoning", "open_weights": true, "reasoning": true, "release_date": "2025-08-21", "temperature": true, "tool_call": true }, "command-a-translate-08-2025": { "attachment": false, "cost": { "input": 2.5, "output": 10 }, "description": "Command A Translate is an AI model provided by cohere.", "family": "command-a", "id": "command-a-translate-08-2025", "knowledge": "2024-06-01", "last_updated": "2025-08-28", "limit": { "context": 8000, "output": 8000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Command A Translate", "open_weights": true, "reasoning": false, "release_date": "2025-08-28", "temperature": true, "tool_call": true }, "command-a-vision-07-2025": { "attachment": false, "cost": { "input": 2.5, "output": 10 }, "description": "Command A Vision is an AI model provided by cohere.", "family": "command-a", "id": "command-a-vision-07-2025", "knowledge": "2024-06-01", "last_updated": "2025-07-31", "limit": { "context": 128000, "output": 8000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Command A Vision", "open_weights": true, "reasoning": false, "release_date": "2025-07-31", "temperature": true, "tool_call": false }, "command-r-08-2024": { "attachment": false, "cost": { "input": 0.15, "output": 0.6 }, "description": "Command R is an AI model provided by cohere.", "family": "command-r", "id": "command-r-08-2024", "knowledge": "2024-06-01", "last_updated": "2024-08-30", "limit": { "context": 128000, "output": 4000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Command R", "open_weights": true, "reasoning": false, "release_date": "2024-08-30", "temperature": true, "tool_call": true }, "command-r-plus-08-2024": { "attachment": false, "cost": { "input": 2.5, "output": 10 }, "description": "Command R+ is an AI model provided by cohere.", "family": "command-r", "id": "command-r-plus-08-2024", "knowledge": "2024-06-01", "last_updated": "2024-08-30", "limit": { "context": 128000, "output": 4000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Command R+", "open_weights": true, "reasoning": false, "release_date": "2024-08-30", "temperature": true, "tool_call": true }, "command-r7b-12-2024": { "attachment": false, "cost": { "input": 0.0375, "output": 0.15 }, "description": "Command R7B is an AI model provided by cohere.", "family": "command-r", "id": "command-r7b-12-2024", "knowledge": "2024-06-01", "last_updated": "2024-02-27", "limit": { "context": 128000, "output": 4000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Command R7B", "open_weights": true, "reasoning": false, "release_date": "2024-02-27", "temperature": true, "tool_call": true }, "command-r7b-arabic-02-2025": { "attachment": false, "cost": { "input": 0.0375, "output": 0.15 }, "description": "Command R7B Arabic is an AI model provided by cohere.", "family": "command-r", "id": "command-r7b-arabic-02-2025", "knowledge": "2024-06-01", "last_updated": "2025-02-27", "limit": { "context": 128000, "output": 4000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Command R7B Arabic", "open_weights": true, "reasoning": false, "release_date": "2025-02-27", "temperature": true, "tool_call": true } }, "name": "Cohere", "npm": "@ai-sdk/cohere" }, "cortecs": { "api": "https://api.cortecs.ai/v1", "doc": "https://api.cortecs.ai/v1/models", "env": [ "CORTECS_API_KEY" ], "iconURL": "https://models.dev/logos/cortecs.svg", "id": "cortecs", "models": { "claude-4-5-sonnet": { "attachment": true, "cost": { "input": 3.259, "output": 16.296 }, "description": "Claude 4.5 Sonnet is an AI model provided by cortecs.", "family": "claude-sonnet", "id": "claude-4-5-sonnet", "knowledge": "2025-07-31", "last_updated": "2025-09-29", "limit": { "context": 200000, "output": 200000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude 4.5 Sonnet", "open_weights": false, "reasoning": true, "release_date": "2025-09-29", "temperature": true, "tool_call": true }, "claude-4-6-sonnet": { "attachment": true, "cost": { "input": 3.59, "output": 17.92 }, "description": "Claude Sonnet 4.6 is an AI model provided by cortecs.", "family": "claude-sonnet", "id": "claude-4-6-sonnet", "knowledge": "2025-08-31", "last_updated": "2026-03-13", "limit": { "context": 1000000, "output": 1000000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.6", "open_weights": false, "reasoning": true, "release_date": "2026-02-17", "temperature": true, "tool_call": true }, "claude-haiku-4-5": { "attachment": true, "cost": { "input": 1.09, "output": 5.43 }, "description": "Claude Haiku 4.5 is an AI model provided by cortecs.", "family": "claude-haiku", "id": "claude-haiku-4-5", "knowledge": "2025-02-28", "last_updated": "2025-10-15", "limit": { "context": 200000, "output": 200000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Haiku 4.5", "open_weights": false, "reasoning": true, "release_date": "2025-10-15", "temperature": true, "tool_call": true }, "claude-opus4-5": { "attachment": true, "cost": { "input": 5.98, "output": 29.89 }, "description": "Claude Opus 4.5 is an AI model provided by cortecs.", "family": "claude-opus", "id": "claude-opus4-5", "knowledge": "2025-03-31", "last_updated": "2025-11-24", "limit": { "context": 200000, "output": 200000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.5", "open_weights": false, "reasoning": true, "release_date": "2025-11-24", "temperature": true, "tool_call": true }, "claude-opus4-6": { "attachment": true, "cost": { "input": 5.98, "output": 29.89 }, "description": "Claude Opus 4.6 is an AI model provided by cortecs.", "family": "claude-opus", "id": "claude-opus4-6", "knowledge": "2025-05-31", "last_updated": "2026-03-13", "limit": { "context": 1000000, "output": 1000000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.6", "open_weights": false, "reasoning": true, "release_date": "2026-02-05", "temperature": true, "tool_call": true }, "claude-opus4-7": { "attachment": true, "cost": { "cache_read": 0.56, "cache_write": 6.99, "input": 5.6, "output": 27.99 }, "description": "Claude Opus 4.7 is an AI model provided by cortecs.", "family": "claude-opus", "id": "claude-opus4-7", "knowledge": "2026-01-31", "last_updated": "2026-04-16", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.7", "open_weights": false, "reasoning": true, "release_date": "2026-04-16", "temperature": false, "tool_call": true }, "claude-sonnet-4": { "attachment": false, "cost": { "input": 3.307, "output": 16.536 }, "description": "Claude Sonnet 4 is an AI model provided by cortecs.", "family": "claude-sonnet", "id": "claude-sonnet-4", "knowledge": "2025-03", "last_updated": "2025-05-22", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4", "open_weights": false, "reasoning": false, "release_date": "2025-05-22", "temperature": true, "tool_call": true }, "codestral-2508": { "attachment": false, "cost": { "cache_read": 0.03, "input": 0.3, "output": 0.9 }, "description": "Codestral 2508 is an AI model provided by cortecs.", "family": "mistral", "id": "codestral-2508", "knowledge": "2025-03", "last_updated": "2025-07-30", "limit": { "context": 256000, "output": 256000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Codestral 2508", "open_weights": true, "reasoning": false, "release_date": "2025-07-30", "temperature": true, "tool_call": true }, "deepseek-r1-0528": { "attachment": false, "cost": { "input": 0.585, "output": 2.307 }, "description": "DeepSeek R1 0528 is an AI model provided by cortecs.", "family": "deepseek-thinking", "id": "deepseek-r1-0528", "knowledge": "2024-07", "last_updated": "2025-05-28", "limit": { "context": 164000, "output": 164000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek R1 0528", "open_weights": true, "reasoning": true, "release_date": "2025-05-28", "temperature": true, "tool_call": true }, "deepseek-v3-0324": { "attachment": false, "cost": { "input": 0.551, "output": 1.654 }, "description": "DeepSeek V3 0324 is an AI model provided by cortecs.", "family": "deepseek", "id": "deepseek-v3-0324", "knowledge": "2024-07", "last_updated": "2025-03-24", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3 0324", "open_weights": true, "reasoning": false, "release_date": "2025-03-24", "temperature": true, "tool_call": true }, "deepseek-v3.2": { "attachment": false, "cost": { "input": 0.266, "output": 0.444 }, "description": "DeepSeek V3.2 is an AI model provided by cortecs.", "family": "deepseek", "id": "deepseek-v3.2", "knowledge": "2024-07", "last_updated": "2025-12-01", "limit": { "context": 163840, "output": 163840 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3.2", "open_weights": true, "reasoning": true, "release_date": "2025-12-01", "temperature": true, "tool_call": true }, "deepseek-v4-flash": { "attachment": false, "cost": { "cache_read": 0.028, "input": 0.133, "output": 0.266 }, "description": "DeepSeek V4 Flash is an AI model provided by cortecs.", "family": "deepseek-flash", "id": "deepseek-v4-flash", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-05", "last_updated": "2026-04-24", "limit": { "context": 1048576, "output": 384000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V4 Flash", "open_weights": true, "reasoning": true, "release_date": "2026-04-24", "temperature": true, "tool_call": true }, "deepseek-v4-pro": { "attachment": false, "cost": { "cache_read": 0.145, "input": 1.553, "output": 3.106 }, "description": "DeepSeek V4 Pro is an AI model provided by cortecs.", "family": "deepseek-thinking", "id": "deepseek-v4-pro", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-05", "last_updated": "2026-04-24", "limit": { "context": 1048576, "output": 384000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V4 Pro", "open_weights": true, "reasoning": true, "release_date": "2026-04-24", "temperature": true, "tool_call": true }, "devstral-2512": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Devstral 2 2512 is an AI model provided by cortecs.", "id": "devstral-2512", "knowledge": "2025-12", "last_updated": "2025-12-09", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Devstral 2 2512", "open_weights": true, "reasoning": false, "release_date": "2025-12-09", "temperature": true, "tool_call": true }, "devstral-small-2512": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Devstral Small 2 2512 is an AI model provided by cortecs.", "id": "devstral-small-2512", "knowledge": "2025-12", "last_updated": "2025-12-09", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Devstral Small 2 2512", "open_weights": true, "reasoning": false, "release_date": "2025-12-09", "temperature": true, "tool_call": true }, "gemini-2.5-pro": { "attachment": false, "cost": { "input": 1.654, "output": 11.024 }, "description": "Gemini 2.5 Pro is an AI model provided by cortecs.", "family": "gemini-pro", "id": "gemini-2.5-pro", "knowledge": "2025-01", "last_updated": "2025-06-17", "limit": { "context": 1048576, "output": 65535 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemini 2.5 Pro", "open_weights": false, "reasoning": false, "release_date": "2025-03-20", "temperature": true, "tool_call": true }, "glm-4.5": { "attachment": false, "cost": { "input": 0.67, "output": 2.46 }, "description": "GLM 4.5 is an AI model provided by cortecs.", "family": "glm", "id": "glm-4.5", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-04", "last_updated": "2025-07-29", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.5", "open_weights": true, "reasoning": true, "release_date": "2025-07-29", "temperature": true, "tool_call": true }, "glm-4.5-air": { "attachment": false, "cost": { "input": 0.22, "output": 1.34 }, "description": "GLM 4.5 Air is an AI model provided by cortecs.", "family": "glm-air", "id": "glm-4.5-air", "knowledge": "2025-04", "last_updated": "2025-08-01", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.5 Air", "open_weights": true, "reasoning": true, "release_date": "2025-08-01", "temperature": true, "tool_call": true }, "glm-4.7": { "attachment": false, "cost": { "input": 0.45, "output": 2.23 }, "description": "GLM 4.7 is an AI model provided by cortecs.", "family": "glm", "id": "glm-4.7", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-04", "last_updated": "2025-12-22", "limit": { "context": 198000, "output": 198000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.7", "open_weights": true, "reasoning": true, "release_date": "2025-12-22", "temperature": true, "tool_call": true }, "glm-4.7-flash": { "attachment": false, "cost": { "input": 0.09, "output": 0.53 }, "description": "GLM-4.7-Flash is an AI model provided by cortecs.", "family": "glm", "id": "glm-4.7-flash", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-04", "last_updated": "2025-08-08", "limit": { "context": 203000, "output": 203000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.7-Flash", "open_weights": true, "reasoning": true, "release_date": "2025-08-08", "temperature": true, "tool_call": true }, "glm-5": { "attachment": false, "cost": { "input": 1.08, "output": 3.44 }, "description": "GLM 5 is an AI model provided by cortecs.", "family": "glm", "id": "glm-5", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-02-11", "limit": { "context": 202752, "output": 202752 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 5", "open_weights": true, "reasoning": true, "release_date": "2026-02-11", "temperature": true, "tool_call": true }, "glm-5.1": { "attachment": false, "cost": { "cache_read": 0.24, "input": 1.31, "output": 4.1 }, "description": "GLM-5.1 is an AI model provided by cortecs.", "family": "glm", "id": "glm-5.1", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-14", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5.1", "open_weights": true, "reasoning": true, "release_date": "2026-04-14", "structured_output": true, "temperature": true, "tool_call": true }, "gpt-4.1": { "attachment": false, "cost": { "input": 2.354, "output": 9.417 }, "description": "GPT 4.1 is an AI model provided by cortecs.", "family": "gpt", "id": "gpt-4.1", "knowledge": "2024-06", "last_updated": "2025-04-14", "limit": { "context": 1047576, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT 4.1", "open_weights": false, "reasoning": false, "release_date": "2025-04-14", "temperature": true, "tool_call": true }, "gpt-oss-120b": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "GPT Oss 120b is an AI model provided by cortecs.", "family": "gpt-oss", "id": "gpt-oss-120b", "knowledge": "2024-01", "last_updated": "2025-08-05", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT Oss 120b", "open_weights": true, "reasoning": false, "release_date": "2025-08-05", "temperature": true, "tool_call": true }, "hermes-4-70b": { "attachment": false, "cost": { "input": 0.116, "output": 0.358 }, "description": "Hermes 4 70B is an AI model provided by cortecs.", "id": "hermes-4-70b", "knowledge": "2023-12", "last_updated": "2025-08-26", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Hermes 4 70B", "open_weights": true, "reasoning": true, "release_date": "2025-08-26", "temperature": true, "tool_call": true }, "intellect-3": { "attachment": true, "cost": { "input": 0.219, "output": 1.202 }, "description": "INTELLECT 3 is an AI model provided by cortecs.", "id": "intellect-3", "knowledge": "2025-11", "last_updated": "2025-11-26", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "INTELLECT 3", "open_weights": true, "reasoning": true, "release_date": "2025-11-26", "temperature": true, "tool_call": true }, "kimi-k2-instruct": { "attachment": false, "cost": { "input": 0.551, "output": 2.646 }, "description": "Kimi K2 Instruct is an AI model provided by cortecs.", "family": "kimi", "id": "kimi-k2-instruct", "knowledge": "2024-07", "last_updated": "2025-09-05", "limit": { "context": 131000, "output": 131000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-07-11", "temperature": true, "tool_call": true }, "kimi-k2-thinking": { "attachment": true, "cost": { "input": 0.656, "output": 2.731 }, "description": "Kimi K2 Thinking is an AI model provided by cortecs.", "id": "kimi-k2-thinking", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-12", "last_updated": "2025-12-08", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 Thinking", "open_weights": true, "reasoning": true, "release_date": "2025-12-08", "temperature": true, "tool_call": true }, "kimi-k2.5": { "attachment": false, "cost": { "input": 0.55, "output": 2.76 }, "description": "Kimi K2.5 is an AI model provided by cortecs.", "family": "kimi-thinking", "id": "kimi-k2.5", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-01", "last_updated": "2026-01-27", "limit": { "context": 256000, "output": 256000 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Kimi K2.5", "open_weights": true, "reasoning": true, "release_date": "2026-01-27", "temperature": true, "tool_call": true }, "kimi-k2.6": { "attachment": false, "cost": { "cache_read": 0.2, "input": 0.81, "output": 3.54 }, "description": "Kimi K2.6 is an AI model provided by cortecs.", "family": "kimi-thinking", "id": "kimi-k2.6", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-17", "limit": { "context": 256000, "output": 256000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Kimi K2.6", "open_weights": true, "reasoning": true, "release_date": "2026-04-17", "temperature": true, "tool_call": true }, "llama-3.1-405b-instruct": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Llama 3.1 405B Instruct is an AI model provided by cortecs.", "family": "llama", "id": "llama-3.1-405b-instruct", "knowledge": "2023-12", "last_updated": "2024-07-23", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.1 405B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-07-23", "temperature": true, "tool_call": true }, "llama-3.3-70b-instruct": { "attachment": false, "cost": { "input": 0.089, "output": 0.275 }, "description": "Llama 3.3 70B Instruct is an AI model provided by cortecs.", "family": "llama", "id": "llama-3.3-70b-instruct", "knowledge": "2023-12", "last_updated": "2024-12-06", "limit": { "context": 131000, "output": 131000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B Instruct", "open_weights": true, "reasoning": true, "release_date": "2024-12-06", "temperature": true, "tool_call": true }, "minimax-m2": { "attachment": false, "cost": { "input": 0.39, "output": 1.57 }, "description": "MiniMax-M2 is an AI model provided by cortecs.", "family": "minimax", "id": "minimax-m2", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-11", "last_updated": "2025-10-27", "limit": { "context": 400000, "output": 400000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2", "open_weights": true, "reasoning": true, "release_date": "2025-10-27", "temperature": true, "tool_call": true }, "minimax-m2.1": { "attachment": false, "cost": { "input": 0.34, "output": 1.34 }, "description": "MiniMax-M2.1 is an AI model provided by cortecs.", "family": "minimax", "id": "minimax-m2.1", "interleaved": { "field": "reasoning_content" }, "last_updated": "2025-12-23", "limit": { "context": 196000, "output": 196000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.1", "open_weights": true, "reasoning": true, "release_date": "2025-12-23", "temperature": true, "tool_call": true }, "minimax-m2.5": { "attachment": false, "cost": { "input": 0.32, "output": 1.18 }, "description": "MiniMax-M2.5 is an AI model provided by cortecs.", "family": "minimax", "id": "minimax-m2.5", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-02-12", "limit": { "context": 196608, "output": 196608 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.5", "open_weights": true, "reasoning": true, "release_date": "2026-02-12", "temperature": true, "tool_call": true }, "minimax-m2.7": { "attachment": false, "cost": { "input": 0.47, "output": 1.4 }, "description": "MiniMax-m2.7 is an AI model provided by cortecs.", "family": "minimax", "id": "minimax-m2.7", "last_updated": "2026-03-18", "limit": { "context": 202752, "output": 196072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-m2.7", "open_weights": true, "reasoning": true, "release_date": "2026-03-18", "structured_output": true, "temperature": true, "tool_call": true }, "mistral-large-2512": { "attachment": true, "cost": { "cache_read": 0.05, "input": 0.5, "output": 1.5 }, "description": "Mistral Large 3 2512 is an AI model provided by cortecs.", "family": "mistral-large", "id": "mistral-large-2512", "knowledge": "2025-12", "last_updated": "2025-12-01", "limit": { "context": 256000, "output": 256000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Mistral Large 3 2512", "open_weights": true, "reasoning": false, "release_date": "2025-12-01", "temperature": true, "tool_call": true }, "mixtral-8x7B-instruct-v0.1": { "attachment": false, "cost": { "input": 0.438, "output": 0.68 }, "description": "Mixtral 8x7B Instruct v0.1 is an AI model provided by cortecs.", "id": "mixtral-8x7B-instruct-v0.1", "knowledge": "2023-09", "last_updated": "2023-12-11", "limit": { "context": 32000, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mixtral 8x7B Instruct v0.1", "open_weights": true, "reasoning": true, "release_date": "2023-12-11", "temperature": true, "tool_call": false }, "nemotron-3-super-120b-a12b": { "attachment": false, "cost": { "input": 0.266, "output": 0.799 }, "description": "Nemotron 3 Super 120B A12B is an AI model provided by cortecs.", "id": "nemotron-3-super-120b-a12b", "knowledge": "2025-12", "last_updated": "2026-03-11", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Nemotron 3 Super 120B A12B", "open_weights": true, "reasoning": true, "release_date": "2026-03-11", "temperature": true, "tool_call": true }, "nova-pro-v1": { "attachment": false, "cost": { "input": 1.016, "output": 4.061 }, "description": "Nova Pro 1.0 is an AI model provided by cortecs.", "family": "nova-pro", "id": "nova-pro-v1", "knowledge": "2024-04", "last_updated": "2024-12-03", "limit": { "context": 300000, "output": 5000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Nova Pro 1.0", "open_weights": false, "reasoning": false, "release_date": "2024-12-03", "temperature": true, "tool_call": true }, "qwen-2.5-72b-instruct": { "attachment": false, "cost": { "input": 0.062, "output": 0.231 }, "description": "Qwen2.5 72B Instruct is an AI model provided by cortecs.", "family": "qwen", "id": "qwen-2.5-72b-instruct", "knowledge": "2024-06", "last_updated": "2024-09-19", "limit": { "context": 33000, "output": 33000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen2.5 72B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-09-19", "temperature": true, "tool_call": true }, "qwen3-235b-a22b-instruct-2507": { "attachment": false, "cost": { "input": 0.062, "output": 0.408 }, "description": "Qwen3 235B A22B Instruct 2507 is an AI model provided by cortecs.", "family": "qwen", "id": "qwen3-235b-a22b-instruct-2507", "knowledge": "2025-04", "last_updated": "2025-07-23", "limit": { "context": 131000, "output": 131000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 235B A22B Instruct 2507", "open_weights": true, "reasoning": true, "release_date": "2025-07-23", "temperature": true, "tool_call": true }, "qwen3-32b": { "attachment": false, "cost": { "input": 0.099, "output": 0.33 }, "description": "Qwen3 32B is an AI model provided by cortecs.", "family": "qwen", "id": "qwen3-32b", "knowledge": "2024-12", "last_updated": "2025-04-29", "limit": { "context": 16384, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 32B", "open_weights": true, "reasoning": false, "release_date": "2025-04-29", "temperature": true, "tool_call": true }, "qwen3-coder-30b-a3b-instruct": { "attachment": false, "cost": { "input": 0.053, "output": 0.222 }, "description": "Qwen3 Coder 30B A3B Instruct is an AI model provided by cortecs.", "family": "qwen", "id": "qwen3-coder-30b-a3b-instruct", "knowledge": "2025-04", "last_updated": "2025-07-31", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Coder 30B A3B Instruct", "open_weights": true, "reasoning": true, "release_date": "2025-07-31", "temperature": true, "tool_call": true }, "qwen3-coder-480b-a35b-instruct": { "attachment": false, "cost": { "input": 0.441, "output": 1.984 }, "description": "Qwen3 Coder 480B A35B Instruct is an AI model provided by cortecs.", "family": "qwen", "id": "qwen3-coder-480b-a35b-instruct", "knowledge": "2025-01", "last_updated": "2025-07-25", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Coder 480B A35B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-07-25", "temperature": true, "tool_call": true }, "qwen3-coder-next": { "attachment": false, "cost": { "input": 0.158, "output": 0.84 }, "description": "Qwen3 Coder Next 80B is an AI model provided by cortecs.", "family": "qwen", "id": "qwen3-coder-next", "knowledge": "2025-04", "last_updated": "2026-02-04", "limit": { "context": 256000, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Coder Next 80B", "open_weights": true, "reasoning": true, "release_date": "2026-02-04", "temperature": true, "tool_call": true }, "qwen3-next-80b-a3b-thinking": { "attachment": false, "cost": { "input": 0.164, "output": 1.311 }, "description": "Qwen3 Next 80B A3B Thinking is an AI model provided by cortecs.", "id": "qwen3-next-80b-a3b-thinking", "knowledge": "2025-04", "last_updated": "2025-09-11", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Next 80B A3B Thinking", "open_weights": true, "reasoning": true, "release_date": "2025-09-11", "temperature": true, "tool_call": true }, "qwen3.5-122b-a10b": { "attachment": false, "cost": { "input": 0.444, "output": 3.106 }, "description": "Qwen3.5 122B A10B is an AI model provided by cortecs.", "family": "qwen", "id": "qwen3.5-122b-a10b", "knowledge": "2026-01", "last_updated": "2026-02-24", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3.5 122B A10B", "open_weights": true, "reasoning": true, "release_date": "2026-02-24", "temperature": true, "tool_call": true }, "qwen3.5-397b-a17b": { "attachment": false, "cost": { "input": 0.6, "output": 3.6 }, "description": "Qwen3.5 397B A17B is an AI model provided by cortecs.", "family": "qwen", "id": "qwen3.5-397b-a17b", "knowledge": "2026-01", "last_updated": "2026-02-16", "limit": { "context": 250000, "output": 250000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3.5 397B A17B", "open_weights": true, "reasoning": true, "release_date": "2026-02-16", "temperature": true, "tool_call": true } }, "name": "Cortecs", "npm": "@ai-sdk/openai-compatible" }, "databricks": { "api": "https://${DATABRICKS_HOST}/ai-gateway/mlflow/v1", "doc": "https://docs.databricks.com/aws/en/machine-learning/foundation-models/", "env": [ "DATABRICKS_HOST", "DATABRICKS_TOKEN" ], "iconURL": "https://models.dev/logos/databricks.svg", "id": "databricks", "models": { "databricks-claude-haiku-4-5": { "attachment": true, "cost": { "cache_read": 0.1, "cache_write": 1.25, "input": 1, "output": 5 }, "description": "Claude Haiku 4.5 (latest) is an AI model provided by databricks.", "family": "claude-haiku", "id": "databricks-claude-haiku-4-5", "knowledge": "2025-02-28", "last_updated": "2025-10-15", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Haiku 4.5 (latest)", "open_weights": false, "reasoning": true, "release_date": "2025-10-15", "temperature": true, "tool_call": true }, "databricks-claude-opus-4-1": { "attachment": true, "cost": { "cache_read": 1.5, "cache_write": 18.75, "input": 15, "output": 75 }, "description": "Claude Opus 4.1 (latest) is an AI model provided by databricks.", "family": "claude-opus", "id": "databricks-claude-opus-4-1", "knowledge": "2025-03-31", "last_updated": "2025-08-05", "limit": { "context": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.1 (latest)", "open_weights": false, "reasoning": true, "release_date": "2025-08-05", "temperature": true, "tool_call": true }, "databricks-claude-opus-4-5": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "input": 5, "output": 25 }, "description": "Claude Opus 4.5 (latest) is an AI model provided by databricks.", "family": "claude-opus", "id": "databricks-claude-opus-4-5", "knowledge": "2025-03-31", "last_updated": "2025-11-24", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.5 (latest)", "open_weights": false, "reasoning": true, "release_date": "2025-11-24", "temperature": true, "tool_call": true }, "databricks-claude-opus-4-6": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "input": 5, "output": 25 }, "description": "Claude Opus 4.6 is an AI model provided by databricks.", "experimental": { "modes": { "fast": { "cost": { "cache_read": 3, "cache_write": 37.5, "input": 30, "output": 150 }, "provider": { "body": { "speed": "fast" }, "headers": { "anthropic-beta": "fast-mode-2026-02-01" } } } } }, "family": "claude-opus", "id": "databricks-claude-opus-4-6", "knowledge": "2025-05-31", "last_updated": "2026-03-13", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.6", "open_weights": false, "reasoning": true, "release_date": "2026-02-05", "temperature": true, "tool_call": true }, "databricks-claude-opus-4-7": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "input": 5, "output": 25 }, "description": "Claude Opus 4.7 is an AI model provided by databricks.", "experimental": { "modes": { "fast": { "cost": { "cache_read": 3, "cache_write": 37.5, "input": 30, "output": 150 }, "provider": { "body": { "speed": "fast" }, "headers": { "anthropic-beta": "fast-mode-2026-02-01" } } } } }, "family": "claude-opus", "id": "databricks-claude-opus-4-7", "knowledge": "2026-01-31", "last_updated": "2026-04-16", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.7", "open_weights": false, "reasoning": true, "release_date": "2026-04-16", "temperature": false, "tool_call": true }, "databricks-claude-sonnet-4": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 4.5 is an AI model provided by databricks.", "family": "claude-sonnet", "id": "databricks-claude-sonnet-4", "knowledge": "2025-07-31", "last_updated": "2025-09-29", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.5", "open_weights": false, "reasoning": true, "release_date": "2025-09-29", "temperature": true, "tool_call": true }, "databricks-claude-sonnet-4-5": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 4.5 (latest) is an AI model provided by databricks.", "family": "claude-sonnet", "id": "databricks-claude-sonnet-4-5", "knowledge": "2025-07-31", "last_updated": "2025-09-29", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.5 (latest)", "open_weights": false, "reasoning": true, "release_date": "2025-09-29", "temperature": true, "tool_call": true }, "databricks-claude-sonnet-4-6": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 4.6 is an AI model provided by databricks.", "family": "claude-sonnet", "id": "databricks-claude-sonnet-4-6", "knowledge": "2025-08-31", "last_updated": "2026-03-13", "limit": { "context": 1000000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.6", "open_weights": false, "reasoning": true, "release_date": "2026-02-17", "temperature": true, "tool_call": true }, "databricks-gemini-2-5-flash": { "attachment": true, "cost": { "cache_read": 0.03, "input": 0.3, "input_audio": 1, "output": 2.5 }, "description": "Gemini 2.5 Flash is an AI model provided by databricks.", "family": "gemini-flash", "id": "databricks-gemini-2-5-flash", "knowledge": "2025-01", "last_updated": "2025-06-05", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Flash", "open_weights": false, "reasoning": true, "release_date": "2025-03-20", "structured_output": true, "temperature": true, "tool_call": true }, "databricks-gemini-2-5-pro": { "attachment": true, "cost": { "cache_read": 0.125, "context_over_200k": { "cache_read": 0.25, "input": 2.5, "output": 15 }, "input": 1.25, "output": 10, "tiers": [ { "cache_read": 0.25, "input": 2.5, "output": 15, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Gemini 2.5 Pro is an AI model provided by databricks.", "family": "gemini-pro", "id": "databricks-gemini-2-5-pro", "knowledge": "2025-01", "last_updated": "2025-06-05", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Pro", "open_weights": false, "reasoning": true, "release_date": "2025-03-20", "structured_output": true, "temperature": true, "tool_call": true }, "databricks-gemini-3-1-flash-lite": { "attachment": true, "cost": { "cache_read": 0.025, "input": 0.25, "input_audio": 0.5, "output": 1.5 }, "description": "Gemini 3.1 Flash Lite Preview is an AI model provided by databricks.", "family": "gemini-flash-lite", "id": "databricks-gemini-3-1-flash-lite", "knowledge": "2025-01", "last_updated": "2026-03-03", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "name": "Gemini 3.1 Flash Lite Preview", "open_weights": false, "reasoning": true, "release_date": "2026-03-03", "structured_output": true, "temperature": true, "tool_call": true }, "databricks-gemini-3-1-pro": { "attachment": true, "cost": { "cache_read": 0.2, "context_over_200k": { "cache_read": 0.4, "input": 4, "output": 18 }, "input": 2, "output": 12, "tiers": [ { "cache_read": 0.4, "input": 4, "output": 18, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Gemini 3.1 Pro Preview Custom Tools is an AI model provided by databricks.", "family": "gemini-pro", "id": "databricks-gemini-3-1-pro", "knowledge": "2025-01", "last_updated": "2026-02-19", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "name": "Gemini 3.1 Pro Preview Custom Tools", "open_weights": false, "reasoning": true, "release_date": "2026-02-19", "structured_output": true, "temperature": true, "tool_call": true }, "databricks-gemini-3-flash": { "attachment": true, "cost": { "cache_read": 0.05, "input": 0.5, "input_audio": 1, "output": 3 }, "description": "Gemini 3 Flash Preview is an AI model provided by databricks.", "family": "gemini-flash", "id": "databricks-gemini-3-flash", "knowledge": "2025-01", "last_updated": "2025-12-17", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "name": "Gemini 3 Flash Preview", "open_weights": false, "reasoning": true, "release_date": "2025-12-17", "structured_output": true, "temperature": true, "tool_call": true }, "databricks-gemini-3-pro": { "attachment": true, "cost": { "cache_read": 0.2, "context_over_200k": { "cache_read": 0.4, "input": 4, "output": 18 }, "input": 2, "output": 12, "tiers": [ { "cache_read": 0.4, "input": 4, "output": 18, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Gemini 3 Pro Preview is an AI model provided by databricks.", "family": "gemini-pro", "id": "databricks-gemini-3-pro", "knowledge": "2025-01", "last_updated": "2025-11-18", "limit": { "context": 1000000, "output": 64000 }, "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "name": "Gemini 3 Pro Preview", "open_weights": false, "reasoning": true, "release_date": "2025-11-18", "structured_output": true, "temperature": true, "tool_call": true }, "databricks-gpt-5": { "attachment": true, "cost": { "cache_read": 0.125, "input": 1.25, "output": 10 }, "description": "GPT-5 is an AI model provided by databricks.", "family": "gpt", "id": "databricks-gpt-5", "knowledge": "2024-09-30", "last_updated": "2025-08-07", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "structured_output": true, "temperature": false, "tool_call": true }, "databricks-gpt-5-1": { "attachment": true, "cost": { "cache_read": 0.13, "input": 1.25, "output": 10 }, "description": "GPT-5.1 is an AI model provided by databricks.", "family": "gpt", "id": "databricks-gpt-5-1", "knowledge": "2024-09-30", "last_updated": "2025-11-13", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.1", "open_weights": false, "reasoning": true, "release_date": "2025-11-13", "structured_output": true, "temperature": false, "tool_call": true }, "databricks-gpt-5-2": { "attachment": true, "cost": { "cache_read": 0.175, "input": 1.75, "output": 14 }, "description": "GPT-5.2 is an AI model provided by databricks.", "family": "gpt", "id": "databricks-gpt-5-2", "knowledge": "2025-08-31", "last_updated": "2025-12-11", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.2", "open_weights": false, "reasoning": true, "release_date": "2025-12-11", "structured_output": true, "temperature": false, "tool_call": true }, "databricks-gpt-5-4": { "attachment": true, "cost": { "cache_read": 0.25, "context_over_200k": { "cache_read": 0.5, "input": 5, "output": 22.5 }, "input": 2.5, "output": 15, "tiers": [ { "cache_read": 0.5, "input": 5, "output": 22.5, "tier": { "size": 272000, "type": "context" } } ] }, "description": "GPT-5.4 is an AI model provided by databricks.", "experimental": { "modes": { "fast": { "cost": { "cache_read": 0.5, "input": 5, "output": 30 }, "provider": { "body": { "service_tier": "priority" } } } } }, "family": "gpt", "id": "databricks-gpt-5-4", "knowledge": "2025-08-31", "last_updated": "2026-03-05", "limit": { "context": 1050000, "input": 922000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.4", "open_weights": false, "reasoning": true, "release_date": "2026-03-05", "structured_output": true, "temperature": false, "tool_call": true }, "databricks-gpt-5-4-mini": { "attachment": true, "cost": { "cache_read": 0.075, "input": 0.75, "output": 4.5 }, "description": "GPT-5.4 mini is an AI model provided by databricks.", "experimental": { "modes": { "fast": { "cost": { "cache_read": 0.15, "input": 1.5, "output": 9 }, "provider": { "body": { "service_tier": "priority" } } } } }, "family": "gpt-mini", "id": "databricks-gpt-5-4-mini", "knowledge": "2025-08-31", "last_updated": "2026-03-17", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.4 mini", "open_weights": false, "reasoning": true, "release_date": "2026-03-17", "structured_output": true, "temperature": false, "tool_call": true }, "databricks-gpt-5-4-nano": { "attachment": true, "cost": { "cache_read": 0.02, "input": 0.2, "output": 1.25 }, "description": "GPT-5.4 nano is an AI model provided by databricks.", "family": "gpt-nano", "id": "databricks-gpt-5-4-nano", "knowledge": "2025-08-31", "last_updated": "2026-03-17", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.4 nano", "open_weights": false, "reasoning": true, "release_date": "2026-03-17", "structured_output": true, "temperature": false, "tool_call": true }, "databricks-gpt-5-5": { "attachment": true, "cost": { "cache_read": 0.5, "context_over_200k": { "cache_read": 1, "input": 10, "output": 45 }, "input": 5, "output": 30, "tiers": [ { "cache_read": 1, "input": 10, "output": 45, "tier": { "size": 272000, "type": "context" } } ] }, "description": "GPT-5.5 is an AI model provided by databricks.", "experimental": { "modes": { "fast": { "cost": { "cache_read": 1.25, "input": 12.5, "output": 75 }, "provider": { "body": { "service_tier": "priority" } } } } }, "family": "gpt", "id": "databricks-gpt-5-5", "knowledge": "2025-12-01", "last_updated": "2026-04-23", "limit": { "context": 1050000, "input": 922000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.5", "open_weights": false, "reasoning": true, "release_date": "2026-04-23", "structured_output": true, "temperature": false, "tool_call": true }, "databricks-gpt-5-mini": { "attachment": true, "cost": { "cache_read": 0.025, "input": 0.25, "output": 2 }, "description": "GPT-5 Mini is an AI model provided by databricks.", "family": "gpt-mini", "id": "databricks-gpt-5-mini", "knowledge": "2024-05-30", "last_updated": "2025-08-07", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5 Mini", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "structured_output": true, "temperature": false, "tool_call": true }, "databricks-gpt-5-nano": { "attachment": true, "cost": { "cache_read": 0.005, "input": 0.05, "output": 0.4 }, "description": "GPT-5 Nano is an AI model provided by databricks.", "family": "gpt-nano", "id": "databricks-gpt-5-nano", "knowledge": "2024-05-30", "last_updated": "2025-08-07", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5 Nano", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "structured_output": true, "temperature": false, "tool_call": true }, "databricks-gpt-oss-120b": { "attachment": false, "cost": { "input": 0.072, "output": 0.28 }, "description": "GPT OSS 120B is an AI model provided by databricks.", "family": "gpt-oss", "id": "databricks-gpt-oss-120b", "last_updated": "2025-08-05", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT OSS 120B", "open_weights": true, "reasoning": true, "release_date": "2025-08-05", "structured_output": true, "temperature": true, "tool_call": true }, "databricks-gpt-oss-20b": { "attachment": false, "cost": { "input": 0.05, "output": 0.2 }, "description": "GPT OSS 20B is an AI model provided by databricks.", "family": "gpt-oss", "id": "databricks-gpt-oss-20b", "last_updated": "2025-08-05", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT OSS 20B", "open_weights": true, "reasoning": true, "release_date": "2025-08-05", "structured_output": true, "temperature": true, "tool_call": true } }, "name": "Databricks", "npm": "@ai-sdk/openai-compatible" }, "deepinfra": { "doc": "https://deepinfra.com/models", "env": [ "DEEPINFRA_API_KEY" ], "iconURL": "https://models.dev/logos/deepinfra.svg", "id": "deepinfra", "lobeIcon": "DeepInfra", "models": { "MiniMaxAI/MiniMax-M2": { "attachment": false, "cost": { "input": 0.254, "output": 1.02 }, "description": "MiniMax M2 is an AI model provided by deepinfra.", "family": "minimax", "id": "MiniMaxAI/MiniMax-M2", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-10", "last_updated": "2025-11-13", "limit": { "context": 262144, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M2", "open_weights": true, "reasoning": true, "release_date": "2025-11-13", "temperature": true, "tool_call": true }, "MiniMaxAI/MiniMax-M2.1": { "attachment": false, "cost": { "input": 0.28, "output": 1.2 }, "description": "MiniMax M2.1 is an AI model provided by deepinfra.", "id": "MiniMaxAI/MiniMax-M2.1", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-06", "last_updated": "2025-12-23", "limit": { "context": 196608, "output": 196608 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M2.1", "open_weights": true, "reasoning": true, "release_date": "2025-12-23", "temperature": true, "tool_call": true }, "MiniMaxAI/MiniMax-M2.5": { "attachment": false, "cost": { "cache_read": 0.03, "cache_write": 0.375, "input": 0.27, "output": 0.95 }, "description": "MiniMax M2.5 is an AI model provided by deepinfra.", "family": "minimax", "id": "MiniMaxAI/MiniMax-M2.5", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-06", "last_updated": "2026-02-12", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M2.5", "open_weights": true, "reasoning": true, "release_date": "2026-02-12", "temperature": true, "tool_call": true }, "Qwen/Qwen3-Coder-480B-A35B-Instruct": { "attachment": false, "cost": { "input": 0.4, "output": 1.6 }, "description": "Qwen3 Coder 480B A35B Instruct is an AI model provided by deepinfra.", "family": "qwen", "id": "Qwen/Qwen3-Coder-480B-A35B-Instruct", "knowledge": "2025-04", "last_updated": "2025-07-23", "limit": { "context": 262144, "output": 66536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Coder 480B A35B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-07-23", "temperature": true, "tool_call": true }, "Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo": { "attachment": false, "cost": { "input": 0.3, "output": 1.2 }, "description": "Qwen3 Coder 480B A35B Instruct Turbo is an AI model provided by deepinfra.", "family": "qwen", "id": "Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo", "knowledge": "2025-04", "last_updated": "2025-07-23", "limit": { "context": 262144, "output": 66536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Coder 480B A35B Instruct Turbo", "open_weights": true, "reasoning": false, "release_date": "2025-07-23", "temperature": true, "tool_call": true }, "Qwen/Qwen3.5-35B-A3B": { "attachment": true, "cost": { "input": 0.2, "output": 0.95 }, "description": "Qwen 3.5 35B A3B is an AI model provided by deepinfra.", "family": "qwen", "id": "Qwen/Qwen3.5-35B-A3B", "knowledge": "2025-01", "last_updated": "2026-04-20", "limit": { "context": 262144, "output": 81920 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen 3.5 35B A3B", "open_weights": true, "reasoning": true, "release_date": "2026-02-01", "temperature": true, "tool_call": true }, "Qwen/Qwen3.5-397B-A17B": { "attachment": true, "cost": { "input": 0.54, "output": 3.4 }, "description": "Qwen 3.5 397B A17B is an AI model provided by deepinfra.", "family": "qwen", "id": "Qwen/Qwen3.5-397B-A17B", "knowledge": "2025-01", "last_updated": "2026-04-20", "limit": { "context": 262144, "output": 81920 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen 3.5 397B A17B", "open_weights": true, "reasoning": true, "release_date": "2026-02-01", "temperature": true, "tool_call": true }, "Qwen/Qwen3.6-35B-A3B": { "attachment": true, "cost": { "input": 0.2, "output": 1 }, "description": "Qwen3.6 35B A3B is an AI model provided by deepinfra.", "family": "qwen", "id": "Qwen/Qwen3.6-35B-A3B", "last_updated": "2026-04-01", "limit": { "context": 262144, "output": 81920 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen3.6 35B A3B", "open_weights": true, "reasoning": true, "release_date": "2026-04-01", "temperature": true, "tool_call": true }, "anthropic/claude-3-7-sonnet-latest": { "attachment": true, "cost": { "cache_read": 0.33, "input": 3.3, "output": 16.5 }, "description": "Claude Sonnet 3.7 (Latest) is an AI model provided by deepinfra.", "family": "claude-sonnet", "id": "anthropic/claude-3-7-sonnet-latest", "knowledge": "2024-10-31", "last_updated": "2025-03-13", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Claude Sonnet 3.7 (Latest)", "open_weights": false, "reasoning": true, "release_date": "2025-03-13", "temperature": true, "tool_call": true }, "anthropic/claude-4-opus": { "attachment": true, "cost": { "input": 16.5, "output": 82.5 }, "description": "Claude Opus 4 is an AI model provided by deepinfra.", "family": "claude-opus", "id": "anthropic/claude-4-opus", "knowledge": "2025-03-31", "last_updated": "2025-06-12", "limit": { "context": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Claude Opus 4", "open_weights": false, "reasoning": true, "release_date": "2025-06-12", "temperature": true, "tool_call": true }, "deepseek-ai/DeepSeek-R1-0528": { "attachment": false, "cost": { "cache_read": 0.35, "input": 0.5, "output": 2.15 }, "description": "DeepSeek-R1-0528 is an AI model provided by deepinfra.", "id": "deepseek-ai/DeepSeek-R1-0528", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-07", "last_updated": "2025-05-28", "limit": { "context": 163840, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek-R1-0528", "open_weights": false, "reasoning": true, "release_date": "2025-05-28", "temperature": true, "tool_call": false }, "deepseek-ai/DeepSeek-V3.2": { "attachment": false, "cost": { "cache_read": 0.13, "input": 0.26, "output": 0.38 }, "description": "DeepSeek-V3.2 is an AI model provided by deepinfra.", "id": "deepseek-ai/DeepSeek-V3.2", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-12", "last_updated": "2025-12-02", "limit": { "context": 163840, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek-V3.2", "open_weights": false, "reasoning": true, "release_date": "2025-12-02", "temperature": true, "tool_call": true }, "deepseek-ai/DeepSeek-V4-Flash": { "attachment": false, "cost": { "cache_read": 0.028, "input": 0.14, "output": 0.28 }, "description": "DeepSeek V4 Flash is an AI model provided by deepinfra.", "family": "deepseek-flash", "id": "deepseek-ai/DeepSeek-V4-Flash", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-05", "last_updated": "2026-04-24", "limit": { "context": 1000000, "output": 384000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V4 Flash", "open_weights": true, "reasoning": true, "release_date": "2026-04-24", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek-ai/DeepSeek-V4-Pro": { "attachment": false, "cost": { "cache_read": 0.145, "input": 1.74, "output": 3.48 }, "description": "DeepSeek V4 Pro is an AI model provided by deepinfra.", "family": "deepseek-thinking", "id": "deepseek-ai/DeepSeek-V4-Pro", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-05", "last_updated": "2026-04-24", "limit": { "context": 65536, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V4 Pro", "open_weights": true, "reasoning": true, "release_date": "2026-04-24", "structured_output": true, "temperature": true, "tool_call": true }, "google/gemma-4-26B-A4B-it": { "attachment": false, "cost": { "input": 0.07, "output": 0.34 }, "description": "Gemma 4 26B is an AI model provided by deepinfra.", "family": "gemma", "id": "google/gemma-4-26B-A4B-it", "last_updated": "2026-04-02", "limit": { "context": 256000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemma 4 26B", "open_weights": true, "reasoning": true, "release_date": "2026-04-02", "structured_output": true, "temperature": true, "tool_call": true }, "google/gemma-4-31B-it": { "attachment": false, "cost": { "input": 0.13, "output": 0.38 }, "description": "Gemma 4 31B is an AI model provided by deepinfra.", "family": "gemma", "id": "google/gemma-4-31B-it", "last_updated": "2026-04-02", "limit": { "context": 256000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemma 4 31B", "open_weights": true, "reasoning": true, "release_date": "2026-04-02", "structured_output": true, "temperature": true, "tool_call": true }, "meta-llama/Llama-3.1-70B-Instruct": { "attachment": false, "cost": { "input": 0.4, "output": 0.4 }, "description": "Llama 3.1 70B is an AI model provided by deepinfra.", "family": "llama", "id": "meta-llama/Llama-3.1-70B-Instruct", "last_updated": "2024-07-23", "limit": { "context": 131072, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.1 70B", "open_weights": true, "reasoning": false, "release_date": "2024-07-23", "tool_call": true }, "meta-llama/Llama-3.1-70B-Instruct-Turbo": { "attachment": false, "cost": { "input": 0.4, "output": 0.4 }, "description": "Llama 3.1 70B Turbo is an AI model provided by deepinfra.", "family": "llama", "id": "meta-llama/Llama-3.1-70B-Instruct-Turbo", "last_updated": "2024-07-23", "limit": { "context": 131072, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.1 70B Turbo", "open_weights": true, "reasoning": false, "release_date": "2024-07-23", "tool_call": true }, "meta-llama/Llama-3.1-8B-Instruct": { "attachment": false, "cost": { "input": 0.02, "output": 0.05 }, "description": "Llama 3.1 8B is an AI model provided by deepinfra.", "family": "llama", "id": "meta-llama/Llama-3.1-8B-Instruct", "last_updated": "2024-07-23", "limit": { "context": 131072, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.1 8B", "open_weights": true, "reasoning": false, "release_date": "2024-07-23", "tool_call": true }, "meta-llama/Llama-3.1-8B-Instruct-Turbo": { "attachment": false, "cost": { "input": 0.02, "output": 0.03 }, "description": "Llama 3.1 8B Turbo is an AI model provided by deepinfra.", "family": "llama", "id": "meta-llama/Llama-3.1-8B-Instruct-Turbo", "last_updated": "2024-07-23", "limit": { "context": 131072, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.1 8B Turbo", "open_weights": true, "reasoning": false, "release_date": "2024-07-23", "tool_call": true }, "meta-llama/Llama-3.3-70B-Instruct-Turbo": { "attachment": false, "cost": { "input": 0.1, "output": 0.32 }, "description": "Llama 3.3 70B Turbo is an AI model provided by deepinfra.", "family": "llama", "id": "meta-llama/Llama-3.3-70B-Instruct-Turbo", "last_updated": "2024-12-06", "limit": { "context": 131072, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B Turbo", "open_weights": true, "reasoning": false, "release_date": "2024-12-06", "tool_call": true }, "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { "attachment": false, "cost": { "input": 0.15, "output": 0.6 }, "description": "Llama 4 Maverick 17B FP8 is an AI model provided by deepinfra.", "family": "llama", "id": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8", "last_updated": "2025-04-05", "limit": { "context": 1000000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Llama 4 Maverick 17B FP8", "open_weights": true, "reasoning": false, "release_date": "2025-04-05", "tool_call": true }, "meta-llama/Llama-4-Scout-17B-16E-Instruct": { "attachment": false, "cost": { "input": 0.08, "output": 0.3 }, "description": "Llama 4 Scout 17B is an AI model provided by deepinfra.", "family": "llama", "id": "meta-llama/Llama-4-Scout-17B-16E-Instruct", "last_updated": "2025-04-05", "limit": { "context": 10000000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Llama 4 Scout 17B", "open_weights": true, "reasoning": false, "release_date": "2025-04-05", "tool_call": true }, "moonshotai/Kimi-K2-Instruct": { "attachment": false, "cost": { "input": 0.5, "output": 2 }, "description": "Kimi K2 is an AI model provided by deepinfra.", "family": "kimi", "id": "moonshotai/Kimi-K2-Instruct", "knowledge": "2024-10", "last_updated": "2025-07-11", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2", "open_weights": true, "reasoning": false, "release_date": "2025-07-11", "temperature": true, "tool_call": true }, "moonshotai/Kimi-K2-Instruct-0905": { "attachment": false, "cost": { "cache_read": 0.15, "input": 0.4, "output": 2 }, "description": "Kimi K2 0905 is an AI model provided by deepinfra.", "family": "kimi", "id": "moonshotai/Kimi-K2-Instruct-0905", "knowledge": "2024-10", "last_updated": "2025-09-05", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 0905", "open_weights": true, "reasoning": false, "release_date": "2025-09-05", "temperature": true, "tool_call": true }, "moonshotai/Kimi-K2-Thinking": { "attachment": false, "cost": { "input": 0.47, "output": 2 }, "description": "Kimi K2 Thinking is an AI model provided by deepinfra.", "family": "kimi-thinking", "id": "moonshotai/Kimi-K2-Thinking", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-10", "last_updated": "2025-11-07", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 Thinking", "open_weights": true, "reasoning": true, "release_date": "2025-11-06", "temperature": true, "tool_call": true }, "moonshotai/Kimi-K2.5": { "attachment": true, "cost": { "input": 0.5, "output": 2.8 }, "description": "Kimi K2.5 is an AI model provided by deepinfra.", "family": "kimi", "id": "moonshotai/Kimi-K2.5", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-01", "last_updated": "2026-01-27", "limit": { "context": 262144, "output": 32768 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Kimi K2.5", "open_weights": true, "reasoning": true, "release_date": "2026-01-27", "structured_output": true, "temperature": true, "tool_call": true }, "moonshotai/Kimi-K2.6": { "attachment": true, "cost": { "cache_read": 0.15, "input": 0.75, "output": 3.5 }, "description": "Kimi K2.6 is an AI model provided by deepinfra.", "family": "kimi", "id": "moonshotai/Kimi-K2.6", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-04", "last_updated": "2026-04-21", "limit": { "context": 262144, "output": 16384 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Kimi K2.6", "open_weights": true, "reasoning": true, "release_date": "2026-04-21", "structured_output": true, "temperature": true, "tool_call": true }, "openai/gpt-oss-120b": { "attachment": false, "cost": { "input": 0.05, "output": 0.24 }, "description": "GPT OSS 120B is an AI model provided by deepinfra.", "family": "gpt-oss", "id": "openai/gpt-oss-120b", "last_updated": "2025-08-05", "limit": { "context": 131072, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT OSS 120B", "open_weights": true, "reasoning": true, "release_date": "2025-08-05", "temperature": true, "tool_call": true }, "openai/gpt-oss-20b": { "attachment": false, "cost": { "input": 0.03, "output": 0.14 }, "description": "GPT OSS 20B is an AI model provided by deepinfra.", "family": "gpt-oss", "id": "openai/gpt-oss-20b", "last_updated": "2025-08-05", "limit": { "context": 131072, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT OSS 20B", "open_weights": true, "reasoning": true, "release_date": "2025-08-05", "temperature": true, "tool_call": true }, "xiaomi/mimo-v2.5": { "attachment": true, "cost": { "cache_read": 0.08, "context_over_200k": { "cache_read": 0.16, "input": 0.8, "output": 4 }, "input": 0.4, "output": 2, "tiers": [ { "cache_read": 0.16, "input": 0.8, "output": 4, "tier": { "size": 256000, "type": "context" } } ] }, "description": "MiMo-V2.5 is an AI model provided by deepinfra.", "family": "mimo", "id": "xiaomi/mimo-v2.5", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-12", "last_updated": "2026-04-22", "limit": { "context": 262144, "output": 16384 }, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "name": "MiMo-V2.5", "open_weights": true, "reasoning": true, "release_date": "2026-04-22", "temperature": true, "tool_call": true }, "xiaomi/mimo-v2.5-pro": { "attachment": false, "cost": { "cache_read": 0.2, "context_over_200k": { "cache_read": 0.4, "input": 2, "output": 6 }, "input": 1, "output": 3, "tiers": [ { "cache_read": 0.4, "input": 2, "output": 6, "tier": { "size": 256000, "type": "context" } } ] }, "description": "MiMo-V2.5-Pro is an AI model provided by deepinfra.", "family": "mimo", "id": "xiaomi/mimo-v2.5-pro", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-12", "last_updated": "2026-04-22", "limit": { "context": 1048576, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiMo-V2.5-Pro", "open_weights": true, "reasoning": true, "release_date": "2026-04-22", "temperature": true, "tool_call": true }, "zai-org/GLM-4.5": { "attachment": false, "cost": { "input": 0.6, "output": 2.2 }, "description": "GLM-4.5 is an AI model provided by deepinfra.", "family": "glm", "id": "zai-org/GLM-4.5", "knowledge": "2025-04", "last_updated": "2025-07-28", "limit": { "context": 131072, "output": 98304 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.5", "open_weights": true, "reasoning": false, "release_date": "2025-07-28", "status": "deprecated", "temperature": true, "tool_call": true }, "zai-org/GLM-4.6": { "attachment": false, "cost": { "cache_read": 0.08, "input": 0.43, "output": 1.74 }, "description": "GLM-4.6 is an AI model provided by deepinfra.", "family": "glm", "id": "zai-org/GLM-4.6", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-04", "last_updated": "2025-09-30", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.6", "open_weights": true, "reasoning": true, "release_date": "2025-09-30", "temperature": true, "tool_call": true }, "zai-org/GLM-4.6V": { "attachment": true, "cost": { "input": 0.3, "output": 0.9 }, "description": "GLM-4.6V is an AI model provided by deepinfra.", "family": "glm", "id": "zai-org/GLM-4.6V", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-04", "last_updated": "2025-09-30", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GLM-4.6V", "open_weights": true, "reasoning": true, "release_date": "2025-09-30", "temperature": true, "tool_call": true }, "zai-org/GLM-4.7": { "attachment": false, "cost": { "cache_read": 0.08, "input": 0.43, "output": 1.75 }, "description": "GLM-4.7 is an AI model provided by deepinfra.", "family": "glm", "id": "zai-org/GLM-4.7", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-04", "last_updated": "2025-12-22", "limit": { "context": 202752, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.7", "open_weights": true, "reasoning": true, "release_date": "2025-12-22", "temperature": true, "tool_call": true }, "zai-org/GLM-4.7-Flash": { "attachment": false, "cost": { "input": 0.06, "output": 0.4 }, "description": "GLM-4.7-Flash is an AI model provided by deepinfra.", "family": "glm-flash", "id": "zai-org/GLM-4.7-Flash", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-04", "last_updated": "2026-01-19", "limit": { "context": 202752, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.7-Flash", "open_weights": true, "reasoning": true, "release_date": "2026-01-19", "temperature": true, "tool_call": true }, "zai-org/GLM-5": { "attachment": false, "cost": { "cache_read": 0.16, "input": 0.8, "output": 2.56 }, "description": "GLM-5 is an AI model provided by deepinfra.", "family": "glm", "id": "zai-org/GLM-5", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-12", "last_updated": "2026-02-12", "limit": { "context": 202752, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5", "open_weights": true, "reasoning": true, "release_date": "2026-02-12", "temperature": true, "tool_call": true }, "zai-org/GLM-5.1": { "attachment": false, "cost": { "cache_read": 0.26, "input": 1.4, "output": 4.4 }, "description": "GLM-5.1 is an AI model provided by deepinfra.", "family": "glm", "id": "zai-org/GLM-5.1", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-04", "last_updated": "2026-04-07", "limit": { "context": 202752, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5.1", "open_weights": true, "reasoning": true, "release_date": "2026-04-07", "structured_output": true, "temperature": true, "tool_call": true } }, "name": "Deep Infra", "npm": "@ai-sdk/deepinfra" }, "deepseek": { "api": "https://api.deepseek.com", "doc": "https://api-docs.deepseek.com/quick_start/pricing", "env": [ "DEEPSEEK_API_KEY" ], "iconURL": "https://models.dev/logos/deepseek.svg", "id": "deepseek", "lobeIcon": "DeepSeek.Color", "models": { "deepseek-chat": { "attachment": true, "cost": { "cache_read": 0.028, "input": 0.14, "output": 0.28 }, "description": "DeepSeek Chat is an AI model provided by deepseek.", "family": "deepseek", "id": "deepseek-chat", "knowledge": "2025-09", "last_updated": "2026-02-28", "limit": { "context": 1000000, "output": 384000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek Chat", "open_weights": true, "reasoning": false, "release_date": "2025-12-01", "temperature": true, "tool_call": true }, "deepseek-reasoner": { "attachment": true, "cost": { "cache_read": 0.028, "input": 0.14, "output": 0.28 }, "description": "DeepSeek Reasoner is an AI model provided by deepseek.", "family": "deepseek-thinking", "id": "deepseek-reasoner", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-09", "last_updated": "2026-02-28", "limit": { "context": 1000000, "output": 384000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek Reasoner", "open_weights": true, "reasoning": true, "release_date": "2025-12-01", "temperature": true, "tool_call": true }, "deepseek-v4-flash": { "attachment": false, "cost": { "cache_read": 0.028, "input": 0.14, "output": 0.28 }, "description": "DeepSeek V4 Flash is an AI model provided by deepseek.", "family": "deepseek-flash", "id": "deepseek-v4-flash", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-05", "last_updated": "2026-04-24", "limit": { "context": 1000000, "output": 384000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V4 Flash", "open_weights": true, "reasoning": true, "release_date": "2026-04-24", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek-v4-pro": { "attachment": false, "cost": { "cache_read": 0.145, "input": 1.74, "output": 3.48 }, "description": "DeepSeek V4 Pro is an AI model provided by deepseek.", "family": "deepseek-thinking", "id": "deepseek-v4-pro", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-05", "last_updated": "2026-04-24", "limit": { "context": 1000000, "output": 384000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V4 Pro", "open_weights": true, "reasoning": true, "release_date": "2026-04-24", "structured_output": true, "temperature": true, "tool_call": true } }, "name": "DeepSeek", "npm": "@ai-sdk/openai-compatible" }, "digitalocean": { "api": "https://inference.do-ai.run/v1", "doc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/", "env": [ "DIGITALOCEAN_ACCESS_TOKEN" ], "iconURL": "https://models.dev/logos/digitalocean.svg", "id": "digitalocean", "models": { "alibaba-qwen3-32b": { "attachment": false, "cost": { "input": 0.25, "output": 0.55 }, "description": "Qwen3-32B is an AI model provided by digitalocean.", "family": "qwen", "id": "alibaba-qwen3-32b", "last_updated": "2026-04-16", "limit": { "context": 131000, "output": 40960 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3-32B", "open_weights": true, "reasoning": true, "release_date": "2025-04-30", "structured_output": true, "temperature": true, "tool_call": true }, "all-mini-lm-l6-v2": { "attachment": false, "cost": { "input": 0.009, "output": 0 }, "description": "All-MiniLM-L6-v2 is an AI model provided by digitalocean.", "family": "text-embedding", "id": "all-mini-lm-l6-v2", "last_updated": "2026-04-16", "limit": { "context": 256, "output": 384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "All-MiniLM-L6-v2", "open_weights": true, "reasoning": false, "release_date": "2021-08-30", "temperature": false, "tool_call": false }, "anthropic-claude-3-opus": { "attachment": true, "cost": { "cache_read": 1.5, "cache_write": 18.75, "input": 15, "output": 75 }, "description": "Claude 3 Opus is an AI model provided by digitalocean.", "family": "claude-opus", "id": "anthropic-claude-3-opus", "knowledge": "2023-08", "last_updated": "2024-02-29", "limit": { "context": 200000, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Claude 3 Opus", "open_weights": false, "reasoning": false, "release_date": "2024-02-29", "status": "deprecated", "temperature": true, "tool_call": true }, "anthropic-claude-3.5-haiku": { "attachment": false, "cost": { "cache_read": 0.08, "cache_write": 1, "input": 0.8, "output": 4 }, "description": "Claude 3.5 Haiku is an AI model provided by digitalocean.", "family": "claude-haiku", "id": "anthropic-claude-3.5-haiku", "knowledge": "2024-07", "last_updated": "2024-11-05", "limit": { "context": 200000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Claude 3.5 Haiku", "open_weights": false, "reasoning": false, "release_date": "2024-11-05", "status": "deprecated", "temperature": true, "tool_call": true }, "anthropic-claude-3.5-sonnet": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude 3.5 Sonnet is an AI model provided by digitalocean.", "family": "claude-sonnet", "id": "anthropic-claude-3.5-sonnet", "knowledge": "2024-04", "last_updated": "2024-10-22", "limit": { "context": 200000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Claude 3.5 Sonnet", "open_weights": false, "reasoning": false, "release_date": "2024-06-20", "status": "deprecated", "temperature": true, "tool_call": true }, "anthropic-claude-3.7-sonnet": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude 3.7 Sonnet is an AI model provided by digitalocean.", "family": "claude-sonnet", "id": "anthropic-claude-3.7-sonnet", "knowledge": "2024-11", "last_updated": "2025-02-24", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Claude 3.7 Sonnet", "open_weights": false, "reasoning": true, "release_date": "2025-02-24", "status": "deprecated", "temperature": true, "tool_call": true }, "anthropic-claude-4.1-opus": { "attachment": true, "cost": { "cache_read": 1.5, "cache_write": 18.75, "input": 15, "output": 75 }, "description": "Claude Opus 4.1 is an AI model provided by digitalocean.", "family": "claude-opus", "id": "anthropic-claude-4.1-opus", "knowledge": "2025-03-31", "last_updated": "2025-08-05", "limit": { "context": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.1", "open_weights": false, "reasoning": true, "release_date": "2025-08-05", "temperature": true, "tool_call": true }, "anthropic-claude-4.5-haiku": { "attachment": true, "cost": { "cache_read": 1, "cache_write": 1.25, "input": 1, "output": 5 }, "description": "Claude Haiku 4.5 is an AI model provided by digitalocean.", "family": "claude-haiku", "id": "anthropic-claude-4.5-haiku", "knowledge": "2025-02-28", "last_updated": "2025-10-15", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Claude Haiku 4.5", "open_weights": false, "reasoning": true, "release_date": "2025-10-15", "temperature": true, "tool_call": true }, "anthropic-claude-4.5-sonnet": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "context_over_200k": { "cache_read": 0.3, "cache_write": 3.75, "input": 6, "output": 22.5 }, "input": 3, "output": 15, "tiers": [ { "cache_read": 0.3, "cache_write": 3.75, "input": 6, "output": 22.5, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Claude Sonnet 4.5 is an AI model provided by digitalocean.", "family": "claude-sonnet", "id": "anthropic-claude-4.5-sonnet", "knowledge": "2025-07-31", "last_updated": "2025-09-29", "limit": { "context": 1000000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.5", "open_weights": false, "reasoning": true, "release_date": "2025-09-29", "temperature": true, "tool_call": true }, "anthropic-claude-4.6-sonnet": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "context_over_200k": { "cache_read": 0.3, "cache_write": 3.75, "input": 6, "output": 22.5 }, "input": 3, "output": 15, "tiers": [ { "cache_read": 0.3, "cache_write": 3.75, "input": 6, "output": 22.5, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Claude Sonnet 4.6 is an AI model provided by digitalocean.", "family": "claude-sonnet", "id": "anthropic-claude-4.6-sonnet", "knowledge": "2025-08-31", "last_updated": "2026-03-13", "limit": { "context": 1000000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.6", "open_weights": false, "reasoning": true, "release_date": "2026-02-17", "temperature": true, "tool_call": true }, "anthropic-claude-haiku-4.5": { "attachment": true, "cost": { "cache_read": 1, "cache_write": 1.25, "input": 1, "output": 5 }, "description": "Claude Haiku 4.5 is an AI model provided by digitalocean.", "family": "claude-haiku", "id": "anthropic-claude-haiku-4.5", "knowledge": "2025-02-28", "last_updated": "2025-10-15", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Haiku 4.5", "open_weights": false, "reasoning": true, "release_date": "2025-10-15", "temperature": true, "tool_call": true }, "anthropic-claude-opus-4": { "attachment": true, "cost": { "cache_read": 1.5, "cache_write": 18.75, "input": 15, "output": 75 }, "description": "Claude Opus 4 is an AI model provided by digitalocean.", "family": "claude-opus", "id": "anthropic-claude-opus-4", "knowledge": "2025-03-31", "last_updated": "2025-05-22", "limit": { "context": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4", "open_weights": false, "reasoning": true, "release_date": "2025-05-22", "temperature": true, "tool_call": true }, "anthropic-claude-opus-4.5": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "input": 5, "output": 25 }, "description": "Claude Opus 4.5 is an AI model provided by digitalocean.", "family": "claude-opus", "id": "anthropic-claude-opus-4.5", "knowledge": "2025-03-31", "last_updated": "2025-11-24", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.5", "open_weights": false, "reasoning": true, "release_date": "2025-11-24", "temperature": true, "tool_call": true }, "anthropic-claude-opus-4.6": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "context_over_200k": { "cache_read": 0.5, "cache_write": 6.25, "input": 10, "output": 37.5 }, "input": 5, "output": 25, "tiers": [ { "cache_read": 0.5, "cache_write": 6.25, "input": 10, "output": 37.5, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Claude Opus 4.6 is an AI model provided by digitalocean.", "family": "claude-opus", "id": "anthropic-claude-opus-4.6", "knowledge": "2025-05-31", "last_updated": "2026-03-13", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.6", "open_weights": false, "reasoning": true, "release_date": "2026-02-05", "temperature": true, "tool_call": true }, "anthropic-claude-opus-4.7": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "input": 5, "output": 25 }, "description": "Claude Opus 4.7 is an AI model provided by digitalocean.", "family": "claude-opus", "id": "anthropic-claude-opus-4.7", "knowledge": "2026-01-31", "last_updated": "2026-04-16", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.7", "open_weights": false, "reasoning": true, "release_date": "2026-04-16", "temperature": false, "tool_call": true }, "anthropic-claude-sonnet-4": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "context_over_200k": { "cache_read": 0.3, "cache_write": 3.75, "input": 6, "output": 22.5 }, "input": 3, "output": 15, "tiers": [ { "cache_read": 0.3, "cache_write": 3.75, "input": 6, "output": 22.5, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Claude Sonnet 4 is an AI model provided by digitalocean.", "family": "claude-sonnet", "id": "anthropic-claude-sonnet-4", "knowledge": "2025-03-31", "last_updated": "2025-05-22", "limit": { "context": 1000000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4", "open_weights": false, "reasoning": true, "release_date": "2025-05-22", "temperature": true, "tool_call": true }, "arcee-trinity-large-thinking": { "attachment": false, "cost": { "cache_read": 0.06, "input": 0.25, "output": 0.9 }, "description": "Trinity Large Thinking is an AI model provided by digitalocean.", "family": "trinity", "id": "arcee-trinity-large-thinking", "last_updated": "2026-04-16", "limit": { "context": 256000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Trinity Large Thinking", "open_weights": true, "reasoning": true, "release_date": "2026-04-02", "status": "beta", "temperature": true, "tool_call": true }, "bge-m3": { "attachment": false, "cost": { "input": 0.02, "output": 0 }, "description": "BGE M3 is an AI model provided by digitalocean.", "family": "bge", "id": "bge-m3", "last_updated": "2026-04-30", "limit": { "context": 8192, "output": 1024 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "BGE M3", "open_weights": true, "reasoning": false, "release_date": "2024-01-30", "temperature": false, "tool_call": false }, "bge-reranker-v2-m3": { "attachment": false, "cost": { "input": 0.01, "output": 0 }, "description": "BGE Reranker v2 M3 is an AI model provided by digitalocean.", "family": "bge", "id": "bge-reranker-v2-m3", "last_updated": "2026-04-30", "limit": { "context": 8192, "output": 1 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "BGE Reranker v2 M3", "open_weights": true, "reasoning": false, "release_date": "2024-03-12", "temperature": false, "tool_call": false }, "deepseek-3.2": { "attachment": false, "cost": { "input": 0.5, "output": 1.6 }, "description": "DeepSeek V3.2 is an AI model provided by digitalocean.", "family": "deepseek", "id": "deepseek-3.2", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-12", "last_updated": "2026-04-30", "limit": { "context": 128000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3.2", "open_weights": true, "reasoning": true, "release_date": "2025-12-02", "temperature": true, "tool_call": true }, "deepseek-r1-distill-llama-70b": { "attachment": false, "cost": { "input": 0.99, "output": 0.99 }, "description": "DeepSeek R1 Distill Llama 70B is an AI model provided by digitalocean.", "family": "deepseek-thinking", "id": "deepseek-r1-distill-llama-70b", "last_updated": "2025-01-30", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek R1 Distill Llama 70B", "open_weights": true, "reasoning": true, "release_date": "2025-01-30", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek-v3": { "attachment": false, "description": "DeepSeek V3 is an AI model provided by digitalocean.", "family": "deepseek", "id": "deepseek-v3", "knowledge": "2024-07", "last_updated": "2025-03-24", "limit": { "context": 163840, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3", "open_weights": true, "reasoning": false, "release_date": "2024-12-26", "temperature": true, "tool_call": true }, "deepseek-v4-pro": { "attachment": false, "cost": { "input": 1.74, "output": 3.48 }, "description": "DeepSeek V4 Pro is an AI model provided by digitalocean.", "family": "deepseek-thinking", "id": "deepseek-v4-pro", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-05", "last_updated": "2026-04-24", "limit": { "context": 1048576, "output": 393216 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V4 Pro", "open_weights": true, "reasoning": true, "release_date": "2026-04-24", "structured_output": true, "temperature": true, "tool_call": true }, "e5-large-v2": { "attachment": false, "cost": { "input": 0.02, "output": 0 }, "description": "E5 Large v2 is an AI model provided by digitalocean.", "family": "text-embedding", "id": "e5-large-v2", "last_updated": "2026-04-30", "limit": { "context": 512, "output": 1024 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "E5 Large v2", "open_weights": true, "reasoning": false, "release_date": "2023-05-19", "temperature": false, "tool_call": false }, "fal-ai/elevenlabs/tts/multilingual-v2": { "attachment": false, "description": "ElevenLabs Multilingual TTS v2 is an AI model provided by digitalocean.", "family": "elevenlabs", "id": "fal-ai/elevenlabs/tts/multilingual-v2", "last_updated": "2026-04-16", "limit": { "context": 0, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "name": "ElevenLabs Multilingual TTS v2", "open_weights": false, "reasoning": false, "release_date": "2023-08-22", "temperature": false, "tool_call": false }, "fal-ai/fast-sdxl": { "attachment": false, "description": "Fast SDXL is an AI model provided by digitalocean.", "family": "stable-diffusion", "id": "fal-ai/fast-sdxl", "last_updated": "2026-04-16", "limit": { "context": 0, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "name": "Fast SDXL", "open_weights": true, "reasoning": false, "release_date": "2023-07-26", "temperature": false, "tool_call": false }, "fal-ai/flux/schnell": { "attachment": false, "description": "FLUX.1 [schnell] is an AI model provided by digitalocean.", "family": "flux", "id": "fal-ai/flux/schnell", "last_updated": "2026-04-16", "limit": { "context": 0, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "name": "FLUX.1 [schnell]", "open_weights": true, "reasoning": false, "release_date": "2024-08-01", "temperature": false, "tool_call": false }, "fal-ai/stable-audio-25/text-to-audio": { "attachment": false, "description": "Stable Audio 2.5 (Text-to-Audio) is an AI model provided by digitalocean.", "id": "fal-ai/stable-audio-25/text-to-audio", "last_updated": "2026-04-16", "limit": { "context": 0, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "name": "Stable Audio 2.5 (Text-to-Audio)", "open_weights": false, "reasoning": false, "release_date": "2025-10-08", "temperature": false, "tool_call": false }, "gemma-4-31B-it": { "attachment": true, "cost": { "input": 0.18, "output": 0.5 }, "description": "Gemma 4 31B is an AI model provided by digitalocean.", "family": "gemma", "id": "gemma-4-31B-it", "last_updated": "2026-04-30", "limit": { "context": 256000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemma 4 31B", "open_weights": true, "reasoning": false, "release_date": "2026-04-22", "structured_output": true, "temperature": true, "tool_call": true }, "glm-5": { "attachment": false, "cost": { "input": 1, "output": 3.2 }, "description": "GLM 5 is an AI model provided by digitalocean.", "family": "glm", "id": "glm-5", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-16", "limit": { "context": 202752, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 5", "open_weights": true, "reasoning": true, "release_date": "2026-02-11", "tool_call": true }, "gte-large-en-v1.5": { "attachment": false, "cost": { "input": 0.09, "output": 0 }, "description": "GTE Large (v1.5) is an AI model provided by digitalocean.", "family": "text-embedding", "id": "gte-large-en-v1.5", "last_updated": "2026-04-16", "limit": { "context": 8192, "output": 1024 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GTE Large (v1.5)", "open_weights": true, "reasoning": false, "release_date": "2024-03-27", "temperature": false, "tool_call": false }, "kimi-k2.5": { "attachment": false, "cost": { "input": 0.5, "output": 2.7 }, "description": "Kimi K2.5 is an AI model provided by digitalocean.", "family": "kimi", "id": "kimi-k2.5", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-01", "last_updated": "2026-04-16", "limit": { "context": 262144, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2.5", "open_weights": true, "reasoning": true, "release_date": "2026-01", "structured_output": true, "temperature": false, "tool_call": true }, "kimi-k2.6": { "attachment": true, "cost": { "input": 0.95, "output": 4 }, "description": "Kimi K2.6 is an AI model provided by digitalocean.", "family": "kimi", "id": "kimi-k2.6", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-01", "last_updated": "2026-04-21", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Kimi K2.6", "open_weights": true, "reasoning": true, "release_date": "2026-04-21", "structured_output": true, "temperature": false, "tool_call": true }, "llama-4-maverick": { "attachment": true, "cost": { "input": 0.25, "output": 0.87 }, "description": "Llama 4 Maverick 17B 128E Instruct is an AI model provided by digitalocean.", "family": "llama", "id": "llama-4-maverick", "knowledge": "2024-08", "last_updated": "2026-04-30", "limit": { "context": 1000000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Llama 4 Maverick 17B 128E Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-04-05", "structured_output": true, "temperature": true, "tool_call": true }, "llama3-8b-instruct": { "attachment": false, "cost": { "input": 0.198, "output": 0.198 }, "description": "Llama 3.1 Instruct (8B) is an AI model provided by digitalocean.", "family": "llama", "id": "llama3-8b-instruct", "knowledge": "2023-12", "last_updated": "2024-07-23", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.1 Instruct (8B)", "open_weights": true, "reasoning": false, "release_date": "2024-07-23", "temperature": true, "tool_call": true }, "llama3.3-70b-instruct": { "attachment": false, "cost": { "input": 0.65, "output": 0.65 }, "description": "Llama 3.3 Instruct 70B is an AI model provided by digitalocean.", "family": "llama", "id": "llama3.3-70b-instruct", "knowledge": "2023-12", "last_updated": "2024-12-06", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 Instruct 70B", "open_weights": true, "reasoning": false, "release_date": "2024-12-06", "temperature": true, "tool_call": true }, "minimax-m2.5": { "attachment": false, "cost": { "input": 0.3, "output": 1.2 }, "description": "MiniMax M2.5 is an AI model provided by digitalocean.", "family": "minimax-m2.5", "id": "minimax-m2.5", "knowledge": "2025-08", "last_updated": "2026-04-16", "limit": { "context": 204800, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M2.5", "open_weights": true, "reasoning": true, "release_date": "2026-02-12", "status": "beta", "temperature": true, "tool_call": true }, "ministral-3-8b-instruct-2512": { "attachment": true, "description": "Ministral 3 8B is an AI model provided by digitalocean.", "family": "ministral", "id": "ministral-3-8b-instruct-2512", "last_updated": "2025-12-15", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Ministral 3 8B", "open_weights": true, "reasoning": false, "release_date": "2025-12-15", "temperature": true, "tool_call": true }, "mistral-3-14B": { "attachment": false, "cost": { "input": 0.2, "output": 0.2 }, "description": "Ministral 3 14B Instruct is an AI model provided by digitalocean.", "family": "ministral", "id": "mistral-3-14B", "last_updated": "2026-04-30", "limit": { "context": 262144, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Ministral 3 14B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-12-15", "structured_output": true, "temperature": true, "tool_call": true }, "mistral-7b-instruct-v0.3": { "attachment": false, "description": "Mistral 7B Instruct v0.3 is an AI model provided by digitalocean.", "family": "mistral", "id": "mistral-7b-instruct-v0.3", "last_updated": "2024-05-22", "limit": { "context": 32768, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral 7B Instruct v0.3", "open_weights": true, "reasoning": false, "release_date": "2024-05-22", "temperature": true, "tool_call": true }, "mistral-nemo-instruct-2407": { "attachment": false, "cost": { "input": 0.3, "output": 0.3 }, "description": "Mistral Nemo Instruct is an AI model provided by digitalocean.", "family": "mistral", "id": "mistral-nemo-instruct-2407", "last_updated": "2024-07-18", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral Nemo Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-07-18", "status": "deprecated", "temperature": true, "tool_call": true }, "multi-qa-mpnet-base-dot-v1": { "attachment": false, "cost": { "input": 0.009, "output": 0 }, "description": "Multi-QA-mpnet-base-dot-v1 is an AI model provided by digitalocean.", "family": "text-embedding", "id": "multi-qa-mpnet-base-dot-v1", "last_updated": "2026-04-16", "limit": { "context": 512, "output": 768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Multi-QA-mpnet-base-dot-v1", "open_weights": true, "reasoning": false, "release_date": "2021-08-30", "temperature": false, "tool_call": false }, "nemotron-3-nano-30b": { "attachment": false, "description": "Nemotron 3 Nano 30B A3B is an AI model provided by digitalocean.", "family": "nemotron", "id": "nemotron-3-nano-30b", "last_updated": "2025-04-14", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Nemotron 3 Nano 30B A3B", "open_weights": true, "reasoning": true, "release_date": "2025-04-14", "temperature": true, "tool_call": true }, "nemotron-3-nano-omni": { "attachment": true, "cost": { "input": 0.5, "output": 0.9 }, "description": "Nemotron Nano 3 Omni is an AI model provided by digitalocean.", "family": "nemotron", "id": "nemotron-3-nano-omni", "last_updated": "2026-04-30", "limit": { "context": 65536, "output": 65536 }, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text" ] }, "name": "Nemotron Nano 3 Omni", "open_weights": true, "reasoning": true, "release_date": "2026-04-28", "structured_output": true, "temperature": true, "tool_call": true }, "nemotron-nano-12b-v2-vl": { "attachment": true, "cost": { "input": 0.2, "output": 0.6 }, "description": "Nemotron Nano 12B v2 VL is an AI model provided by digitalocean.", "family": "nemotron", "id": "nemotron-nano-12b-v2-vl", "knowledge": "2024-10", "last_updated": "2026-04-30", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Nemotron Nano 12B v2 VL", "open_weights": true, "reasoning": true, "release_date": "2025-12-01", "temperature": true, "tool_call": true }, "nvidia-nemotron-3-super-120b": { "attachment": false, "cost": { "input": 0.3, "output": 0.65 }, "description": "Nemotron-3-Super-120B is an AI model provided by digitalocean.", "family": "nemotron", "id": "nvidia-nemotron-3-super-120b", "knowledge": "2026-02", "last_updated": "2026-04-16", "limit": { "context": 256000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Nemotron-3-Super-120B", "open_weights": true, "reasoning": true, "release_date": "2026-03-11", "status": "beta", "structured_output": true, "temperature": true, "tool_call": true }, "openai-gpt-4.1": { "attachment": true, "cost": { "cache_read": 0.5, "input": 2, "output": 8 }, "description": "GPT-4.1 is an AI model provided by digitalocean.", "family": "gpt", "id": "openai-gpt-4.1", "knowledge": "2024-04", "last_updated": "2025-04-14", "limit": { "context": 1047576, "output": 32768 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-4.1", "open_weights": false, "reasoning": false, "release_date": "2025-04-14", "structured_output": true, "temperature": true, "tool_call": true }, "openai-gpt-4o": { "attachment": true, "cost": { "cache_read": 1.25, "input": 2.5, "output": 10 }, "description": "GPT-4o is an AI model provided by digitalocean.", "family": "gpt", "id": "openai-gpt-4o", "knowledge": "2023-09", "last_updated": "2024-08-06", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-4o", "open_weights": false, "reasoning": false, "release_date": "2024-05-13", "structured_output": true, "temperature": true, "tool_call": true }, "openai-gpt-4o-mini": { "attachment": true, "cost": { "cache_read": 0.075, "input": 0.15, "output": 0.6 }, "description": "GPT-4o mini is an AI model provided by digitalocean.", "family": "gpt-mini", "id": "openai-gpt-4o-mini", "knowledge": "2023-09", "last_updated": "2024-07-18", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-4o mini", "open_weights": false, "reasoning": false, "release_date": "2024-07-18", "structured_output": true, "temperature": true, "tool_call": true }, "openai-gpt-5": { "attachment": true, "cost": { "cache_read": 0.125, "input": 1.25, "output": 10 }, "description": "GPT-5 is an AI model provided by digitalocean.", "family": "gpt", "id": "openai-gpt-5", "knowledge": "2024-09-30", "last_updated": "2025-08-07", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "structured_output": true, "temperature": false, "tool_call": true }, "openai-gpt-5-mini": { "attachment": true, "cost": { "cache_read": 0.025, "input": 0.25, "output": 2 }, "description": "GPT-5 mini is an AI model provided by digitalocean.", "family": "gpt-mini", "id": "openai-gpt-5-mini", "knowledge": "2024-05-30", "last_updated": "2025-08-07", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5 mini", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "structured_output": true, "temperature": false, "tool_call": true }, "openai-gpt-5-nano": { "attachment": true, "cost": { "cache_read": 0.005, "input": 0.05, "output": 0.4 }, "description": "GPT-5 nano is an AI model provided by digitalocean.", "family": "gpt-nano", "id": "openai-gpt-5-nano", "knowledge": "2024-05-30", "last_updated": "2025-08-07", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5 nano", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "structured_output": true, "temperature": false, "tool_call": true }, "openai-gpt-5.1-codex-max": { "attachment": true, "cost": { "cache_read": 0.125, "input": 1.25, "output": 10 }, "description": "GPT-5.1 Codex Max is an AI model provided by digitalocean.", "family": "gpt-codex", "id": "openai-gpt-5.1-codex-max", "knowledge": "2024-09-30", "last_updated": "2025-11-13", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.1 Codex Max", "open_weights": false, "reasoning": true, "release_date": "2025-11-13", "structured_output": true, "temperature": false, "tool_call": true }, "openai-gpt-5.2": { "attachment": true, "cost": { "cache_read": 0.175, "input": 1.75, "output": 14 }, "description": "GPT-5.2 is an AI model provided by digitalocean.", "family": "gpt", "id": "openai-gpt-5.2", "knowledge": "2025-08-31", "last_updated": "2025-12-11", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.2", "open_weights": false, "reasoning": true, "release_date": "2025-12-11", "structured_output": true, "temperature": false, "tool_call": true }, "openai-gpt-5.2-pro": { "attachment": true, "cost": { "input": 21, "output": 168 }, "description": "GPT-5.2 pro is an AI model provided by digitalocean.", "family": "gpt-pro", "id": "openai-gpt-5.2-pro", "knowledge": "2025-08-31", "last_updated": "2025-12-11", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.2 pro", "open_weights": false, "reasoning": true, "release_date": "2025-12-11", "temperature": false, "tool_call": true }, "openai-gpt-5.3-codex": { "attachment": true, "cost": { "cache_read": 0.175, "input": 1.75, "output": 14 }, "description": "GPT-5.3 Codex is an AI model provided by digitalocean.", "family": "gpt-codex", "id": "openai-gpt-5.3-codex", "knowledge": "2025-08-31", "last_updated": "2026-02-05", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.3 Codex", "open_weights": false, "reasoning": true, "release_date": "2026-02-05", "structured_output": true, "temperature": false, "tool_call": true }, "openai-gpt-5.4": { "attachment": true, "cost": { "cache_read": 0.25, "input": 2.5, "output": 15 }, "description": "GPT-5.4 is an AI model provided by digitalocean.", "family": "gpt", "id": "openai-gpt-5.4", "knowledge": "2025-08-31", "last_updated": "2026-03-05", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.4", "open_weights": false, "reasoning": true, "release_date": "2026-03-05", "structured_output": true, "temperature": false, "tool_call": true }, "openai-gpt-5.4-mini": { "attachment": true, "cost": { "cache_read": 0.075, "input": 0.75, "output": 4.5 }, "description": "GPT-5.4 mini is an AI model provided by digitalocean.", "family": "gpt-mini", "id": "openai-gpt-5.4-mini", "knowledge": "2025-08-31", "last_updated": "2026-03-17", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.4 mini", "open_weights": false, "reasoning": true, "release_date": "2026-03-17", "structured_output": true, "temperature": false, "tool_call": true }, "openai-gpt-5.4-nano": { "attachment": true, "cost": { "cache_read": 0.02, "input": 0.2, "output": 1.25 }, "description": "GPT-5.4 nano is an AI model provided by digitalocean.", "family": "gpt-nano", "id": "openai-gpt-5.4-nano", "knowledge": "2025-08-31", "last_updated": "2026-03-17", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.4 nano", "open_weights": false, "reasoning": true, "release_date": "2026-03-17", "structured_output": true, "temperature": false, "tool_call": true }, "openai-gpt-5.4-pro": { "attachment": true, "cost": { "input": 30, "output": 180 }, "description": "GPT-5.4 pro is an AI model provided by digitalocean.", "family": "gpt-pro", "id": "openai-gpt-5.4-pro", "knowledge": "2025-08-31", "last_updated": "2026-03-05", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.4 pro", "open_weights": false, "reasoning": true, "release_date": "2026-03-05", "temperature": false, "tool_call": true }, "openai-gpt-5.5": { "attachment": true, "cost": { "cache_read": 0.5, "context_over_200k": { "cache_read": 1, "input": 10, "output": 45 }, "input": 5, "output": 30, "tiers": [ { "cache_read": 1, "input": 10, "output": 45, "tier": { "size": 272000, "type": "context" } } ] }, "description": "GPT-5.5 is an AI model provided by digitalocean.", "family": "gpt", "id": "openai-gpt-5.5", "knowledge": "2025-12-01", "last_updated": "2026-04-30", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.5", "open_weights": false, "reasoning": true, "release_date": "2026-04-23", "structured_output": true, "temperature": false, "tool_call": true }, "openai-gpt-image-1": { "attachment": true, "cost": { "cache_read": 1.25, "input": 5, "output": 40 }, "description": "GPT Image 1 is an AI model provided by digitalocean.", "family": "gpt-image", "id": "openai-gpt-image-1", "last_updated": "2025-04-24", "limit": { "context": 0, "output": 0 }, "modalities": { "input": [ "text", "image" ], "output": [ "image" ] }, "name": "GPT Image 1", "open_weights": false, "reasoning": false, "release_date": "2025-04-24", "temperature": false, "tool_call": false }, "openai-gpt-image-1.5": { "attachment": true, "cost": { "cache_read": 1, "input": 5, "output": 10 }, "description": "GPT Image 1.5 is an AI model provided by digitalocean.", "family": "gpt-image", "id": "openai-gpt-image-1.5", "last_updated": "2025-11-25", "limit": { "context": 0, "output": 0 }, "modalities": { "input": [ "text", "image" ], "output": [ "image" ] }, "name": "GPT Image 1.5", "open_weights": false, "reasoning": false, "release_date": "2025-11-25", "temperature": false, "tool_call": false }, "openai-gpt-image-2": { "attachment": true, "description": "GPT Image 2 is an AI model provided by digitalocean.", "family": "gpt-image", "id": "openai-gpt-image-2", "last_updated": "2025-04-24", "limit": { "context": 0, "output": 0 }, "modalities": { "input": [ "text", "image" ], "output": [ "image" ] }, "name": "GPT Image 2", "open_weights": false, "reasoning": false, "release_date": "2025-04-24", "temperature": false, "tool_call": false }, "openai-gpt-oss-120b": { "attachment": false, "cost": { "input": 0.1, "output": 0.7 }, "description": "gpt-oss-120b is an AI model provided by digitalocean.", "family": "gpt-oss", "id": "openai-gpt-oss-120b", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-06", "last_updated": "2026-04-16", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "gpt-oss-120b", "open_weights": true, "reasoning": true, "release_date": "2025-08-05", "structured_output": true, "temperature": true, "tool_call": true }, "openai-gpt-oss-20b": { "attachment": false, "cost": { "input": 0.05, "output": 0.45 }, "description": "gpt-oss-20b is an AI model provided by digitalocean.", "family": "gpt-oss", "id": "openai-gpt-oss-20b", "knowledge": "2024-06", "last_updated": "2026-04-16", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "gpt-oss-20b", "open_weights": true, "reasoning": true, "release_date": "2025-08-05", "structured_output": true, "temperature": true, "tool_call": true }, "openai-o1": { "attachment": true, "cost": { "cache_read": 7.5, "input": 15, "output": 60 }, "description": "o1 is an AI model provided by digitalocean.", "family": "o", "id": "openai-o1", "knowledge": "2023-09", "last_updated": "2024-12-05", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "o1", "open_weights": false, "reasoning": true, "release_date": "2024-12-05", "structured_output": true, "temperature": false, "tool_call": true }, "openai-o3": { "attachment": true, "cost": { "cache_read": 0.5, "input": 2, "output": 8 }, "description": "o3 is an AI model provided by digitalocean.", "family": "o", "id": "openai-o3", "knowledge": "2024-05", "last_updated": "2025-04-16", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "o3", "open_weights": false, "reasoning": true, "release_date": "2025-04-16", "structured_output": true, "temperature": false, "tool_call": true }, "openai-o3-mini": { "attachment": false, "cost": { "cache_read": 0.55, "input": 1.1, "output": 4.4 }, "description": "o3-mini is an AI model provided by digitalocean.", "family": "o-mini", "id": "openai-o3-mini", "knowledge": "2024-05", "last_updated": "2025-01-29", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "o3-mini", "open_weights": false, "reasoning": true, "release_date": "2024-12-20", "structured_output": true, "temperature": false, "tool_call": true }, "qwen-2.5-14b-instruct": { "attachment": false, "description": "Qwen 2.5 14B Instruct is an AI model provided by digitalocean.", "family": "qwen", "id": "qwen-2.5-14b-instruct", "knowledge": "2024-09", "last_updated": "2024-09-19", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen 2.5 14B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-09-19", "temperature": true, "tool_call": true }, "qwen3-coder-flash": { "attachment": false, "cost": { "input": 0.45, "output": 1.7 }, "description": "Qwen3 Coder Flash is an AI model provided by digitalocean.", "family": "qwen", "id": "qwen3-coder-flash", "knowledge": "2025-04", "last_updated": "2026-04-30", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Coder Flash", "open_weights": true, "reasoning": false, "release_date": "2025-07-28", "temperature": true, "tool_call": true }, "qwen3-embedding-0.6b": { "attachment": false, "cost": { "input": 0.04, "output": 0 }, "description": "Qwen3 Embedding 0.6B is an AI model provided by digitalocean.", "family": "text-embedding", "id": "qwen3-embedding-0.6b", "last_updated": "2026-04-16", "limit": { "context": 8000, "output": 1024 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Embedding 0.6B", "open_weights": true, "reasoning": false, "release_date": "2025-06-03", "status": "beta", "temperature": false, "tool_call": false }, "qwen3-tts-voicedesign": { "attachment": false, "description": "Qwen3 TTS VoiceDesign is an AI model provided by digitalocean.", "family": "qwen", "id": "qwen3-tts-voicedesign", "last_updated": "2026-04-30", "limit": { "context": 32768, "output": 1 }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "name": "Qwen3 TTS VoiceDesign", "open_weights": true, "reasoning": false, "release_date": "2026-04-21", "temperature": false, "tool_call": false }, "qwen3.5-397b-a17b": { "attachment": false, "cost": { "input": 0.55, "output": 3.5 }, "description": "Qwen 3.5 397B A17B is an AI model provided by digitalocean.", "family": "qwen3.5", "id": "qwen3.5-397b-a17b", "last_updated": "2026-04-30", "limit": { "context": 262144, "output": 81920 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen 3.5 397B A17B", "open_weights": true, "reasoning": true, "release_date": "2026-02-15", "structured_output": true, "temperature": true, "tool_call": true }, "stable-diffusion-3.5-large": { "attachment": false, "cost": { "input": 0.08, "output": 0 }, "description": "Stable Diffusion 3.5 Large is an AI model provided by digitalocean.", "family": "stable-diffusion", "id": "stable-diffusion-3.5-large", "last_updated": "2026-04-30", "limit": { "context": 256, "output": 1 }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "name": "Stable Diffusion 3.5 Large", "open_weights": true, "reasoning": false, "release_date": "2024-10-22", "temperature": false, "tool_call": false }, "wan2-2-t2v-a14b": { "attachment": false, "cost": { "input": 0.6, "output": 0 }, "description": "Wan2.2-T2V-A14B is an AI model provided by digitalocean.", "id": "wan2-2-t2v-a14b", "last_updated": "2026-04-30", "limit": { "context": 100, "output": 1 }, "modalities": { "input": [ "text" ], "output": [ "video" ] }, "name": "Wan2.2-T2V-A14B", "open_weights": true, "reasoning": false, "release_date": "2025-07-28", "temperature": false, "tool_call": false } }, "name": "DigitalOcean", "npm": "@ai-sdk/openai-compatible" }, "dinference": { "api": "https://api.dinference.com/v1", "doc": "https://dinference.com", "env": [ "DINFERENCE_API_KEY" ], "iconURL": "https://models.dev/logos/dinference.svg", "id": "dinference", "models": { "glm-4.7": { "attachment": false, "cost": { "input": 0.45, "output": 1.65 }, "description": "GLM-4.7 is an AI model provided by dinference.", "family": "glm", "id": "glm-4.7", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-04", "last_updated": "2025-12-22", "limit": { "context": 200000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.7", "open_weights": true, "reasoning": true, "release_date": "2025-12-22", "temperature": true, "tool_call": true }, "glm-5": { "attachment": false, "cost": { "input": 0.75, "output": 2.4 }, "description": "GLM-5 is an AI model provided by dinference.", "family": "glm", "id": "glm-5", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-02-11", "limit": { "context": 200000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5", "open_weights": true, "reasoning": true, "release_date": "2026-02-11", "temperature": true, "tool_call": true }, "glm-5.1": { "attachment": false, "cost": { "input": 1.25, "output": 3.89 }, "description": "GLM-5.1 is an AI model provided by dinference.", "family": "glm", "id": "glm-5.1", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-03-27", "limit": { "context": 200000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5.1", "open_weights": false, "reasoning": true, "release_date": "2026-03-27", "structured_output": true, "temperature": true, "tool_call": true }, "gpt-oss-120b": { "attachment": false, "cost": { "input": 0.0675, "output": 0.27 }, "description": "GPT OSS 120B is an AI model provided by dinference.", "id": "gpt-oss-120b", "last_updated": "2025-08", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT OSS 120B", "open_weights": true, "reasoning": false, "release_date": "2025-08", "temperature": true, "tool_call": true }, "minimax-m2.5": { "attachment": false, "cost": { "input": 0.22, "output": 0.88 }, "description": "MiniMax-M2.5 is an AI model provided by dinference.", "family": "minimax", "id": "minimax-m2.5", "last_updated": "2026-02-12", "limit": { "context": 200000, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.5", "open_weights": true, "reasoning": true, "release_date": "2026-02-12", "temperature": true, "tool_call": true } }, "name": "DInference", "npm": "@ai-sdk/openai-compatible" }, "doubao": { "api": "https://www.volcengine.com/docs/82379", "id": "doubao", "lobeIcon": "Doubao.Color", "models": { "doubao-seed-1-6": { "description": "A multimodal large language model (LLM) launched by ByteDance.", "id": "doubao-seed-1-6", "knowledge": "2023-10", "last_updated": "2025-06-15", "limit": { "context": 256000, "output": 32000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "doubao-seed-1-6", "reasoning": true, "release_date": "2025-06-11", "temperature": true, "tool_call": true }, "doubao-seed-1-6-flash": { "description": "A multimodal large language model (LLM) launched by ByteDance.", "id": "doubao-seed-1-6-flash", "knowledge": "2023-10", "last_updated": "2025-07-15", "limit": { "context": 256000, "output": 32000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "doubao-seed-1-6-flash", "reasoning": false, "release_date": "2025-06-11", "temperature": true, "tool_call": true }, "doubao-seed-1-6-thinking": { "description": "A multimodal large language model (LLM) launched by ByteDance.", "id": "doubao-seed-1-6-thinking", "knowledge": "2023-10", "last_updated": "2025-07-15", "limit": { "context": 256000, "output": 32000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "doubao-seed-1-6-thinking", "reasoning": true, "release_date": "2025-06-11", "temperature": true, "tool_call": true } } }, "drun": { "api": "https://chat.d.run/v1", "doc": "https://www.d.run", "env": [ "DRUN_API_KEY" ], "iconURL": "https://models.dev/logos/drun.svg", "id": "drun", "models": { "public/deepseek-r1": { "attachment": false, "cost": { "input": 0.55, "output": 2.2 }, "description": "DeepSeek R1 is an AI model provided by drun.", "family": "deepseek-thinking", "id": "public/deepseek-r1", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-12", "last_updated": "2025-01-20", "limit": { "context": 131072, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek R1", "open_weights": true, "reasoning": true, "release_date": "2025-01-20", "temperature": true, "tool_call": true }, "public/deepseek-v3": { "attachment": false, "cost": { "input": 0.28, "output": 1.1 }, "description": "DeepSeek V3 is an AI model provided by drun.", "family": "deepseek", "id": "public/deepseek-v3", "knowledge": "2024-07", "last_updated": "2024-12-26", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3", "open_weights": true, "reasoning": false, "release_date": "2024-12-26", "temperature": true, "tool_call": true }, "public/minimax-m25": { "attachment": false, "cost": { "input": 0.29, "output": 1.16 }, "description": "MiniMax M2.5 is an AI model provided by drun.", "family": "minimax", "id": "public/minimax-m25", "interleaved": { "field": "reasoning_details" }, "last_updated": "2025-03-01", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M2.5", "open_weights": false, "reasoning": true, "release_date": "2025-03-01", "temperature": true, "tool_call": true } }, "name": "D.Run (China)", "npm": "@ai-sdk/openai-compatible" }, "evroc": { "api": "https://models.think.evroc.com/v1", "doc": "https://docs.evroc.com/products/think/overview.html", "env": [ "EVROC_API_KEY" ], "iconURL": "https://models.dev/logos/evroc.svg", "id": "evroc", "models": { "KBLab/kb-whisper-large": { "attachment": false, "cost": { "input": 0.00236, "output": 0.00236, "output_audio": 2.36 }, "description": "KB Whisper is an AI model provided by evroc.", "family": "whisper", "id": "KBLab/kb-whisper-large", "last_updated": "2024-10-01", "limit": { "context": 448, "output": 448 }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "name": "KB Whisper", "open_weights": true, "reasoning": false, "release_date": "2024-10-01", "tool_call": false }, "Qwen/Qwen3-30B-A3B-Instruct-2507-FP8": { "attachment": false, "cost": { "input": 0.35, "output": 1.42 }, "description": "Qwen3 30B 2507 is an AI model provided by evroc.", "family": "qwen", "id": "Qwen/Qwen3-30B-A3B-Instruct-2507-FP8", "last_updated": "2025-07-30", "limit": { "context": 64000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 30B 2507", "open_weights": true, "reasoning": false, "release_date": "2025-07-30", "tool_call": true }, "Qwen/Qwen3-Embedding-8B": { "attachment": false, "cost": { "input": 0.12, "output": 0.12 }, "description": "Qwen3 Embedding 8B is an AI model provided by evroc.", "family": "text-embedding", "id": "Qwen/Qwen3-Embedding-8B", "last_updated": "2025-07-30", "limit": { "context": 40960, "output": 40960 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Embedding 8B", "open_weights": true, "reasoning": false, "release_date": "2025-07-30", "tool_call": false }, "Qwen/Qwen3-VL-30B-A3B-Instruct": { "attachment": false, "cost": { "input": 0.24, "output": 0.94 }, "description": "Qwen3 VL 30B is an AI model provided by evroc.", "family": "qwen", "id": "Qwen/Qwen3-VL-30B-A3B-Instruct", "last_updated": "2025-07-30", "limit": { "context": 100000, "output": 100000 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen3 VL 30B", "open_weights": true, "reasoning": false, "release_date": "2025-07-30", "tool_call": true }, "intfloat/multilingual-e5-large-instruct": { "attachment": false, "cost": { "input": 0.12, "output": 0.12 }, "description": "E5 Multi-Lingual Large Embeddings 0.6B is an AI model provided by evroc.", "family": "text-embedding", "id": "intfloat/multilingual-e5-large-instruct", "last_updated": "2024-06-01", "limit": { "context": 512, "output": 512 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "E5 Multi-Lingual Large Embeddings 0.6B", "open_weights": true, "reasoning": false, "release_date": "2024-06-01", "tool_call": false }, "microsoft/Phi-4-multimodal-instruct": { "attachment": false, "cost": { "input": 0.24, "output": 0.47 }, "description": "Phi-4 15B is an AI model provided by evroc.", "family": "phi", "id": "microsoft/Phi-4-multimodal-instruct", "last_updated": "2025-01-01", "limit": { "context": 32000, "output": 32000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Phi-4 15B", "open_weights": true, "reasoning": false, "release_date": "2025-01-01", "tool_call": false }, "mistralai/Magistral-Small-2509": { "attachment": false, "cost": { "input": 0.59, "output": 2.36 }, "description": "Magistral Small 1.2 24B is an AI model provided by evroc.", "family": "magistral-small", "id": "mistralai/Magistral-Small-2509", "last_updated": "2025-06-01", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Magistral Small 1.2 24B", "open_weights": true, "reasoning": false, "release_date": "2025-06-01", "tool_call": false }, "mistralai/Voxtral-Small-24B-2507": { "attachment": false, "cost": { "input": 0.00236, "output": 0.00236, "output_audio": 2.36 }, "description": "Voxtral Small 24B is an AI model provided by evroc.", "family": "voxtral", "id": "mistralai/Voxtral-Small-24B-2507", "last_updated": "2025-03-01", "limit": { "context": 32000, "output": 32000 }, "modalities": { "input": [ "audio", "text" ], "output": [ "text" ] }, "name": "Voxtral Small 24B", "open_weights": true, "reasoning": false, "release_date": "2025-03-01", "tool_call": false }, "mistralai/devstral-small-2-24b-instruct-2512": { "attachment": false, "cost": { "input": 0.12, "output": 0.47 }, "description": "Devstral Small 2 24B Instruct 2512 is an AI model provided by evroc.", "family": "devstral", "id": "mistralai/devstral-small-2-24b-instruct-2512", "last_updated": "2025-12-01", "limit": { "context": 32768, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Devstral Small 2 24B Instruct 2512", "open_weights": true, "reasoning": false, "release_date": "2025-12-01", "tool_call": true }, "moonshotai/Kimi-K2.5": { "attachment": false, "cost": { "input": 1.47, "output": 5.9 }, "description": "Kimi K2.5 is an AI model provided by evroc.", "family": "kimi", "id": "moonshotai/Kimi-K2.5", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-01-27", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Kimi K2.5", "open_weights": true, "reasoning": true, "release_date": "2026-01-27", "tool_call": true }, "nvidia/Llama-3.3-70B-Instruct-FP8": { "attachment": false, "cost": { "input": 1.18, "output": 1.18 }, "description": "Llama 3.3 70B is an AI model provided by evroc.", "family": "llama", "id": "nvidia/Llama-3.3-70B-Instruct-FP8", "last_updated": "2024-12-01", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B", "open_weights": true, "reasoning": false, "release_date": "2024-12-01", "tool_call": false }, "openai/gpt-oss-120b": { "attachment": false, "cost": { "input": 0.24, "output": 0.94 }, "description": "GPT OSS 120B is an AI model provided by evroc.", "family": "gpt-oss", "id": "openai/gpt-oss-120b", "last_updated": "2025-08-05", "limit": { "context": 65536, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT OSS 120B", "open_weights": true, "reasoning": true, "release_date": "2025-08-05", "tool_call": true }, "openai/whisper-large-v3": { "attachment": false, "cost": { "input": 0.00236, "output": 0.00236, "output_audio": 2.36 }, "description": "Whisper 3 Large is an AI model provided by evroc.", "family": "whisper", "id": "openai/whisper-large-v3", "last_updated": "2024-10-01", "limit": { "context": 448, "output": 4096 }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "name": "Whisper 3 Large", "open_weights": true, "reasoning": false, "release_date": "2024-10-01", "tool_call": false } }, "name": "evroc", "npm": "@ai-sdk/openai-compatible" }, "examplecorp": { "api": "https://api.examplecorp.com", "description": "Fictional provider for demonstration and testing.", "doc": "https://docs.examplecorp.com", "iconURL": "https://cdn.examplecorp.com/icons/examplecorp.svg", "id": "examplecorp", "lobeIcon": "ExampleCorp.Color", "models": { "novus-1": { "attachment": true, "cost": { "cache_read": 0.075, "cache_write": 0.5, "input": 5, "output": 15 }, "description": "Fictional example multimodal model.", "id": "novus-1", "knowledge": "2024-07", "last_updated": "2025-08-21", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text", "image", "audio", "video", "pdf" ] }, "name": "Novus 1", "open_weights": false, "reasoning": true, "release_date": "2025-01-20", "temperature": true, "tool_call": true } }, "name": "ExampleCorp AI" }, "fastrouter": { "api": "https://go.fastrouter.ai/api/v1", "doc": "https://fastrouter.ai/models", "env": [ "FASTROUTER_API_KEY" ], "iconURL": "https://models.dev/logos/fastrouter.svg", "id": "fastrouter", "lobeIcon": "FastGPT", "models": { "anthropic/claude-opus-4.1": { "attachment": true, "cost": { "cache_read": 1.5, "cache_write": 18.75, "input": 15, "output": 75 }, "description": "Claude Opus 4.1 is an AI model provided by fastrouter.", "family": "claude-opus", "id": "anthropic/claude-opus-4.1", "knowledge": "2025-03-31", "last_updated": "2025-08-05", "limit": { "context": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.1", "open_weights": false, "reasoning": true, "release_date": "2025-08-05", "temperature": true, "tool_call": true }, "anthropic/claude-sonnet-4": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 4 is an AI model provided by fastrouter.", "family": "claude-sonnet", "id": "anthropic/claude-sonnet-4", "knowledge": "2025-03-31", "last_updated": "2025-05-22", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4", "open_weights": false, "reasoning": true, "release_date": "2025-05-22", "temperature": true, "tool_call": true }, "deepseek-ai/deepseek-r1-distill-llama-70b": { "attachment": false, "cost": { "input": 0.03, "output": 0.14 }, "description": "DeepSeek R1 Distill Llama 70B is an AI model provided by fastrouter.", "family": "deepseek-thinking", "id": "deepseek-ai/deepseek-r1-distill-llama-70b", "knowledge": "2024-10", "last_updated": "2025-01-23", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek R1 Distill Llama 70B", "open_weights": true, "reasoning": true, "release_date": "2025-01-23", "temperature": true, "tool_call": false }, "google/gemini-2.5-flash": { "attachment": true, "cost": { "cache_read": 0.0375, "input": 0.3, "output": 2.5 }, "description": "Gemini 2.5 Flash is an AI model provided by fastrouter.", "family": "gemini-flash", "id": "google/gemini-2.5-flash", "knowledge": "2025-01", "last_updated": "2025-06-17", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Flash", "open_weights": false, "reasoning": true, "release_date": "2025-06-17", "temperature": true, "tool_call": true }, "google/gemini-2.5-pro": { "attachment": true, "cost": { "cache_read": 0.31, "input": 1.25, "output": 10 }, "description": "Gemini 2.5 Pro is an AI model provided by fastrouter.", "family": "gemini-pro", "id": "google/gemini-2.5-pro", "knowledge": "2025-01", "last_updated": "2025-06-17", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Pro", "open_weights": false, "reasoning": true, "release_date": "2025-06-17", "temperature": true, "tool_call": true }, "moonshotai/kimi-k2": { "attachment": false, "cost": { "input": 0.55, "output": 2.2 }, "description": "Kimi K2 is an AI model provided by fastrouter.", "family": "kimi", "id": "moonshotai/kimi-k2", "knowledge": "2024-10", "last_updated": "2025-07-11", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2", "open_weights": true, "reasoning": false, "release_date": "2025-07-11", "temperature": true, "tool_call": true }, "openai/gpt-4.1": { "attachment": true, "cost": { "cache_read": 0.5, "input": 2, "output": 8 }, "description": "GPT-4.1 is an AI model provided by fastrouter.", "family": "gpt", "id": "openai/gpt-4.1", "knowledge": "2024-04", "last_updated": "2025-04-14", "limit": { "context": 1047576, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4.1", "open_weights": false, "reasoning": false, "release_date": "2025-04-14", "temperature": true, "tool_call": true }, "openai/gpt-5": { "attachment": true, "cost": { "cache_read": 0.125, "input": 1.25, "output": 10 }, "description": "GPT-5 is an AI model provided by fastrouter.", "family": "gpt", "id": "openai/gpt-5", "knowledge": "2024-10-01", "last_updated": "2025-08-07", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "temperature": true, "tool_call": true }, "openai/gpt-5-mini": { "attachment": true, "cost": { "cache_read": 0.025, "input": 0.25, "output": 2 }, "description": "GPT-5 Mini is an AI model provided by fastrouter.", "family": "gpt-mini", "id": "openai/gpt-5-mini", "knowledge": "2024-10-01", "last_updated": "2025-08-07", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5 Mini", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "temperature": true, "tool_call": true }, "openai/gpt-5-nano": { "attachment": true, "cost": { "cache_read": 0.005, "input": 0.05, "output": 0.4 }, "description": "GPT-5 Nano is an AI model provided by fastrouter.", "family": "gpt-nano", "id": "openai/gpt-5-nano", "knowledge": "2024-10-01", "last_updated": "2025-08-07", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5 Nano", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "temperature": true, "tool_call": true }, "openai/gpt-oss-120b": { "attachment": false, "cost": { "input": 0.15, "output": 0.6 }, "description": "GPT OSS 120B is an AI model provided by fastrouter.", "family": "gpt-oss", "id": "openai/gpt-oss-120b", "last_updated": "2025-08-05", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT OSS 120B", "open_weights": true, "reasoning": true, "release_date": "2025-08-05", "temperature": true, "tool_call": true }, "openai/gpt-oss-20b": { "attachment": false, "cost": { "input": 0.05, "output": 0.2 }, "description": "GPT OSS 20B is an AI model provided by fastrouter.", "family": "gpt-oss", "id": "openai/gpt-oss-20b", "last_updated": "2025-08-05", "limit": { "context": 131072, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT OSS 20B", "open_weights": true, "reasoning": true, "release_date": "2025-08-05", "temperature": true, "tool_call": true }, "qwen/qwen3-coder": { "attachment": false, "cost": { "input": 0.3, "output": 1.2 }, "description": "Qwen3 Coder is an AI model provided by fastrouter.", "family": "qwen", "id": "qwen/qwen3-coder", "knowledge": "2025-04", "last_updated": "2025-07-23", "limit": { "context": 262144, "output": 66536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Coder", "open_weights": true, "reasoning": false, "release_date": "2025-07-23", "temperature": true, "tool_call": true }, "x-ai/grok-4": { "attachment": false, "cost": { "cache_read": 0.75, "cache_write": 15, "input": 3, "output": 15 }, "description": "Grok 4 is an AI model provided by fastrouter.", "family": "grok", "id": "x-ai/grok-4", "knowledge": "2025-07", "last_updated": "2025-07-09", "limit": { "context": 256000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok 4", "open_weights": false, "reasoning": true, "release_date": "2025-07-09", "temperature": true, "tool_call": true }, "z-ai/glm-5": { "attachment": false, "cost": { "input": 0.95, "output": 3.15 }, "description": "GLM-5 is an AI model provided by fastrouter.", "family": "glm", "id": "z-ai/glm-5", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-02-11", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5", "open_weights": true, "reasoning": true, "release_date": "2026-02-11", "temperature": true, "tool_call": true } }, "name": "FastRouter", "npm": "@ai-sdk/openai-compatible" }, "firepass": { "api": "https://api.fireworks.ai/inference/v1/", "doc": "https://docs.fireworks.ai/firepass", "env": [ "FIREPASS_API_KEY" ], "iconURL": "https://models.dev/logos/firepass.svg", "id": "firepass", "models": { "accounts/fireworks/routers/kimi-k2p6-turbo": { "attachment": false, "cost": { "cache_read": 0, "input": 0, "output": 0 }, "description": "Kimi K2.6 Turbo is an AI model provided by firepass.", "family": "kimi-thinking", "id": "accounts/fireworks/routers/kimi-k2p6-turbo", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-17", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Kimi K2.6 Turbo", "open_weights": true, "reasoning": true, "release_date": "2026-04-17", "temperature": true, "tool_call": true } }, "name": "Fireworks (Firepass)", "npm": "@ai-sdk/openai-compatible" }, "fireworks-ai": { "api": "https://api.fireworks.ai/inference/v1/", "doc": "https://fireworks.ai/docs/", "env": [ "FIREWORKS_API_KEY" ], "iconURL": "https://models.dev/logos/fireworks-ai.svg", "id": "fireworks-ai", "lobeIcon": "Fireworks", "models": { "accounts/fireworks/models/deepseek-v3p1": { "attachment": false, "cost": { "input": 0.56, "output": 1.68 }, "description": "DeepSeek V3.1 is an AI model provided by fireworks-ai.", "family": "deepseek", "id": "accounts/fireworks/models/deepseek-v3p1", "knowledge": "2025-07", "last_updated": "2025-08-21", "limit": { "context": 163840, "output": 163840 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3.1", "open_weights": true, "reasoning": true, "release_date": "2025-08-21", "temperature": true, "tool_call": true }, "accounts/fireworks/models/deepseek-v3p2": { "attachment": false, "cost": { "cache_read": 0.28, "input": 0.56, "output": 1.68 }, "description": "DeepSeek V3.2 is an AI model provided by fireworks-ai.", "family": "deepseek", "id": "accounts/fireworks/models/deepseek-v3p2", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-09", "last_updated": "2025-12-01", "limit": { "context": 160000, "output": 160000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3.2", "open_weights": true, "reasoning": true, "release_date": "2025-12-01", "temperature": true, "tool_call": true }, "accounts/fireworks/models/deepseek-v4-pro": { "attachment": false, "cost": { "cache_read": 0.15, "input": 1.74, "output": 3.48 }, "description": "DeepSeek V4 Pro is an AI model provided by fireworks-ai.", "family": "deepseek-thinking", "id": "accounts/fireworks/models/deepseek-v4-pro", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-05", "last_updated": "2026-04-24", "limit": { "context": 1000000, "output": 384000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V4 Pro", "open_weights": true, "reasoning": true, "release_date": "2026-04-24", "structured_output": true, "temperature": true, "tool_call": true }, "accounts/fireworks/models/glm-4p5": { "attachment": false, "cost": { "input": 0.55, "output": 2.19 }, "description": "GLM 4.5 is an AI model provided by fireworks-ai.", "family": "glm", "id": "accounts/fireworks/models/glm-4p5", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-04", "last_updated": "2025-07-29", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.5", "open_weights": true, "reasoning": true, "release_date": "2025-07-29", "temperature": true, "tool_call": true }, "accounts/fireworks/models/glm-4p5-air": { "attachment": false, "cost": { "input": 0.22, "output": 0.88 }, "description": "GLM 4.5 Air is an AI model provided by fireworks-ai.", "family": "glm-air", "id": "accounts/fireworks/models/glm-4p5-air", "knowledge": "2025-04", "last_updated": "2025-08-01", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.5 Air", "open_weights": true, "reasoning": true, "release_date": "2025-08-01", "temperature": true, "tool_call": true }, "accounts/fireworks/models/glm-4p7": { "attachment": false, "cost": { "cache_read": 0.3, "input": 0.6, "output": 2.2 }, "description": "GLM 4.7 is an AI model provided by fireworks-ai.", "family": "glm", "id": "accounts/fireworks/models/glm-4p7", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-04", "last_updated": "2025-12-22", "limit": { "context": 198000, "output": 198000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.7", "open_weights": true, "reasoning": true, "release_date": "2025-12-22", "temperature": true, "tool_call": true }, "accounts/fireworks/models/glm-5": { "attachment": false, "cost": { "cache_read": 0.5, "input": 1, "output": 3.2 }, "description": "GLM 5 is an AI model provided by fireworks-ai.", "family": "glm", "id": "accounts/fireworks/models/glm-5", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-02-11", "limit": { "context": 202752, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 5", "open_weights": true, "reasoning": true, "release_date": "2026-02-11", "temperature": true, "tool_call": true }, "accounts/fireworks/models/glm-5p1": { "attachment": false, "cost": { "cache_read": 0.26, "input": 1.4, "output": 4.4 }, "description": "GLM 5.1 is an AI model provided by fireworks-ai.", "family": "glm", "id": "accounts/fireworks/models/glm-5p1", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-01", "limit": { "context": 202800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 5.1", "open_weights": true, "reasoning": true, "release_date": "2026-04-01", "temperature": true, "tool_call": true }, "accounts/fireworks/models/gpt-oss-120b": { "attachment": false, "cost": { "input": 0.15, "output": 0.6 }, "description": "GPT OSS 120B is an AI model provided by fireworks-ai.", "family": "gpt-oss", "id": "accounts/fireworks/models/gpt-oss-120b", "last_updated": "2025-08-05", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT OSS 120B", "open_weights": true, "reasoning": true, "release_date": "2025-08-05", "temperature": true, "tool_call": true }, "accounts/fireworks/models/gpt-oss-20b": { "attachment": false, "cost": { "input": 0.05, "output": 0.2 }, "description": "GPT OSS 20B is an AI model provided by fireworks-ai.", "family": "gpt-oss", "id": "accounts/fireworks/models/gpt-oss-20b", "last_updated": "2025-08-05", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT OSS 20B", "open_weights": true, "reasoning": true, "release_date": "2025-08-05", "temperature": true, "tool_call": true }, "accounts/fireworks/models/kimi-k2-instruct": { "attachment": false, "cost": { "input": 1, "output": 3 }, "description": "Kimi K2 Instruct is an AI model provided by fireworks-ai.", "family": "kimi", "id": "accounts/fireworks/models/kimi-k2-instruct", "knowledge": "2024-10", "last_updated": "2025-07-11", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-07-11", "temperature": true, "tool_call": true }, "accounts/fireworks/models/kimi-k2-thinking": { "attachment": false, "cost": { "cache_read": 0.3, "input": 0.6, "output": 2.5 }, "description": "Kimi K2 Thinking is an AI model provided by fireworks-ai.", "family": "kimi-thinking", "id": "accounts/fireworks/models/kimi-k2-thinking", "interleaved": { "field": "reasoning_content" }, "last_updated": "2025-11-06", "limit": { "context": 256000, "output": 256000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 Thinking", "open_weights": true, "reasoning": true, "release_date": "2025-11-06", "temperature": true, "tool_call": true }, "accounts/fireworks/models/kimi-k2p5": { "attachment": false, "cost": { "cache_read": 0.1, "input": 0.6, "output": 3 }, "description": "Kimi K2.5 is an AI model provided by fireworks-ai.", "family": "kimi-thinking", "id": "accounts/fireworks/models/kimi-k2p5", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-01", "last_updated": "2026-01-27", "limit": { "context": 256000, "output": 256000 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Kimi K2.5", "open_weights": true, "reasoning": true, "release_date": "2026-01-27", "temperature": true, "tool_call": true }, "accounts/fireworks/models/kimi-k2p6": { "attachment": false, "cost": { "cache_read": 0.16, "input": 0.95, "output": 4 }, "description": "Kimi K2.6 is an AI model provided by fireworks-ai.", "family": "kimi-thinking", "id": "accounts/fireworks/models/kimi-k2p6", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-17", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Kimi K2.6", "open_weights": true, "reasoning": true, "release_date": "2026-04-17", "temperature": true, "tool_call": true }, "accounts/fireworks/models/minimax-m2p1": { "attachment": false, "cost": { "cache_read": 0.03, "input": 0.3, "output": 1.2 }, "description": "MiniMax-M2.1 is an AI model provided by fireworks-ai.", "family": "minimax", "id": "accounts/fireworks/models/minimax-m2p1", "interleaved": { "field": "reasoning_content" }, "last_updated": "2025-12-23", "limit": { "context": 200000, "output": 200000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.1", "open_weights": true, "reasoning": true, "release_date": "2025-12-23", "temperature": true, "tool_call": true }, "accounts/fireworks/models/minimax-m2p5": { "attachment": false, "cost": { "cache_read": 0.03, "input": 0.3, "output": 1.2 }, "description": "MiniMax-M2.5 is an AI model provided by fireworks-ai.", "family": "minimax", "id": "accounts/fireworks/models/minimax-m2p5", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-02-12", "limit": { "context": 196608, "output": 196608 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.5", "open_weights": true, "reasoning": true, "release_date": "2026-02-12", "temperature": true, "tool_call": true }, "accounts/fireworks/models/minimax-m2p7": { "attachment": false, "cost": { "cache_read": 0.03, "input": 0.3, "output": 1.2 }, "description": "MiniMax-M2.7 is an AI model provided by fireworks-ai.", "family": "minimax", "id": "accounts/fireworks/models/minimax-m2p7", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-12", "limit": { "context": 196608, "output": 196608 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.7", "open_weights": true, "reasoning": true, "release_date": "2026-04-12", "temperature": true, "tool_call": true }, "accounts/fireworks/models/qwen3p6-plus": { "attachment": true, "cost": { "cache_read": 0.1, "input": 0.5, "output": 3 }, "description": "Qwen 3.6 Plus is an AI model provided by fireworks-ai.", "family": "qwen", "id": "accounts/fireworks/models/qwen3p6-plus", "last_updated": "2026-04-04", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen 3.6 Plus", "open_weights": false, "reasoning": true, "release_date": "2026-04-04", "temperature": true, "tool_call": true }, "accounts/fireworks/routers/kimi-k2p5-turbo": { "attachment": false, "cost": { "cache_read": 0, "input": 0, "output": 0 }, "description": "Kimi K2.5 Turbo is an AI model provided by fireworks-ai.", "family": "kimi-thinking", "id": "accounts/fireworks/routers/kimi-k2p5-turbo", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-01", "last_updated": "2026-01-27", "limit": { "context": 256000, "output": 256000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Kimi K2.5 Turbo", "open_weights": true, "reasoning": true, "release_date": "2026-01-27", "temperature": true, "tool_call": true } }, "name": "Fireworks AI", "npm": "@ai-sdk/openai-compatible" }, "friendli": { "api": "https://api.friendli.ai/serverless/v1", "doc": "https://friendli.ai/docs/guides/serverless_endpoints/introduction", "env": [ "FRIENDLI_TOKEN" ], "iconURL": "https://models.dev/logos/friendli.svg", "id": "friendli", "models": { "MiniMaxAI/MiniMax-M2.5": { "attachment": false, "cost": { "cache_read": 0.06, "input": 0.3, "output": 1.2 }, "description": "MiniMax-M2.5 is an AI model provided by friendli.", "family": "minimax", "id": "MiniMaxAI/MiniMax-M2.5", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-02-12", "limit": { "context": 196608, "output": 196608 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.5", "open_weights": true, "reasoning": true, "release_date": "2026-02-12", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-235B-A22B-Instruct-2507": { "attachment": false, "cost": { "input": 0.2, "output": 0.8 }, "description": "Qwen3 235B A22B Instruct 2507 is an AI model provided by friendli.", "family": "qwen", "id": "Qwen/Qwen3-235B-A22B-Instruct-2507", "last_updated": "2026-01-29", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 235B A22B Instruct 2507", "open_weights": true, "reasoning": false, "release_date": "2025-07-29", "structured_output": true, "temperature": true, "tool_call": true }, "meta-llama/Llama-3.1-8B-Instruct": { "attachment": false, "cost": { "input": 0.1, "output": 0.1 }, "description": "Llama 3.1 8B Instruct is an AI model provided by friendli.", "family": "llama", "id": "meta-llama/Llama-3.1-8B-Instruct", "last_updated": "2025-12-23", "limit": { "context": 131072, "output": 8000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.1 8B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-08-01", "structured_output": true, "temperature": true, "tool_call": true }, "meta-llama/Llama-3.3-70B-Instruct": { "attachment": false, "cost": { "input": 0.6, "output": 0.6 }, "description": "Llama 3.3 70B Instruct is an AI model provided by friendli.", "family": "llama", "id": "meta-llama/Llama-3.3-70B-Instruct", "last_updated": "2025-12-23", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-08-01", "structured_output": true, "temperature": true, "tool_call": true }, "zai-org/GLM-5": { "attachment": false, "cost": { "cache_read": 0.5, "input": 1, "output": 3.2 }, "description": "GLM-5 is an AI model provided by friendli.", "family": "glm", "id": "zai-org/GLM-5", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-02-12", "limit": { "context": 202752, "output": 202752 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5", "open_weights": true, "reasoning": true, "release_date": "2026-02-12", "structured_output": true, "temperature": true, "tool_call": true }, "zai-org/GLM-5.1": { "attachment": false, "cost": { "cache_read": 0.26, "input": 1.4, "output": 4.4 }, "description": "GLM-5.1 is an AI model provided by friendli.", "family": "glm", "id": "zai-org/GLM-5.1", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-07", "limit": { "context": 202752, "output": 202752 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5.1", "open_weights": true, "reasoning": true, "release_date": "2026-04-07", "structured_output": true, "temperature": true, "tool_call": true } }, "name": "Friendli", "npm": "@ai-sdk/openai-compatible" }, "frogbot": { "api": "https://app.frogbot.ai/api/v1", "doc": "https://docs.frogbot.ai", "env": [ "FROGBOT_API_KEY" ], "iconURL": "https://models.dev/logos/frogbot.svg", "id": "frogbot", "models": { "claude-haiku-4-5": { "attachment": true, "cost": { "cache_read": 0.1, "cache_write": 1.25, "input": 1, "output": 5 }, "description": "Claude Haiku 4.5 is an AI model provided by frogbot.", "family": "claude-haiku", "id": "claude-haiku-4-5", "knowledge": "2025-02-28", "last_updated": "2025-10-15", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Haiku 4.5", "open_weights": false, "reasoning": true, "release_date": "2025-10-15", "temperature": true, "tool_call": true }, "claude-opus-4-6": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "input": 5, "output": 25 }, "description": "Claude Opus 4.6 is an AI model provided by frogbot.", "family": "claude-opus", "id": "claude-opus-4-6", "knowledge": "2025-05-31", "last_updated": "2026-02-05", "limit": { "context": 200000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.6", "open_weights": false, "reasoning": true, "release_date": "2026-02-05", "temperature": true, "tool_call": true }, "claude-opus-4-7": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "input": 5, "output": 25 }, "description": "Claude Opus 4.7 is an AI model provided by frogbot.", "family": "claude-opus", "id": "claude-opus-4-7", "knowledge": "2026-01-31", "last_updated": "2026-04-16", "limit": { "context": 200000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.7", "open_weights": false, "reasoning": true, "release_date": "2026-04-16", "temperature": false, "tool_call": true }, "claude-sonnet-4-6": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 4.6 is an AI model provided by frogbot.", "family": "claude-sonnet", "id": "claude-sonnet-4-6", "knowledge": "2025-08-31", "last_updated": "2026-02-17", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.6", "open_weights": false, "reasoning": true, "release_date": "2026-02-17", "temperature": true, "tool_call": true }, "deepseek-v4-pro": { "attachment": true, "cost": { "cache_read": 0.14, "input": 1.74, "output": 3.48 }, "description": "DeepSeek v4 Pro is an AI model provided by frogbot.", "family": "deepseek", "id": "deepseek-v4-pro", "knowledge": "2026-01", "last_updated": "2026-04-24", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek v4 Pro", "open_weights": false, "reasoning": false, "release_date": "2026-04-24", "temperature": true, "tool_call": true }, "gemini-2.5-flash": { "attachment": true, "cost": { "cache_read": 0.075, "input": 0.3, "output": 2.5 }, "description": "Gemini 2.5 Flash is an AI model provided by frogbot.", "family": "gemini-flash", "id": "gemini-2.5-flash", "knowledge": "2025-01", "last_updated": "2025-07-17", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Flash", "open_weights": false, "reasoning": true, "release_date": "2025-07-17", "temperature": true, "tool_call": true }, "gemini-2.5-pro": { "attachment": true, "cost": { "cache_read": 0.31, "input": 1.25, "output": 10 }, "description": "Gemini 2.5 Pro is an AI model provided by frogbot.", "family": "gemini-pro", "id": "gemini-2.5-pro", "knowledge": "2025-01", "last_updated": "2025-06-05", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Pro", "open_weights": false, "reasoning": true, "release_date": "2025-03-20", "temperature": true, "tool_call": true }, "gemini-3-1-pro-preview": { "attachment": true, "cost": { "cache_read": 0.2, "input": 2, "output": 12 }, "description": "Gemini 3.1 Pro Preview is an AI model provided by frogbot.", "family": "gemini-pro", "id": "gemini-3-1-pro-preview", "knowledge": "2026-01", "last_updated": "2026-02-18", "limit": { "context": 1000000, "output": 64000 }, "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "name": "Gemini 3.1 Pro Preview", "open_weights": false, "reasoning": true, "release_date": "2026-02-18", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-3-flash-preview": { "attachment": true, "cost": { "cache_read": 0.05, "input": 0.5, "output": 3 }, "description": "Gemini 3 Flash Preview is an AI model provided by frogbot.", "family": "gemini-flash", "id": "gemini-3-flash-preview", "knowledge": "2025-01", "last_updated": "2025-12-17", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "name": "Gemini 3 Flash Preview", "open_weights": false, "reasoning": true, "release_date": "2025-12-17", "structured_output": true, "temperature": true, "tool_call": true }, "gpt-4o": { "attachment": true, "cost": { "cache_read": 1.25, "input": 2.5, "output": 10 }, "description": "GPT-4o is an AI model provided by frogbot.", "family": "gpt", "id": "gpt-4o", "knowledge": "2023-09", "last_updated": "2024-08-06", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4o", "open_weights": false, "reasoning": false, "release_date": "2024-05-13", "structured_output": true, "temperature": true, "tool_call": true }, "gpt-5-3-codex": { "attachment": true, "cost": { "cache_read": 0.175, "input": 1.75, "output": 14 }, "description": "GPT-5.3 Codex is an AI model provided by frogbot.", "family": "gpt", "id": "gpt-5-3-codex", "knowledge": "2026-01-31", "last_updated": "2026-02-15", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.3 Codex", "open_weights": false, "reasoning": true, "release_date": "2026-02-15", "temperature": false, "tool_call": true }, "gpt-5-4-mini": { "attachment": true, "cost": { "cache_read": 0.075, "input": 0.75, "output": 4.5 }, "description": "GPT-5.4 Mini is an AI model provided by frogbot.", "family": "gpt-mini", "id": "gpt-5-4-mini", "knowledge": "2025-08-31", "last_updated": "2026-03-17", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.4 Mini", "open_weights": false, "reasoning": true, "release_date": "2026-03-17", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5-4-nano": { "attachment": true, "cost": { "cache_read": 0.02, "input": 0.2, "output": 1.25 }, "description": "GPT-5.4 Nano is an AI model provided by frogbot.", "family": "gpt-nano", "id": "gpt-5-4-nano", "knowledge": "2024-05-30", "last_updated": "2025-08-07", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.4 Nano", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5-5": { "attachment": true, "cost": { "cache_read": 0.25, "input": 2.5, "output": 15 }, "description": "GPT-5.5 is an AI model provided by frogbot.", "family": "gpt", "id": "gpt-5-5", "knowledge": "2025-08-31", "last_updated": "2026-03-05", "limit": { "context": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.5", "open_weights": false, "reasoning": true, "release_date": "2026-03-05", "temperature": false, "tool_call": true }, "gpt-oss-120b": { "attachment": false, "cost": { "input": 0.15, "output": 0.6 }, "description": "GPT OSS 120B is an AI model provided by frogbot.", "family": "gpt-oss", "id": "gpt-oss-120b", "last_updated": "1970-01-01", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT OSS 120B", "open_weights": true, "reasoning": true, "release_date": "1970-01-01", "structured_output": true, "temperature": true, "tool_call": true }, "gpt-oss-20b": { "attachment": false, "cost": { "input": 0.07, "output": 0.2 }, "description": "GPT OSS 20B is an AI model provided by frogbot.", "family": "gpt-oss", "id": "gpt-oss-20b", "last_updated": "1970-01-01", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT OSS 20B", "open_weights": true, "reasoning": true, "release_date": "1970-01-01", "structured_output": true, "temperature": true, "tool_call": true }, "grok-4-1-fast-non-reasoning": { "attachment": true, "cost": { "cache_read": 0.05, "input": 0.2, "output": 0.5 }, "description": "Grok 4.1 Fast (Non-Reasoning) is an AI model provided by frogbot.", "family": "grok", "id": "grok-4-1-fast-non-reasoning", "knowledge": "2025-11", "last_updated": "2025-11-25", "limit": { "context": 2000000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 4.1 Fast (Non-Reasoning)", "open_weights": false, "reasoning": false, "release_date": "2025-11-25", "temperature": true, "tool_call": true }, "grok-4-1-fast-reasoning": { "attachment": true, "cost": { "cache_read": 0.05, "input": 0.2, "output": 0.5 }, "description": "Grok 4.1 Fast (Reasoning) is an AI model provided by frogbot.", "family": "grok", "id": "grok-4-1-fast-reasoning", "knowledge": "2025-11", "last_updated": "2025-11-25", "limit": { "context": 2000000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 4.1 Fast (Reasoning)", "open_weights": false, "reasoning": true, "release_date": "2025-11-25", "temperature": true, "tool_call": true }, "grok-4-3": { "attachment": true, "cost": { "cache_read": 0.2, "input": 1.25, "output": 2.5 }, "description": "Grok 4.3 is an AI model provided by frogbot.", "family": "grok", "id": "grok-4-3", "knowledge": "2024-11", "last_updated": "2026-04-30", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Grok 4.3", "open_weights": false, "reasoning": true, "release_date": "2026-04-30", "structured_output": true, "temperature": true, "tool_call": true }, "grok-code-fast-1": { "attachment": false, "cost": { "cache_read": 0.02, "input": 0.2, "output": 1.5 }, "description": "Grok 4.1 Fast (Reasoning) is an AI model provided by frogbot.", "family": "grok", "id": "grok-code-fast-1", "knowledge": "2023-10", "last_updated": "2025-08-28", "limit": { "context": 256000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok 4.1 Fast (Reasoning)", "open_weights": false, "reasoning": true, "release_date": "2025-08-28", "temperature": true, "tool_call": true }, "kimi-k2-6": { "attachment": false, "cost": { "cache_read": 0.16, "input": 0.95, "output": 4 }, "description": "Kimi-K2.6 is an AI model provided by frogbot.", "id": "kimi-k2-6", "last_updated": "1970-01-01", "limit": { "context": 256000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Kimi-K2.6", "open_weights": false, "reasoning": true, "release_date": "1970-01-01", "structured_output": true, "temperature": true, "tool_call": true }, "kimi-k2.5": { "attachment": false, "cost": { "cache_read": 0.1, "input": 0.6, "output": 3 }, "description": "Kimi-K2.5 is an AI model provided by frogbot.", "id": "kimi-k2.5", "last_updated": "1970-01-01", "limit": { "context": 256000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Kimi-K2.5", "open_weights": false, "reasoning": true, "release_date": "1970-01-01", "structured_output": true, "temperature": true, "tool_call": true }, "minimax-m2-5": { "attachment": true, "cost": { "cache_read": 0.03, "input": 0.3, "output": 1.2 }, "description": "MiniMax-M2.5 is an AI model provided by frogbot.", "family": "minimax", "id": "minimax-m2-5", "knowledge": "2024-09", "last_updated": "2025-02-22", "limit": { "context": 192000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.5", "open_weights": false, "reasoning": false, "release_date": "2025-01-15", "temperature": true, "tool_call": true }, "minimax-m2-7": { "attachment": true, "cost": { "cache_read": 0.06, "input": 0.3, "output": 1.2 }, "description": "MiniMax-M2.7 is an AI model provided by frogbot.", "family": "minimax", "id": "minimax-m2-7", "knowledge": "2024-09", "last_updated": "2026-03-18", "limit": { "context": 192000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.7", "open_weights": false, "reasoning": false, "release_date": "2026-03-18", "temperature": true, "tool_call": true }, "qwen-3-6-plus": { "attachment": true, "cost": { "cache_read": 0.1, "input": 0.5, "output": 3 }, "description": "Qwen 3.6 Plus is an AI model provided by frogbot.", "family": "qwen", "id": "qwen-3-6-plus", "last_updated": "2026-04-03", "limit": { "context": 1000000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Qwen 3.6 Plus", "open_weights": false, "reasoning": true, "release_date": "2026-04-02", "temperature": true, "tool_call": true }, "zai-glm-5-1": { "attachment": true, "cost": { "cache_read": 0.26, "input": 1.4, "output": 4.4 }, "description": "Z.AI GLM-5.1 is an AI model provided by frogbot.", "family": "glm", "id": "zai-glm-5-1", "knowledge": "2024-10", "last_updated": "2025-02-22", "limit": { "context": 198000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Z.AI GLM-5.1", "open_weights": true, "reasoning": false, "release_date": "2025-01-20", "temperature": true, "tool_call": true } }, "name": "FrogBot", "npm": "@ai-sdk/openai-compatible" }, "github-copilot": { "api": "https://api.githubcopilot.com", "doc": "https://docs.github.com/en/copilot", "env": [ "GITHUB_TOKEN" ], "iconURL": "https://models.dev/logos/github-copilot.svg", "id": "github-copilot", "lobeIcon": "GithubCopilot", "models": { "claude-haiku-4.5": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Claude Haiku 4.5 is an AI model provided by github-copilot.", "family": "claude-haiku", "id": "claude-haiku-4.5", "knowledge": "2025-02-28", "last_updated": "2025-10-15", "limit": { "context": 144000, "input": 128000, "output": 32000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Claude Haiku 4.5", "open_weights": false, "reasoning": true, "release_date": "2025-10-15", "temperature": true, "tool_call": true }, "claude-opus-4.5": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Claude Opus 4.5 is an AI model provided by github-copilot.", "family": "claude-opus", "id": "claude-opus-4.5", "knowledge": "2025-03-31", "last_updated": "2025-08-01", "limit": { "context": 160000, "input": 128000, "output": 32000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Claude Opus 4.5", "open_weights": false, "reasoning": true, "release_date": "2025-11-24", "temperature": true, "tool_call": true }, "claude-opus-4.6": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Claude Opus 4.6 is an AI model provided by github-copilot.", "family": "claude-opus", "id": "claude-opus-4.6", "knowledge": "2025-05-31", "last_updated": "2026-02-05", "limit": { "context": 144000, "input": 128000, "output": 64000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Claude Opus 4.6", "open_weights": false, "reasoning": true, "release_date": "2026-02-05", "temperature": true, "tool_call": true }, "claude-opus-4.7": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Claude Opus 4.7 is an AI model provided by github-copilot.", "family": "claude-opus", "id": "claude-opus-4.7", "knowledge": "2026-01-31", "last_updated": "2026-04-16", "limit": { "context": 144000, "input": 128000, "output": 64000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Claude Opus 4.7", "open_weights": false, "reasoning": true, "release_date": "2026-04-16", "temperature": false, "tool_call": true }, "claude-opus-41": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Claude Opus 4.1 is an AI model provided by github-copilot.", "family": "claude-opus", "id": "claude-opus-41", "knowledge": "2025-03-31", "last_updated": "2025-08-05", "limit": { "context": 80000, "output": 16000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Claude Opus 4.1", "open_weights": false, "reasoning": true, "release_date": "2025-08-05", "status": "deprecated", "temperature": true, "tool_call": false }, "claude-sonnet-4": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Claude Sonnet 4 is an AI model provided by github-copilot.", "family": "claude-sonnet", "id": "claude-sonnet-4", "knowledge": "2025-03-31", "last_updated": "2025-05-22", "limit": { "context": 216000, "input": 128000, "output": 16000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Claude Sonnet 4", "open_weights": false, "reasoning": true, "release_date": "2025-05-22", "status": "deprecated", "temperature": true, "tool_call": true }, "claude-sonnet-4.5": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Claude Sonnet 4.5 is an AI model provided by github-copilot.", "family": "claude-sonnet", "id": "claude-sonnet-4.5", "knowledge": "2025-03-31", "last_updated": "2025-09-29", "limit": { "context": 144000, "input": 128000, "output": 32000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.5", "open_weights": false, "reasoning": true, "release_date": "2025-09-29", "temperature": true, "tool_call": true }, "claude-sonnet-4.6": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Claude Sonnet 4.6 is an AI model provided by github-copilot.", "family": "claude-sonnet", "id": "claude-sonnet-4.6", "knowledge": "2025-08-31", "last_updated": "2026-02-17", "limit": { "context": 200000, "input": 128000, "output": 32000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.6", "open_weights": false, "reasoning": true, "release_date": "2026-02-17", "temperature": true, "tool_call": true }, "gemini-2.5-pro": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Gemini 2.5 Pro is an AI model provided by github-copilot.", "family": "gemini-pro", "id": "gemini-2.5-pro", "knowledge": "2025-01", "last_updated": "2025-06-05", "limit": { "context": 128000, "input": 128000, "output": 64000 }, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "name": "Gemini 2.5 Pro", "open_weights": false, "reasoning": false, "release_date": "2025-03-20", "temperature": true, "tool_call": true }, "gemini-3-flash-preview": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Gemini 3 Flash is an AI model provided by github-copilot.", "family": "gemini-flash", "id": "gemini-3-flash-preview", "knowledge": "2025-01", "last_updated": "2025-12-17", "limit": { "context": 128000, "input": 128000, "output": 64000 }, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "name": "Gemini 3 Flash", "open_weights": false, "reasoning": true, "release_date": "2025-12-17", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-3-pro-preview": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Gemini 3 Pro Preview is an AI model provided by github-copilot.", "family": "gemini-pro", "id": "gemini-3-pro-preview", "knowledge": "2025-01", "last_updated": "2025-11-18", "limit": { "context": 128000, "input": 128000, "output": 64000 }, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "name": "Gemini 3 Pro Preview", "open_weights": false, "reasoning": true, "release_date": "2025-11-18", "status": "deprecated", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-3.1-pro-preview": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Gemini 3.1 Pro Preview is an AI model provided by github-copilot.", "family": "gemini-pro", "id": "gemini-3.1-pro-preview", "knowledge": "2025-01", "last_updated": "2026-02-19", "limit": { "context": 128000, "input": 128000, "output": 64000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemini 3.1 Pro Preview", "open_weights": false, "reasoning": true, "release_date": "2026-02-19", "structured_output": true, "temperature": true, "tool_call": true }, "gpt-4.1": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "GPT-4.1 is an AI model provided by github-copilot.", "family": "gpt", "id": "gpt-4.1", "knowledge": "2024-04", "last_updated": "2025-04-14", "limit": { "context": 128000, "input": 64000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4.1", "open_weights": false, "reasoning": false, "release_date": "2025-04-14", "temperature": true, "tool_call": true }, "gpt-4o": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "GPT-4o is an AI model provided by github-copilot.", "family": "gpt", "id": "gpt-4o", "knowledge": "2023-09", "last_updated": "2024-05-13", "limit": { "context": 128000, "input": 64000, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4o", "open_weights": false, "reasoning": false, "release_date": "2024-05-13", "temperature": true, "tool_call": true }, "gpt-5": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "GPT-5 is an AI model provided by github-copilot.", "family": "gpt", "id": "gpt-5", "knowledge": "2024-10", "last_updated": "2025-08-07", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "status": "deprecated", "temperature": true, "tool_call": true }, "gpt-5-mini": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "GPT-5-mini is an AI model provided by github-copilot.", "family": "gpt-mini", "id": "gpt-5-mini", "knowledge": "2024-06", "last_updated": "2025-08-13", "limit": { "context": 264000, "input": 128000, "output": 64000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5-mini", "open_weights": false, "reasoning": true, "release_date": "2025-08-13", "temperature": true, "tool_call": true }, "gpt-5.1": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "GPT-5.1 is an AI model provided by github-copilot.", "family": "gpt", "id": "gpt-5.1", "knowledge": "2024-09-30", "last_updated": "2025-11-13", "limit": { "context": 264000, "input": 128000, "output": 64000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.1", "open_weights": false, "reasoning": true, "release_date": "2025-11-13", "status": "deprecated", "temperature": false, "tool_call": true }, "gpt-5.1-codex": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "GPT-5.1-Codex is an AI model provided by github-copilot.", "family": "gpt-codex", "id": "gpt-5.1-codex", "knowledge": "2024-09-30", "last_updated": "2025-11-13", "limit": { "context": 400000, "input": 128000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.1-Codex", "open_weights": false, "reasoning": true, "release_date": "2025-11-13", "status": "deprecated", "temperature": false, "tool_call": true }, "gpt-5.1-codex-max": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "GPT-5.1-Codex-max is an AI model provided by github-copilot.", "family": "gpt-codex", "id": "gpt-5.1-codex-max", "knowledge": "2024-09-30", "last_updated": "2025-12-04", "limit": { "context": 400000, "input": 128000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.1-Codex-max", "open_weights": false, "reasoning": true, "release_date": "2025-12-04", "status": "deprecated", "temperature": false, "tool_call": true }, "gpt-5.1-codex-mini": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "GPT-5.1-Codex-mini is an AI model provided by github-copilot.", "family": "gpt-codex", "id": "gpt-5.1-codex-mini", "knowledge": "2024-09-30", "last_updated": "2025-11-13", "limit": { "context": 400000, "input": 128000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.1-Codex-mini", "open_weights": false, "reasoning": true, "release_date": "2025-11-13", "status": "deprecated", "temperature": false, "tool_call": true }, "gpt-5.2": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "GPT-5.2 is an AI model provided by github-copilot.", "family": "gpt", "id": "gpt-5.2", "knowledge": "2025-08-31", "last_updated": "2025-12-11", "limit": { "context": 264000, "input": 128000, "output": 64000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.2", "open_weights": false, "reasoning": true, "release_date": "2025-12-11", "temperature": false, "tool_call": true }, "gpt-5.2-codex": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "GPT-5.2-Codex is an AI model provided by github-copilot.", "family": "gpt-codex", "id": "gpt-5.2-codex", "knowledge": "2025-08-31", "last_updated": "2025-12-11", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.2-Codex", "open_weights": false, "reasoning": true, "release_date": "2025-12-11", "temperature": false, "tool_call": true }, "gpt-5.3-codex": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "GPT-5.3-Codex is an AI model provided by github-copilot.", "family": "gpt-codex", "id": "gpt-5.3-codex", "knowledge": "2025-08-31", "last_updated": "2026-02-24", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.3-Codex", "open_weights": false, "reasoning": true, "release_date": "2026-02-24", "temperature": false, "tool_call": true }, "gpt-5.4": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "GPT-5.4 is an AI model provided by github-copilot.", "family": "gpt", "id": "gpt-5.4", "knowledge": "2025-08-31", "last_updated": "2026-03-05", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.4", "open_weights": false, "reasoning": true, "release_date": "2026-03-05", "temperature": false, "tool_call": true }, "gpt-5.4-mini": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "GPT-5.4 Mini is an AI model provided by github-copilot.", "family": "gpt-mini", "id": "gpt-5.4-mini", "knowledge": "2025-08-31", "last_updated": "2026-03-17", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.4 Mini", "open_weights": false, "reasoning": true, "release_date": "2026-03-17", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.5": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "GPT-5.5 is an AI model provided by github-copilot.", "family": "gpt", "id": "gpt-5.5", "knowledge": "2025-08-31", "last_updated": "2026-04-22", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.5", "open_weights": false, "reasoning": true, "release_date": "2026-04-22", "temperature": false, "tool_call": true }, "grok-code-fast-1": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Grok Code Fast 1 is an AI model provided by github-copilot.", "family": "grok", "id": "grok-code-fast-1", "knowledge": "2025-08", "last_updated": "2025-08-27", "limit": { "context": 128000, "input": 128000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok Code Fast 1", "open_weights": false, "reasoning": true, "release_date": "2025-08-27", "temperature": true, "tool_call": true } }, "name": "GitHub Copilot", "npm": "@ai-sdk/openai-compatible" }, "github-models": { "api": "https://models.github.ai/inference", "doc": "https://docs.github.com/en/github-models", "env": [ "GITHUB_TOKEN" ], "iconURL": "https://models.dev/logos/github-models.svg", "id": "github-models", "lobeIcon": "GithubCopilot", "models": { "ai21-labs/ai21-jamba-1.5-large": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "AI21 Jamba 1.5 Large is an AI model provided by github-models.", "family": "jamba", "id": "ai21-labs/ai21-jamba-1.5-large", "knowledge": "2024-03", "last_updated": "2024-08-29", "limit": { "context": 256000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "AI21 Jamba 1.5 Large", "open_weights": false, "reasoning": true, "release_date": "2024-08-29", "temperature": true, "tool_call": true }, "ai21-labs/ai21-jamba-1.5-mini": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "AI21 Jamba 1.5 Mini is an AI model provided by github-models.", "family": "jamba", "id": "ai21-labs/ai21-jamba-1.5-mini", "knowledge": "2024-03", "last_updated": "2024-08-29", "limit": { "context": 256000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "AI21 Jamba 1.5 Mini", "open_weights": false, "reasoning": true, "release_date": "2024-08-29", "temperature": true, "tool_call": true }, "cohere/cohere-command-a": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Cohere Command A is an AI model provided by github-models.", "family": "command-a", "id": "cohere/cohere-command-a", "knowledge": "2024-03", "last_updated": "2024-11-01", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Cohere Command A", "open_weights": false, "reasoning": true, "release_date": "2024-11-01", "temperature": true, "tool_call": true }, "cohere/cohere-command-r": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Cohere Command R is an AI model provided by github-models.", "family": "command-r", "id": "cohere/cohere-command-r", "knowledge": "2024-03", "last_updated": "2024-08-01", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Cohere Command R", "open_weights": false, "reasoning": true, "release_date": "2024-03-11", "temperature": true, "tool_call": true }, "cohere/cohere-command-r-08-2024": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Cohere Command R 08-2024 is an AI model provided by github-models.", "family": "command-r", "id": "cohere/cohere-command-r-08-2024", "knowledge": "2024-03", "last_updated": "2024-08-01", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Cohere Command R 08-2024", "open_weights": false, "reasoning": false, "release_date": "2024-08-01", "temperature": true, "tool_call": true }, "cohere/cohere-command-r-plus": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Cohere Command R+ is an AI model provided by github-models.", "family": "command-r", "id": "cohere/cohere-command-r-plus", "knowledge": "2024-03", "last_updated": "2024-08-01", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Cohere Command R+", "open_weights": false, "reasoning": false, "release_date": "2024-04-04", "temperature": true, "tool_call": true }, "cohere/cohere-command-r-plus-08-2024": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Cohere Command R+ 08-2024 is an AI model provided by github-models.", "family": "command-r", "id": "cohere/cohere-command-r-plus-08-2024", "knowledge": "2024-03", "last_updated": "2024-08-01", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Cohere Command R+ 08-2024", "open_weights": false, "reasoning": false, "release_date": "2024-08-01", "temperature": true, "tool_call": true }, "core42/jais-30b-chat": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "JAIS 30b Chat is an AI model provided by github-models.", "family": "jais", "id": "core42/jais-30b-chat", "knowledge": "2023-03", "last_updated": "2023-08-30", "limit": { "context": 8192, "output": 2048 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "JAIS 30b Chat", "open_weights": true, "reasoning": true, "release_date": "2023-08-30", "temperature": true, "tool_call": true }, "deepseek/deepseek-r1": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "DeepSeek-R1 is an AI model provided by github-models.", "family": "deepseek-thinking", "id": "deepseek/deepseek-r1", "knowledge": "2024-06", "last_updated": "2025-01-20", "limit": { "context": 65536, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek-R1", "open_weights": true, "reasoning": true, "release_date": "2025-01-20", "temperature": true, "tool_call": true }, "deepseek/deepseek-r1-0528": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "DeepSeek-R1-0528 is an AI model provided by github-models.", "family": "deepseek-thinking", "id": "deepseek/deepseek-r1-0528", "knowledge": "2024-06", "last_updated": "2025-05-28", "limit": { "context": 65536, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek-R1-0528", "open_weights": true, "reasoning": true, "release_date": "2025-05-28", "temperature": true, "tool_call": true }, "deepseek/deepseek-v3-0324": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "DeepSeek-V3-0324 is an AI model provided by github-models.", "family": "deepseek", "id": "deepseek/deepseek-v3-0324", "knowledge": "2024-06", "last_updated": "2025-03-24", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek-V3-0324", "open_weights": true, "reasoning": true, "release_date": "2025-03-24", "temperature": true, "tool_call": true }, "meta/llama-3.2-11b-vision-instruct": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Llama-3.2-11B-Vision-Instruct is an AI model provided by github-models.", "family": "llama", "id": "meta/llama-3.2-11b-vision-instruct", "knowledge": "2023-12", "last_updated": "2024-09-25", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text", "image", "audio" ], "output": [ "text" ] }, "name": "Llama-3.2-11B-Vision-Instruct", "open_weights": true, "reasoning": true, "release_date": "2024-09-25", "temperature": true, "tool_call": true }, "meta/llama-3.2-90b-vision-instruct": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Llama-3.2-90B-Vision-Instruct is an AI model provided by github-models.", "family": "llama", "id": "meta/llama-3.2-90b-vision-instruct", "knowledge": "2023-12", "last_updated": "2024-09-25", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text", "image", "audio" ], "output": [ "text" ] }, "name": "Llama-3.2-90B-Vision-Instruct", "open_weights": true, "reasoning": true, "release_date": "2024-09-25", "temperature": true, "tool_call": true }, "meta/llama-3.3-70b-instruct": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Llama-3.3-70B-Instruct is an AI model provided by github-models.", "family": "llama", "id": "meta/llama-3.3-70b-instruct", "knowledge": "2023-12", "last_updated": "2024-12-06", "limit": { "context": 128000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama-3.3-70B-Instruct", "open_weights": true, "reasoning": true, "release_date": "2024-12-06", "temperature": true, "tool_call": true }, "meta/llama-4-maverick-17b-128e-instruct-fp8": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Llama 4 Maverick 17B 128E Instruct FP8 is an AI model provided by github-models.", "family": "llama", "id": "meta/llama-4-maverick-17b-128e-instruct-fp8", "knowledge": "2024-12", "last_updated": "2025-01-31", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Llama 4 Maverick 17B 128E Instruct FP8", "open_weights": true, "reasoning": true, "release_date": "2025-01-31", "temperature": true, "tool_call": true }, "meta/llama-4-scout-17b-16e-instruct": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Llama 4 Scout 17B 16E Instruct is an AI model provided by github-models.", "family": "llama", "id": "meta/llama-4-scout-17b-16e-instruct", "knowledge": "2024-12", "last_updated": "2025-01-31", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Llama 4 Scout 17B 16E Instruct", "open_weights": true, "reasoning": true, "release_date": "2025-01-31", "temperature": true, "tool_call": true }, "meta/meta-llama-3-70b-instruct": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Meta-Llama-3-70B-Instruct is an AI model provided by github-models.", "family": "llama", "id": "meta/meta-llama-3-70b-instruct", "knowledge": "2023-12", "last_updated": "2024-04-18", "limit": { "context": 8192, "output": 2048 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Meta-Llama-3-70B-Instruct", "open_weights": true, "reasoning": true, "release_date": "2024-04-18", "temperature": true, "tool_call": true }, "meta/meta-llama-3-8b-instruct": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Meta-Llama-3-8B-Instruct is an AI model provided by github-models.", "family": "llama", "id": "meta/meta-llama-3-8b-instruct", "knowledge": "2023-12", "last_updated": "2024-04-18", "limit": { "context": 8192, "output": 2048 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Meta-Llama-3-8B-Instruct", "open_weights": true, "reasoning": true, "release_date": "2024-04-18", "temperature": true, "tool_call": true }, "meta/meta-llama-3.1-405b-instruct": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Meta-Llama-3.1-405B-Instruct is an AI model provided by github-models.", "family": "llama", "id": "meta/meta-llama-3.1-405b-instruct", "knowledge": "2023-12", "last_updated": "2024-07-23", "limit": { "context": 128000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Meta-Llama-3.1-405B-Instruct", "open_weights": true, "reasoning": true, "release_date": "2024-07-23", "temperature": true, "tool_call": true }, "meta/meta-llama-3.1-70b-instruct": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Meta-Llama-3.1-70B-Instruct is an AI model provided by github-models.", "family": "llama", "id": "meta/meta-llama-3.1-70b-instruct", "knowledge": "2023-12", "last_updated": "2024-07-23", "limit": { "context": 128000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Meta-Llama-3.1-70B-Instruct", "open_weights": true, "reasoning": true, "release_date": "2024-07-23", "temperature": true, "tool_call": true }, "meta/meta-llama-3.1-8b-instruct": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Meta-Llama-3.1-8B-Instruct is an AI model provided by github-models.", "family": "llama", "id": "meta/meta-llama-3.1-8b-instruct", "knowledge": "2023-12", "last_updated": "2024-07-23", "limit": { "context": 128000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Meta-Llama-3.1-8B-Instruct", "open_weights": true, "reasoning": true, "release_date": "2024-07-23", "temperature": true, "tool_call": true }, "microsoft/mai-ds-r1": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "MAI-DS-R1 is an AI model provided by github-models.", "family": "mai", "id": "microsoft/mai-ds-r1", "knowledge": "2024-06", "last_updated": "2025-01-20", "limit": { "context": 65536, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MAI-DS-R1", "open_weights": false, "reasoning": true, "release_date": "2025-01-20", "temperature": true, "tool_call": true }, "microsoft/phi-3-medium-128k-instruct": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Phi-3-medium instruct (128k) is an AI model provided by github-models.", "family": "phi", "id": "microsoft/phi-3-medium-128k-instruct", "knowledge": "2023-10", "last_updated": "2024-04-23", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Phi-3-medium instruct (128k)", "open_weights": true, "reasoning": true, "release_date": "2024-04-23", "temperature": true, "tool_call": true }, "microsoft/phi-3-medium-4k-instruct": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Phi-3-medium instruct (4k) is an AI model provided by github-models.", "family": "phi", "id": "microsoft/phi-3-medium-4k-instruct", "knowledge": "2023-10", "last_updated": "2024-04-23", "limit": { "context": 4096, "output": 1024 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Phi-3-medium instruct (4k)", "open_weights": true, "reasoning": true, "release_date": "2024-04-23", "temperature": true, "tool_call": true }, "microsoft/phi-3-mini-128k-instruct": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Phi-3-mini instruct (128k) is an AI model provided by github-models.", "family": "phi", "id": "microsoft/phi-3-mini-128k-instruct", "knowledge": "2023-10", "last_updated": "2024-04-23", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Phi-3-mini instruct (128k)", "open_weights": true, "reasoning": true, "release_date": "2024-04-23", "temperature": true, "tool_call": true }, "microsoft/phi-3-mini-4k-instruct": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Phi-3-mini instruct (4k) is an AI model provided by github-models.", "family": "phi", "id": "microsoft/phi-3-mini-4k-instruct", "knowledge": "2023-10", "last_updated": "2024-04-23", "limit": { "context": 4096, "output": 1024 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Phi-3-mini instruct (4k)", "open_weights": true, "reasoning": true, "release_date": "2024-04-23", "temperature": true, "tool_call": true }, "microsoft/phi-3-small-128k-instruct": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Phi-3-small instruct (128k) is an AI model provided by github-models.", "family": "phi", "id": "microsoft/phi-3-small-128k-instruct", "knowledge": "2023-10", "last_updated": "2024-04-23", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Phi-3-small instruct (128k)", "open_weights": true, "reasoning": true, "release_date": "2024-04-23", "temperature": true, "tool_call": true }, "microsoft/phi-3-small-8k-instruct": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Phi-3-small instruct (8k) is an AI model provided by github-models.", "family": "phi", "id": "microsoft/phi-3-small-8k-instruct", "knowledge": "2023-10", "last_updated": "2024-04-23", "limit": { "context": 8192, "output": 2048 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Phi-3-small instruct (8k)", "open_weights": true, "reasoning": true, "release_date": "2024-04-23", "temperature": true, "tool_call": true }, "microsoft/phi-3.5-mini-instruct": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Phi-3.5-mini instruct (128k) is an AI model provided by github-models.", "family": "phi", "id": "microsoft/phi-3.5-mini-instruct", "knowledge": "2023-10", "last_updated": "2024-08-20", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Phi-3.5-mini instruct (128k)", "open_weights": true, "reasoning": true, "release_date": "2024-08-20", "temperature": true, "tool_call": true }, "microsoft/phi-3.5-moe-instruct": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Phi-3.5-MoE instruct (128k) is an AI model provided by github-models.", "family": "phi", "id": "microsoft/phi-3.5-moe-instruct", "knowledge": "2023-10", "last_updated": "2024-08-20", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Phi-3.5-MoE instruct (128k)", "open_weights": true, "reasoning": true, "release_date": "2024-08-20", "temperature": true, "tool_call": true }, "microsoft/phi-3.5-vision-instruct": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Phi-3.5-vision instruct (128k) is an AI model provided by github-models.", "family": "phi", "id": "microsoft/phi-3.5-vision-instruct", "knowledge": "2023-10", "last_updated": "2024-08-20", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Phi-3.5-vision instruct (128k)", "open_weights": true, "reasoning": true, "release_date": "2024-08-20", "temperature": true, "tool_call": true }, "microsoft/phi-4": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Phi-4 is an AI model provided by github-models.", "family": "phi", "id": "microsoft/phi-4", "knowledge": "2023-10", "last_updated": "2024-12-11", "limit": { "context": 16000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Phi-4", "open_weights": true, "reasoning": true, "release_date": "2024-12-11", "temperature": true, "tool_call": true }, "microsoft/phi-4-mini-instruct": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Phi-4-mini-instruct is an AI model provided by github-models.", "family": "phi", "id": "microsoft/phi-4-mini-instruct", "knowledge": "2023-10", "last_updated": "2024-12-11", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Phi-4-mini-instruct", "open_weights": true, "reasoning": true, "release_date": "2024-12-11", "temperature": true, "tool_call": true }, "microsoft/phi-4-mini-reasoning": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Phi-4-mini-reasoning is an AI model provided by github-models.", "family": "phi", "id": "microsoft/phi-4-mini-reasoning", "knowledge": "2023-10", "last_updated": "2024-12-11", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Phi-4-mini-reasoning", "open_weights": true, "reasoning": true, "release_date": "2024-12-11", "temperature": true, "tool_call": true }, "microsoft/phi-4-multimodal-instruct": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Phi-4-multimodal-instruct is an AI model provided by github-models.", "family": "phi", "id": "microsoft/phi-4-multimodal-instruct", "knowledge": "2023-10", "last_updated": "2024-12-11", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text", "image", "audio" ], "output": [ "text" ] }, "name": "Phi-4-multimodal-instruct", "open_weights": true, "reasoning": true, "release_date": "2024-12-11", "temperature": true, "tool_call": true }, "microsoft/phi-4-reasoning": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Phi-4-Reasoning is an AI model provided by github-models.", "family": "phi", "id": "microsoft/phi-4-reasoning", "knowledge": "2023-10", "last_updated": "2024-12-11", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Phi-4-Reasoning", "open_weights": true, "reasoning": true, "release_date": "2024-12-11", "temperature": true, "tool_call": true }, "mistral-ai/codestral-2501": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Codestral 25.01 is an AI model provided by github-models.", "family": "codestral", "id": "mistral-ai/codestral-2501", "knowledge": "2024-03", "last_updated": "2025-01-01", "limit": { "context": 32000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Codestral 25.01", "open_weights": false, "reasoning": true, "release_date": "2025-01-01", "temperature": true, "tool_call": true }, "mistral-ai/ministral-3b": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Ministral 3B is an AI model provided by github-models.", "family": "ministral", "id": "mistral-ai/ministral-3b", "knowledge": "2024-03", "last_updated": "2024-10-22", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Ministral 3B", "open_weights": true, "reasoning": true, "release_date": "2024-10-22", "temperature": true, "tool_call": true }, "mistral-ai/mistral-large-2411": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Mistral Large 24.11 is an AI model provided by github-models.", "family": "mistral-large", "id": "mistral-ai/mistral-large-2411", "knowledge": "2024-09", "last_updated": "2024-11-01", "limit": { "context": 128000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral Large 24.11", "open_weights": false, "reasoning": true, "release_date": "2024-11-01", "temperature": true, "tool_call": true }, "mistral-ai/mistral-medium-2505": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Mistral Medium 3 (25.05) is an AI model provided by github-models.", "family": "mistral-medium", "id": "mistral-ai/mistral-medium-2505", "knowledge": "2024-09", "last_updated": "2025-05-01", "limit": { "context": 128000, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Mistral Medium 3 (25.05)", "open_weights": false, "reasoning": true, "release_date": "2025-05-01", "temperature": true, "tool_call": true }, "mistral-ai/mistral-nemo": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Mistral Nemo is an AI model provided by github-models.", "family": "mistral-nemo", "id": "mistral-ai/mistral-nemo", "knowledge": "2024-03", "last_updated": "2024-07-18", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral Nemo", "open_weights": true, "reasoning": true, "release_date": "2024-07-18", "temperature": true, "tool_call": true }, "mistral-ai/mistral-small-2503": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Mistral Small 3.1 is an AI model provided by github-models.", "family": "mistral-small", "id": "mistral-ai/mistral-small-2503", "knowledge": "2024-09", "last_updated": "2025-03-01", "limit": { "context": 128000, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Mistral Small 3.1", "open_weights": false, "reasoning": true, "release_date": "2025-03-01", "temperature": true, "tool_call": true }, "openai/gpt-4.1": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "GPT-4.1 is an AI model provided by github-models.", "family": "gpt", "id": "openai/gpt-4.1", "knowledge": "2024-04", "last_updated": "2025-04-14", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4.1", "open_weights": false, "reasoning": false, "release_date": "2025-04-14", "temperature": true, "tool_call": true }, "openai/gpt-4.1-mini": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "GPT-4.1-mini is an AI model provided by github-models.", "family": "gpt-mini", "id": "openai/gpt-4.1-mini", "knowledge": "2024-04", "last_updated": "2025-04-14", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4.1-mini", "open_weights": false, "reasoning": false, "release_date": "2025-04-14", "temperature": true, "tool_call": true }, "openai/gpt-4.1-nano": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "GPT-4.1-nano is an AI model provided by github-models.", "family": "gpt-nano", "id": "openai/gpt-4.1-nano", "knowledge": "2024-04", "last_updated": "2025-04-14", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4.1-nano", "open_weights": false, "reasoning": false, "release_date": "2025-04-14", "temperature": true, "tool_call": true }, "openai/gpt-4o": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "GPT-4o is an AI model provided by github-models.", "family": "gpt", "id": "openai/gpt-4o", "knowledge": "2023-10", "last_updated": "2024-05-13", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image", "audio" ], "output": [ "text" ] }, "name": "GPT-4o", "open_weights": false, "reasoning": false, "release_date": "2024-05-13", "temperature": true, "tool_call": true }, "openai/gpt-4o-mini": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "GPT-4o mini is an AI model provided by github-models.", "family": "gpt-mini", "id": "openai/gpt-4o-mini", "knowledge": "2023-10", "last_updated": "2024-07-18", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image", "audio" ], "output": [ "text" ] }, "name": "GPT-4o mini", "open_weights": false, "reasoning": false, "release_date": "2024-07-18", "temperature": true, "tool_call": true }, "openai/o1": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "OpenAI o1 is an AI model provided by github-models.", "family": "o", "id": "openai/o1", "knowledge": "2023-10", "last_updated": "2024-12-17", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "OpenAI o1", "open_weights": false, "reasoning": true, "release_date": "2024-09-12", "temperature": false, "tool_call": false }, "openai/o1-mini": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "OpenAI o1-mini is an AI model provided by github-models.", "family": "o-mini", "id": "openai/o1-mini", "knowledge": "2023-10", "last_updated": "2024-12-17", "limit": { "context": 128000, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "OpenAI o1-mini", "open_weights": false, "reasoning": true, "release_date": "2024-09-12", "temperature": false, "tool_call": false }, "openai/o1-preview": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "OpenAI o1-preview is an AI model provided by github-models.", "family": "o", "id": "openai/o1-preview", "knowledge": "2023-10", "last_updated": "2024-09-12", "limit": { "context": 128000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "OpenAI o1-preview", "open_weights": false, "reasoning": true, "release_date": "2024-09-12", "temperature": false, "tool_call": false }, "openai/o3": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "OpenAI o3 is an AI model provided by github-models.", "family": "o", "id": "openai/o3", "knowledge": "2024-04", "last_updated": "2025-01-31", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "OpenAI o3", "open_weights": false, "reasoning": true, "release_date": "2025-01-31", "temperature": false, "tool_call": false }, "openai/o3-mini": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "OpenAI o3-mini is an AI model provided by github-models.", "family": "o-mini", "id": "openai/o3-mini", "knowledge": "2024-04", "last_updated": "2025-01-31", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "OpenAI o3-mini", "open_weights": false, "reasoning": true, "release_date": "2025-01-31", "temperature": false, "tool_call": false }, "openai/o4-mini": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "OpenAI o4-mini is an AI model provided by github-models.", "family": "o-mini", "id": "openai/o4-mini", "knowledge": "2024-04", "last_updated": "2025-01-31", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "OpenAI o4-mini", "open_weights": false, "reasoning": true, "release_date": "2025-01-31", "temperature": false, "tool_call": false }, "xai/grok-3": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Grok 3 is an AI model provided by github-models.", "family": "grok", "id": "xai/grok-3", "knowledge": "2024-10", "last_updated": "2024-12-09", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok 3", "open_weights": false, "reasoning": true, "release_date": "2024-12-09", "temperature": true, "tool_call": true }, "xai/grok-3-mini": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Grok 3 Mini is an AI model provided by github-models.", "family": "grok", "id": "xai/grok-3-mini", "knowledge": "2024-10", "last_updated": "2024-12-09", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok 3 Mini", "open_weights": false, "reasoning": true, "release_date": "2024-12-09", "temperature": true, "tool_call": true } }, "name": "GitHub Models", "npm": "@ai-sdk/openai-compatible" }, "gitlab": { "doc": "https://docs.gitlab.com/user/duo_agent_platform/", "env": [ "GITLAB_TOKEN" ], "iconURL": "https://models.dev/logos/gitlab.svg", "id": "gitlab", "models": { "duo-chat-gpt-5-1": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Agentic Chat (GPT-5.1) is an AI model provided by gitlab.", "family": "gpt", "id": "duo-chat-gpt-5-1", "knowledge": "2024-09-30", "last_updated": "2026-01-22", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Agentic Chat (GPT-5.1)", "open_weights": false, "reasoning": true, "release_date": "2026-01-22", "structured_output": true, "temperature": false, "tool_call": true }, "duo-chat-gpt-5-2": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Agentic Chat (GPT-5.2) is an AI model provided by gitlab.", "family": "gpt", "id": "duo-chat-gpt-5-2", "knowledge": "2025-08-31", "last_updated": "2026-01-23", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Agentic Chat (GPT-5.2)", "open_weights": false, "reasoning": true, "release_date": "2026-01-23", "structured_output": true, "temperature": false, "tool_call": true }, "duo-chat-gpt-5-2-codex": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Agentic Chat (GPT-5.2 Codex) is an AI model provided by gitlab.", "family": "gpt-codex", "id": "duo-chat-gpt-5-2-codex", "knowledge": "2025-08-31", "last_updated": "2026-01-22", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Agentic Chat (GPT-5.2 Codex)", "open_weights": false, "reasoning": true, "release_date": "2026-01-22", "structured_output": true, "temperature": false, "tool_call": true }, "duo-chat-gpt-5-3-codex": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Agentic Chat (GPT-5.3 Codex) is an AI model provided by gitlab.", "family": "gpt-codex", "id": "duo-chat-gpt-5-3-codex", "knowledge": "2025-08-31", "last_updated": "2026-02-05", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Agentic Chat (GPT-5.3 Codex)", "open_weights": false, "reasoning": true, "release_date": "2026-02-05", "structured_output": true, "temperature": false, "tool_call": true }, "duo-chat-gpt-5-4": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Agentic Chat (GPT-5.4) is an AI model provided by gitlab.", "family": "gpt", "id": "duo-chat-gpt-5-4", "knowledge": "2025-08-31", "last_updated": "2026-03-05", "limit": { "context": 1050000, "input": 922000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Agentic Chat (GPT-5.4)", "open_weights": false, "reasoning": true, "release_date": "2026-03-05", "structured_output": true, "temperature": false, "tool_call": true }, "duo-chat-gpt-5-4-mini": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Agentic Chat (GPT-5.4 Mini) is an AI model provided by gitlab.", "family": "gpt-mini", "id": "duo-chat-gpt-5-4-mini", "knowledge": "2025-08-31", "last_updated": "2026-03-17", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Agentic Chat (GPT-5.4 Mini)", "open_weights": false, "reasoning": true, "release_date": "2026-03-17", "structured_output": true, "temperature": false, "tool_call": true }, "duo-chat-gpt-5-4-nano": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Agentic Chat (GPT-5.4 Nano) is an AI model provided by gitlab.", "family": "gpt-nano", "id": "duo-chat-gpt-5-4-nano", "knowledge": "2025-08-31", "last_updated": "2026-03-17", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Agentic Chat (GPT-5.4 Nano)", "open_weights": false, "reasoning": true, "release_date": "2026-03-17", "structured_output": true, "temperature": false, "tool_call": true }, "duo-chat-gpt-5-codex": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Agentic Chat (GPT-5 Codex) is an AI model provided by gitlab.", "family": "gpt-codex", "id": "duo-chat-gpt-5-codex", "knowledge": "2024-09-30", "last_updated": "2026-01-22", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Agentic Chat (GPT-5 Codex)", "open_weights": false, "reasoning": true, "release_date": "2026-01-22", "structured_output": true, "temperature": false, "tool_call": true }, "duo-chat-gpt-5-mini": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Agentic Chat (GPT-5 Mini) is an AI model provided by gitlab.", "family": "gpt-mini", "id": "duo-chat-gpt-5-mini", "knowledge": "2024-05-30", "last_updated": "2026-01-22", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Agentic Chat (GPT-5 Mini)", "open_weights": false, "reasoning": true, "release_date": "2026-01-22", "structured_output": true, "temperature": false, "tool_call": true }, "duo-chat-haiku-4-5": { "attachment": true, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "Agentic Chat (Claude Haiku 4.5) is an AI model provided by gitlab.", "family": "claude-haiku", "id": "duo-chat-haiku-4-5", "knowledge": "2025-02-28", "last_updated": "2026-01-08", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Agentic Chat (Claude Haiku 4.5)", "open_weights": false, "reasoning": true, "release_date": "2026-01-08", "temperature": true, "tool_call": true }, "duo-chat-opus-4-5": { "attachment": true, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "Agentic Chat (Claude Opus 4.5) is an AI model provided by gitlab.", "family": "claude-opus", "id": "duo-chat-opus-4-5", "knowledge": "2025-03-31", "last_updated": "2026-01-08", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Agentic Chat (Claude Opus 4.5)", "open_weights": false, "reasoning": true, "release_date": "2026-01-08", "temperature": true, "tool_call": true }, "duo-chat-opus-4-6": { "attachment": true, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "Agentic Chat (Claude Opus 4.6) is an AI model provided by gitlab.", "family": "claude-opus", "id": "duo-chat-opus-4-6", "knowledge": "2025-05-31", "last_updated": "2026-02-05", "limit": { "context": 1000000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Agentic Chat (Claude Opus 4.6)", "open_weights": false, "reasoning": true, "release_date": "2026-02-05", "temperature": true, "tool_call": true }, "duo-chat-opus-4-7": { "attachment": true, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "Agentic Chat (Claude Opus 4.7) is an AI model provided by gitlab.", "family": "claude-opus", "id": "duo-chat-opus-4-7", "knowledge": "2026-01-31", "last_updated": "2026-04-16", "limit": { "context": 1000000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Agentic Chat (Claude Opus 4.7)", "open_weights": false, "reasoning": true, "release_date": "2026-04-16", "temperature": false, "tool_call": true }, "duo-chat-sonnet-4-5": { "attachment": true, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "Agentic Chat (Claude Sonnet 4.5) is an AI model provided by gitlab.", "family": "claude-sonnet", "id": "duo-chat-sonnet-4-5", "knowledge": "2025-07-31", "last_updated": "2026-01-08", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Agentic Chat (Claude Sonnet 4.5)", "open_weights": false, "reasoning": true, "release_date": "2026-01-08", "temperature": true, "tool_call": true }, "duo-chat-sonnet-4-6": { "attachment": true, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "Agentic Chat (Claude Sonnet 4.6) is an AI model provided by gitlab.", "family": "claude-sonnet", "id": "duo-chat-sonnet-4-6", "knowledge": "2025-08-31", "last_updated": "2026-02-17", "limit": { "context": 1000000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Agentic Chat (Claude Sonnet 4.6)", "open_weights": false, "reasoning": true, "release_date": "2026-02-17", "temperature": true, "tool_call": true } }, "name": "GitLab Duo", "npm": "gitlab-ai-provider" }, "google": { "doc": "https://ai.google.dev/gemini-api/docs/models", "env": [ "GOOGLE_GENERATIVE_AI_API_KEY", "GEMINI_API_KEY" ], "iconURL": "https://models.dev/logos/google.svg", "id": "google", "lobeIcon": "Gemini.Color", "models": { "gemini-1.5-flash": { "attachment": true, "cost": { "cache_read": 0.01875, "input": 0.075, "output": 0.3 }, "description": "Gemini 1.5 Flash is an AI model provided by google.", "family": "gemini-flash", "id": "gemini-1.5-flash", "knowledge": "2024-04", "last_updated": "2024-05-14", "limit": { "context": 1000000, "output": 8192 }, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "name": "Gemini 1.5 Flash", "open_weights": false, "reasoning": false, "release_date": "2024-05-14", "temperature": true, "tool_call": true }, "gemini-1.5-flash-8b": { "attachment": true, "cost": { "cache_read": 0.01, "input": 0.0375, "output": 0.15 }, "description": "Gemini 1.5 Flash-8B is an AI model provided by google.", "family": "gemini-flash", "id": "gemini-1.5-flash-8b", "knowledge": "2024-04", "last_updated": "2024-10-03", "limit": { "context": 1000000, "output": 8192 }, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "name": "Gemini 1.5 Flash-8B", "open_weights": false, "reasoning": false, "release_date": "2024-10-03", "temperature": true, "tool_call": true }, "gemini-1.5-pro": { "attachment": true, "cost": { "cache_read": 0.3125, "input": 1.25, "output": 5 }, "description": "Gemini 1.5 Pro is an AI model provided by google.", "family": "gemini-pro", "id": "gemini-1.5-pro", "knowledge": "2024-04", "last_updated": "2024-02-15", "limit": { "context": 1000000, "output": 8192 }, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "name": "Gemini 1.5 Pro", "open_weights": false, "reasoning": false, "release_date": "2024-02-15", "temperature": true, "tool_call": true }, "gemini-2.0-flash": { "attachment": true, "cost": { "cache_read": 0.025, "input": 0.1, "output": 0.4 }, "description": "Gemini 2.0 Flash is an AI model provided by google.", "family": "gemini-flash", "id": "gemini-2.0-flash", "knowledge": "2024-06", "last_updated": "2024-12-11", "limit": { "context": 1048576, "output": 8192 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.0 Flash", "open_weights": false, "reasoning": false, "release_date": "2024-12-11", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-2.0-flash-lite": { "attachment": true, "cost": { "input": 0.075, "output": 0.3 }, "description": "Gemini 2.0 Flash Lite is an AI model provided by google.", "family": "gemini-flash-lite", "id": "gemini-2.0-flash-lite", "knowledge": "2024-06", "last_updated": "2024-12-11", "limit": { "context": 1048576, "output": 8192 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.0 Flash Lite", "open_weights": false, "reasoning": false, "release_date": "2024-12-11", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-2.5-flash": { "attachment": true, "cost": { "cache_read": 0.03, "input": 0.3, "input_audio": 1, "output": 2.5 }, "description": "Gemini 2.5 Flash is an AI model provided by google.", "family": "gemini-flash", "id": "gemini-2.5-flash", "knowledge": "2025-01", "last_updated": "2025-06-05", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Flash", "open_weights": false, "reasoning": true, "release_date": "2025-03-20", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-2.5-flash-image": { "attachment": true, "cost": { "cache_read": 0.075, "input": 0.3, "output": 30 }, "description": "Gemini 2.5 Flash Image is an AI model provided by google.", "family": "gemini-flash", "id": "gemini-2.5-flash-image", "knowledge": "2025-06", "last_updated": "2025-08-26", "limit": { "context": 32768, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text", "image" ] }, "name": "Gemini 2.5 Flash Image", "open_weights": false, "reasoning": true, "release_date": "2025-08-26", "temperature": true, "tool_call": false }, "gemini-2.5-flash-image-preview": { "attachment": true, "cost": { "cache_read": 0.075, "input": 0.3, "output": 30 }, "description": "Gemini 2.5 Flash Image (Preview) is an AI model provided by google.", "family": "gemini-flash", "id": "gemini-2.5-flash-image-preview", "knowledge": "2025-06", "last_updated": "2025-08-26", "limit": { "context": 32768, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text", "image" ] }, "name": "Gemini 2.5 Flash Image (Preview)", "open_weights": false, "reasoning": true, "release_date": "2025-08-26", "temperature": true, "tool_call": false }, "gemini-2.5-flash-lite": { "attachment": true, "cost": { "cache_read": 0.01, "input": 0.1, "input_audio": 0.3, "output": 0.4 }, "description": "A Gemini 2.5 Flash model optimized for cost-efficiency and high throughput.", "family": "gemini-flash-lite", "id": "gemini-2.5-flash-lite", "knowledge": "2025-01", "last_updated": "2025-06-17", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Flash-Lite", "open_weights": false, "reasoning": true, "release_date": "2025-06-17", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-2.5-flash-lite-preview-06-17": { "attachment": true, "cost": { "cache_read": 0.025, "input": 0.1, "input_audio": 0.3, "output": 0.4 }, "description": "Gemini 2.5 Flash Lite Preview 06-17 is an AI model provided by google.", "family": "gemini-flash-lite", "id": "gemini-2.5-flash-lite-preview-06-17", "knowledge": "2025-01", "last_updated": "2025-06-17", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Flash Lite Preview 06-17", "open_weights": false, "reasoning": true, "release_date": "2025-06-17", "temperature": true, "tool_call": true }, "gemini-2.5-flash-lite-preview-09-2025": { "attachment": true, "cost": { "cache_read": 0.025, "input": 0.1, "output": 0.4 }, "description": "Gemini 2.5 Flash Lite Preview 09-25 is an AI model provided by google.", "family": "gemini-flash-lite", "id": "gemini-2.5-flash-lite-preview-09-2025", "knowledge": "2025-01", "last_updated": "2025-09-25", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Flash Lite Preview 09-25", "open_weights": false, "reasoning": true, "release_date": "2025-09-25", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-2.5-flash-preview-04-17": { "attachment": true, "cost": { "cache_read": 0.0375, "input": 0.15, "output": 0.6 }, "description": "Gemini 2.5 Flash Preview 04-17 is an AI model provided by google.", "family": "gemini-flash", "id": "gemini-2.5-flash-preview-04-17", "knowledge": "2025-01", "last_updated": "2025-04-17", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Flash Preview 04-17", "open_weights": false, "reasoning": true, "release_date": "2025-04-17", "temperature": true, "tool_call": true }, "gemini-2.5-flash-preview-05-20": { "attachment": true, "cost": { "cache_read": 0.0375, "input": 0.15, "output": 0.6 }, "description": "Gemini 2.5 Flash Preview 05-20 is an AI model provided by google.", "family": "gemini-flash", "id": "gemini-2.5-flash-preview-05-20", "knowledge": "2025-01", "last_updated": "2025-05-20", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Flash Preview 05-20", "open_weights": false, "reasoning": true, "release_date": "2025-05-20", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-2.5-flash-preview-09-2025": { "attachment": true, "cost": { "cache_read": 0.075, "input": 0.3, "input_audio": 1, "output": 2.5 }, "description": "Gemini 2.5 Flash Preview 09-25 is an AI model provided by google.", "family": "gemini-flash", "id": "gemini-2.5-flash-preview-09-2025", "knowledge": "2025-01", "last_updated": "2025-09-25", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Flash Preview 09-25", "open_weights": false, "reasoning": true, "release_date": "2025-09-25", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-2.5-flash-preview-tts": { "attachment": false, "cost": { "input": 0.5, "output": 10 }, "description": "Gemini 2.5 Flash Preview TTS is an AI model provided by google.", "family": "gemini-flash", "id": "gemini-2.5-flash-preview-tts", "knowledge": "2025-01", "last_updated": "2025-05-01", "limit": { "context": 8000, "output": 16000 }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "name": "Gemini 2.5 Flash Preview TTS", "open_weights": false, "reasoning": false, "release_date": "2025-05-01", "temperature": false, "tool_call": false }, "gemini-2.5-pro": { "attachment": true, "cost": { "cache_read": 0.125, "context_over_200k": { "cache_read": 0.25, "input": 2.5, "output": 15 }, "input": 1.25, "output": 10, "tiers": [ { "cache_read": 0.25, "input": 2.5, "output": 15, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Gemini 2.5 Pro is an AI model provided by google.", "family": "gemini-pro", "id": "gemini-2.5-pro", "knowledge": "2025-01", "last_updated": "2025-06-05", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Pro", "open_weights": false, "reasoning": true, "release_date": "2025-03-20", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-2.5-pro-preview-05-06": { "attachment": true, "cost": { "cache_read": 0.31, "input": 1.25, "output": 10 }, "description": "Gemini 2.5 Pro Preview 05-06 is an AI model provided by google.", "family": "gemini-pro", "id": "gemini-2.5-pro-preview-05-06", "knowledge": "2025-01", "last_updated": "2025-05-06", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Pro Preview 05-06", "open_weights": false, "reasoning": true, "release_date": "2025-05-06", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-2.5-pro-preview-06-05": { "attachment": true, "cost": { "cache_read": 0.31, "input": 1.25, "output": 10 }, "description": "Gemini 2.5 Pro Preview 06-05 is an AI model provided by google.", "family": "gemini-pro", "id": "gemini-2.5-pro-preview-06-05", "knowledge": "2025-01", "last_updated": "2025-06-05", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Pro Preview 06-05", "open_weights": false, "reasoning": true, "release_date": "2025-06-05", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-2.5-pro-preview-tts": { "attachment": false, "cost": { "input": 1, "output": 20 }, "description": "Gemini 2.5 Pro Preview TTS is an AI model provided by google.", "family": "gemini-flash", "id": "gemini-2.5-pro-preview-tts", "knowledge": "2025-01", "last_updated": "2025-05-01", "limit": { "context": 8000, "output": 16000 }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "name": "Gemini 2.5 Pro Preview TTS", "open_weights": false, "reasoning": false, "release_date": "2025-05-01", "temperature": false, "tool_call": false }, "gemini-3-flash-preview": { "attachment": true, "cost": { "cache_read": 0.05, "input": 0.5, "input_audio": 1, "output": 3 }, "description": "Gemini 3 Flash Preview is an AI model provided by google.", "family": "gemini-flash", "id": "gemini-3-flash-preview", "knowledge": "2025-01", "last_updated": "2025-12-17", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "name": "Gemini 3 Flash Preview", "open_weights": false, "reasoning": true, "release_date": "2025-12-17", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-3-pro-preview": { "attachment": true, "cost": { "cache_read": 0.2, "context_over_200k": { "cache_read": 0.4, "input": 4, "output": 18 }, "input": 2, "output": 12, "tiers": [ { "cache_read": 0.4, "input": 4, "output": 18, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Gemini 3 Pro Preview is an AI model provided by google.", "family": "gemini-pro", "id": "gemini-3-pro-preview", "knowledge": "2025-01", "last_updated": "2025-11-18", "limit": { "context": 1000000, "output": 64000 }, "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "name": "Gemini 3 Pro Preview", "open_weights": false, "reasoning": true, "release_date": "2025-11-18", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-3.1-flash-image-preview": { "attachment": true, "cost": { "input": 0.5, "output": 60 }, "description": "Gemini 3.1 Flash Image (Preview) is an AI model provided by google.", "family": "gemini-flash", "id": "gemini-3.1-flash-image-preview", "knowledge": "2025-01", "last_updated": "2026-02-26", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text", "image" ] }, "name": "Gemini 3.1 Flash Image (Preview)", "open_weights": false, "reasoning": true, "release_date": "2026-02-26", "temperature": true, "tool_call": false }, "gemini-3.1-flash-lite": { "attachment": true, "cost": { "cache_read": 0.025, "input": 0.25, "input_audio": 0.5, "output": 1.5 }, "description": "Gemini 3.1 Flash Lite is an AI model provided by google.", "family": "gemini-flash-lite", "id": "gemini-3.1-flash-lite", "knowledge": "2025-01", "last_updated": "2026-05-07", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "name": "Gemini 3.1 Flash Lite", "open_weights": false, "reasoning": true, "release_date": "2026-05-07", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-3.1-flash-lite-preview": { "attachment": true, "cost": { "cache_read": 0.025, "input": 0.25, "input_audio": 0.5, "output": 1.5 }, "description": "Gemini 3.1 Flash Lite Preview is an AI model provided by google.", "family": "gemini-flash-lite", "id": "gemini-3.1-flash-lite-preview", "knowledge": "2025-01", "last_updated": "2026-03-03", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "name": "Gemini 3.1 Flash Lite Preview", "open_weights": false, "reasoning": true, "release_date": "2026-03-03", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-3.1-pro-preview": { "attachment": true, "cost": { "cache_read": 0.2, "context_over_200k": { "cache_read": 0.4, "input": 4, "output": 18 }, "input": 2, "output": 12, "tiers": [ { "cache_read": 0.4, "input": 4, "output": 18, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Gemini 3.1 Pro Preview is an AI model provided by google.", "family": "gemini-pro", "id": "gemini-3.1-pro-preview", "knowledge": "2025-01", "last_updated": "2026-02-19", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "name": "Gemini 3.1 Pro Preview", "open_weights": false, "reasoning": true, "release_date": "2026-02-19", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-3.1-pro-preview-customtools": { "attachment": true, "cost": { "cache_read": 0.2, "context_over_200k": { "cache_read": 0.4, "input": 4, "output": 18 }, "input": 2, "output": 12, "tiers": [ { "cache_read": 0.4, "input": 4, "output": 18, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Gemini 3.1 Pro Preview Custom Tools is an AI model provided by google.", "family": "gemini-pro", "id": "gemini-3.1-pro-preview-customtools", "knowledge": "2025-01", "last_updated": "2026-02-19", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "name": "Gemini 3.1 Pro Preview Custom Tools", "open_weights": false, "reasoning": true, "release_date": "2026-02-19", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-embedding-001": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0.15, "output": 0 }, "description": "Provides text embedding models for generating embeddings for words, phrases, sentences, and code. These foundational embeddings support advanced NLP tasks such as semantic search, classification, and clustering, offering more accurate and context-aware search results compared to keyword-based approaches.\n\nBuilding Retrieval Augmented Generation (RAG) systems is a common use case for embeddings. Embeddings play a crucial role in significantly enhancing model outputs, improving factual accuracy, coherence, and contextual richness. They enable efficient retrieval of relevant information from knowledge bases (represented as embeddings), which is then passed as additional background information in the input prompt to the language model, guiding it to generate more informed and accurate responses.", "family": "gemini", "id": "gemini-embedding-001", "knowledge": "2025-06", "last_updated": "2025-06-01", "limit": { "context": 2048, "output": 3072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "gemini-embedding-001", "open_weights": false, "reasoning": false, "release_date": "2025-06-01", "temperature": false, "tool_call": true }, "gemini-flash-latest": { "attachment": true, "cost": { "cache_read": 0.075, "input": 0.3, "input_audio": 1, "output": 2.5 }, "description": "Gemini Flash Latest is an AI model provided by google.", "family": "gemini-flash", "id": "gemini-flash-latest", "knowledge": "2025-01", "last_updated": "2025-09-25", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini Flash Latest", "open_weights": false, "reasoning": true, "release_date": "2025-09-25", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-flash-lite-latest": { "attachment": true, "cost": { "cache_read": 0.025, "input": 0.1, "output": 0.4 }, "description": "Gemini Flash-Lite Latest is an AI model provided by google.", "family": "gemini-flash-lite", "id": "gemini-flash-lite-latest", "knowledge": "2025-01", "last_updated": "2025-09-25", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini Flash-Lite Latest", "open_weights": false, "reasoning": true, "release_date": "2025-09-25", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-live-2.5-flash": { "attachment": true, "cost": { "input": 0.5, "input_audio": 3, "output": 2, "output_audio": 12 }, "description": "Gemini Live 2.5 Flash is an AI model provided by google.", "family": "gemini-flash", "id": "gemini-live-2.5-flash", "knowledge": "2025-01", "last_updated": "2025-09-01", "limit": { "context": 128000, "output": 8000 }, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text", "audio" ] }, "name": "Gemini Live 2.5 Flash", "open_weights": false, "reasoning": true, "release_date": "2025-09-01", "temperature": true, "tool_call": true }, "gemini-live-2.5-flash-preview-native-audio": { "attachment": false, "cost": { "input": 0.5, "input_audio": 3, "output": 2, "output_audio": 12 }, "description": "Gemini Live 2.5 Flash Preview Native Audio is an AI model provided by google.", "family": "gemini-flash", "id": "gemini-live-2.5-flash-preview-native-audio", "knowledge": "2025-01", "last_updated": "2025-09-18", "limit": { "context": 131072, "output": 65536 }, "modalities": { "input": [ "text", "audio", "video" ], "output": [ "text", "audio" ] }, "name": "Gemini Live 2.5 Flash Preview Native Audio", "open_weights": false, "reasoning": true, "release_date": "2025-06-17", "temperature": false, "tool_call": true }, "gemma-3-12b-it": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Gemma 3 12B is an AI model provided by google.", "family": "gemma", "id": "gemma-3-12b-it", "knowledge": "2024-10", "last_updated": "2025-03-13", "limit": { "context": 32768, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemma 3 12B", "open_weights": true, "reasoning": false, "release_date": "2025-03-13", "structured_output": true, "temperature": true, "tool_call": false }, "gemma-3-27b-it": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Gemma 3 27B is an AI model provided by google.", "family": "gemma", "id": "gemma-3-27b-it", "knowledge": "2024-10", "last_updated": "2025-03-12", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemma 3 27B", "open_weights": true, "reasoning": false, "release_date": "2025-03-12", "structured_output": true, "temperature": true, "tool_call": true }, "gemma-3-4b-it": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Gemma 3 4B is an AI model provided by google.", "family": "gemma", "id": "gemma-3-4b-it", "knowledge": "2024-10", "last_updated": "2025-03-13", "limit": { "context": 32768, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemma 3 4B", "open_weights": true, "reasoning": false, "release_date": "2025-03-13", "temperature": true, "tool_call": false }, "gemma-3n-e2b-it": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Gemma 3n 2B is an AI model provided by google.", "family": "gemma", "id": "gemma-3n-e2b-it", "knowledge": "2024-10", "last_updated": "2025-07-09", "limit": { "context": 8192, "output": 2000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Gemma 3n 2B", "open_weights": true, "reasoning": false, "release_date": "2025-07-09", "temperature": true, "tool_call": false }, "gemma-3n-e4b-it": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Gemma 3n 4B is an AI model provided by google.", "family": "gemma", "id": "gemma-3n-e4b-it", "knowledge": "2024-10", "last_updated": "2025-05-20", "limit": { "context": 8192, "output": 2000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Gemma 3n 4B", "open_weights": true, "reasoning": false, "release_date": "2025-05-20", "temperature": true, "tool_call": false }, "gemma-4-26b-a4b-it": { "attachment": false, "description": "Gemma 4 26B is an AI model provided by google.", "family": "gemma", "id": "gemma-4-26b-a4b-it", "last_updated": "2026-04-02", "limit": { "context": 256000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemma 4 26B", "open_weights": true, "reasoning": true, "release_date": "2026-04-02", "structured_output": true, "temperature": true, "tool_call": true }, "gemma-4-31b-it": { "attachment": false, "description": "Gemma 4 31B is an AI model provided by google.", "family": "gemma", "id": "gemma-4-31b-it", "last_updated": "2026-04-02", "limit": { "context": 256000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemma 4 31B", "open_weights": true, "reasoning": true, "release_date": "2026-04-02", "structured_output": true, "temperature": true, "tool_call": true } }, "name": "Google", "npm": "@ai-sdk/google" }, "google-vertex": { "doc": "https://cloud.google.com/vertex-ai/generative-ai/docs/models", "env": [ "GOOGLE_VERTEX_PROJECT", "GOOGLE_VERTEX_LOCATION", "GOOGLE_APPLICATION_CREDENTIALS" ], "iconURL": "https://models.dev/logos/google-vertex.svg", "id": "google-vertex", "lobeIcon": "VertexAI.Color", "models": { "claude-3-5-haiku@20241022": { "attachment": true, "cost": { "cache_read": 0.08, "cache_write": 1, "input": 0.8, "output": 4 }, "description": "Claude Haiku 3.5 is an AI model provided by google-vertex.", "family": "claude-haiku", "id": "claude-3-5-haiku@20241022", "knowledge": "2024-07-31", "last_updated": "2024-10-22", "limit": { "context": 200000, "output": 8192 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Haiku 3.5", "open_weights": false, "provider": { "npm": "@ai-sdk/google-vertex/anthropic" }, "reasoning": false, "release_date": "2024-10-22", "temperature": true, "tool_call": true }, "claude-3-5-sonnet@20241022": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 3.5 v2 is an AI model provided by google-vertex.", "family": "claude-sonnet", "id": "claude-3-5-sonnet@20241022", "knowledge": "2024-04-30", "last_updated": "2024-10-22", "limit": { "context": 200000, "output": 8192 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 3.5 v2", "open_weights": false, "provider": { "npm": "@ai-sdk/google-vertex/anthropic" }, "reasoning": false, "release_date": "2024-10-22", "temperature": true, "tool_call": true }, "claude-3-7-sonnet@20250219": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 3.7 is an AI model provided by google-vertex.", "family": "claude-sonnet", "id": "claude-3-7-sonnet@20250219", "knowledge": "2024-10-31", "last_updated": "2025-02-19", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 3.7", "open_weights": false, "provider": { "npm": "@ai-sdk/google-vertex/anthropic" }, "reasoning": true, "release_date": "2025-02-19", "temperature": true, "tool_call": true }, "claude-haiku-4-5@20251001": { "attachment": true, "cost": { "cache_read": 0.1, "cache_write": 1.25, "input": 1, "output": 5 }, "description": "Claude Haiku 4.5 is an AI model provided by google-vertex.", "family": "claude-haiku", "id": "claude-haiku-4-5@20251001", "knowledge": "2025-02-28", "last_updated": "2025-10-15", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Haiku 4.5", "open_weights": false, "provider": { "npm": "@ai-sdk/google-vertex/anthropic" }, "reasoning": true, "release_date": "2025-10-15", "temperature": true, "tool_call": true }, "claude-opus-4-1@20250805": { "attachment": true, "cost": { "cache_read": 1.5, "cache_write": 18.75, "input": 15, "output": 75 }, "description": "Claude Opus 4.1 is an AI model provided by google-vertex.", "family": "claude-opus", "id": "claude-opus-4-1@20250805", "knowledge": "2025-03-31", "last_updated": "2025-08-05", "limit": { "context": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.1", "open_weights": false, "provider": { "npm": "@ai-sdk/google-vertex/anthropic" }, "reasoning": true, "release_date": "2025-08-05", "temperature": true, "tool_call": true }, "claude-opus-4-5@20251101": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "input": 5, "output": 25 }, "description": "Claude Opus 4.5 is an AI model provided by google-vertex.", "family": "claude-opus", "id": "claude-opus-4-5@20251101", "knowledge": "2025-03-31", "last_updated": "2025-11-01", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.5", "open_weights": false, "provider": { "npm": "@ai-sdk/google-vertex/anthropic" }, "reasoning": true, "release_date": "2025-11-01", "temperature": true, "tool_call": true }, "claude-opus-4-6@default": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "context_over_200k": { "cache_read": 1, "cache_write": 12.5, "input": 10, "output": 37.5 }, "input": 5, "output": 25, "tiers": [ { "cache_read": 1, "cache_write": 12.5, "input": 10, "output": 37.5, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Claude Opus 4.6 is an AI model provided by google-vertex.", "family": "claude-opus", "id": "claude-opus-4-6@default", "knowledge": "2025-05-31", "last_updated": "2026-03-13", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.6", "open_weights": false, "provider": { "npm": "@ai-sdk/google-vertex/anthropic" }, "reasoning": true, "release_date": "2026-02-05", "temperature": true, "tool_call": true }, "claude-opus-4-7@default": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "context_over_200k": { "cache_read": 1, "cache_write": 12.5, "input": 10, "output": 37.5 }, "input": 5, "output": 25, "tiers": [ { "cache_read": 1, "cache_write": 12.5, "input": 10, "output": 37.5, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Claude Opus 4.7 is an AI model provided by google-vertex.", "family": "claude-opus", "id": "claude-opus-4-7@default", "knowledge": "2026-01-31", "last_updated": "2026-04-16", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.7", "open_weights": false, "provider": { "npm": "@ai-sdk/google-vertex/anthropic" }, "reasoning": true, "release_date": "2026-04-16", "temperature": false, "tool_call": true }, "claude-opus-4@20250514": { "attachment": true, "cost": { "cache_read": 1.5, "cache_write": 18.75, "input": 15, "output": 75 }, "description": "Claude Opus 4 is an AI model provided by google-vertex.", "family": "claude-opus", "id": "claude-opus-4@20250514", "knowledge": "2025-03-31", "last_updated": "2025-05-22", "limit": { "context": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4", "open_weights": false, "provider": { "npm": "@ai-sdk/google-vertex/anthropic" }, "reasoning": true, "release_date": "2025-05-22", "temperature": true, "tool_call": true }, "claude-sonnet-4-5@20250929": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 4.5 is an AI model provided by google-vertex.", "family": "claude-sonnet", "id": "claude-sonnet-4-5@20250929", "knowledge": "2025-07-31", "last_updated": "2025-09-29", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.5", "open_weights": false, "provider": { "npm": "@ai-sdk/google-vertex/anthropic" }, "reasoning": true, "release_date": "2025-09-29", "temperature": true, "tool_call": true }, "claude-sonnet-4-6@default": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "context_over_200k": { "cache_read": 0.6, "cache_write": 7.5, "input": 6, "output": 22.5 }, "input": 3, "output": 15, "tiers": [ { "cache_read": 0.6, "cache_write": 7.5, "input": 6, "output": 22.5, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Claude Sonnet 4.6 is an AI model provided by google-vertex.", "family": "claude-sonnet", "id": "claude-sonnet-4-6@default", "knowledge": "2025-08-31", "last_updated": "2026-03-13", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.6", "open_weights": false, "provider": { "npm": "@ai-sdk/google-vertex/anthropic" }, "reasoning": true, "release_date": "2026-02-17", "temperature": true, "tool_call": true }, "claude-sonnet-4@20250514": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 4 is an AI model provided by google-vertex.", "family": "claude-sonnet", "id": "claude-sonnet-4@20250514", "knowledge": "2025-03-31", "last_updated": "2025-05-22", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4", "open_weights": false, "provider": { "npm": "@ai-sdk/google-vertex/anthropic" }, "reasoning": true, "release_date": "2025-05-22", "temperature": true, "tool_call": true }, "deepseek-ai/deepseek-v3.1-maas": { "attachment": false, "cost": { "input": 0.6, "output": 1.7 }, "description": "DeepSeek V3.1 is an AI model provided by google-vertex.", "family": "deepseek", "id": "deepseek-ai/deepseek-v3.1-maas", "last_updated": "2025-08-28", "limit": { "context": 163840, "output": 32768 }, "modalities": { "input": [ "text", "pdf" ], "output": [ "text" ] }, "name": "DeepSeek V3.1", "open_weights": true, "provider": { "api": "https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi", "npm": "@ai-sdk/openai-compatible" }, "reasoning": true, "release_date": "2025-08-28", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek-ai/deepseek-v3.2-maas": { "attachment": false, "cost": { "cache_read": 0.056, "input": 0.56, "output": 1.68 }, "description": "DeepSeek V3.2 is an AI model provided by google-vertex.", "family": "deepseek", "id": "deepseek-ai/deepseek-v3.2-maas", "last_updated": "2026-04-04", "limit": { "context": 163840, "output": 65536 }, "modalities": { "input": [ "text", "pdf" ], "output": [ "text" ] }, "name": "DeepSeek V3.2", "open_weights": true, "provider": { "api": "https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi", "npm": "@ai-sdk/openai-compatible" }, "reasoning": true, "release_date": "2025-12-17", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-2.0-flash": { "attachment": true, "cost": { "cache_read": 0.025, "input": 0.15, "output": 0.6 }, "description": "Gemini 2.0 Flash is an AI model provided by google-vertex.", "family": "gemini-flash", "id": "gemini-2.0-flash", "knowledge": "2024-06", "last_updated": "2024-12-11", "limit": { "context": 1048576, "output": 8192 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.0 Flash", "open_weights": false, "reasoning": false, "release_date": "2024-12-11", "temperature": true, "tool_call": true }, "gemini-2.0-flash-lite": { "attachment": true, "cost": { "input": 0.075, "output": 0.3 }, "description": "Gemini 2.0 Flash Lite is an AI model provided by google-vertex.", "family": "gemini-flash-lite", "id": "gemini-2.0-flash-lite", "knowledge": "2024-06", "last_updated": "2024-12-11", "limit": { "context": 1048576, "output": 8192 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.0 Flash Lite", "open_weights": false, "reasoning": false, "release_date": "2024-12-11", "temperature": true, "tool_call": true }, "gemini-2.5-flash": { "attachment": true, "cost": { "cache_read": 0.075, "cache_write": 0.383, "input": 0.3, "output": 2.5 }, "description": "Gemini 2.5 Flash is an AI model provided by google-vertex.", "family": "gemini-flash", "id": "gemini-2.5-flash", "knowledge": "2025-01", "last_updated": "2025-06-17", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Flash", "open_weights": false, "reasoning": true, "release_date": "2025-06-17", "temperature": true, "tool_call": true }, "gemini-2.5-flash-lite": { "attachment": true, "cost": { "cache_read": 0.01, "input": 0.1, "input_audio": 0.3, "output": 0.4 }, "description": "Gemini 2.5 Flash Lite is an AI model provided by google-vertex.", "family": "gemini-flash-lite", "id": "gemini-2.5-flash-lite", "knowledge": "2025-01", "last_updated": "2025-06-17", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Flash Lite", "open_weights": false, "reasoning": true, "release_date": "2025-06-17", "temperature": true, "tool_call": true }, "gemini-2.5-flash-lite-preview-06-17": { "attachment": true, "cost": { "cache_read": 0.025, "input": 0.1, "output": 0.4 }, "description": "Gemini 2.5 Flash Lite Preview 06-17 is an AI model provided by google-vertex.", "family": "gemini-flash-lite", "id": "gemini-2.5-flash-lite-preview-06-17", "knowledge": "2025-01", "last_updated": "2025-06-17", "limit": { "context": 65536, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Flash Lite Preview 06-17", "open_weights": false, "reasoning": true, "release_date": "2025-06-17", "temperature": true, "tool_call": true }, "gemini-2.5-flash-lite-preview-09-2025": { "attachment": true, "cost": { "cache_read": 0.025, "input": 0.1, "output": 0.4 }, "description": "Gemini 2.5 Flash Lite Preview 09-25 is an AI model provided by google-vertex.", "family": "gemini-flash-lite", "id": "gemini-2.5-flash-lite-preview-09-2025", "knowledge": "2025-01", "last_updated": "2025-09-25", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Flash Lite Preview 09-25", "open_weights": false, "reasoning": true, "release_date": "2025-09-25", "temperature": true, "tool_call": true }, "gemini-2.5-flash-preview-04-17": { "attachment": true, "cost": { "cache_read": 0.0375, "input": 0.15, "output": 0.6 }, "description": "Gemini 2.5 Flash Preview 04-17 is an AI model provided by google-vertex.", "family": "gemini-flash", "id": "gemini-2.5-flash-preview-04-17", "knowledge": "2025-01", "last_updated": "2025-04-17", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Flash Preview 04-17", "open_weights": false, "reasoning": true, "release_date": "2025-04-17", "temperature": true, "tool_call": true }, "gemini-2.5-flash-preview-05-20": { "attachment": true, "cost": { "cache_read": 0.0375, "input": 0.15, "output": 0.6 }, "description": "Gemini 2.5 Flash Preview 05-20 is an AI model provided by google-vertex.", "family": "gemini-flash", "id": "gemini-2.5-flash-preview-05-20", "knowledge": "2025-01", "last_updated": "2025-05-20", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Flash Preview 05-20", "open_weights": false, "reasoning": true, "release_date": "2025-05-20", "temperature": true, "tool_call": true }, "gemini-2.5-flash-preview-09-2025": { "attachment": true, "cost": { "cache_read": 0.075, "cache_write": 0.383, "input": 0.3, "output": 2.5 }, "description": "Gemini 2.5 Flash Preview 09-25 is an AI model provided by google-vertex.", "family": "gemini-flash", "id": "gemini-2.5-flash-preview-09-2025", "knowledge": "2025-01", "last_updated": "2025-09-25", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Flash Preview 09-25", "open_weights": false, "reasoning": true, "release_date": "2025-09-25", "temperature": true, "tool_call": true }, "gemini-2.5-pro": { "attachment": true, "cost": { "cache_read": 0.125, "context_over_200k": { "cache_read": 0.25, "input": 2.5, "output": 15 }, "input": 1.25, "output": 10, "tiers": [ { "cache_read": 0.25, "input": 2.5, "output": 15, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Gemini 2.5 Pro is an AI model provided by google-vertex.", "family": "gemini-pro", "id": "gemini-2.5-pro", "knowledge": "2025-01", "last_updated": "2025-06-05", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Pro", "open_weights": false, "reasoning": true, "release_date": "2025-03-20", "temperature": true, "tool_call": true }, "gemini-2.5-pro-preview-05-06": { "attachment": true, "cost": { "cache_read": 0.31, "input": 1.25, "output": 10 }, "description": "Gemini 2.5 Pro Preview 05-06 is an AI model provided by google-vertex.", "family": "gemini-pro", "id": "gemini-2.5-pro-preview-05-06", "knowledge": "2025-01", "last_updated": "2025-05-06", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Pro Preview 05-06", "open_weights": false, "reasoning": true, "release_date": "2025-05-06", "temperature": true, "tool_call": true }, "gemini-2.5-pro-preview-06-05": { "attachment": true, "cost": { "cache_read": 0.31, "input": 1.25, "output": 10 }, "description": "Gemini 2.5 Pro Preview 06-05 is an AI model provided by google-vertex.", "family": "gemini-pro", "id": "gemini-2.5-pro-preview-06-05", "knowledge": "2025-01", "last_updated": "2025-06-05", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Pro Preview 06-05", "open_weights": false, "reasoning": true, "release_date": "2025-06-05", "temperature": true, "tool_call": true }, "gemini-3-flash-preview": { "attachment": true, "cost": { "cache_read": 0.05, "input": 0.5, "input_audio": 1, "output": 3 }, "description": "Gemini 3 Flash Preview is an AI model provided by google-vertex.", "family": "gemini-flash", "id": "gemini-3-flash-preview", "knowledge": "2025-01", "last_updated": "2025-12-17", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "name": "Gemini 3 Flash Preview", "open_weights": false, "reasoning": true, "release_date": "2025-12-17", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-3-pro-preview": { "attachment": true, "cost": { "cache_read": 0.2, "context_over_200k": { "cache_read": 0.4, "input": 4, "output": 18 }, "input": 2, "output": 12, "tiers": [ { "cache_read": 0.4, "input": 4, "output": 18, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Gemini 3 Pro Preview is an AI model provided by google-vertex.", "family": "gemini-pro", "id": "gemini-3-pro-preview", "knowledge": "2025-01", "last_updated": "2025-11-18", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "name": "Gemini 3 Pro Preview", "open_weights": false, "reasoning": true, "release_date": "2025-11-18", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-3.1-flash-lite": { "attachment": true, "cost": { "cache_read": 0.025, "input": 0.25, "input_audio": 0.5, "output": 1.5 }, "description": "Gemini 3.1 Flash Lite is an AI model provided by google-vertex.", "family": "gemini-flash-lite", "id": "gemini-3.1-flash-lite", "knowledge": "2025-01", "last_updated": "2026-05-07", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "name": "Gemini 3.1 Flash Lite", "open_weights": false, "reasoning": true, "release_date": "2026-05-07", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-3.1-flash-lite-preview": { "attachment": true, "cost": { "cache_read": 0.025, "input": 0.25, "input_audio": 0.5, "output": 1.5 }, "description": "Gemini 3.1 Flash Lite Preview is an AI model provided by google-vertex.", "family": "gemini-flash-lite", "id": "gemini-3.1-flash-lite-preview", "knowledge": "2025-01", "last_updated": "2026-03-03", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "name": "Gemini 3.1 Flash Lite Preview", "open_weights": false, "reasoning": true, "release_date": "2026-03-03", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-3.1-pro-preview": { "attachment": true, "cost": { "cache_read": 0.2, "context_over_200k": { "cache_read": 0.4, "input": 4, "output": 18 }, "input": 2, "output": 12, "tiers": [ { "cache_read": 0.4, "input": 4, "output": 18, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Gemini 3.1 Pro Preview is an AI model provided by google-vertex.", "family": "gemini-pro", "id": "gemini-3.1-pro-preview", "knowledge": "2025-01", "last_updated": "2026-02-19", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "name": "Gemini 3.1 Pro Preview", "open_weights": false, "reasoning": true, "release_date": "2026-02-19", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-3.1-pro-preview-customtools": { "attachment": true, "cost": { "cache_read": 0.2, "context_over_200k": { "cache_read": 0.4, "input": 4, "output": 18 }, "input": 2, "output": 12, "tiers": [ { "cache_read": 0.4, "input": 4, "output": 18, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Gemini 3.1 Pro Preview Custom Tools is an AI model provided by google-vertex.", "family": "gemini-pro", "id": "gemini-3.1-pro-preview-customtools", "knowledge": "2025-01", "last_updated": "2026-02-19", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "name": "Gemini 3.1 Pro Preview Custom Tools", "open_weights": false, "reasoning": true, "release_date": "2026-02-19", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-embedding-001": { "attachment": false, "cost": { "input": 0.15, "output": 0 }, "description": "Gemini Embedding 001 is an AI model provided by google-vertex.", "family": "gemini", "id": "gemini-embedding-001", "knowledge": "2025-05", "last_updated": "2025-05-20", "limit": { "context": 2048, "output": 3072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Gemini Embedding 001", "open_weights": false, "reasoning": false, "release_date": "2025-05-20", "temperature": false, "tool_call": false }, "gemini-flash-latest": { "attachment": true, "cost": { "cache_read": 0.075, "cache_write": 0.383, "input": 0.3, "output": 2.5 }, "description": "Gemini Flash Latest is an AI model provided by google-vertex.", "family": "gemini-flash", "id": "gemini-flash-latest", "knowledge": "2025-01", "last_updated": "2025-09-25", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini Flash Latest", "open_weights": false, "reasoning": true, "release_date": "2025-09-25", "temperature": true, "tool_call": true }, "gemini-flash-lite-latest": { "attachment": true, "cost": { "cache_read": 0.025, "input": 0.1, "output": 0.4 }, "description": "Gemini Flash-Lite Latest is an AI model provided by google-vertex.", "family": "gemini-flash-lite", "id": "gemini-flash-lite-latest", "knowledge": "2025-01", "last_updated": "2025-09-25", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini Flash-Lite Latest", "open_weights": false, "reasoning": true, "release_date": "2025-09-25", "temperature": true, "tool_call": true }, "meta/llama-3.3-70b-instruct-maas": { "attachment": false, "cost": { "input": 0.72, "output": 0.72 }, "description": "Llama 3.3 70B Instruct is an AI model provided by google-vertex.", "family": "llama", "id": "meta/llama-3.3-70b-instruct-maas", "knowledge": "2023-12", "last_updated": "2025-04-29", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B Instruct", "open_weights": true, "provider": { "api": "https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi", "npm": "@ai-sdk/openai-compatible" }, "reasoning": false, "release_date": "2025-04-29", "structured_output": true, "temperature": true, "tool_call": true }, "meta/llama-4-maverick-17b-128e-instruct-maas": { "attachment": true, "cost": { "input": 0.35, "output": 1.15 }, "description": "Llama 4 Maverick 17B 128E Instruct is an AI model provided by google-vertex.", "family": "llama", "id": "meta/llama-4-maverick-17b-128e-instruct-maas", "knowledge": "2024-08", "last_updated": "2025-04-29", "limit": { "context": 524288, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Llama 4 Maverick 17B 128E Instruct", "open_weights": true, "provider": { "api": "https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi", "npm": "@ai-sdk/openai-compatible" }, "reasoning": false, "release_date": "2025-04-29", "structured_output": true, "temperature": true, "tool_call": true }, "moonshotai/kimi-k2-thinking-maas": { "attachment": false, "cost": { "input": 0.6, "output": 2.5 }, "description": "Kimi K2 Thinking is an AI model provided by google-vertex.", "family": "kimi-thinking", "id": "moonshotai/kimi-k2-thinking-maas", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-08", "last_updated": "2025-11-13", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 Thinking", "open_weights": true, "provider": { "api": "https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi", "npm": "@ai-sdk/openai-compatible" }, "reasoning": true, "release_date": "2025-11-13", "structured_output": true, "temperature": true, "tool_call": true }, "openai/gpt-oss-120b-maas": { "attachment": false, "cost": { "input": 0.09, "output": 0.36 }, "description": "GPT OSS 120B is an AI model provided by google-vertex.", "family": "gpt-oss", "id": "openai/gpt-oss-120b-maas", "last_updated": "2025-08-05", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT OSS 120B", "open_weights": true, "reasoning": true, "release_date": "2025-08-05", "temperature": true, "tool_call": true }, "openai/gpt-oss-20b-maas": { "attachment": false, "cost": { "input": 0.07, "output": 0.25 }, "description": "GPT OSS 20B is an AI model provided by google-vertex.", "family": "gpt-oss", "id": "openai/gpt-oss-20b-maas", "last_updated": "2025-08-05", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT OSS 20B", "open_weights": true, "reasoning": true, "release_date": "2025-08-05", "temperature": true, "tool_call": true }, "qwen/qwen3-235b-a22b-instruct-2507-maas": { "attachment": false, "cost": { "input": 0.22, "output": 0.88 }, "description": "Qwen3 235B A22B Instruct is an AI model provided by google-vertex.", "family": "qwen", "id": "qwen/qwen3-235b-a22b-instruct-2507-maas", "last_updated": "2025-08-13", "limit": { "context": 262144, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 235B A22B Instruct", "open_weights": true, "provider": { "api": "https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi", "npm": "@ai-sdk/openai-compatible" }, "reasoning": true, "release_date": "2025-08-13", "structured_output": true, "temperature": true, "tool_call": true }, "zai-org/glm-4.7-maas": { "attachment": false, "cost": { "input": 0.6, "output": 2.2 }, "description": "GLM-4.7 is an AI model provided by google-vertex.", "family": "glm", "id": "zai-org/glm-4.7-maas", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-04", "last_updated": "2026-01-06", "limit": { "context": 200000, "output": 128000 }, "modalities": { "input": [ "text", "pdf" ], "output": [ "text" ] }, "name": "GLM-4.7", "open_weights": true, "provider": { "api": "https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi", "npm": "@ai-sdk/openai-compatible" }, "reasoning": true, "release_date": "2026-01-06", "structured_output": true, "temperature": true, "tool_call": true }, "zai-org/glm-5-maas": { "attachment": false, "cost": { "cache_read": 0.1, "input": 1, "output": 3.2 }, "description": "GLM-5 is an AI model provided by google-vertex.", "family": "glm", "id": "zai-org/glm-5-maas", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-02-11", "limit": { "context": 202752, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5", "open_weights": true, "provider": { "api": "https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi", "npm": "@ai-sdk/openai-compatible" }, "reasoning": true, "release_date": "2026-02-11", "temperature": true, "tool_call": true } }, "name": "Vertex", "npm": "@ai-sdk/google-vertex" }, "google-vertex-anthropic": { "doc": "https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude", "env": [ "GOOGLE_VERTEX_PROJECT", "GOOGLE_VERTEX_LOCATION", "GOOGLE_APPLICATION_CREDENTIALS" ], "iconURL": "https://models.dev/logos/google-vertex-anthropic.svg", "id": "google-vertex-anthropic", "lobeIcon": "VertexAI.Color", "models": { "claude-3-5-haiku@20241022": { "attachment": true, "cost": { "cache_read": 0.08, "cache_write": 1, "input": 0.8, "output": 4 }, "description": "Claude Haiku 3.5 is an AI model provided by google-vertex-anthropic.", "family": "claude-haiku", "id": "claude-3-5-haiku@20241022", "knowledge": "2024-07-31", "last_updated": "2024-10-22", "limit": { "context": 200000, "output": 8192 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Haiku 3.5", "open_weights": false, "reasoning": false, "release_date": "2024-10-22", "temperature": true, "tool_call": true }, "claude-3-5-sonnet@20241022": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 3.5 v2 is an AI model provided by google-vertex-anthropic.", "family": "claude-sonnet", "id": "claude-3-5-sonnet@20241022", "knowledge": "2024-04-30", "last_updated": "2024-10-22", "limit": { "context": 200000, "output": 8192 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 3.5 v2", "open_weights": false, "reasoning": false, "release_date": "2024-10-22", "temperature": true, "tool_call": true }, "claude-3-7-sonnet@20250219": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 3.7 is an AI model provided by google-vertex-anthropic.", "family": "claude-sonnet", "id": "claude-3-7-sonnet@20250219", "knowledge": "2024-10-31", "last_updated": "2025-02-19", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 3.7", "open_weights": false, "reasoning": true, "release_date": "2025-02-19", "temperature": true, "tool_call": true }, "claude-haiku-4-5@20251001": { "attachment": true, "cost": { "cache_read": 0.1, "cache_write": 1.25, "input": 1, "output": 5 }, "description": "Claude Haiku 4.5 is an AI model provided by google-vertex-anthropic.", "family": "claude-haiku", "id": "claude-haiku-4-5@20251001", "knowledge": "2025-02-28", "last_updated": "2025-10-15", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Haiku 4.5", "open_weights": false, "reasoning": true, "release_date": "2025-10-15", "temperature": true, "tool_call": true }, "claude-opus-4-1@20250805": { "attachment": true, "cost": { "cache_read": 1.5, "cache_write": 18.75, "input": 15, "output": 75 }, "description": "Claude Opus 4.1 is an AI model provided by google-vertex-anthropic.", "family": "claude-opus", "id": "claude-opus-4-1@20250805", "knowledge": "2025-03-31", "last_updated": "2025-08-05", "limit": { "context": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.1", "open_weights": false, "reasoning": true, "release_date": "2025-08-05", "temperature": true, "tool_call": true }, "claude-opus-4-5@20251101": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "input": 5, "output": 25 }, "description": "Claude Opus 4.5 is an AI model provided by google-vertex-anthropic.", "family": "claude-opus", "id": "claude-opus-4-5@20251101", "knowledge": "2025-03-31", "last_updated": "2025-11-01", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.5", "open_weights": false, "reasoning": true, "release_date": "2025-11-01", "temperature": true, "tool_call": true }, "claude-opus-4-6@default": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "context_over_200k": { "cache_read": 1, "cache_write": 12.5, "input": 10, "output": 37.5 }, "input": 5, "output": 25, "tiers": [ { "cache_read": 1, "cache_write": 12.5, "input": 10, "output": 37.5, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Claude Opus 4.6 is an AI model provided by google-vertex-anthropic.", "family": "claude-opus", "id": "claude-opus-4-6@default", "knowledge": "2025-05-31", "last_updated": "2026-03-13", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.6", "open_weights": false, "reasoning": true, "release_date": "2026-02-05", "temperature": true, "tool_call": true }, "claude-opus-4-7@default": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "context_over_200k": { "cache_read": 1, "cache_write": 12.5, "input": 10, "output": 37.5 }, "input": 5, "output": 25, "tiers": [ { "cache_read": 1, "cache_write": 12.5, "input": 10, "output": 37.5, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Claude Opus 4.7 is an AI model provided by google-vertex-anthropic.", "family": "claude-opus", "id": "claude-opus-4-7@default", "knowledge": "2026-01-31", "last_updated": "2026-04-16", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.7", "open_weights": false, "reasoning": true, "release_date": "2026-04-16", "temperature": false, "tool_call": true }, "claude-opus-4@20250514": { "attachment": true, "cost": { "cache_read": 1.5, "cache_write": 18.75, "input": 15, "output": 75 }, "description": "Claude Opus 4 is an AI model provided by google-vertex-anthropic.", "family": "claude-opus", "id": "claude-opus-4@20250514", "knowledge": "2025-03-31", "last_updated": "2025-05-22", "limit": { "context": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4", "open_weights": false, "reasoning": true, "release_date": "2025-05-22", "temperature": true, "tool_call": true }, "claude-sonnet-4-5@20250929": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 4.5 is an AI model provided by google-vertex-anthropic.", "family": "claude-sonnet", "id": "claude-sonnet-4-5@20250929", "knowledge": "2025-07-31", "last_updated": "2025-09-29", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.5", "open_weights": false, "reasoning": true, "release_date": "2025-09-29", "temperature": true, "tool_call": true }, "claude-sonnet-4-6@default": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "context_over_200k": { "cache_read": 0.6, "cache_write": 7.5, "input": 6, "output": 22.5 }, "input": 3, "output": 15, "tiers": [ { "cache_read": 0.6, "cache_write": 7.5, "input": 6, "output": 22.5, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Claude Sonnet 4.6 is an AI model provided by google-vertex-anthropic.", "family": "claude-sonnet", "id": "claude-sonnet-4-6@default", "knowledge": "2025-08-31", "last_updated": "2026-03-13", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.6", "open_weights": false, "reasoning": true, "release_date": "2026-02-17", "temperature": true, "tool_call": true }, "claude-sonnet-4@20250514": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 4 is an AI model provided by google-vertex-anthropic.", "family": "claude-sonnet", "id": "claude-sonnet-4@20250514", "knowledge": "2025-03-31", "last_updated": "2025-05-22", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4", "open_weights": false, "reasoning": true, "release_date": "2025-05-22", "temperature": true, "tool_call": true } }, "name": "Vertex (Anthropic)", "npm": "@ai-sdk/google-vertex/anthropic" }, "groq": { "doc": "https://console.groq.com/docs/models", "env": [ "GROQ_API_KEY" ], "iconURL": "https://models.dev/logos/groq.svg", "id": "groq", "lobeIcon": "Groq.Color", "models": { "allam-2-7b": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "ALLaM-2-7b is an AI model provided by groq.", "family": "allam", "id": "allam-2-7b", "knowledge": "2024-09", "last_updated": "2024-09", "limit": { "context": 4096, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "ALLaM-2-7b", "open_weights": false, "reasoning": false, "release_date": "2024-09", "temperature": true, "tool_call": false }, "canopylabs/orpheus-arabic-saudi": { "attachment": false, "cost": { "input": 40, "output": 0 }, "description": "Orpheus Arabic Saudi is an AI model provided by groq.", "family": "canopylabs", "id": "canopylabs/orpheus-arabic-saudi", "knowledge": "2025-12-16", "last_updated": "2025-12-16", "limit": { "context": 4000, "output": 50000 }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "name": "Orpheus Arabic Saudi", "open_weights": false, "reasoning": false, "release_date": "2025-12-16", "temperature": true, "tool_call": false }, "canopylabs/orpheus-v1-english": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Orpheus V1 English is an AI model provided by groq.", "family": "canopylabs", "id": "canopylabs/orpheus-v1-english", "knowledge": "2025-12-19", "last_updated": "2025-12-19", "limit": { "context": 4000, "output": 50000 }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "name": "Orpheus V1 English", "open_weights": false, "reasoning": false, "release_date": "2025-12-19", "temperature": true, "tool_call": false }, "deepseek-r1-distill-llama-70b": { "attachment": false, "cost": { "input": 0.75, "output": 0.99 }, "description": "DeepSeek R1 Distill Llama 70B is an AI model provided by groq.", "family": "deepseek-thinking", "id": "deepseek-r1-distill-llama-70b", "knowledge": "2024-07", "last_updated": "2025-01-20", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek R1 Distill Llama 70B", "open_weights": true, "reasoning": true, "release_date": "2025-01-20", "status": "deprecated", "temperature": true, "tool_call": true }, "gemma2-9b-it": { "attachment": false, "cost": { "input": 0.2, "output": 0.2 }, "description": "Gemma 2 9B is an AI model provided by groq.", "family": "gemma", "id": "gemma2-9b-it", "knowledge": "2024-06", "last_updated": "2024-06-27", "limit": { "context": 8192, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Gemma 2 9B", "open_weights": true, "reasoning": false, "release_date": "2024-06-27", "status": "deprecated", "temperature": true, "tool_call": true }, "groq/compound": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Compound is an AI model provided by groq.", "family": "groq", "id": "groq/compound", "knowledge": "2025-09-04", "last_updated": "2025-09-04", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Compound", "open_weights": false, "reasoning": true, "release_date": "2025-09-04", "temperature": true, "tool_call": true }, "groq/compound-mini": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Compound Mini is an AI model provided by groq.", "family": "groq", "id": "groq/compound-mini", "knowledge": "2025-09-04", "last_updated": "2025-09-04", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Compound Mini", "open_weights": false, "reasoning": true, "release_date": "2025-09-04", "temperature": true, "tool_call": true }, "llama-3.1-8b-instant": { "attachment": false, "cost": { "input": 0.05, "output": 0.08 }, "description": "Llama 3.1 8B Instant is an AI model provided by groq.", "family": "llama", "id": "llama-3.1-8b-instant", "knowledge": "2023-12", "last_updated": "2024-07-23", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.1 8B Instant", "open_weights": true, "reasoning": false, "release_date": "2024-07-23", "temperature": true, "tool_call": true }, "llama-3.3-70b-versatile": { "attachment": false, "cost": { "input": 0.59, "output": 0.79 }, "description": "Llama 3.3 70B Versatile is an AI model provided by groq.", "family": "llama", "id": "llama-3.3-70b-versatile", "knowledge": "2023-12", "last_updated": "2024-12-06", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B Versatile", "open_weights": true, "reasoning": false, "release_date": "2024-12-06", "temperature": true, "tool_call": true }, "llama-guard-3-8b": { "attachment": false, "cost": { "input": 0.2, "output": 0.2 }, "description": "Llama Guard 3 8B is an AI model provided by groq.", "family": "llama", "id": "llama-guard-3-8b", "last_updated": "2024-07-23", "limit": { "context": 8192, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama Guard 3 8B", "open_weights": true, "reasoning": false, "release_date": "2024-07-23", "status": "deprecated", "temperature": true, "tool_call": false }, "llama3-70b-8192": { "attachment": false, "cost": { "input": 0.59, "output": 0.79 }, "description": "Llama 3 70B is an AI model provided by groq.", "family": "llama", "id": "llama3-70b-8192", "knowledge": "2023-03", "last_updated": "2024-04-18", "limit": { "context": 8192, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3 70B", "open_weights": true, "reasoning": false, "release_date": "2024-04-18", "status": "deprecated", "temperature": true, "tool_call": true }, "llama3-8b-8192": { "attachment": false, "cost": { "input": 0.05, "output": 0.08 }, "description": "Llama 3 8B is an AI model provided by groq.", "family": "llama", "id": "llama3-8b-8192", "knowledge": "2023-03", "last_updated": "2024-04-18", "limit": { "context": 8192, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3 8B", "open_weights": true, "reasoning": false, "release_date": "2024-04-18", "status": "deprecated", "temperature": true, "tool_call": true }, "meta-llama/llama-4-maverick-17b-128e-instruct": { "attachment": false, "cost": { "input": 0.2, "output": 0.6 }, "description": "Llama 4 Maverick 17B is an AI model provided by groq.", "family": "llama", "id": "meta-llama/llama-4-maverick-17b-128e-instruct", "knowledge": "2024-08", "last_updated": "2025-04-05", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Llama 4 Maverick 17B", "open_weights": true, "reasoning": false, "release_date": "2025-04-05", "status": "deprecated", "structured_output": true, "temperature": true, "tool_call": true }, "meta-llama/llama-4-scout-17b-16e-instruct": { "attachment": false, "cost": { "input": 0.11, "output": 0.34 }, "description": "Llama 4 Scout 17B is an AI model provided by groq.", "family": "llama", "id": "meta-llama/llama-4-scout-17b-16e-instruct", "knowledge": "2024-08", "last_updated": "2025-04-05", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Llama 4 Scout 17B", "open_weights": true, "reasoning": false, "release_date": "2025-04-05", "structured_output": true, "temperature": true, "tool_call": true }, "meta-llama/llama-guard-4-12b": { "attachment": false, "cost": { "input": 0.2, "output": 0.2 }, "description": "Llama Guard 4 12B is an AI model provided by groq.", "family": "llama", "id": "meta-llama/llama-guard-4-12b", "last_updated": "2025-04-05", "limit": { "context": 131072, "output": 1024 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Llama Guard 4 12B", "open_weights": true, "reasoning": false, "release_date": "2025-04-05", "status": "deprecated", "temperature": true, "tool_call": false }, "meta-llama/llama-prompt-guard-2-22m": { "attachment": false, "cost": { "input": 0.03, "output": 0.03 }, "description": "Llama Prompt Guard 2 22M is an AI model provided by groq.", "family": "llama", "id": "meta-llama/llama-prompt-guard-2-22m", "knowledge": "2024-10", "last_updated": "2024-10-01", "limit": { "context": 512, "output": 512 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama Prompt Guard 2 22M", "open_weights": true, "reasoning": false, "release_date": "2024-10-01", "temperature": true, "tool_call": false }, "meta-llama/llama-prompt-guard-2-86m": { "attachment": false, "cost": { "input": 0.04, "output": 0.04 }, "description": "Llama Prompt Guard 2 86M is an AI model provided by groq.", "family": "llama", "id": "meta-llama/llama-prompt-guard-2-86m", "knowledge": "2024-10", "last_updated": "2024-10-01", "limit": { "context": 512, "output": 512 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama Prompt Guard 2 86M", "open_weights": true, "reasoning": false, "release_date": "2024-10-01", "temperature": true, "tool_call": false }, "mistral-saba-24b": { "attachment": false, "cost": { "input": 0.79, "output": 0.79 }, "description": "Mistral Saba 24B is an AI model provided by groq.", "family": "mistral", "id": "mistral-saba-24b", "knowledge": "2024-08", "last_updated": "2025-02-06", "limit": { "context": 32768, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral Saba 24B", "open_weights": false, "reasoning": false, "release_date": "2025-02-06", "status": "deprecated", "temperature": true, "tool_call": true }, "moonshotai/kimi-k2-instruct": { "attachment": false, "cost": { "input": 1, "output": 3 }, "description": "Kimi K2 Instruct is an AI model provided by groq.", "family": "kimi", "id": "moonshotai/kimi-k2-instruct", "knowledge": "2024-10", "last_updated": "2025-07-14", "limit": { "context": 131072, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-07-14", "status": "deprecated", "temperature": true, "tool_call": true }, "moonshotai/kimi-k2-instruct-0905": { "attachment": false, "cost": { "input": 1, "output": 3 }, "description": "Kimi K2 Instruct 0905 is an AI model provided by groq.", "family": "kimi", "id": "moonshotai/kimi-k2-instruct-0905", "knowledge": "2024-10", "last_updated": "2025-09-05", "limit": { "context": 262144, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 Instruct 0905", "open_weights": true, "reasoning": false, "release_date": "2025-09-05", "structured_output": true, "temperature": true, "tool_call": true }, "openai/gpt-oss-120b": { "attachment": false, "cost": { "input": 0.15, "output": 0.6 }, "description": "GPT OSS 120B is an AI model provided by groq.", "family": "gpt-oss", "id": "openai/gpt-oss-120b", "last_updated": "2025-08-05", "limit": { "context": 131072, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT OSS 120B", "open_weights": true, "reasoning": true, "release_date": "2025-08-05", "structured_output": true, "temperature": true, "tool_call": true }, "openai/gpt-oss-20b": { "attachment": false, "cost": { "input": 0.075, "output": 0.3 }, "description": "GPT OSS 20B is an AI model provided by groq.", "family": "gpt-oss", "id": "openai/gpt-oss-20b", "last_updated": "2025-08-05", "limit": { "context": 131072, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT OSS 20B", "open_weights": true, "reasoning": true, "release_date": "2025-08-05", "structured_output": true, "temperature": true, "tool_call": true }, "openai/gpt-oss-safeguard-20b": { "attachment": false, "cost": { "cache_read": 0.037, "input": 0.075, "output": 0.3 }, "description": "Safety GPT OSS 20B is an AI model provided by groq.", "family": "gpt-oss", "id": "openai/gpt-oss-safeguard-20b", "last_updated": "2025-03-05", "limit": { "context": 131072, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Safety GPT OSS 20B", "open_weights": true, "reasoning": true, "release_date": "2025-03-05", "temperature": true, "tool_call": true }, "qwen-qwq-32b": { "attachment": false, "cost": { "input": 0.29, "output": 0.39 }, "description": "Qwen QwQ 32B is an AI model provided by groq.", "family": "qwen", "id": "qwen-qwq-32b", "knowledge": "2024-09", "last_updated": "2024-11-27", "limit": { "context": 131072, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen QwQ 32B", "open_weights": true, "reasoning": true, "release_date": "2024-11-27", "status": "deprecated", "temperature": true, "tool_call": true }, "qwen/qwen3-32b": { "attachment": false, "cost": { "input": 0.29, "output": 0.59 }, "description": "Qwen3 32B is an AI model provided by groq.", "family": "qwen", "id": "qwen/qwen3-32b", "knowledge": "2024-11-08", "last_updated": "2024-12-23", "limit": { "context": 131072, "output": 40960 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 32B", "open_weights": true, "reasoning": true, "release_date": "2024-12-23", "temperature": true, "tool_call": true }, "whisper-large-v3": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Whisper Large V3 is an AI model provided by groq.", "family": "whisper", "id": "whisper-large-v3", "knowledge": "2023-09", "last_updated": "2025-09-05", "limit": { "context": 448, "output": 448 }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "name": "Whisper Large V3", "open_weights": true, "reasoning": false, "release_date": "2023-09-01", "temperature": true, "tool_call": false }, "whisper-large-v3-turbo": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Whisper Large v3 Turbo is an AI model provided by groq.", "family": "whisper", "id": "whisper-large-v3-turbo", "knowledge": "2024-10", "last_updated": "2024-10-01", "limit": { "context": 448, "output": 448 }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "name": "Whisper Large v3 Turbo", "open_weights": true, "reasoning": false, "release_date": "2024-10-01", "temperature": true, "tool_call": false } }, "name": "Groq", "npm": "@ai-sdk/groq" }, "helicone": { "api": "https://ai-gateway.helicone.ai/v1", "doc": "https://helicone.ai/models", "env": [ "HELICONE_API_KEY" ], "iconURL": "https://models.dev/logos/helicone.svg", "id": "helicone", "models": { "chatgpt-4o-latest": { "attachment": false, "cost": { "cache_read": 2.5, "input": 5, "output": 20 }, "description": "OpenAI ChatGPT-4o is an AI model provided by helicone.", "family": "gpt", "id": "chatgpt-4o-latest", "knowledge": "2024-08", "last_updated": "2024-08-14", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "OpenAI ChatGPT-4o", "open_weights": false, "reasoning": false, "release_date": "2024-08-14", "temperature": true, "tool_call": true }, "claude-3-haiku-20240307": { "attachment": false, "cost": { "cache_read": 0.03, "cache_write": 0.3, "input": 0.25, "output": 1.25 }, "description": "Anthropic: Claude 3 Haiku is an AI model provided by helicone.", "family": "claude-haiku", "id": "claude-3-haiku-20240307", "knowledge": "2024-03", "last_updated": "2024-03-07", "limit": { "context": 200000, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Anthropic: Claude 3 Haiku", "open_weights": false, "reasoning": false, "release_date": "2024-03-07", "temperature": true, "tool_call": true }, "claude-3.5-haiku": { "attachment": false, "cost": { "cache_read": 0.08, "cache_write": 1, "input": 0.7999999999999999, "output": 4 }, "description": "Anthropic: Claude 3.5 Haiku is an AI model provided by helicone.", "family": "claude-haiku", "id": "claude-3.5-haiku", "knowledge": "2024-10", "last_updated": "2024-10-22", "limit": { "context": 200000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Anthropic: Claude 3.5 Haiku", "open_weights": false, "reasoning": false, "release_date": "2024-10-22", "temperature": true, "tool_call": true }, "claude-3.5-sonnet-v2": { "attachment": false, "cost": { "cache_read": 0.30000000000000004, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Anthropic: Claude 3.5 Sonnet v2 is an AI model provided by helicone.", "family": "claude-sonnet", "id": "claude-3.5-sonnet-v2", "knowledge": "2024-10", "last_updated": "2024-10-22", "limit": { "context": 200000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Anthropic: Claude 3.5 Sonnet v2", "open_weights": false, "reasoning": false, "release_date": "2024-10-22", "temperature": true, "tool_call": true }, "claude-3.7-sonnet": { "attachment": false, "cost": { "cache_read": 0.30000000000000004, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Anthropic: Claude 3.7 Sonnet is an AI model provided by helicone.", "family": "claude-sonnet", "id": "claude-3.7-sonnet", "knowledge": "2025-02", "last_updated": "2025-02-19", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Anthropic: Claude 3.7 Sonnet", "open_weights": false, "reasoning": false, "release_date": "2025-02-19", "temperature": true, "tool_call": true }, "claude-4.5-haiku": { "attachment": false, "cost": { "cache_read": 0.09999999999999999, "cache_write": 1.25, "input": 1, "output": 5 }, "description": "Anthropic: Claude 4.5 Haiku is an AI model provided by helicone.", "family": "claude-haiku", "id": "claude-4.5-haiku", "knowledge": "2025-10", "last_updated": "2025-10-01", "limit": { "context": 200000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Anthropic: Claude 4.5 Haiku", "open_weights": false, "reasoning": false, "release_date": "2025-10-01", "temperature": true, "tool_call": true }, "claude-4.5-opus": { "attachment": false, "cost": { "cache_read": 0.5, "cache_write": 6.25, "input": 5, "output": 25 }, "description": "Anthropic: Claude Opus 4.5 is an AI model provided by helicone.", "family": "claude-opus", "id": "claude-4.5-opus", "knowledge": "2025-11", "last_updated": "2025-11-24", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Anthropic: Claude Opus 4.5", "open_weights": false, "reasoning": true, "release_date": "2025-11-24", "temperature": true, "tool_call": true }, "claude-4.5-sonnet": { "attachment": false, "cost": { "cache_read": 0.30000000000000004, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Anthropic: Claude Sonnet 4.5 is an AI model provided by helicone.", "family": "claude-sonnet", "id": "claude-4.5-sonnet", "knowledge": "2025-09", "last_updated": "2025-09-29", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Anthropic: Claude Sonnet 4.5", "open_weights": false, "reasoning": true, "release_date": "2025-09-29", "temperature": true, "tool_call": true }, "claude-haiku-4-5-20251001": { "attachment": false, "cost": { "cache_read": 0.09999999999999999, "cache_write": 1.25, "input": 1, "output": 5 }, "description": "Anthropic: Claude 4.5 Haiku (20251001) is an AI model provided by helicone.", "family": "claude-haiku", "id": "claude-haiku-4-5-20251001", "knowledge": "2025-10", "last_updated": "2025-10-01", "limit": { "context": 200000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Anthropic: Claude 4.5 Haiku (20251001)", "open_weights": false, "reasoning": false, "release_date": "2025-10-01", "temperature": true, "tool_call": true }, "claude-opus-4": { "attachment": false, "cost": { "cache_read": 1.5, "cache_write": 18.75, "input": 15, "output": 75 }, "description": "Anthropic: Claude Opus 4 is an AI model provided by helicone.", "family": "claude-opus", "id": "claude-opus-4", "knowledge": "2025-05", "last_updated": "2025-05-14", "limit": { "context": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Anthropic: Claude Opus 4", "open_weights": false, "reasoning": true, "release_date": "2025-05-14", "temperature": true, "tool_call": true }, "claude-opus-4-1": { "attachment": false, "cost": { "cache_read": 1.5, "cache_write": 18.75, "input": 15, "output": 75 }, "description": "Anthropic: Claude Opus 4.1 is an AI model provided by helicone.", "family": "claude-opus", "id": "claude-opus-4-1", "knowledge": "2025-08", "last_updated": "2025-08-05", "limit": { "context": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Anthropic: Claude Opus 4.1", "open_weights": false, "reasoning": true, "release_date": "2025-08-05", "temperature": true, "tool_call": true }, "claude-opus-4-1-20250805": { "attachment": false, "cost": { "cache_read": 1.5, "cache_write": 18.75, "input": 15, "output": 75 }, "description": "Anthropic: Claude Opus 4.1 (20250805) is an AI model provided by helicone.", "family": "claude-opus", "id": "claude-opus-4-1-20250805", "knowledge": "2025-08", "last_updated": "2025-08-05", "limit": { "context": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Anthropic: Claude Opus 4.1 (20250805)", "open_weights": false, "reasoning": true, "release_date": "2025-08-05", "temperature": true, "tool_call": true }, "claude-sonnet-4": { "attachment": false, "cost": { "cache_read": 0.30000000000000004, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Anthropic: Claude Sonnet 4 is an AI model provided by helicone.", "family": "claude-sonnet", "id": "claude-sonnet-4", "knowledge": "2025-05", "last_updated": "2025-05-14", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Anthropic: Claude Sonnet 4", "open_weights": false, "reasoning": true, "release_date": "2025-05-14", "temperature": true, "tool_call": true }, "claude-sonnet-4-5-20250929": { "attachment": false, "cost": { "cache_read": 0.30000000000000004, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Anthropic: Claude Sonnet 4.5 (20250929) is an AI model provided by helicone.", "family": "claude-sonnet", "id": "claude-sonnet-4-5-20250929", "knowledge": "2025-09", "last_updated": "2025-09-29", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Anthropic: Claude Sonnet 4.5 (20250929)", "open_weights": false, "reasoning": true, "release_date": "2025-09-29", "temperature": true, "tool_call": true }, "deepseek-r1-distill-llama-70b": { "attachment": false, "cost": { "input": 0.03, "output": 0.13 }, "description": "DeepSeek R1 Distill Llama 70B is an AI model provided by helicone.", "family": "deepseek-thinking", "id": "deepseek-r1-distill-llama-70b", "knowledge": "2025-01", "last_updated": "2025-01-20", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek R1 Distill Llama 70B", "open_weights": false, "reasoning": true, "release_date": "2025-01-20", "temperature": true, "tool_call": true }, "deepseek-reasoner": { "attachment": false, "cost": { "cache_read": 0.07, "input": 0.56, "output": 1.68 }, "description": "DeepSeek Reasoner is an AI model provided by helicone.", "family": "deepseek-thinking", "id": "deepseek-reasoner", "knowledge": "2025-01", "last_updated": "2025-01-20", "limit": { "context": 128000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek Reasoner", "open_weights": false, "reasoning": false, "release_date": "2025-01-20", "temperature": true, "tool_call": false }, "deepseek-tng-r1t2-chimera": { "attachment": false, "cost": { "input": 0.3, "output": 1.2 }, "description": "DeepSeek TNG R1T2 Chimera is an AI model provided by helicone.", "family": "deepseek-thinking", "id": "deepseek-tng-r1t2-chimera", "knowledge": "2025-07", "last_updated": "2025-07-02", "limit": { "context": 130000, "output": 163840 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek TNG R1T2 Chimera", "open_weights": false, "reasoning": false, "release_date": "2025-07-02", "temperature": true, "tool_call": true }, "deepseek-v3": { "attachment": false, "cost": { "cache_read": 0.07, "input": 0.56, "output": 1.68 }, "description": "DeepSeek V3 is an AI model provided by helicone.", "family": "deepseek", "id": "deepseek-v3", "knowledge": "2024-12", "last_updated": "2024-12-26", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3", "open_weights": false, "reasoning": false, "release_date": "2024-12-26", "temperature": true, "tool_call": true }, "deepseek-v3.1-terminus": { "attachment": false, "cost": { "cache_read": 0.21600000000000003, "input": 0.27, "output": 1 }, "description": "DeepSeek V3.1 Terminus is an AI model provided by helicone.", "family": "deepseek", "id": "deepseek-v3.1-terminus", "knowledge": "2025-09", "last_updated": "2025-09-22", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3.1 Terminus", "open_weights": false, "reasoning": true, "release_date": "2025-09-22", "temperature": true, "tool_call": true }, "deepseek-v3.2": { "attachment": false, "cost": { "input": 0.27, "output": 0.41 }, "description": "DeepSeek V3.2 is an AI model provided by helicone.", "family": "deepseek", "id": "deepseek-v3.2", "knowledge": "2025-09", "last_updated": "2025-09-22", "limit": { "context": 163840, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3.2", "open_weights": false, "reasoning": false, "release_date": "2025-09-22", "temperature": true, "tool_call": true }, "ernie-4.5-21b-a3b-thinking": { "attachment": false, "cost": { "input": 0.07, "output": 0.28 }, "description": "Baidu Ernie 4.5 21B A3B Thinking is an AI model provided by helicone.", "family": "ernie", "id": "ernie-4.5-21b-a3b-thinking", "knowledge": "2025-03", "last_updated": "2025-03-16", "limit": { "context": 128000, "output": 8000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Baidu Ernie 4.5 21B A3B Thinking", "open_weights": false, "reasoning": true, "release_date": "2025-03-16", "temperature": true, "tool_call": false }, "gemini-2.5-flash": { "attachment": false, "cost": { "cache_read": 0.075, "cache_write": 0.3, "input": 0.3, "output": 2.5 }, "description": "Google Gemini 2.5 Flash is an AI model provided by helicone.", "family": "gemini-flash", "id": "gemini-2.5-flash", "knowledge": "2025-06", "last_updated": "2025-06-17", "limit": { "context": 1048576, "output": 65535 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Google Gemini 2.5 Flash", "open_weights": false, "reasoning": true, "release_date": "2025-06-17", "temperature": true, "tool_call": true }, "gemini-2.5-flash-lite": { "attachment": false, "cost": { "cache_read": 0.024999999999999998, "cache_write": 0.09999999999999999, "input": 0.09999999999999999, "output": 0.39999999999999997 }, "description": "Google Gemini 2.5 Flash Lite is an AI model provided by helicone.", "family": "gemini-flash-lite", "id": "gemini-2.5-flash-lite", "knowledge": "2025-07", "last_updated": "2025-07-22", "limit": { "context": 1048576, "output": 65535 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Google Gemini 2.5 Flash Lite", "open_weights": false, "reasoning": true, "release_date": "2025-07-22", "temperature": true, "tool_call": true }, "gemini-2.5-pro": { "attachment": false, "cost": { "cache_read": 0.3125, "cache_write": 1.25, "input": 1.25, "output": 10 }, "description": "Google Gemini 2.5 Pro is an AI model provided by helicone.", "family": "gemini-pro", "id": "gemini-2.5-pro", "knowledge": "2025-06", "last_updated": "2025-06-17", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Google Gemini 2.5 Pro", "open_weights": false, "reasoning": true, "release_date": "2025-06-17", "temperature": true, "tool_call": true }, "gemini-3-pro-preview": { "attachment": false, "cost": { "cache_read": 0.19999999999999998, "input": 2, "output": 12 }, "description": "Google Gemini 3 Pro Preview is an AI model provided by helicone.", "family": "gemini-pro", "id": "gemini-3-pro-preview", "knowledge": "2025-11", "last_updated": "2025-11-18", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "name": "Google Gemini 3 Pro Preview", "open_weights": false, "reasoning": true, "release_date": "2025-11-18", "temperature": true, "tool_call": true }, "gemma-3-12b-it": { "attachment": false, "cost": { "input": 0.049999999999999996, "output": 0.09999999999999999 }, "description": "Google Gemma 3 12B is an AI model provided by helicone.", "family": "gemma", "id": "gemma-3-12b-it", "knowledge": "2024-12", "last_updated": "2024-12-01", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Google Gemma 3 12B", "open_weights": false, "reasoning": false, "release_date": "2024-12-01", "temperature": true, "tool_call": false }, "gemma2-9b-it": { "attachment": false, "cost": { "input": 0.01, "output": 0.03 }, "description": "Google Gemma 2 is an AI model provided by helicone.", "family": "gemma", "id": "gemma2-9b-it", "knowledge": "2024-06", "last_updated": "2024-06-25", "limit": { "context": 8192, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Google Gemma 2", "open_weights": false, "reasoning": false, "release_date": "2024-06-25", "temperature": true, "tool_call": false }, "glm-4.6": { "attachment": false, "cost": { "input": 0.44999999999999996, "output": 1.5 }, "description": "Zai GLM-4.6 is an AI model provided by helicone.", "family": "glm", "id": "glm-4.6", "knowledge": "2024-07", "last_updated": "2024-07-18", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Zai GLM-4.6", "open_weights": false, "reasoning": true, "release_date": "2024-07-18", "temperature": true, "tool_call": true }, "gpt-4.1": { "attachment": false, "cost": { "cache_read": 0.5, "input": 2, "output": 8 }, "description": "OpenAI GPT-4.1 is an AI model provided by helicone.", "family": "gpt", "id": "gpt-4.1", "knowledge": "2025-04", "last_updated": "2025-04-14", "limit": { "context": 1047576, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "OpenAI GPT-4.1", "open_weights": false, "reasoning": false, "release_date": "2025-04-14", "temperature": true, "tool_call": true }, "gpt-4.1-mini": { "attachment": false, "cost": { "cache_read": 0.09999999999999999, "input": 0.39999999999999997, "output": 1.5999999999999999 }, "description": "OpenAI GPT-4.1 Mini is an AI model provided by helicone.", "family": "gpt-mini", "id": "gpt-4.1-mini", "knowledge": "2025-04", "last_updated": "2025-04-14", "limit": { "context": 1047576, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "OpenAI GPT-4.1 Mini", "open_weights": false, "reasoning": false, "release_date": "2025-04-14", "temperature": true, "tool_call": true }, "gpt-4.1-mini-2025-04-14": { "attachment": false, "cost": { "cache_read": 0.09999999999999999, "input": 0.39999999999999997, "output": 1.5999999999999999 }, "description": "OpenAI GPT-4.1 Mini is an AI model provided by helicone.", "family": "gpt-mini", "id": "gpt-4.1-mini-2025-04-14", "knowledge": "2025-04", "last_updated": "2025-04-14", "limit": { "context": 1047576, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "OpenAI GPT-4.1 Mini", "open_weights": false, "reasoning": false, "release_date": "2025-04-14", "temperature": true, "tool_call": true }, "gpt-4.1-nano": { "attachment": false, "cost": { "cache_read": 0.024999999999999998, "input": 0.09999999999999999, "output": 0.39999999999999997 }, "description": "OpenAI GPT-4.1 Nano is an AI model provided by helicone.", "family": "gpt-nano", "id": "gpt-4.1-nano", "knowledge": "2025-04", "last_updated": "2025-04-14", "limit": { "context": 1047576, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "OpenAI GPT-4.1 Nano", "open_weights": false, "reasoning": false, "release_date": "2025-04-14", "temperature": true, "tool_call": true }, "gpt-4o": { "attachment": false, "cost": { "cache_read": 1.25, "input": 2.5, "output": 10 }, "description": "OpenAI GPT-4o is an AI model provided by helicone.", "family": "gpt", "id": "gpt-4o", "knowledge": "2024-05", "last_updated": "2024-05-13", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "OpenAI GPT-4o", "open_weights": false, "reasoning": false, "release_date": "2024-05-13", "temperature": true, "tool_call": true }, "gpt-4o-mini": { "attachment": false, "cost": { "cache_read": 0.075, "input": 0.15, "output": 0.6 }, "description": "OpenAI GPT-4o-mini is an AI model provided by helicone.", "family": "gpt-mini", "id": "gpt-4o-mini", "knowledge": "2024-07", "last_updated": "2024-07-18", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "OpenAI GPT-4o-mini", "open_weights": false, "reasoning": false, "release_date": "2024-07-18", "temperature": true, "tool_call": true }, "gpt-5": { "attachment": false, "cost": { "cache_read": 0.12500000000000003, "input": 1.25, "output": 10 }, "description": "OpenAI GPT-5 is an AI model provided by helicone.", "family": "gpt", "id": "gpt-5", "knowledge": "2025-01", "last_updated": "2025-01-01", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "OpenAI GPT-5", "open_weights": false, "reasoning": false, "release_date": "2025-01-01", "temperature": false, "tool_call": true }, "gpt-5-chat-latest": { "attachment": false, "cost": { "cache_read": 0.12500000000000003, "input": 1.25, "output": 10 }, "description": "OpenAI GPT-5 Chat Latest is an AI model provided by helicone.", "family": "gpt-codex", "id": "gpt-5-chat-latest", "knowledge": "2024-09", "last_updated": "2024-09-30", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "OpenAI GPT-5 Chat Latest", "open_weights": false, "reasoning": false, "release_date": "2024-09-30", "temperature": false, "tool_call": true }, "gpt-5-codex": { "attachment": false, "cost": { "cache_read": 0.12500000000000003, "input": 1.25, "output": 10 }, "description": "OpenAI: GPT-5 Codex is an AI model provided by helicone.", "family": "gpt-codex", "id": "gpt-5-codex", "knowledge": "2025-01", "last_updated": "2025-01-01", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "OpenAI: GPT-5 Codex", "open_weights": false, "reasoning": false, "release_date": "2025-01-01", "temperature": false, "tool_call": true }, "gpt-5-mini": { "attachment": false, "cost": { "cache_read": 0.024999999999999998, "input": 0.25, "output": 2 }, "description": "OpenAI GPT-5 Mini is an AI model provided by helicone.", "family": "gpt-mini", "id": "gpt-5-mini", "knowledge": "2025-01", "last_updated": "2025-01-01", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "OpenAI GPT-5 Mini", "open_weights": false, "reasoning": false, "release_date": "2025-01-01", "temperature": false, "tool_call": true }, "gpt-5-nano": { "attachment": false, "cost": { "cache_read": 0.005, "input": 0.049999999999999996, "output": 0.39999999999999997 }, "description": "OpenAI GPT-5 Nano is an AI model provided by helicone.", "family": "gpt-nano", "id": "gpt-5-nano", "knowledge": "2025-01", "last_updated": "2025-01-01", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "OpenAI GPT-5 Nano", "open_weights": false, "reasoning": false, "release_date": "2025-01-01", "temperature": false, "tool_call": true }, "gpt-5-pro": { "attachment": false, "cost": { "input": 15, "output": 120 }, "description": "OpenAI: GPT-5 Pro is an AI model provided by helicone.", "family": "gpt-pro", "id": "gpt-5-pro", "knowledge": "2025-01", "last_updated": "2025-01-01", "limit": { "context": 128000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "OpenAI: GPT-5 Pro", "open_weights": false, "reasoning": false, "release_date": "2025-01-01", "temperature": false, "tool_call": false }, "gpt-5.1": { "attachment": false, "cost": { "cache_read": 0.12500000000000003, "input": 1.25, "output": 10 }, "description": "OpenAI GPT-5.1 is an AI model provided by helicone.", "family": "gpt", "id": "gpt-5.1", "knowledge": "2025-01", "last_updated": "2025-01-01", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text", "image" ] }, "name": "OpenAI GPT-5.1", "open_weights": false, "reasoning": false, "release_date": "2025-01-01", "temperature": false, "tool_call": true }, "gpt-5.1-chat-latest": { "attachment": false, "cost": { "cache_read": 0.12500000000000003, "input": 1.25, "output": 10 }, "description": "OpenAI GPT-5.1 Chat is an AI model provided by helicone.", "family": "gpt-codex", "id": "gpt-5.1-chat-latest", "knowledge": "2025-01", "last_updated": "2025-01-01", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text", "image" ] }, "name": "OpenAI GPT-5.1 Chat", "open_weights": false, "reasoning": false, "release_date": "2025-01-01", "temperature": false, "tool_call": true }, "gpt-5.1-codex": { "attachment": false, "cost": { "cache_read": 0.12500000000000003, "input": 1.25, "output": 10 }, "description": "OpenAI: GPT-5.1 Codex is an AI model provided by helicone.", "family": "gpt-codex", "id": "gpt-5.1-codex", "knowledge": "2025-01", "last_updated": "2025-01-01", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text", "image" ] }, "name": "OpenAI: GPT-5.1 Codex", "open_weights": false, "reasoning": false, "release_date": "2025-01-01", "temperature": false, "tool_call": true }, "gpt-5.1-codex-mini": { "attachment": false, "cost": { "cache_read": 0.024999999999999998, "input": 0.25, "output": 2 }, "description": "OpenAI: GPT-5.1 Codex Mini is an AI model provided by helicone.", "family": "gpt-codex", "id": "gpt-5.1-codex-mini", "knowledge": "2025-01", "last_updated": "2025-01-01", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text", "image" ] }, "name": "OpenAI: GPT-5.1 Codex Mini", "open_weights": false, "reasoning": false, "release_date": "2025-01-01", "temperature": false, "tool_call": true }, "gpt-oss-120b": { "attachment": false, "cost": { "input": 0.04, "output": 0.16 }, "description": "OpenAI GPT-OSS 120b is an AI model provided by helicone.", "family": "gpt-oss", "id": "gpt-oss-120b", "knowledge": "2024-06", "last_updated": "2024-06-01", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "OpenAI GPT-OSS 120b", "open_weights": false, "reasoning": true, "release_date": "2024-06-01", "temperature": true, "tool_call": true }, "gpt-oss-20b": { "attachment": false, "cost": { "input": 0.049999999999999996, "output": 0.19999999999999998 }, "description": "OpenAI GPT-OSS 20b is an AI model provided by helicone.", "family": "gpt-oss", "id": "gpt-oss-20b", "knowledge": "2024-06", "last_updated": "2024-06-01", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "OpenAI GPT-OSS 20b", "open_weights": false, "reasoning": true, "release_date": "2024-06-01", "temperature": true, "tool_call": true }, "grok-3": { "attachment": false, "cost": { "cache_read": 0.75, "input": 3, "output": 15 }, "description": "xAI Grok 3 is an AI model provided by helicone.", "family": "grok", "id": "grok-3", "knowledge": "2024-06", "last_updated": "2024-06-01", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "xAI Grok 3", "open_weights": false, "reasoning": false, "release_date": "2024-06-01", "temperature": true, "tool_call": true }, "grok-3-mini": { "attachment": false, "cost": { "cache_read": 0.075, "input": 0.3, "output": 0.5 }, "description": "xAI Grok 3 Mini is an AI model provided by helicone.", "family": "grok", "id": "grok-3-mini", "knowledge": "2024-06", "last_updated": "2024-06-01", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "xAI Grok 3 Mini", "open_weights": false, "reasoning": false, "release_date": "2024-06-01", "temperature": true, "tool_call": true }, "grok-4": { "attachment": false, "cost": { "cache_read": 0.75, "input": 3, "output": 15 }, "description": "xAI Grok 4 is an AI model provided by helicone.", "family": "grok", "id": "grok-4", "knowledge": "2024-07", "last_updated": "2024-07-09", "limit": { "context": 256000, "output": 256000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "xAI Grok 4", "open_weights": false, "reasoning": false, "release_date": "2024-07-09", "temperature": true, "tool_call": true }, "grok-4-1-fast-non-reasoning": { "attachment": false, "cost": { "cache_read": 0.049999999999999996, "input": 0.19999999999999998, "output": 0.5 }, "description": "xAI Grok 4.1 Fast Non-Reasoning is an AI model provided by helicone.", "family": "grok", "id": "grok-4-1-fast-non-reasoning", "knowledge": "2025-11", "last_updated": "2025-11-17", "limit": { "context": 2000000, "output": 30000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text", "image" ] }, "name": "xAI Grok 4.1 Fast Non-Reasoning", "open_weights": false, "reasoning": false, "release_date": "2025-11-17", "temperature": true, "tool_call": true }, "grok-4-1-fast-reasoning": { "attachment": false, "cost": { "cache_read": 0.049999999999999996, "input": 0.19999999999999998, "output": 0.5 }, "description": "xAI Grok 4.1 Fast Reasoning is an AI model provided by helicone.", "family": "grok", "id": "grok-4-1-fast-reasoning", "knowledge": "2025-11", "last_updated": "2025-11-17", "limit": { "context": 2000000, "output": 2000000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "xAI Grok 4.1 Fast Reasoning", "open_weights": false, "reasoning": true, "release_date": "2025-11-17", "temperature": true, "tool_call": true }, "grok-4-fast-non-reasoning": { "attachment": false, "cost": { "cache_read": 0.049999999999999996, "input": 0.19999999999999998, "output": 0.5 }, "description": "xAI Grok 4 Fast Non-Reasoning is an AI model provided by helicone.", "family": "grok", "id": "grok-4-fast-non-reasoning", "knowledge": "2025-09", "last_updated": "2025-09-19", "limit": { "context": 2000000, "output": 2000000 }, "modalities": { "input": [ "text", "image", "audio" ], "output": [ "text" ] }, "name": "xAI Grok 4 Fast Non-Reasoning", "open_weights": false, "reasoning": false, "release_date": "2025-09-19", "temperature": true, "tool_call": true }, "grok-4-fast-reasoning": { "attachment": false, "cost": { "cache_read": 0.049999999999999996, "input": 0.19999999999999998, "output": 0.5 }, "description": "xAI: Grok 4 Fast Reasoning is an AI model provided by helicone.", "family": "grok", "id": "grok-4-fast-reasoning", "knowledge": "2025-09", "last_updated": "2025-09-01", "limit": { "context": 2000000, "output": 2000000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "xAI: Grok 4 Fast Reasoning", "open_weights": false, "reasoning": true, "release_date": "2025-09-01", "temperature": true, "tool_call": true }, "grok-code-fast-1": { "attachment": false, "cost": { "cache_read": 0.02, "input": 0.19999999999999998, "output": 1.5 }, "description": "xAI Grok Code Fast 1 is an AI model provided by helicone.", "family": "grok", "id": "grok-code-fast-1", "knowledge": "2024-08", "last_updated": "2024-08-25", "limit": { "context": 256000, "output": 10000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "xAI Grok Code Fast 1", "open_weights": false, "reasoning": false, "release_date": "2024-08-25", "temperature": true, "tool_call": true }, "hermes-2-pro-llama-3-8b": { "attachment": false, "cost": { "input": 0.14, "output": 0.14 }, "description": "Hermes 2 Pro Llama 3 8B is an AI model provided by helicone.", "family": "llama", "id": "hermes-2-pro-llama-3-8b", "knowledge": "2024-05", "last_updated": "2024-05-27", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Hermes 2 Pro Llama 3 8B", "open_weights": false, "reasoning": false, "release_date": "2024-05-27", "temperature": true, "tool_call": true }, "kimi-k2-0711": { "attachment": false, "cost": { "input": 0.5700000000000001, "output": 2.3 }, "description": "Kimi K2 (07/11) is an AI model provided by helicone.", "family": "kimi", "id": "kimi-k2-0711", "knowledge": "2025-01", "last_updated": "2025-01-01", "limit": { "context": 131072, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 (07/11)", "open_weights": false, "reasoning": false, "release_date": "2025-01-01", "temperature": true, "tool_call": true }, "kimi-k2-0905": { "attachment": false, "cost": { "cache_read": 0.39999999999999997, "input": 0.5, "output": 2 }, "description": "Kimi K2 (09/05) is an AI model provided by helicone.", "family": "kimi", "id": "kimi-k2-0905", "knowledge": "2025-09", "last_updated": "2025-09-05", "limit": { "context": 262144, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 (09/05)", "open_weights": false, "reasoning": false, "release_date": "2025-09-05", "temperature": true, "tool_call": true }, "kimi-k2-thinking": { "attachment": false, "cost": { "input": 0.48, "output": 2 }, "description": "Kimi K2 Thinking is an AI model provided by helicone.", "family": "kimi-thinking", "id": "kimi-k2-thinking", "knowledge": "2025-11", "last_updated": "2025-11-06", "limit": { "context": 256000, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 Thinking", "open_weights": false, "reasoning": false, "release_date": "2025-11-06", "temperature": true, "tool_call": true }, "llama-3.1-8b-instant": { "attachment": false, "cost": { "input": 0.049999999999999996, "output": 0.08 }, "description": "Meta Llama 3.1 8B Instant is an AI model provided by helicone.", "family": "llama", "id": "llama-3.1-8b-instant", "knowledge": "2024-07", "last_updated": "2024-07-01", "limit": { "context": 131072, "output": 32678 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Meta Llama 3.1 8B Instant", "open_weights": false, "reasoning": false, "release_date": "2024-07-01", "temperature": true, "tool_call": true }, "llama-3.1-8b-instruct": { "attachment": false, "cost": { "input": 0.02, "output": 0.049999999999999996 }, "description": "Meta Llama 3.1 8B Instruct is an AI model provided by helicone.", "family": "llama", "id": "llama-3.1-8b-instruct", "knowledge": "2024-07", "last_updated": "2024-07-23", "limit": { "context": 16384, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Meta Llama 3.1 8B Instruct", "open_weights": false, "reasoning": false, "release_date": "2024-07-23", "temperature": true, "tool_call": true }, "llama-3.1-8b-instruct-turbo": { "attachment": false, "cost": { "input": 0.02, "output": 0.03 }, "description": "Meta Llama 3.1 8B Instruct Turbo is an AI model provided by helicone.", "family": "llama", "id": "llama-3.1-8b-instruct-turbo", "knowledge": "2024-07", "last_updated": "2024-07-23", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Meta Llama 3.1 8B Instruct Turbo", "open_weights": false, "reasoning": false, "release_date": "2024-07-23", "temperature": true, "tool_call": true }, "llama-3.3-70b-instruct": { "attachment": false, "cost": { "input": 0.13, "output": 0.39 }, "description": "Meta Llama 3.3 70B Instruct is an AI model provided by helicone.", "family": "llama", "id": "llama-3.3-70b-instruct", "knowledge": "2024-12", "last_updated": "2024-12-06", "limit": { "context": 128000, "output": 16400 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Meta Llama 3.3 70B Instruct", "open_weights": false, "reasoning": false, "release_date": "2024-12-06", "temperature": true, "tool_call": true }, "llama-3.3-70b-versatile": { "attachment": false, "cost": { "input": 0.59, "output": 0.7899999999999999 }, "description": "Meta Llama 3.3 70B Versatile is an AI model provided by helicone.", "family": "llama", "id": "llama-3.3-70b-versatile", "knowledge": "2024-12", "last_updated": "2024-12-06", "limit": { "context": 131072, "output": 32678 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Meta Llama 3.3 70B Versatile", "open_weights": false, "reasoning": false, "release_date": "2024-12-06", "temperature": true, "tool_call": true }, "llama-4-maverick": { "attachment": false, "cost": { "input": 0.15, "output": 0.6 }, "description": "Meta Llama 4 Maverick 17B 128E is an AI model provided by helicone.", "family": "llama", "id": "llama-4-maverick", "knowledge": "2025-01", "last_updated": "2025-01-01", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Meta Llama 4 Maverick 17B 128E", "open_weights": false, "reasoning": false, "release_date": "2025-01-01", "temperature": true, "tool_call": true }, "llama-4-scout": { "attachment": false, "cost": { "input": 0.08, "output": 0.3 }, "description": "Meta Llama 4 Scout 17B 16E is an AI model provided by helicone.", "family": "llama", "id": "llama-4-scout", "knowledge": "2025-01", "last_updated": "2025-01-01", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Meta Llama 4 Scout 17B 16E", "open_weights": false, "reasoning": false, "release_date": "2025-01-01", "temperature": true, "tool_call": true }, "llama-guard-4": { "attachment": false, "cost": { "input": 0.21, "output": 0.21 }, "description": "Meta Llama Guard 4 12B is an AI model provided by helicone.", "family": "llama", "id": "llama-guard-4", "knowledge": "2025-01", "last_updated": "2025-01-01", "limit": { "context": 131072, "output": 1024 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Meta Llama Guard 4 12B", "open_weights": false, "reasoning": false, "release_date": "2025-01-01", "temperature": true, "tool_call": false }, "llama-prompt-guard-2-22m": { "attachment": false, "cost": { "input": 0.01, "output": 0.01 }, "description": "Meta Llama Prompt Guard 2 22M is an AI model provided by helicone.", "family": "llama", "id": "llama-prompt-guard-2-22m", "knowledge": "2024-10", "last_updated": "2024-10-01", "limit": { "context": 512, "output": 2 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Meta Llama Prompt Guard 2 22M", "open_weights": false, "reasoning": false, "release_date": "2024-10-01", "temperature": true, "tool_call": false }, "llama-prompt-guard-2-86m": { "attachment": false, "cost": { "input": 0.01, "output": 0.01 }, "description": "Meta Llama Prompt Guard 2 86M is an AI model provided by helicone.", "family": "llama", "id": "llama-prompt-guard-2-86m", "knowledge": "2024-10", "last_updated": "2024-10-01", "limit": { "context": 512, "output": 2 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Meta Llama Prompt Guard 2 86M", "open_weights": false, "reasoning": false, "release_date": "2024-10-01", "temperature": true, "tool_call": false }, "mistral-large-2411": { "attachment": false, "cost": { "input": 2, "output": 6 }, "description": "Mistral-Large is an AI model provided by helicone.", "family": "mistral-large", "id": "mistral-large-2411", "knowledge": "2024-07", "last_updated": "2024-07-24", "limit": { "context": 128000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral-Large", "open_weights": false, "reasoning": false, "release_date": "2024-07-24", "temperature": true, "tool_call": true }, "mistral-nemo": { "attachment": false, "cost": { "input": 20, "output": 40 }, "description": "Mistral Nemo is an AI model provided by helicone.", "family": "mistral-nemo", "id": "mistral-nemo", "knowledge": "2024-07", "last_updated": "2024-07-18", "limit": { "context": 128000, "output": 16400 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Mistral Nemo", "open_weights": false, "reasoning": false, "release_date": "2024-07-18", "temperature": true, "tool_call": false }, "mistral-small": { "attachment": false, "cost": { "input": 75, "output": 200 }, "description": "Mistral Small is an AI model provided by helicone.", "family": "mistral-small", "id": "mistral-small", "knowledge": "2024-02", "last_updated": "2024-02-26", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Mistral Small", "open_weights": false, "reasoning": false, "release_date": "2024-02-26", "temperature": true, "tool_call": false }, "o1": { "attachment": false, "cost": { "cache_read": 7.5, "input": 15, "output": 60 }, "description": "OpenAI: o1 is an AI model provided by helicone.", "family": "o", "id": "o1", "knowledge": "2025-01", "last_updated": "2025-01-01", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "OpenAI: o1", "open_weights": false, "reasoning": false, "release_date": "2025-01-01", "temperature": false, "tool_call": false }, "o1-mini": { "attachment": false, "cost": { "cache_read": 0.55, "input": 1.1, "output": 4.4 }, "description": "OpenAI: o1-mini is an AI model provided by helicone.", "family": "o-mini", "id": "o1-mini", "knowledge": "2025-01", "last_updated": "2025-01-01", "limit": { "context": 128000, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "OpenAI: o1-mini", "open_weights": false, "reasoning": false, "release_date": "2025-01-01", "temperature": false, "tool_call": false }, "o3": { "attachment": false, "cost": { "cache_read": 0.5, "input": 2, "output": 8 }, "description": "OpenAI o3 is an AI model provided by helicone.", "family": "o", "id": "o3", "knowledge": "2024-06", "last_updated": "2024-06-01", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "OpenAI o3", "open_weights": false, "reasoning": false, "release_date": "2024-06-01", "temperature": false, "tool_call": true }, "o3-mini": { "attachment": false, "cost": { "cache_read": 0.55, "input": 1.1, "output": 4.4 }, "description": "OpenAI o3 Mini is an AI model provided by helicone.", "family": "o-mini", "id": "o3-mini", "knowledge": "2023-10", "last_updated": "2023-10-01", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "OpenAI o3 Mini", "open_weights": false, "reasoning": false, "release_date": "2023-10-01", "temperature": false, "tool_call": true }, "o3-pro": { "attachment": false, "cost": { "input": 20, "output": 80 }, "description": "OpenAI o3 Pro is an AI model provided by helicone.", "family": "o-pro", "id": "o3-pro", "knowledge": "2024-06", "last_updated": "2024-06-01", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "OpenAI o3 Pro", "open_weights": false, "reasoning": false, "release_date": "2024-06-01", "temperature": false, "tool_call": true }, "o4-mini": { "attachment": false, "cost": { "cache_read": 0.275, "input": 1.1, "output": 4.4 }, "description": "OpenAI o4 Mini is an AI model provided by helicone.", "family": "o-mini", "id": "o4-mini", "knowledge": "2024-06", "last_updated": "2024-06-01", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "OpenAI o4 Mini", "open_weights": false, "reasoning": false, "release_date": "2024-06-01", "temperature": false, "tool_call": true }, "qwen2.5-coder-7b-fast": { "attachment": false, "cost": { "input": 0.03, "output": 0.09 }, "description": "Qwen2.5 Coder 7B fast is an AI model provided by helicone.", "family": "qwen", "id": "qwen2.5-coder-7b-fast", "knowledge": "2024-09", "last_updated": "2024-09-15", "limit": { "context": 32000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen2.5 Coder 7B fast", "open_weights": false, "reasoning": false, "release_date": "2024-09-15", "temperature": true, "tool_call": false }, "qwen3-235b-a22b-thinking": { "attachment": false, "cost": { "input": 0.3, "output": 2.9000000000000004 }, "description": "Qwen3 235B A22B Thinking is an AI model provided by helicone.", "family": "qwen", "id": "qwen3-235b-a22b-thinking", "knowledge": "2025-07", "last_updated": "2025-07-25", "limit": { "context": 262144, "output": 81920 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen3 235B A22B Thinking", "open_weights": false, "reasoning": true, "release_date": "2025-07-25", "temperature": true, "tool_call": false }, "qwen3-30b-a3b": { "attachment": false, "cost": { "input": 0.08, "output": 0.29 }, "description": "Qwen3 30B A3B is an AI model provided by helicone.", "family": "qwen", "id": "qwen3-30b-a3b", "knowledge": "2025-06", "last_updated": "2025-06-01", "limit": { "context": 41000, "output": 41000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen3 30B A3B", "open_weights": false, "reasoning": false, "release_date": "2025-06-01", "temperature": true, "tool_call": true }, "qwen3-32b": { "attachment": false, "cost": { "input": 0.29, "output": 0.59 }, "description": "Qwen3 32B is an AI model provided by helicone.", "family": "qwen", "id": "qwen3-32b", "knowledge": "2025-04", "last_updated": "2025-04-28", "limit": { "context": 131072, "output": 40960 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 32B", "open_weights": false, "reasoning": true, "release_date": "2025-04-28", "temperature": true, "tool_call": true }, "qwen3-coder": { "attachment": false, "cost": { "input": 0.22, "output": 0.95 }, "description": "Qwen3 Coder 480B A35B Instruct Turbo is an AI model provided by helicone.", "family": "qwen", "id": "qwen3-coder", "knowledge": "2025-07", "last_updated": "2025-07-23", "limit": { "context": 262144, "output": 16384 }, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "name": "Qwen3 Coder 480B A35B Instruct Turbo", "open_weights": false, "reasoning": false, "release_date": "2025-07-23", "temperature": true, "tool_call": true }, "qwen3-coder-30b-a3b-instruct": { "attachment": false, "cost": { "input": 0.09999999999999999, "output": 0.3 }, "description": "Qwen3 Coder 30B A3B Instruct is an AI model provided by helicone.", "family": "qwen", "id": "qwen3-coder-30b-a3b-instruct", "knowledge": "2025-07", "last_updated": "2025-07-31", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Coder 30B A3B Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-07-31", "temperature": true, "tool_call": true }, "qwen3-next-80b-a3b-instruct": { "attachment": false, "cost": { "input": 0.14, "output": 1.4 }, "description": "Qwen3 Next 80B A3B Instruct is an AI model provided by helicone.", "family": "qwen", "id": "qwen3-next-80b-a3b-instruct", "knowledge": "2025-01", "last_updated": "2025-01-01", "limit": { "context": 262000, "output": 16384 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen3 Next 80B A3B Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-01-01", "temperature": true, "tool_call": true }, "qwen3-vl-235b-a22b-instruct": { "attachment": false, "cost": { "input": 0.3, "output": 1.5 }, "description": "Qwen3 VL 235B A22B Instruct is an AI model provided by helicone.", "family": "qwen", "id": "qwen3-vl-235b-a22b-instruct", "knowledge": "2025-09", "last_updated": "2025-09-23", "limit": { "context": 256000, "output": 16384 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen3 VL 235B A22B Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-09-23", "temperature": true, "tool_call": true }, "sonar": { "attachment": false, "cost": { "input": 1, "output": 1 }, "description": "Perplexity Sonar is an AI model provided by helicone.", "family": "sonar", "id": "sonar", "knowledge": "2025-01", "last_updated": "2025-01-27", "limit": { "context": 127000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Perplexity Sonar", "open_weights": false, "reasoning": false, "release_date": "2025-01-27", "temperature": true, "tool_call": false }, "sonar-deep-research": { "attachment": false, "cost": { "input": 2, "output": 8 }, "description": "Perplexity Sonar Deep Research is an AI model provided by helicone.", "family": "sonar-deep-research", "id": "sonar-deep-research", "knowledge": "2025-01", "last_updated": "2025-01-27", "limit": { "context": 127000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Perplexity Sonar Deep Research", "open_weights": false, "reasoning": true, "release_date": "2025-01-27", "temperature": true, "tool_call": false }, "sonar-pro": { "attachment": false, "cost": { "input": 3, "output": 15 }, "description": "Perplexity Sonar Pro is an AI model provided by helicone.", "family": "sonar-pro", "id": "sonar-pro", "knowledge": "2025-01", "last_updated": "2025-01-27", "limit": { "context": 200000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Perplexity Sonar Pro", "open_weights": false, "reasoning": false, "release_date": "2025-01-27", "temperature": true, "tool_call": false }, "sonar-reasoning": { "attachment": false, "cost": { "input": 1, "output": 5 }, "description": "Perplexity Sonar Reasoning is an AI model provided by helicone.", "family": "sonar-reasoning", "id": "sonar-reasoning", "knowledge": "2025-01", "last_updated": "2025-01-27", "limit": { "context": 127000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Perplexity Sonar Reasoning", "open_weights": false, "reasoning": true, "release_date": "2025-01-27", "temperature": true, "tool_call": false }, "sonar-reasoning-pro": { "attachment": false, "cost": { "input": 2, "output": 8 }, "description": "Perplexity Sonar Reasoning Pro is an AI model provided by helicone.", "family": "sonar-reasoning", "id": "sonar-reasoning-pro", "knowledge": "2025-01", "last_updated": "2025-01-27", "limit": { "context": 127000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Perplexity Sonar Reasoning Pro", "open_weights": false, "reasoning": true, "release_date": "2025-01-27", "temperature": true, "tool_call": false } }, "name": "Helicone", "npm": "@ai-sdk/openai-compatible" }, "hpc-ai": { "api": "https://api.hpc-ai.com/inference/v1", "doc": "https://www.hpc-ai.com/doc/docs/quickstart/", "env": [ "HPC_AI_API_KEY" ], "iconURL": "https://models.dev/logos/hpc-ai.svg", "id": "hpc-ai", "models": { "minimax/minimax-m2.5": { "attachment": false, "cost": { "cache_read": 0.014, "input": 0.14, "output": 0.56 }, "description": "MiniMax M2.5 is an AI model provided by hpc-ai.", "family": "minimax-m2.5", "id": "minimax/minimax-m2.5", "last_updated": "2026-03-25", "limit": { "context": 1000000, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M2.5", "open_weights": true, "reasoning": true, "release_date": "2026-02-12", "structured_output": false, "temperature": true, "tool_call": true }, "moonshotai/kimi-k2.5": { "attachment": false, "cost": { "cache_read": 0.03, "input": 0.21, "output": 1 }, "description": "Kimi K2.5 is an AI model provided by hpc-ai.", "family": "kimi", "id": "moonshotai/kimi-k2.5", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-01-01", "last_updated": "2026-03-25", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Kimi K2.5", "open_weights": true, "reasoning": true, "release_date": "2026-01-01", "structured_output": true, "temperature": false, "tool_call": true }, "zai-org/glm-5.1": { "attachment": false, "cost": { "cache_read": 0.12, "input": 0.66, "output": 2 }, "description": "GLM 5.1 is an AI model provided by hpc-ai.", "family": "glm", "id": "zai-org/glm-5.1", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-08", "limit": { "context": 202000, "output": 202000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 5.1", "open_weights": true, "reasoning": true, "release_date": "2026-04-08", "structured_output": true, "temperature": true, "tool_call": true } }, "name": "HPC-AI", "npm": "@ai-sdk/openai-compatible" }, "huggingface": { "api": "https://router.huggingface.co/v1", "doc": "https://huggingface.co/docs/inference-providers", "env": [ "HF_TOKEN" ], "iconURL": "https://models.dev/logos/huggingface.svg", "id": "huggingface", "lobeIcon": "HuggingFace.Color", "models": { "MiniMaxAI/MiniMax-M2.1": { "attachment": false, "cost": { "input": 0.3, "output": 1.2 }, "description": "MiniMax-M2.1 is an AI model provided by huggingface.", "family": "minimax", "id": "MiniMaxAI/MiniMax-M2.1", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-10", "last_updated": "2025-12-23", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.1", "open_weights": true, "reasoning": true, "release_date": "2025-12-23", "temperature": true, "tool_call": true }, "MiniMaxAI/MiniMax-M2.5": { "attachment": false, "cost": { "cache_read": 0.03, "input": 0.3, "output": 1.2 }, "description": "MiniMax-M2.5 is an AI model provided by huggingface.", "family": "minimax", "id": "MiniMaxAI/MiniMax-M2.5", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-02-12", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.5", "open_weights": true, "reasoning": true, "release_date": "2026-02-12", "temperature": true, "tool_call": true }, "MiniMaxAI/MiniMax-M2.7": { "attachment": false, "cost": { "cache_read": 0.06, "input": 0.3, "output": 1.2 }, "description": "MiniMax-M2.7 is an AI model provided by huggingface.", "family": "minimax", "id": "MiniMaxAI/MiniMax-M2.7", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-03-18", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.7", "open_weights": true, "reasoning": true, "release_date": "2026-03-18", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-235B-A22B-Thinking-2507": { "attachment": false, "cost": { "input": 0.3, "output": 3 }, "description": "Qwen3-235B-A22B-Thinking-2507 is an AI model provided by huggingface.", "family": "qwen", "id": "Qwen/Qwen3-235B-A22B-Thinking-2507", "knowledge": "2025-04", "last_updated": "2025-07-25", "limit": { "context": 262144, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3-235B-A22B-Thinking-2507", "open_weights": true, "reasoning": true, "release_date": "2025-07-25", "temperature": true, "tool_call": true }, "Qwen/Qwen3-Coder-480B-A35B-Instruct": { "attachment": false, "cost": { "input": 2, "output": 2 }, "description": "Qwen3-Coder-480B-A35B-Instruct is an AI model provided by huggingface.", "family": "qwen", "id": "Qwen/Qwen3-Coder-480B-A35B-Instruct", "knowledge": "2025-04", "last_updated": "2025-07-23", "limit": { "context": 262144, "output": 66536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3-Coder-480B-A35B-Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-07-23", "temperature": true, "tool_call": true }, "Qwen/Qwen3-Coder-Next": { "attachment": false, "cost": { "input": 0.2, "output": 1.5 }, "description": "Qwen3-Coder-Next is an AI model provided by huggingface.", "family": "qwen", "id": "Qwen/Qwen3-Coder-Next", "knowledge": "2025-04", "last_updated": "2026-02-03", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3-Coder-Next", "open_weights": true, "reasoning": false, "release_date": "2026-02-03", "temperature": true, "tool_call": true }, "Qwen/Qwen3-Embedding-4B": { "attachment": false, "cost": { "input": 0.01, "output": 0 }, "description": "Qwen 3 Embedding 4B is an AI model provided by huggingface.", "family": "qwen", "id": "Qwen/Qwen3-Embedding-4B", "knowledge": "2024-12", "last_updated": "2025-01-01", "limit": { "context": 32000, "output": 2048 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen 3 Embedding 4B", "open_weights": true, "reasoning": false, "release_date": "2025-01-01", "temperature": false, "tool_call": false }, "Qwen/Qwen3-Embedding-8B": { "attachment": false, "cost": { "input": 0.01, "output": 0 }, "description": "Qwen 3 Embedding 8B is an AI model provided by huggingface.", "family": "qwen", "id": "Qwen/Qwen3-Embedding-8B", "knowledge": "2024-12", "last_updated": "2025-01-01", "limit": { "context": 32000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen 3 Embedding 8B", "open_weights": true, "reasoning": false, "release_date": "2025-01-01", "temperature": false, "tool_call": false }, "Qwen/Qwen3-Next-80B-A3B-Instruct": { "attachment": false, "cost": { "input": 0.25, "output": 1 }, "description": "Qwen3-Next-80B-A3B-Instruct is an AI model provided by huggingface.", "family": "qwen", "id": "Qwen/Qwen3-Next-80B-A3B-Instruct", "knowledge": "2025-04", "last_updated": "2025-09-11", "limit": { "context": 262144, "output": 66536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3-Next-80B-A3B-Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-09-11", "temperature": true, "tool_call": true }, "Qwen/Qwen3-Next-80B-A3B-Thinking": { "attachment": false, "cost": { "input": 0.3, "output": 2 }, "description": "Qwen3-Next-80B-A3B-Thinking is an AI model provided by huggingface.", "family": "qwen", "id": "Qwen/Qwen3-Next-80B-A3B-Thinking", "knowledge": "2025-04", "last_updated": "2025-09-11", "limit": { "context": 262144, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3-Next-80B-A3B-Thinking", "open_weights": true, "reasoning": false, "release_date": "2025-09-11", "temperature": true, "tool_call": true }, "Qwen/Qwen3.5-397B-A17B": { "attachment": true, "cost": { "input": 0.6, "output": 3.6 }, "description": "Qwen3.5-397B-A17B is an AI model provided by huggingface.", "family": "qwen", "id": "Qwen/Qwen3.5-397B-A17B", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-04", "last_updated": "2026-02-01", "limit": { "context": 262144, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen3.5-397B-A17B", "open_weights": true, "reasoning": true, "release_date": "2026-02-01", "temperature": true, "tool_call": true }, "XiaomiMiMo/MiMo-V2-Flash": { "attachment": false, "cost": { "input": 0.1, "output": 0.3 }, "description": "MiMo-V2-Flash is an AI model provided by huggingface.", "family": "mimo", "id": "XiaomiMiMo/MiMo-V2-Flash", "knowledge": "2024-12", "last_updated": "2025-12-16", "limit": { "context": 262144, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiMo-V2-Flash", "open_weights": true, "reasoning": true, "release_date": "2025-12-16", "temperature": true, "tool_call": true }, "deepseek-ai/DeepSeek-R1-0528": { "attachment": false, "cost": { "input": 3, "output": 5 }, "description": "DeepSeek-R1-0528 is an AI model provided by huggingface.", "family": "deepseek-thinking", "id": "deepseek-ai/DeepSeek-R1-0528", "knowledge": "2025-05", "last_updated": "2025-05-28", "limit": { "context": 163840, "output": 163840 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek-R1-0528", "open_weights": true, "reasoning": true, "release_date": "2025-05-28", "temperature": true, "tool_call": true }, "deepseek-ai/DeepSeek-V3.2": { "attachment": false, "cost": { "input": 0.28, "output": 0.4 }, "description": "DeepSeek-V3.2 is an AI model provided by huggingface.", "family": "deepseek", "id": "deepseek-ai/DeepSeek-V3.2", "knowledge": "2024-07", "last_updated": "2025-12-01", "limit": { "context": 163840, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek-V3.2", "open_weights": true, "reasoning": true, "release_date": "2025-12-01", "temperature": true, "tool_call": true }, "deepseek-ai/DeepSeek-V4-Pro": { "attachment": false, "cost": { "cache_read": 0.145, "input": 1.74, "output": 3.48 }, "description": "DeepSeek V4 Pro is an AI model provided by huggingface.", "family": "deepseek-thinking", "id": "deepseek-ai/DeepSeek-V4-Pro", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-05", "last_updated": "2026-04-24", "limit": { "context": 1048576, "output": 393216 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V4 Pro", "open_weights": true, "reasoning": true, "release_date": "2026-04-24", "structured_output": true, "temperature": true, "tool_call": true }, "moonshotai/Kimi-K2-Instruct": { "attachment": false, "cost": { "input": 1, "output": 3 }, "description": "Kimi-K2-Instruct is an AI model provided by huggingface.", "family": "kimi", "id": "moonshotai/Kimi-K2-Instruct", "knowledge": "2024-10", "last_updated": "2025-07-14", "limit": { "context": 131072, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi-K2-Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-07-14", "temperature": true, "tool_call": true }, "moonshotai/Kimi-K2-Instruct-0905": { "attachment": false, "cost": { "input": 1, "output": 3 }, "description": "Kimi-K2-Instruct-0905 is an AI model provided by huggingface.", "family": "kimi", "id": "moonshotai/Kimi-K2-Instruct-0905", "knowledge": "2024-10", "last_updated": "2025-09-04", "limit": { "context": 262144, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi-K2-Instruct-0905", "open_weights": true, "reasoning": false, "release_date": "2025-09-04", "temperature": true, "tool_call": true }, "moonshotai/Kimi-K2-Thinking": { "attachment": false, "cost": { "cache_read": 0.15, "input": 0.6, "output": 2.5 }, "description": "Kimi-K2-Thinking is an AI model provided by huggingface.", "family": "kimi-thinking", "id": "moonshotai/Kimi-K2-Thinking", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-08", "last_updated": "2025-11-06", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi-K2-Thinking", "open_weights": true, "reasoning": true, "release_date": "2025-11-06", "temperature": true, "tool_call": true }, "moonshotai/Kimi-K2.5": { "attachment": true, "cost": { "cache_read": 0.1, "input": 0.6, "output": 3 }, "description": "Kimi-K2.5 is an AI model provided by huggingface.", "family": "kimi", "id": "moonshotai/Kimi-K2.5", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-01", "last_updated": "2026-01-01", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Kimi-K2.5", "open_weights": true, "reasoning": true, "release_date": "2026-01-01", "temperature": true, "tool_call": true }, "moonshotai/Kimi-K2.6": { "attachment": true, "cost": { "cache_read": 0.16, "input": 0.95, "output": 4 }, "description": "Kimi-K2.6 is an AI model provided by huggingface.", "family": "kimi", "id": "moonshotai/Kimi-K2.6", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-01", "last_updated": "2026-04-20", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Kimi-K2.6", "open_weights": true, "reasoning": true, "release_date": "2026-04-20", "temperature": true, "tool_call": true }, "zai-org/GLM-4.7": { "attachment": false, "cost": { "cache_read": 0.11, "input": 0.6, "output": 2.2 }, "description": "GLM-4.7 is an AI model provided by huggingface.", "family": "glm", "id": "zai-org/GLM-4.7", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-04", "last_updated": "2025-12-22", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.7", "open_weights": true, "reasoning": true, "release_date": "2025-12-22", "temperature": true, "tool_call": true }, "zai-org/GLM-4.7-Flash": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "GLM-4.7-Flash is an AI model provided by huggingface.", "family": "glm", "id": "zai-org/GLM-4.7-Flash", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-04", "last_updated": "2025-08-08", "limit": { "context": 200000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.7-Flash", "open_weights": true, "reasoning": true, "release_date": "2025-08-08", "temperature": true, "tool_call": true }, "zai-org/GLM-5": { "attachment": false, "cost": { "cache_read": 0.2, "input": 1, "output": 3.2 }, "description": "GLM-5 is an AI model provided by huggingface.", "family": "glm", "id": "zai-org/GLM-5", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-02-11", "limit": { "context": 202752, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5", "open_weights": true, "reasoning": true, "release_date": "2026-02-11", "temperature": true, "tool_call": true }, "zai-org/GLM-5.1": { "attachment": false, "cost": { "cache_read": 0.2, "input": 1, "output": 3.2 }, "description": "GLM-5.1 is an AI model provided by huggingface.", "family": "glm", "id": "zai-org/GLM-5.1", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-03", "limit": { "context": 202752, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5.1", "open_weights": true, "reasoning": true, "release_date": "2026-04-03", "temperature": true, "tool_call": true } }, "name": "Hugging Face", "npm": "@ai-sdk/openai-compatible" }, "iflowcn": { "api": "https://apis.iflow.cn/v1", "doc": "https://platform.iflow.cn/en/docs", "env": [ "IFLOW_API_KEY" ], "iconURL": "https://models.dev/logos/iflowcn.svg", "id": "iflowcn", "models": { "deepseek-r1": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "DeepSeek-R1 is an AI model provided by iflowcn.", "family": "deepseek-thinking", "id": "deepseek-r1", "knowledge": "2024-12", "last_updated": "2025-01-20", "limit": { "context": 128000, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek-R1", "open_weights": true, "reasoning": true, "release_date": "2025-01-20", "temperature": true, "tool_call": true }, "deepseek-v3": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "DeepSeek-V3 is an AI model provided by iflowcn.", "family": "deepseek", "id": "deepseek-v3", "knowledge": "2024-10", "last_updated": "2024-12-26", "limit": { "context": 128000, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek-V3", "open_weights": true, "reasoning": false, "release_date": "2024-12-26", "temperature": true, "tool_call": true }, "deepseek-v3.2": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "DeepSeek-V3.2-Exp is an AI model provided by iflowcn.", "family": "deepseek", "id": "deepseek-v3.2", "knowledge": "2024-12", "last_updated": "2025-01-01", "limit": { "context": 128000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek-V3.2-Exp", "open_weights": true, "reasoning": false, "release_date": "2025-01-01", "temperature": true, "tool_call": true }, "glm-4.6": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "GLM-4.6 is an AI model provided by iflowcn.", "family": "glm", "id": "glm-4.6", "knowledge": "2024-10", "last_updated": "2025-11-13", "limit": { "context": 200000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.6", "open_weights": false, "reasoning": true, "release_date": "2024-12-01", "temperature": true, "tool_call": true }, "kimi-k2": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Kimi-K2 is an AI model provided by iflowcn.", "family": "kimi", "id": "kimi-k2", "knowledge": "2024-10", "last_updated": "2024-12-01", "limit": { "context": 128000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi-K2", "open_weights": false, "reasoning": false, "release_date": "2024-12-01", "temperature": true, "tool_call": true }, "kimi-k2-0905": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Kimi-K2-0905 is an AI model provided by iflowcn.", "family": "kimi", "id": "kimi-k2-0905", "knowledge": "2024-12", "last_updated": "2025-09-05", "limit": { "context": 256000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi-K2-0905", "open_weights": false, "reasoning": false, "release_date": "2025-09-05", "temperature": true, "tool_call": true }, "qwen3-235b": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Qwen3-235B-A22B is an AI model provided by iflowcn.", "family": "qwen", "id": "qwen3-235b", "knowledge": "2024-10", "last_updated": "2024-12-01", "limit": { "context": 128000, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3-235B-A22B", "open_weights": true, "reasoning": true, "release_date": "2024-12-01", "temperature": true, "tool_call": true }, "qwen3-235b-a22b-instruct": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Qwen3-235B-A22B-Instruct is an AI model provided by iflowcn.", "family": "qwen", "id": "qwen3-235b-a22b-instruct", "knowledge": "2025-04", "last_updated": "2025-07-01", "limit": { "context": 256000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3-235B-A22B-Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-07-01", "temperature": true, "tool_call": true }, "qwen3-235b-a22b-thinking-2507": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Qwen3-235B-A22B-Thinking is an AI model provided by iflowcn.", "family": "qwen", "id": "qwen3-235b-a22b-thinking-2507", "knowledge": "2025-04", "last_updated": "2025-07-01", "limit": { "context": 256000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3-235B-A22B-Thinking", "open_weights": true, "reasoning": true, "release_date": "2025-07-01", "temperature": true, "tool_call": true }, "qwen3-32b": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Qwen3-32B is an AI model provided by iflowcn.", "family": "qwen", "id": "qwen3-32b", "knowledge": "2024-10", "last_updated": "2024-12-01", "limit": { "context": 128000, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3-32B", "open_weights": true, "reasoning": false, "release_date": "2024-12-01", "temperature": true, "tool_call": true }, "qwen3-coder-plus": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Qwen3-Coder-Plus is an AI model provided by iflowcn.", "family": "qwen", "id": "qwen3-coder-plus", "knowledge": "2025-04", "last_updated": "2025-07-01", "limit": { "context": 256000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3-Coder-Plus", "open_weights": true, "reasoning": false, "release_date": "2025-07-01", "temperature": true, "tool_call": true }, "qwen3-max": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Qwen3-Max is an AI model provided by iflowcn.", "family": "qwen", "id": "qwen3-max", "knowledge": "2024-12", "last_updated": "2025-01-01", "limit": { "context": 256000, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3-Max", "open_weights": false, "reasoning": false, "release_date": "2025-01-01", "temperature": true, "tool_call": true }, "qwen3-max-preview": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Qwen3-Max-Preview is an AI model provided by iflowcn.", "family": "qwen", "id": "qwen3-max-preview", "knowledge": "2024-12", "last_updated": "2025-01-01", "limit": { "context": 256000, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3-Max-Preview", "open_weights": false, "reasoning": false, "release_date": "2025-01-01", "temperature": true, "tool_call": true }, "qwen3-vl-plus": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Qwen3-VL-Plus is an AI model provided by iflowcn.", "family": "qwen", "id": "qwen3-vl-plus", "knowledge": "2024-12", "last_updated": "2025-01-01", "limit": { "context": 256000, "output": 32000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen3-VL-Plus", "open_weights": false, "reasoning": false, "release_date": "2025-01-01", "temperature": true, "tool_call": true } }, "name": "iFlow", "npm": "@ai-sdk/openai-compatible" }, "inception": { "api": "https://api.inceptionlabs.ai/v1/", "doc": "https://platform.inceptionlabs.ai/docs", "env": [ "INCEPTION_API_KEY" ], "iconURL": "https://models.dev/logos/inception.svg", "id": "inception", "lobeIcon": "Inception", "models": { "mercury-2": { "attachment": false, "cost": { "cache_read": 0.025, "input": 0.25, "output": 0.75 }, "description": "Mercury 2 is an AI model provided by inception.", "family": "mercury", "id": "mercury-2", "knowledge": "2025-01-01", "last_updated": "2026-02-24", "limit": { "context": 128000, "output": 50000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mercury 2", "open_weights": false, "reasoning": true, "release_date": "2026-02-24", "structured_output": true, "temperature": true, "tool_call": true }, "mercury-edit-2": { "attachment": false, "cost": { "cache_read": 0.025, "input": 0.25, "output": 0.75 }, "description": "Mercury Edit 2 is an AI model provided by inception.", "id": "mercury-edit-2", "last_updated": "2026-03-30", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mercury Edit 2", "open_weights": false, "reasoning": true, "release_date": "2026-03-30", "temperature": true, "tool_call": false } }, "name": "Inception", "npm": "@ai-sdk/openai-compatible" }, "inference": { "api": "https://inference.net/v1", "doc": "https://inference.net/models", "env": [ "INFERENCE_API_KEY" ], "iconURL": "https://models.dev/logos/inference.svg", "id": "inference", "lobeIcon": "Xinference", "models": { "google/gemma-3": { "attachment": true, "cost": { "input": 0.15, "output": 0.3 }, "description": "Google Gemma 3 is an AI model provided by inference.", "family": "gemma", "id": "google/gemma-3", "knowledge": "2024-12", "last_updated": "2025-01-01", "limit": { "context": 125000, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Google Gemma 3", "open_weights": true, "reasoning": false, "release_date": "2025-01-01", "temperature": true, "tool_call": true }, "meta/llama-3.1-8b-instruct": { "attachment": false, "cost": { "input": 0.025, "output": 0.025 }, "description": "Llama 3.1 8B Instruct is an AI model provided by inference.", "family": "llama", "id": "meta/llama-3.1-8b-instruct", "knowledge": "2023-12", "last_updated": "2025-01-01", "limit": { "context": 16000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.1 8B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-01-01", "temperature": true, "tool_call": true }, "meta/llama-3.2-11b-vision-instruct": { "attachment": true, "cost": { "input": 0.055, "output": 0.055 }, "description": "Llama 3.2 11B Vision Instruct is an AI model provided by inference.", "family": "llama", "id": "meta/llama-3.2-11b-vision-instruct", "knowledge": "2023-12", "last_updated": "2025-01-01", "limit": { "context": 16000, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Llama 3.2 11B Vision Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-01-01", "temperature": true, "tool_call": true }, "meta/llama-3.2-1b-instruct": { "attachment": false, "cost": { "input": 0.01, "output": 0.01 }, "description": "Llama 3.2 1B Instruct is an AI model provided by inference.", "family": "llama", "id": "meta/llama-3.2-1b-instruct", "knowledge": "2023-12", "last_updated": "2025-01-01", "limit": { "context": 16000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.2 1B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-01-01", "temperature": true, "tool_call": true }, "meta/llama-3.2-3b-instruct": { "attachment": false, "cost": { "input": 0.02, "output": 0.02 }, "description": "Llama 3.2 3B Instruct is an AI model provided by inference.", "family": "llama", "id": "meta/llama-3.2-3b-instruct", "knowledge": "2023-12", "last_updated": "2025-01-01", "limit": { "context": 16000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.2 3B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-01-01", "temperature": true, "tool_call": true }, "mistral/mistral-nemo-12b-instruct": { "attachment": false, "cost": { "input": 0.038, "output": 0.1 }, "description": "Mistral Nemo 12B Instruct is an AI model provided by inference.", "family": "mistral-nemo", "id": "mistral/mistral-nemo-12b-instruct", "knowledge": "2024-12", "last_updated": "2025-01-01", "limit": { "context": 16000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral Nemo 12B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-01-01", "temperature": true, "tool_call": true }, "osmosis/osmosis-structure-0.6b": { "attachment": false, "cost": { "input": 0.1, "output": 0.5 }, "description": "Osmosis Structure 0.6B is an AI model provided by inference.", "family": "osmosis", "id": "osmosis/osmosis-structure-0.6b", "knowledge": "2024-12", "last_updated": "2025-01-01", "limit": { "context": 4000, "output": 2048 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Osmosis Structure 0.6B", "open_weights": true, "reasoning": false, "release_date": "2025-01-01", "temperature": true, "tool_call": true }, "qwen/qwen-2.5-7b-vision-instruct": { "attachment": true, "cost": { "input": 0.2, "output": 0.2 }, "description": "Qwen 2.5 7B Vision Instruct is an AI model provided by inference.", "family": "qwen", "id": "qwen/qwen-2.5-7b-vision-instruct", "knowledge": "2024-12", "last_updated": "2025-01-01", "limit": { "context": 125000, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen 2.5 7B Vision Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-01-01", "temperature": true, "tool_call": true }, "qwen/qwen3-embedding-4b": { "attachment": false, "cost": { "input": 0.01, "output": 0 }, "description": "Qwen 3 Embedding 4B is an AI model provided by inference.", "family": "qwen", "id": "qwen/qwen3-embedding-4b", "knowledge": "2024-12", "last_updated": "2025-01-01", "limit": { "context": 32000, "output": 2048 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen 3 Embedding 4B", "open_weights": true, "reasoning": false, "release_date": "2025-01-01", "temperature": false, "tool_call": false } }, "name": "Inference", "npm": "@ai-sdk/openai-compatible" }, "io-net": { "api": "https://api.intelligence.io.solutions/api/v1", "doc": "https://io.net/docs/guides/intelligence/io-intelligence", "env": [ "IOINTELLIGENCE_API_KEY" ], "iconURL": "https://models.dev/logos/io-net.svg", "id": "io-net", "models": { "Intel/Qwen3-Coder-480B-A35B-Instruct-int4-mixed-ar": { "attachment": false, "cost": { "cache_read": 0.11, "cache_write": 0.44, "input": 0.22, "output": 0.95 }, "description": "Qwen 3 Coder 480B is an AI model provided by io-net.", "family": "qwen", "id": "Intel/Qwen3-Coder-480B-A35B-Instruct-int4-mixed-ar", "knowledge": "2024-12", "last_updated": "2025-01-15", "limit": { "context": 106000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen 3 Coder 480B", "open_weights": true, "reasoning": false, "release_date": "2025-01-15", "temperature": true, "tool_call": true }, "Qwen/Qwen2.5-VL-32B-Instruct": { "attachment": false, "cost": { "cache_read": 0.025, "cache_write": 0.1, "input": 0.05, "output": 0.22 }, "description": "Qwen 2.5 VL 32B Instruct is an AI model provided by io-net.", "family": "qwen", "id": "Qwen/Qwen2.5-VL-32B-Instruct", "knowledge": "2024-09", "last_updated": "2024-11-01", "limit": { "context": 32000, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen 2.5 VL 32B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-11-01", "temperature": true, "tool_call": true }, "Qwen/Qwen3-235B-A22B-Thinking-2507": { "attachment": false, "cost": { "cache_read": 0.055, "cache_write": 0.22, "input": 0.11, "output": 0.6 }, "description": "Qwen 3 235B Thinking is an AI model provided by io-net.", "family": "qwen", "id": "Qwen/Qwen3-235B-A22B-Thinking-2507", "knowledge": "2024-12", "last_updated": "2025-07-01", "limit": { "context": 262144, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen 3 235B Thinking", "open_weights": true, "reasoning": true, "release_date": "2025-07-01", "temperature": true, "tool_call": true }, "Qwen/Qwen3-Next-80B-A3B-Instruct": { "attachment": false, "cost": { "cache_read": 0.05, "cache_write": 0.2, "input": 0.1, "output": 0.8 }, "description": "Qwen 3 Next 80B Instruct is an AI model provided by io-net.", "family": "qwen", "id": "Qwen/Qwen3-Next-80B-A3B-Instruct", "knowledge": "2024-12", "last_updated": "2025-01-10", "limit": { "context": 262144, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen 3 Next 80B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-01-10", "temperature": true, "tool_call": true }, "deepseek-ai/DeepSeek-R1-0528": { "attachment": false, "cost": { "cache_read": 1, "cache_write": 4, "input": 2, "output": 8.75 }, "description": "DeepSeek R1 is an AI model provided by io-net.", "family": "deepseek-thinking", "id": "deepseek-ai/DeepSeek-R1-0528", "knowledge": "2024-07", "last_updated": "2025-05-28", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek R1", "open_weights": true, "reasoning": true, "release_date": "2025-01-20", "temperature": true, "tool_call": true }, "meta-llama/Llama-3.2-90B-Vision-Instruct": { "attachment": false, "cost": { "cache_read": 0.175, "cache_write": 0.7, "input": 0.35, "output": 0.4 }, "description": "Llama 3.2 90B Vision Instruct is an AI model provided by io-net.", "family": "llama", "id": "meta-llama/Llama-3.2-90B-Vision-Instruct", "knowledge": "2023-12", "last_updated": "2024-09-25", "limit": { "context": 16000, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Llama 3.2 90B Vision Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-09-25", "temperature": true, "tool_call": true }, "meta-llama/Llama-3.3-70B-Instruct": { "attachment": false, "cost": { "cache_read": 0.065, "cache_write": 0.26, "input": 0.13, "output": 0.38 }, "description": "Llama 3.3 70B Instruct is an AI model provided by io-net.", "family": "llama", "id": "meta-llama/Llama-3.3-70B-Instruct", "knowledge": "2023-12", "last_updated": "2024-12-06", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-12-06", "temperature": true, "tool_call": true }, "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { "attachment": false, "cost": { "cache_read": 0.075, "cache_write": 0.3, "input": 0.15, "output": 0.6 }, "description": "Llama 4 Maverick 17B 128E Instruct is an AI model provided by io-net.", "family": "llama", "id": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8", "knowledge": "2024-12", "last_updated": "2025-01-15", "limit": { "context": 430000, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Llama 4 Maverick 17B 128E Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-01-15", "temperature": true, "tool_call": true }, "mistralai/Devstral-Small-2505": { "attachment": false, "cost": { "cache_read": 0.025, "cache_write": 0.1, "input": 0.05, "output": 0.22 }, "description": "Devstral Small 2505 is an AI model provided by io-net.", "family": "devstral", "id": "mistralai/Devstral-Small-2505", "knowledge": "2024-12", "last_updated": "2025-05-01", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Devstral Small 2505", "open_weights": false, "reasoning": false, "release_date": "2025-05-01", "temperature": true, "tool_call": true }, "mistralai/Magistral-Small-2506": { "attachment": false, "cost": { "cache_read": 0.25, "cache_write": 1, "input": 0.5, "output": 1.5 }, "description": "Magistral Small 2506 is an AI model provided by io-net.", "family": "magistral-small", "id": "mistralai/Magistral-Small-2506", "knowledge": "2025-01", "last_updated": "2025-06-01", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Magistral Small 2506", "open_weights": false, "reasoning": false, "release_date": "2025-06-01", "temperature": true, "tool_call": true }, "mistralai/Mistral-Large-Instruct-2411": { "attachment": false, "cost": { "cache_read": 1, "cache_write": 4, "input": 2, "output": 6 }, "description": "Mistral Large Instruct 2411 is an AI model provided by io-net.", "family": "mistral-large", "id": "mistralai/Mistral-Large-Instruct-2411", "knowledge": "2024-10", "last_updated": "2024-11-01", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Mistral Large Instruct 2411", "open_weights": false, "reasoning": false, "release_date": "2024-11-01", "temperature": true, "tool_call": true }, "mistralai/Mistral-Nemo-Instruct-2407": { "attachment": false, "cost": { "cache_read": 0.01, "cache_write": 0.04, "input": 0.02, "output": 0.04 }, "description": "Mistral Nemo Instruct 2407 is an AI model provided by io-net.", "family": "mistral-nemo", "id": "mistralai/Mistral-Nemo-Instruct-2407", "knowledge": "2024-05", "last_updated": "2024-07-01", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral Nemo Instruct 2407", "open_weights": true, "reasoning": false, "release_date": "2024-07-01", "temperature": true, "tool_call": true }, "moonshotai/Kimi-K2-Instruct-0905": { "attachment": false, "cost": { "cache_read": 0.195, "cache_write": 0.78, "input": 0.39, "output": 1.9 }, "description": "Kimi K2 Instruct is an AI model provided by io-net.", "family": "kimi", "id": "moonshotai/Kimi-K2-Instruct-0905", "knowledge": "2024-08", "last_updated": "2024-09-05", "limit": { "context": 32768, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 Instruct", "open_weights": false, "reasoning": false, "release_date": "2024-09-05", "temperature": true, "tool_call": true }, "moonshotai/Kimi-K2-Thinking": { "attachment": false, "cost": { "cache_read": 0.275, "cache_write": 1.1, "input": 0.55, "output": 2.25 }, "description": "Kimi K2 Thinking is an AI model provided by io-net.", "family": "kimi-thinking", "id": "moonshotai/Kimi-K2-Thinking", "knowledge": "2024-08", "last_updated": "2024-11-01", "limit": { "context": 32768, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 Thinking", "open_weights": false, "reasoning": true, "release_date": "2024-11-01", "temperature": true, "tool_call": true }, "openai/gpt-oss-120b": { "attachment": false, "cost": { "cache_read": 0.02, "cache_write": 0.08, "input": 0.04, "output": 0.4 }, "description": "GPT-OSS 120B is an AI model provided by io-net.", "family": "gpt-oss", "id": "openai/gpt-oss-120b", "knowledge": "2024-10", "last_updated": "2024-12-01", "limit": { "context": 131072, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT-OSS 120B", "open_weights": true, "reasoning": false, "release_date": "2024-12-01", "temperature": true, "tool_call": true }, "openai/gpt-oss-20b": { "attachment": false, "cost": { "cache_read": 0.015, "cache_write": 0.06, "input": 0.03, "output": 0.14 }, "description": "GPT-OSS 20B is an AI model provided by io-net.", "family": "gpt-oss", "id": "openai/gpt-oss-20b", "knowledge": "2024-10", "last_updated": "2024-12-01", "limit": { "context": 64000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT-OSS 20B", "open_weights": true, "reasoning": false, "release_date": "2024-12-01", "temperature": true, "tool_call": true }, "zai-org/GLM-4.6": { "attachment": false, "cost": { "cache_read": 0.2, "cache_write": 0.8, "input": 0.4, "output": 1.75 }, "description": "GLM 4.6 is an AI model provided by io-net.", "family": "glm", "id": "zai-org/GLM-4.6", "knowledge": "2024-10", "last_updated": "2024-11-15", "limit": { "context": 200000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.6", "open_weights": false, "reasoning": false, "release_date": "2024-11-15", "temperature": true, "tool_call": true } }, "name": "IO.NET", "npm": "@ai-sdk/openai-compatible" }, "jiekou": { "api": "https://api.jiekou.ai/openai", "doc": "https://docs.jiekou.ai/docs/support/quickstart?utm_source=github_models.dev", "env": [ "JIEKOU_API_KEY" ], "iconURL": "https://models.dev/logos/jiekou.svg", "id": "jiekou", "models": { "baidu/ernie-4.5-300b-a47b-paddle": { "attachment": false, "cost": { "input": 0.28, "output": 1.1 }, "description": "ERNIE 4.5 300B A47B is an AI model provided by jiekou.", "family": "ernie", "id": "baidu/ernie-4.5-300b-a47b-paddle", "last_updated": "2026-01", "limit": { "context": 123000, "output": 12000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "ERNIE 4.5 300B A47B", "open_weights": true, "reasoning": false, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "baidu/ernie-4.5-vl-424b-a47b": { "attachment": true, "cost": { "input": 0.42, "output": 1.25 }, "description": "ERNIE 4.5 VL 424B A47B is an AI model provided by jiekou.", "family": "ernie", "id": "baidu/ernie-4.5-vl-424b-a47b", "last_updated": "2026-01", "limit": { "context": 123000, "output": 16000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "ERNIE 4.5 VL 424B A47B", "open_weights": true, "reasoning": true, "release_date": "2026-01", "structured_output": false, "temperature": true, "tool_call": true }, "claude-haiku-4-5-20251001": { "attachment": true, "cost": { "input": 0.9, "output": 4.5 }, "description": "claude-haiku-4-5-20251001 is an AI model provided by jiekou.", "family": "claude-haiku", "id": "claude-haiku-4-5-20251001", "last_updated": "2026-01", "limit": { "context": 20000, "output": 64000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "claude-haiku-4-5-20251001", "open_weights": false, "reasoning": false, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "claude-opus-4-1-20250805": { "attachment": true, "cost": { "input": 13.5, "output": 67.5 }, "description": "claude-opus-4-1-20250805 is an AI model provided by jiekou.", "family": "claude-opus", "id": "claude-opus-4-1-20250805", "last_updated": "2026-01", "limit": { "context": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "claude-opus-4-1-20250805", "open_weights": false, "reasoning": false, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "claude-opus-4-20250514": { "attachment": true, "cost": { "input": 13.5, "output": 67.5 }, "description": "claude-opus-4-20250514 is an AI model provided by jiekou.", "family": "claude-opus", "id": "claude-opus-4-20250514", "last_updated": "2026-01", "limit": { "context": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "claude-opus-4-20250514", "open_weights": false, "reasoning": false, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "claude-opus-4-5-20251101": { "attachment": true, "cost": { "input": 4.5, "output": 22.5 }, "description": "claude-opus-4-5-20251101 is an AI model provided by jiekou.", "family": "claude-opus", "id": "claude-opus-4-5-20251101", "last_updated": "2026-01", "limit": { "context": 200000, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "claude-opus-4-5-20251101", "open_weights": false, "reasoning": false, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "claude-opus-4-6": { "attachment": true, "cost": { "input": 5, "output": 25 }, "description": "claude-opus-4-6 is an AI model provided by jiekou.", "family": "claude-opus", "id": "claude-opus-4-6", "knowledge": "2025-05-31", "last_updated": "2026-02", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "claude-opus-4-6", "open_weights": false, "reasoning": true, "release_date": "2026-02", "structured_output": true, "temperature": true, "tool_call": true }, "claude-sonnet-4-20250514": { "attachment": true, "cost": { "input": 2.7, "output": 13.5 }, "description": "claude-sonnet-4-20250514 is an AI model provided by jiekou.", "family": "claude-sonnet", "id": "claude-sonnet-4-20250514", "last_updated": "2026-01", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "claude-sonnet-4-20250514", "open_weights": false, "reasoning": false, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "claude-sonnet-4-5-20250929": { "attachment": true, "cost": { "input": 2.7, "output": 13.5 }, "description": "claude-sonnet-4-5-20250929 is an AI model provided by jiekou.", "family": "claude-sonnet", "id": "claude-sonnet-4-5-20250929", "last_updated": "2026-01", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "claude-sonnet-4-5-20250929", "open_weights": false, "reasoning": false, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek/deepseek-r1-0528": { "attachment": false, "cost": { "input": 0.7, "output": 2.5 }, "description": "DeepSeek R1 0528 is an AI model provided by jiekou.", "family": "deepseek-thinking", "id": "deepseek/deepseek-r1-0528", "last_updated": "2026-01", "limit": { "context": 163840, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek R1 0528", "open_weights": true, "reasoning": true, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek/deepseek-v3-0324": { "attachment": false, "cost": { "input": 0.28, "output": 1.14 }, "description": "DeepSeek V3 0324 is an AI model provided by jiekou.", "family": "deepseek", "id": "deepseek/deepseek-v3-0324", "last_updated": "2026-01", "limit": { "context": 163840, "output": 163840 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3 0324", "open_weights": true, "reasoning": false, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek/deepseek-v3.1": { "attachment": false, "cost": { "input": 0.27, "output": 1 }, "description": "DeepSeek V3.1 is an AI model provided by jiekou.", "family": "deepseek", "id": "deepseek/deepseek-v3.1", "last_updated": "2026-01", "limit": { "context": 163840, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3.1", "open_weights": true, "reasoning": true, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-2.5-flash": { "attachment": true, "cost": { "input": 0.27, "output": 2.25 }, "description": "gemini-2.5-flash is an AI model provided by jiekou.", "family": "gemini-flash", "id": "gemini-2.5-flash", "last_updated": "2026-01", "limit": { "context": 1048576, "output": 65535 }, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text" ] }, "name": "gemini-2.5-flash", "open_weights": false, "reasoning": false, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-2.5-flash-lite": { "attachment": true, "cost": { "input": 0.09, "output": 0.36 }, "description": "gemini-2.5-flash-lite is an AI model provided by jiekou.", "family": "gemini-flash-lite", "id": "gemini-2.5-flash-lite", "last_updated": "2026-01", "limit": { "context": 1048576, "output": 65535 }, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text" ] }, "name": "gemini-2.5-flash-lite", "open_weights": false, "reasoning": false, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-2.5-flash-lite-preview-06-17": { "attachment": true, "cost": { "input": 0.09, "output": 0.36 }, "description": "gemini-2.5-flash-lite-preview-06-17 is an AI model provided by jiekou.", "family": "gemini-flash-lite", "id": "gemini-2.5-flash-lite-preview-06-17", "last_updated": "2026-01", "limit": { "context": 1048576, "output": 65535 }, "modalities": { "input": [ "text", "video", "image", "audio" ], "output": [ "text" ] }, "name": "gemini-2.5-flash-lite-preview-06-17", "open_weights": false, "reasoning": false, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-2.5-flash-lite-preview-09-2025": { "attachment": true, "cost": { "input": 0.09, "output": 0.36 }, "description": "gemini-2.5-flash-lite-preview-09-2025 is an AI model provided by jiekou.", "family": "gemini-flash-lite", "id": "gemini-2.5-flash-lite-preview-09-2025", "last_updated": "2026-01", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text" ] }, "name": "gemini-2.5-flash-lite-preview-09-2025", "open_weights": false, "reasoning": true, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-2.5-flash-preview-05-20": { "attachment": true, "cost": { "input": 0.135, "output": 3.15 }, "description": "gemini-2.5-flash-preview-05-20 is an AI model provided by jiekou.", "family": "gemini-flash", "id": "gemini-2.5-flash-preview-05-20", "last_updated": "2026-01", "limit": { "context": 1048576, "output": 200000 }, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text" ] }, "name": "gemini-2.5-flash-preview-05-20", "open_weights": false, "reasoning": false, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-2.5-pro": { "attachment": true, "cost": { "input": 1.125, "output": 9 }, "description": "gemini-2.5-pro is an AI model provided by jiekou.", "family": "gemini-pro", "id": "gemini-2.5-pro", "last_updated": "2026-01", "limit": { "context": 1048576, "output": 65535 }, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text" ] }, "name": "gemini-2.5-pro", "open_weights": false, "reasoning": false, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-2.5-pro-preview-06-05": { "attachment": true, "cost": { "input": 1.125, "output": 9 }, "description": "gemini-2.5-pro-preview-06-05 is an AI model provided by jiekou.", "family": "gemini-pro", "id": "gemini-2.5-pro-preview-06-05", "last_updated": "2026-01", "limit": { "context": 1048576, "output": 200000 }, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text" ] }, "name": "gemini-2.5-pro-preview-06-05", "open_weights": false, "reasoning": false, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-3-flash-preview": { "attachment": true, "cost": { "input": 0.5, "output": 3 }, "description": "gemini-3-flash-preview is an AI model provided by jiekou.", "family": "gemini-flash", "id": "gemini-3-flash-preview", "last_updated": "2026-01", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text" ] }, "name": "gemini-3-flash-preview", "open_weights": false, "reasoning": false, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-3-pro-preview": { "attachment": true, "cost": { "input": 1.8, "output": 10.8 }, "description": "gemini-3-pro-preview is an AI model provided by jiekou.", "family": "gemini-pro", "id": "gemini-3-pro-preview", "last_updated": "2026-01", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text" ] }, "name": "gemini-3-pro-preview", "open_weights": false, "reasoning": false, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "gpt-5-chat-latest": { "attachment": true, "cost": { "input": 1.125, "output": 9 }, "description": "gpt-5-chat-latest is an AI model provided by jiekou.", "family": "gpt", "id": "gpt-5-chat-latest", "last_updated": "2026-01", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "gpt-5-chat-latest", "open_weights": false, "reasoning": false, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "gpt-5-codex": { "attachment": true, "cost": { "input": 1.125, "output": 9 }, "description": "gpt-5-codex is an AI model provided by jiekou.", "family": "gpt-codex", "id": "gpt-5-codex", "last_updated": "2026-01", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "gpt-5-codex", "open_weights": false, "reasoning": false, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "gpt-5-mini": { "attachment": true, "cost": { "input": 0.225, "output": 1.8 }, "description": "gpt-5-mini is an AI model provided by jiekou.", "family": "gpt-mini", "id": "gpt-5-mini", "last_updated": "2026-01", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "gpt-5-mini", "open_weights": false, "reasoning": true, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "gpt-5-nano": { "attachment": true, "cost": { "input": 0.045, "output": 0.36 }, "description": "gpt-5-nano is an AI model provided by jiekou.", "family": "gpt-nano", "id": "gpt-5-nano", "last_updated": "2026-01", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "gpt-5-nano", "open_weights": false, "reasoning": false, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "gpt-5-pro": { "attachment": true, "cost": { "input": 13.5, "output": 108 }, "description": "gpt-5-pro is an AI model provided by jiekou.", "family": "gpt-pro", "id": "gpt-5-pro", "last_updated": "2026-01", "limit": { "context": 400000, "output": 272000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "gpt-5-pro", "open_weights": false, "reasoning": true, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "gpt-5.1": { "attachment": true, "cost": { "input": 1.125, "output": 9 }, "description": "gpt-5.1 is an AI model provided by jiekou.", "family": "gpt", "id": "gpt-5.1", "last_updated": "2026-02", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "gpt-5.1", "open_weights": false, "reasoning": true, "release_date": "2026-02", "structured_output": true, "temperature": true, "tool_call": true }, "gpt-5.1-codex": { "attachment": true, "cost": { "input": 1.125, "output": 9 }, "description": "gpt-5.1-codex is an AI model provided by jiekou.", "family": "gpt-codex", "id": "gpt-5.1-codex", "last_updated": "2026-01", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "gpt-5.1-codex", "open_weights": false, "reasoning": true, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "gpt-5.1-codex-max": { "attachment": true, "cost": { "input": 1.125, "output": 9 }, "description": "gpt-5.1-codex-max is an AI model provided by jiekou.", "family": "gpt-codex", "id": "gpt-5.1-codex-max", "last_updated": "2026-01", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "gpt-5.1-codex-max", "open_weights": false, "reasoning": true, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "gpt-5.1-codex-mini": { "attachment": true, "cost": { "input": 0.225, "output": 1.8 }, "description": "gpt-5.1-codex-mini is an AI model provided by jiekou.", "family": "gpt-codex", "id": "gpt-5.1-codex-mini", "last_updated": "2026-01", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "gpt-5.1-codex-mini", "open_weights": false, "reasoning": true, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "gpt-5.2": { "attachment": true, "cost": { "input": 1.575, "output": 12.6 }, "description": "gpt-5.2 is an AI model provided by jiekou.", "family": "gpt", "id": "gpt-5.2", "last_updated": "2026-01", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "gpt-5.2", "open_weights": false, "reasoning": false, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "gpt-5.2-codex": { "attachment": true, "cost": { "input": 1.75, "output": 14 }, "description": "gpt-5.2-codex is an AI model provided by jiekou.", "family": "gpt-codex", "id": "gpt-5.2-codex", "last_updated": "2026-01", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "gpt-5.2-codex", "open_weights": false, "reasoning": true, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "gpt-5.2-pro": { "attachment": true, "cost": { "input": 18.9, "output": 151.2 }, "description": "gpt-5.2-pro is an AI model provided by jiekou.", "family": "gpt-pro", "id": "gpt-5.2-pro", "last_updated": "2026-01", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "gpt-5.2-pro", "open_weights": false, "reasoning": true, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "grok-4-0709": { "attachment": true, "cost": { "input": 2.7, "output": 13.5 }, "description": "grok-4-0709 is an AI model provided by jiekou.", "family": "grok", "id": "grok-4-0709", "last_updated": "2026-01", "limit": { "context": 256000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "grok-4-0709", "open_weights": false, "reasoning": false, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "grok-4-1-fast-non-reasoning": { "attachment": true, "cost": { "input": 0.18, "output": 0.45 }, "description": "grok-4-1-fast-non-reasoning is an AI model provided by jiekou.", "family": "grok", "id": "grok-4-1-fast-non-reasoning", "last_updated": "2026-01", "limit": { "context": 2000000, "output": 2000000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "grok-4-1-fast-non-reasoning", "open_weights": false, "reasoning": false, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "grok-4-1-fast-reasoning": { "attachment": true, "cost": { "input": 0.18, "output": 0.45 }, "description": "grok-4-1-fast-reasoning is an AI model provided by jiekou.", "family": "grok", "id": "grok-4-1-fast-reasoning", "last_updated": "2026-01", "limit": { "context": 2000000, "output": 2000000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "grok-4-1-fast-reasoning", "open_weights": false, "reasoning": false, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "grok-4-fast-non-reasoning": { "attachment": true, "cost": { "input": 0.18, "output": 0.45 }, "description": "grok-4-fast-non-reasoning is an AI model provided by jiekou.", "family": "grok", "id": "grok-4-fast-non-reasoning", "last_updated": "2026-01", "limit": { "context": 2000000, "output": 2000000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "grok-4-fast-non-reasoning", "open_weights": false, "reasoning": false, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "grok-4-fast-reasoning": { "attachment": true, "cost": { "input": 0.18, "output": 0.45 }, "description": "grok-4-fast-reasoning is an AI model provided by jiekou.", "family": "grok", "id": "grok-4-fast-reasoning", "last_updated": "2026-01", "limit": { "context": 2000000, "output": 2000000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "grok-4-fast-reasoning", "open_weights": false, "reasoning": false, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "grok-code-fast-1": { "attachment": true, "cost": { "input": 0.18, "output": 1.35 }, "description": "grok-code-fast-1 is an AI model provided by jiekou.", "family": "grok", "id": "grok-code-fast-1", "last_updated": "2026-01", "limit": { "context": 256000, "output": 256000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "grok-code-fast-1", "open_weights": false, "reasoning": false, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "minimax/minimax-m2.1": { "attachment": false, "cost": { "input": 0.3, "output": 1.2 }, "description": "Minimax M2.1 is an AI model provided by jiekou.", "family": "minimax", "id": "minimax/minimax-m2.1", "last_updated": "2026-01", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Minimax M2.1", "open_weights": true, "reasoning": true, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "minimaxai/minimax-m1-80k": { "attachment": false, "cost": { "input": 0.55, "output": 2.2 }, "description": "MiniMax M1 is an AI model provided by jiekou.", "family": "minimax", "id": "minimaxai/minimax-m1-80k", "last_updated": "2026-01", "limit": { "context": 1000000, "output": 40000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M1", "open_weights": true, "reasoning": true, "release_date": "2026-01", "structured_output": false, "temperature": true, "tool_call": true }, "moonshotai/kimi-k2-0905": { "attachment": false, "cost": { "input": 0.6, "output": 2.5 }, "description": "Kimi K2 0905 is an AI model provided by jiekou.", "family": "kimi", "id": "moonshotai/kimi-k2-0905", "last_updated": "2026-01", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 0905", "open_weights": true, "reasoning": false, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "moonshotai/kimi-k2-instruct": { "attachment": false, "cost": { "input": 0.57, "output": 2.3 }, "description": "Kimi K2 Instruct is an AI model provided by jiekou.", "family": "kimi", "id": "moonshotai/kimi-k2-instruct", "last_updated": "2026-01", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 Instruct", "open_weights": true, "reasoning": false, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "moonshotai/kimi-k2.5": { "attachment": true, "cost": { "input": 0.6, "output": 3 }, "description": "Kimi K2.5 is an AI model provided by jiekou.", "family": "kimi", "id": "moonshotai/kimi-k2.5", "last_updated": "2026-01", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Kimi K2.5", "open_weights": true, "reasoning": true, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "o3": { "attachment": true, "cost": { "input": 10, "output": 40 }, "description": "o3 is an AI model provided by jiekou.", "id": "o3", "last_updated": "2026-01", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "o3", "open_weights": false, "reasoning": false, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "o3-mini": { "attachment": true, "cost": { "input": 1.1, "output": 4.4 }, "description": "o3-mini is an AI model provided by jiekou.", "family": "o", "id": "o3-mini", "last_updated": "2026-01", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "o3-mini", "open_weights": false, "reasoning": false, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "o4-mini": { "attachment": true, "cost": { "input": 1.1, "output": 4.4 }, "description": "o4-mini is an AI model provided by jiekou.", "family": "o", "id": "o4-mini", "last_updated": "2026-01", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "o4-mini", "open_weights": false, "reasoning": false, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "qwen/qwen3-235b-a22b-fp8": { "attachment": false, "cost": { "input": 0.2, "output": 0.8 }, "description": "Qwen3 235B A22B is an AI model provided by jiekou.", "family": "qwen", "id": "qwen/qwen3-235b-a22b-fp8", "last_updated": "2026-01", "limit": { "context": 40960, "output": 20000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 235B A22B", "open_weights": true, "reasoning": true, "release_date": "2026-01", "structured_output": false, "temperature": true, "tool_call": false }, "qwen/qwen3-235b-a22b-instruct-2507": { "attachment": false, "cost": { "input": 0.15, "output": 0.8 }, "description": "Qwen3 235B A22B Instruct 2507 is an AI model provided by jiekou.", "family": "qwen", "id": "qwen/qwen3-235b-a22b-instruct-2507", "last_updated": "2026-01", "limit": { "context": 131072, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 235B A22B Instruct 2507", "open_weights": true, "reasoning": false, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "qwen/qwen3-235b-a22b-thinking-2507": { "attachment": false, "cost": { "input": 0.3, "output": 3 }, "description": "Qwen3 235B A22b Thinking 2507 is an AI model provided by jiekou.", "family": "qwen", "id": "qwen/qwen3-235b-a22b-thinking-2507", "last_updated": "2026-01", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 235B A22b Thinking 2507", "open_weights": true, "reasoning": true, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "qwen/qwen3-30b-a3b-fp8": { "attachment": false, "cost": { "input": 0.09, "output": 0.45 }, "description": "Qwen3 30B A3B is an AI model provided by jiekou.", "family": "qwen", "id": "qwen/qwen3-30b-a3b-fp8", "last_updated": "2026-01", "limit": { "context": 40960, "output": 20000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 30B A3B", "open_weights": true, "reasoning": true, "release_date": "2026-01", "structured_output": false, "temperature": true, "tool_call": false }, "qwen/qwen3-32b-fp8": { "attachment": false, "cost": { "input": 0.1, "output": 0.45 }, "description": "Qwen3 32B is an AI model provided by jiekou.", "family": "qwen", "id": "qwen/qwen3-32b-fp8", "last_updated": "2026-01", "limit": { "context": 40960, "output": 20000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 32B", "open_weights": true, "reasoning": true, "release_date": "2026-01", "structured_output": false, "temperature": true, "tool_call": false }, "qwen/qwen3-coder-480b-a35b-instruct": { "attachment": false, "cost": { "input": 0.29, "output": 1.2 }, "description": "Qwen3 Coder 480B A35B Instruct is an AI model provided by jiekou.", "family": "qwen", "id": "qwen/qwen3-coder-480b-a35b-instruct", "last_updated": "2026-01", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Coder 480B A35B Instruct", "open_weights": true, "reasoning": false, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "qwen/qwen3-coder-next": { "attachment": false, "cost": { "input": 0.2, "output": 1.5 }, "description": "qwen/qwen3-coder-next is an AI model provided by jiekou.", "family": "qwen", "id": "qwen/qwen3-coder-next", "last_updated": "2026-02", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "qwen/qwen3-coder-next", "open_weights": true, "reasoning": false, "release_date": "2026-02", "structured_output": true, "temperature": true, "tool_call": true }, "qwen/qwen3-next-80b-a3b-instruct": { "attachment": false, "cost": { "input": 0.15, "output": 1.5 }, "description": "Qwen3 Next 80B A3B Instruct is an AI model provided by jiekou.", "family": "qwen", "id": "qwen/qwen3-next-80b-a3b-instruct", "last_updated": "2026-01", "limit": { "context": 65536, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Next 80B A3B Instruct", "open_weights": true, "reasoning": false, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "qwen/qwen3-next-80b-a3b-thinking": { "attachment": false, "cost": { "input": 0.15, "output": 1.5 }, "description": "Qwen3 Next 80B A3B Thinking is an AI model provided by jiekou.", "family": "qwen", "id": "qwen/qwen3-next-80b-a3b-thinking", "last_updated": "2026-01", "limit": { "context": 65536, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Next 80B A3B Thinking", "open_weights": true, "reasoning": true, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "xiaomimimo/mimo-v2-flash": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "XiaomiMiMo/MiMo-V2-Flash is an AI model provided by jiekou.", "family": "mimo", "id": "xiaomimimo/mimo-v2-flash", "last_updated": "2026-01", "limit": { "context": 262144, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "XiaomiMiMo/MiMo-V2-Flash", "open_weights": true, "reasoning": true, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "zai-org/glm-4.5": { "attachment": false, "cost": { "input": 0.6, "output": 2.2 }, "description": "GLM-4.5 is an AI model provided by jiekou.", "family": "glm", "id": "zai-org/glm-4.5", "last_updated": "2026-01", "limit": { "context": 131072, "output": 98304 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.5", "open_weights": true, "reasoning": true, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "zai-org/glm-4.5v": { "attachment": true, "cost": { "input": 0.6, "output": 1.8 }, "description": "GLM 4.5V is an AI model provided by jiekou.", "family": "glmv", "id": "zai-org/glm-4.5v", "last_updated": "2026-01", "limit": { "context": 65536, "output": 16384 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "GLM 4.5V", "open_weights": true, "reasoning": true, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "zai-org/glm-4.7": { "attachment": false, "cost": { "input": 0.6, "output": 2.2 }, "description": "GLM-4.7 is an AI model provided by jiekou.", "family": "glm", "id": "zai-org/glm-4.7", "last_updated": "2026-01", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.7", "open_weights": true, "reasoning": true, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "zai-org/glm-4.7-flash": { "attachment": false, "cost": { "input": 0.07, "output": 0.4 }, "description": "GLM-4.7-Flash is an AI model provided by jiekou.", "family": "glm", "id": "zai-org/glm-4.7-flash", "last_updated": "2026-01", "limit": { "context": 200000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.7-Flash", "open_weights": true, "reasoning": true, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true } }, "name": "Jiekou.AI", "npm": "@ai-sdk/openai-compatible" }, "kilo": { "api": "https://api.kilo.ai/api/gateway", "doc": "https://kilo.ai", "env": [ "KILO_API_KEY" ], "iconURL": "https://models.dev/logos/kilo.svg", "id": "kilo", "models": { "ai21/jamba-large-1.7": { "attachment": false, "cost": { "input": 2, "output": 8 }, "description": "AI21: Jamba Large 1.7 is an AI model provided by kilo.", "id": "ai21/jamba-large-1.7", "last_updated": "2026-03-15", "limit": { "context": 256000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "AI21: Jamba Large 1.7", "open_weights": false, "reasoning": false, "release_date": "2025-08-09", "temperature": true, "tool_call": true }, "aion-labs/aion-1.0": { "attachment": false, "cost": { "input": 4, "output": 8 }, "description": "AionLabs: Aion-1.0 is an AI model provided by kilo.", "id": "aion-labs/aion-1.0", "last_updated": "2026-03-15", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "AionLabs: Aion-1.0", "open_weights": false, "reasoning": true, "release_date": "2025-02-05", "temperature": true, "tool_call": false }, "aion-labs/aion-1.0-mini": { "attachment": false, "cost": { "input": 0.7, "output": 1.4 }, "description": "AionLabs: Aion-1.0-Mini is an AI model provided by kilo.", "id": "aion-labs/aion-1.0-mini", "last_updated": "2026-03-15", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "AionLabs: Aion-1.0-Mini", "open_weights": false, "reasoning": true, "release_date": "2025-02-05", "temperature": true, "tool_call": false }, "aion-labs/aion-2.0": { "attachment": false, "cost": { "input": 0.8, "output": 1.6 }, "description": "AionLabs: Aion-2.0 is an AI model provided by kilo.", "id": "aion-labs/aion-2.0", "last_updated": "2026-03-15", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "AionLabs: Aion-2.0", "open_weights": false, "reasoning": true, "release_date": "2026-02-24", "temperature": true, "tool_call": false }, "aion-labs/aion-rp-llama-3.1-8b": { "attachment": false, "cost": { "input": 0.8, "output": 1.6 }, "description": "AionLabs: Aion-RP 1.0 (8B) is an AI model provided by kilo.", "id": "aion-labs/aion-rp-llama-3.1-8b", "last_updated": "2026-03-15", "limit": { "context": 32768, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "AionLabs: Aion-RP 1.0 (8B)", "open_weights": false, "reasoning": false, "release_date": "2025-02-05", "temperature": true, "tool_call": false }, "alfredpros/codellama-7b-instruct-solidity": { "attachment": false, "cost": { "input": 0.8, "output": 1.2 }, "description": "AlfredPros: CodeLLaMa 7B Instruct Solidity is an AI model provided by kilo.", "id": "alfredpros/codellama-7b-instruct-solidity", "last_updated": "2026-03-15", "limit": { "context": 4096, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "AlfredPros: CodeLLaMa 7B Instruct Solidity", "open_weights": true, "reasoning": false, "release_date": "2025-04-14", "temperature": true, "tool_call": false }, "alibaba/tongyi-deepresearch-30b-a3b": { "attachment": false, "cost": { "input": 0.09, "output": 0.45 }, "description": "Tongyi DeepResearch 30B A3B is an AI model provided by kilo.", "id": "alibaba/tongyi-deepresearch-30b-a3b", "last_updated": "2026-03-15", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Tongyi DeepResearch 30B A3B", "open_weights": false, "reasoning": true, "release_date": "2025-09-18", "temperature": true, "tool_call": true }, "allenai/olmo-3-32b-think": { "attachment": false, "cost": { "input": 0.15, "output": 0.5 }, "description": "AllenAI: Olmo 3 32B Think is an AI model provided by kilo.", "id": "allenai/olmo-3-32b-think", "last_updated": "2026-03-15", "limit": { "context": 65536, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "AllenAI: Olmo 3 32B Think", "open_weights": true, "reasoning": true, "release_date": "2025-11-22", "temperature": true, "tool_call": false }, "alpindale/goliath-120b": { "attachment": false, "cost": { "input": 3.75, "output": 7.5 }, "description": "Goliath 120B is an AI model provided by kilo.", "id": "alpindale/goliath-120b", "last_updated": "2026-03-15", "limit": { "context": 6144, "output": 1024 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Goliath 120B", "open_weights": true, "reasoning": false, "release_date": "2023-11-10", "temperature": true, "tool_call": false }, "amazon/nova-2-lite-v1": { "attachment": true, "cost": { "input": 0.3, "output": 2.5 }, "description": "Amazon: Nova 2 Lite is an AI model provided by kilo.", "id": "amazon/nova-2-lite-v1", "last_updated": "2026-03-15", "limit": { "context": 1000000, "output": 65535 }, "modalities": { "input": [ "image", "pdf", "text", "video" ], "output": [ "text" ] }, "name": "Amazon: Nova 2 Lite", "open_weights": false, "reasoning": true, "release_date": "2024-12-01", "temperature": true, "tool_call": true }, "amazon/nova-lite-v1": { "attachment": true, "cost": { "input": 0.06, "output": 0.24 }, "description": "Amazon: Nova Lite 1.0 is an AI model provided by kilo.", "id": "amazon/nova-lite-v1", "last_updated": "2026-03-15", "limit": { "context": 300000, "output": 5120 }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "name": "Amazon: Nova Lite 1.0", "open_weights": false, "reasoning": false, "release_date": "2024-12-06", "temperature": true, "tool_call": true }, "amazon/nova-micro-v1": { "attachment": false, "cost": { "input": 0.035, "output": 0.14 }, "description": "Amazon: Nova Micro 1.0 is an AI model provided by kilo.", "id": "amazon/nova-micro-v1", "last_updated": "2026-03-15", "limit": { "context": 128000, "output": 5120 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Amazon: Nova Micro 1.0", "open_weights": false, "reasoning": false, "release_date": "2024-12-06", "temperature": true, "tool_call": true }, "amazon/nova-premier-v1": { "attachment": true, "cost": { "input": 2.5, "output": 12.5 }, "description": "Amazon: Nova Premier 1.0 is an AI model provided by kilo.", "id": "amazon/nova-premier-v1", "last_updated": "2026-03-15", "limit": { "context": 1000000, "output": 32000 }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "name": "Amazon: Nova Premier 1.0", "open_weights": false, "reasoning": false, "release_date": "2025-11-01", "temperature": true, "tool_call": true }, "amazon/nova-pro-v1": { "attachment": true, "cost": { "input": 0.8, "output": 3.2 }, "description": "Amazon: Nova Pro 1.0 is an AI model provided by kilo.", "id": "amazon/nova-pro-v1", "last_updated": "2024-12-03", "limit": { "context": 300000, "output": 5120 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Amazon: Nova Pro 1.0", "open_weights": false, "reasoning": false, "release_date": "2024-12-03", "temperature": true, "tool_call": true }, "anthracite-org/magnum-v4-72b": { "attachment": false, "cost": { "input": 3, "output": 5 }, "description": "Magnum v4 72B is an AI model provided by kilo.", "id": "anthracite-org/magnum-v4-72b", "last_updated": "2026-03-15", "limit": { "context": 16384, "output": 2048 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Magnum v4 72B", "open_weights": true, "reasoning": false, "release_date": "2024-10-22", "temperature": true, "tool_call": false }, "anthropic/claude-3-haiku": { "attachment": true, "cost": { "cache_read": 0.03, "cache_write": 0.3, "input": 0.25, "output": 1.25 }, "description": "Anthropic: Claude 3 Haiku is an AI model provided by kilo.", "id": "anthropic/claude-3-haiku", "last_updated": "2024-03-07", "limit": { "context": 200000, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Anthropic: Claude 3 Haiku", "open_weights": false, "reasoning": false, "release_date": "2024-03-07", "temperature": true, "tool_call": true }, "anthropic/claude-3.5-haiku": { "attachment": true, "cost": { "cache_read": 0.08, "cache_write": 1, "input": 0.8, "output": 4 }, "description": "Anthropic: Claude 3.5 Haiku is an AI model provided by kilo.", "id": "anthropic/claude-3.5-haiku", "last_updated": "2024-10-22", "limit": { "context": 200000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Anthropic: Claude 3.5 Haiku", "open_weights": false, "reasoning": false, "release_date": "2024-10-22", "temperature": true, "tool_call": true }, "anthropic/claude-3.7-sonnet": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Anthropic: Claude 3.7 Sonnet is an AI model provided by kilo.", "id": "anthropic/claude-3.7-sonnet", "last_updated": "2026-03-15", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "name": "Anthropic: Claude 3.7 Sonnet", "open_weights": false, "reasoning": true, "release_date": "2025-02-19", "temperature": true, "tool_call": true }, "anthropic/claude-3.7-sonnet:thinking": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Anthropic: Claude 3.7 Sonnet (thinking) is an AI model provided by kilo.", "id": "anthropic/claude-3.7-sonnet:thinking", "last_updated": "2026-03-15", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "name": "Anthropic: Claude 3.7 Sonnet (thinking)", "open_weights": false, "reasoning": true, "release_date": "2025-02-19", "temperature": true, "tool_call": true }, "anthropic/claude-haiku-4.5": { "attachment": true, "cost": { "cache_read": 0.1, "cache_write": 1.25, "input": 1, "output": 5 }, "description": "Anthropic: Claude Haiku 4.5 is an AI model provided by kilo.", "id": "anthropic/claude-haiku-4.5", "last_updated": "2025-10-15", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "name": "Anthropic: Claude Haiku 4.5", "open_weights": false, "reasoning": true, "release_date": "2025-10-15", "temperature": true, "tool_call": true }, "anthropic/claude-opus-4": { "attachment": true, "cost": { "cache_read": 1.5, "cache_write": 18.75, "input": 15, "output": 75 }, "description": "Anthropic: Claude Opus 4 is an AI model provided by kilo.", "id": "anthropic/claude-opus-4", "last_updated": "2026-03-15", "limit": { "context": 200000, "output": 32000 }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "name": "Anthropic: Claude Opus 4", "open_weights": false, "reasoning": true, "release_date": "2025-05-22", "temperature": true, "tool_call": true }, "anthropic/claude-opus-4.1": { "attachment": true, "cost": { "cache_read": 1.5, "cache_write": 18.75, "input": 15, "output": 75 }, "description": "Anthropic: Claude Opus 4.1 is an AI model provided by kilo.", "id": "anthropic/claude-opus-4.1", "last_updated": "2026-03-15", "limit": { "context": 200000, "output": 32000 }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "name": "Anthropic: Claude Opus 4.1", "open_weights": false, "reasoning": true, "release_date": "2025-08-05", "temperature": true, "tool_call": true }, "anthropic/claude-opus-4.5": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "input": 5, "output": 25 }, "description": "Anthropic: Claude Opus 4.5 is an AI model provided by kilo.", "id": "anthropic/claude-opus-4.5", "last_updated": "2026-03-15", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "name": "Anthropic: Claude Opus 4.5", "open_weights": false, "reasoning": true, "release_date": "2025-11-24", "temperature": true, "tool_call": true }, "anthropic/claude-opus-4.6": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "input": 5, "output": 25 }, "description": "Anthropic: Claude Opus 4.6 is an AI model provided by kilo.", "id": "anthropic/claude-opus-4.6", "knowledge": "2025-05-31", "last_updated": "2026-02-05", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Anthropic: Claude Opus 4.6", "open_weights": false, "reasoning": true, "release_date": "2026-02-05", "temperature": true, "tool_call": true }, "anthropic/claude-opus-4.6-fast": { "attachment": true, "cost": { "cache_read": 3, "cache_write": 37.5, "input": 30, "output": 150 }, "description": "Anthropic: Claude Opus 4.6 (Fast) is an AI model provided by kilo.", "id": "anthropic/claude-opus-4.6-fast", "knowledge": "2025-05-31", "last_updated": "2026-04-11", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "name": "Anthropic: Claude Opus 4.6 (Fast)", "open_weights": false, "reasoning": true, "release_date": "2026-04-07", "temperature": true, "tool_call": true }, "anthropic/claude-opus-4.7": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "input": 5, "output": 25 }, "description": "Anthropic: Claude Opus 4.7 is an AI model provided by kilo.", "id": "anthropic/claude-opus-4.7", "last_updated": "2026-05-01", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Anthropic: Claude Opus 4.7", "open_weights": false, "reasoning": true, "release_date": "2026-04-16", "temperature": false, "tool_call": true }, "anthropic/claude-sonnet-4": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Anthropic: Claude Sonnet 4 is an AI model provided by kilo.", "id": "anthropic/claude-sonnet-4", "last_updated": "2026-03-15", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "name": "Anthropic: Claude Sonnet 4", "open_weights": false, "reasoning": true, "release_date": "2025-05-22", "temperature": true, "tool_call": true }, "anthropic/claude-sonnet-4.5": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Anthropic: Claude Sonnet 4.5 is an AI model provided by kilo.", "id": "anthropic/claude-sonnet-4.5", "last_updated": "2026-03-15", "limit": { "context": 1000000, "output": 64000 }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "name": "Anthropic: Claude Sonnet 4.5", "open_weights": false, "reasoning": true, "release_date": "2025-09-29", "temperature": true, "tool_call": true }, "anthropic/claude-sonnet-4.6": { "attachment": true, "cost": { "input": 3, "output": 15 }, "description": "Anthropic: Claude Sonnet 4.6 is an AI model provided by kilo.", "id": "anthropic/claude-sonnet-4.6", "knowledge": "2025-08-31", "last_updated": "2026-03-15", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "name": "Anthropic: Claude Sonnet 4.6", "open_weights": false, "reasoning": true, "release_date": "2026-02-17", "temperature": true, "tool_call": true }, "arcee-ai/coder-large": { "attachment": false, "cost": { "input": 0.5, "output": 0.8 }, "description": "Arcee AI: Coder Large is an AI model provided by kilo.", "id": "arcee-ai/coder-large", "last_updated": "2026-03-15", "limit": { "context": 32768, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Arcee AI: Coder Large", "open_weights": true, "reasoning": false, "release_date": "2025-05-06", "temperature": true, "tool_call": false }, "arcee-ai/maestro-reasoning": { "attachment": false, "cost": { "input": 0.9, "output": 3.3 }, "description": "Arcee AI: Maestro Reasoning is an AI model provided by kilo.", "id": "arcee-ai/maestro-reasoning", "last_updated": "2026-03-15", "limit": { "context": 131072, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Arcee AI: Maestro Reasoning", "open_weights": true, "reasoning": false, "release_date": "2025-05-06", "temperature": true, "tool_call": false }, "arcee-ai/spotlight": { "attachment": true, "cost": { "input": 0.18, "output": 0.18 }, "description": "Arcee AI: Spotlight is an AI model provided by kilo.", "id": "arcee-ai/spotlight", "last_updated": "2026-03-15", "limit": { "context": 131072, "output": 65537 }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "name": "Arcee AI: Spotlight", "open_weights": true, "reasoning": false, "release_date": "2025-05-06", "temperature": true, "tool_call": false }, "arcee-ai/trinity-large-preview": { "attachment": false, "cost": { "input": 0.15, "output": 0.45 }, "description": "Arcee AI: Trinity Large Preview is an AI model provided by kilo.", "id": "arcee-ai/trinity-large-preview", "last_updated": "2026-05-01", "limit": { "context": 131000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Arcee AI: Trinity Large Preview", "open_weights": false, "reasoning": false, "release_date": "2026-01-28", "temperature": true, "tool_call": true }, "arcee-ai/trinity-large-thinking": { "attachment": false, "cost": { "input": 0.22, "output": 0.85 }, "description": "Arcee AI: Trinity Large Thinking is an AI model provided by kilo.", "id": "arcee-ai/trinity-large-thinking", "last_updated": "2026-04-11", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Arcee AI: Trinity Large Thinking", "open_weights": true, "reasoning": true, "release_date": "2026-04-01", "temperature": true, "tool_call": true }, "arcee-ai/trinity-mini": { "attachment": false, "cost": { "input": 0.045, "output": 0.15 }, "description": "Arcee AI: Trinity Mini is an AI model provided by kilo.", "id": "arcee-ai/trinity-mini", "last_updated": "2026-01-28", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Arcee AI: Trinity Mini", "open_weights": true, "reasoning": true, "release_date": "2025-12", "temperature": true, "tool_call": true }, "arcee-ai/virtuoso-large": { "attachment": false, "cost": { "input": 0.75, "output": 1.2 }, "description": "Arcee AI: Virtuoso Large is an AI model provided by kilo.", "id": "arcee-ai/virtuoso-large", "last_updated": "2026-03-15", "limit": { "context": 131072, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Arcee AI: Virtuoso Large", "open_weights": true, "reasoning": false, "release_date": "2025-05-06", "temperature": true, "tool_call": true }, "baidu/cobuddy:free": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Baidu: CoBuddy (free) is an AI model provided by kilo.", "id": "baidu/cobuddy:free", "last_updated": "2026-05-07", "limit": { "context": 131072, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Baidu: CoBuddy (free)", "open_weights": false, "reasoning": true, "release_date": "2026-05-06", "temperature": false, "tool_call": true }, "baidu/ernie-4.5-21b-a3b": { "attachment": false, "cost": { "input": 0.07, "output": 0.28 }, "description": "Baidu: ERNIE 4.5 21B A3B is an AI model provided by kilo.", "id": "baidu/ernie-4.5-21b-a3b", "last_updated": "2025-06-30", "limit": { "context": 120000, "output": 8000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Baidu: ERNIE 4.5 21B A3B", "open_weights": true, "reasoning": false, "release_date": "2025-06-30", "temperature": true, "tool_call": true }, "baidu/ernie-4.5-21b-a3b-thinking": { "attachment": false, "cost": { "input": 0.07, "output": 0.28 }, "description": "Baidu: ERNIE 4.5 21B A3B Thinking is an AI model provided by kilo.", "id": "baidu/ernie-4.5-21b-a3b-thinking", "last_updated": "2025-09-19", "limit": { "context": 131072, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Baidu: ERNIE 4.5 21B A3B Thinking", "open_weights": true, "reasoning": true, "release_date": "2025-09-19", "temperature": true, "tool_call": false }, "baidu/ernie-4.5-300b-a47b": { "attachment": false, "cost": { "input": 0.28, "output": 1.1 }, "description": "Baidu: ERNIE 4.5 300B A47B is an AI model provided by kilo.", "id": "baidu/ernie-4.5-300b-a47b", "last_updated": "2026-01", "limit": { "context": 123000, "output": 12000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Baidu: ERNIE 4.5 300B A47B ", "open_weights": true, "reasoning": false, "release_date": "2025-06-30", "temperature": true, "tool_call": false }, "baidu/ernie-4.5-vl-28b-a3b": { "attachment": true, "cost": { "input": 0.14, "output": 0.56 }, "description": "Baidu: ERNIE 4.5 VL 28B A3B is an AI model provided by kilo.", "id": "baidu/ernie-4.5-vl-28b-a3b", "last_updated": "2025-06-30", "limit": { "context": 30000, "output": 8000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Baidu: ERNIE 4.5 VL 28B A3B", "open_weights": true, "reasoning": true, "release_date": "2025-06-30", "temperature": true, "tool_call": true }, "baidu/ernie-4.5-vl-424b-a47b": { "attachment": true, "cost": { "input": 0.42, "output": 1.25 }, "description": "Baidu: ERNIE 4.5 VL 424B A47B is an AI model provided by kilo.", "id": "baidu/ernie-4.5-vl-424b-a47b", "last_updated": "2026-01", "limit": { "context": 123000, "output": 16000 }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "name": "Baidu: ERNIE 4.5 VL 424B A47B ", "open_weights": true, "reasoning": true, "release_date": "2025-06-30", "temperature": true, "tool_call": false }, "baidu/qianfan-ocr-fast:free": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Baidu: Qianfan-OCR-Fast (free) is an AI model provided by kilo.", "id": "baidu/qianfan-ocr-fast:free", "last_updated": "2026-05-01", "limit": { "context": 65536, "output": 28672 }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "name": "Baidu: Qianfan-OCR-Fast (free)", "open_weights": false, "reasoning": true, "release_date": "2026-04-20", "temperature": true, "tool_call": false }, "bytedance-seed/seed-1.6": { "attachment": true, "cost": { "input": 0.25, "output": 2 }, "description": "ByteDance Seed: Seed 1.6 is an AI model provided by kilo.", "id": "bytedance-seed/seed-1.6", "last_updated": "2025-09", "limit": { "context": 262144, "output": 32768 }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "name": "ByteDance Seed: Seed 1.6", "open_weights": false, "reasoning": true, "release_date": "2025-09", "temperature": true, "tool_call": true }, "bytedance-seed/seed-1.6-flash": { "attachment": true, "cost": { "input": 0.075, "output": 0.3 }, "description": "ByteDance Seed: Seed 1.6 Flash is an AI model provided by kilo.", "id": "bytedance-seed/seed-1.6-flash", "last_updated": "2026-03-15", "limit": { "context": 262144, "output": 32768 }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "name": "ByteDance Seed: Seed 1.6 Flash", "open_weights": true, "reasoning": true, "release_date": "2025-12-23", "temperature": true, "tool_call": true }, "bytedance-seed/seed-2.0-lite": { "attachment": true, "cost": { "input": 0.25, "output": 2 }, "description": "ByteDance Seed: Seed-2.0-Lite is an AI model provided by kilo.", "id": "bytedance-seed/seed-2.0-lite", "last_updated": "2026-03-15", "limit": { "context": 262144, "output": 131072 }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "name": "ByteDance Seed: Seed-2.0-Lite", "open_weights": true, "reasoning": true, "release_date": "2026-03-10", "temperature": true, "tool_call": true }, "bytedance-seed/seed-2.0-mini": { "attachment": true, "cost": { "input": 0.1, "output": 0.4 }, "description": "ByteDance Seed: Seed-2.0-Mini is an AI model provided by kilo.", "id": "bytedance-seed/seed-2.0-mini", "last_updated": "2026-03-15", "limit": { "context": 262144, "output": 131072 }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "name": "ByteDance Seed: Seed-2.0-Mini", "open_weights": true, "reasoning": true, "release_date": "2026-02-27", "temperature": true, "tool_call": true }, "bytedance/ui-tars-1.5-7b": { "attachment": true, "cost": { "input": 0.1, "output": 0.2 }, "description": "ByteDance: UI-TARS 7B is an AI model provided by kilo.", "id": "bytedance/ui-tars-1.5-7b", "last_updated": "2026-03-15", "limit": { "context": 128000, "output": 2048 }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "name": "ByteDance: UI-TARS 7B ", "open_weights": false, "reasoning": false, "release_date": "2025-07-23", "temperature": true, "tool_call": false }, "cohere/command-a": { "attachment": false, "cost": { "input": 2.5, "output": 10 }, "description": "Cohere: Command A is an AI model provided by kilo.", "id": "cohere/command-a", "last_updated": "2025-03-13", "limit": { "context": 256000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Cohere: Command A", "open_weights": true, "reasoning": false, "release_date": "2025-03-13", "temperature": true, "tool_call": false }, "cohere/command-r-08-2024": { "attachment": false, "cost": { "input": 0.15, "output": 0.6 }, "description": "Cohere: Command R (08-2024) is an AI model provided by kilo.", "id": "cohere/command-r-08-2024", "last_updated": "2024-08-30", "limit": { "context": 128000, "output": 4000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Cohere: Command R (08-2024)", "open_weights": true, "reasoning": false, "release_date": "2024-08-30", "temperature": true, "tool_call": true }, "cohere/command-r-plus-08-2024": { "attachment": false, "cost": { "input": 2.5, "output": 10 }, "description": "Cohere: Command R+ (08-2024) is an AI model provided by kilo.", "id": "cohere/command-r-plus-08-2024", "last_updated": "2024-08-30", "limit": { "context": 128000, "output": 4000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Cohere: Command R+ (08-2024)", "open_weights": true, "reasoning": false, "release_date": "2024-08-30", "temperature": true, "tool_call": true }, "cohere/command-r7b-12-2024": { "attachment": false, "cost": { "input": 0.0375, "output": 0.15 }, "description": "Cohere: Command R7B (12-2024) is an AI model provided by kilo.", "id": "cohere/command-r7b-12-2024", "last_updated": "2024-02-27", "limit": { "context": 128000, "output": 4000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Cohere: Command R7B (12-2024)", "open_weights": true, "reasoning": false, "release_date": "2024-02-27", "temperature": true, "tool_call": true }, "deepcogito/cogito-v2.1-671b": { "attachment": false, "cost": { "input": 1.25, "output": 1.25 }, "description": "Deep Cogito: Cogito v2.1 671B is an AI model provided by kilo.", "id": "deepcogito/cogito-v2.1-671b", "last_updated": "2026-03-15", "limit": { "context": 128000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Deep Cogito: Cogito v2.1 671B", "open_weights": true, "reasoning": true, "release_date": "2025-11-14", "temperature": true, "tool_call": false }, "deepseek/deepseek-chat": { "attachment": false, "cost": { "cache_read": 0.15, "input": 0.32, "output": 0.89 }, "description": "DeepSeek: DeepSeek V3 is an AI model provided by kilo.", "id": "deepseek/deepseek-chat", "last_updated": "2026-03-15", "limit": { "context": 163840, "output": 163840 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek: DeepSeek V3", "open_weights": true, "reasoning": false, "release_date": "2024-12-01", "temperature": true, "tool_call": true }, "deepseek/deepseek-chat-v3-0324": { "attachment": false, "cost": { "cache_read": 0.095, "input": 0.2, "output": 0.77 }, "description": "DeepSeek: DeepSeek V3 0324 is an AI model provided by kilo.", "id": "deepseek/deepseek-chat-v3-0324", "last_updated": "2026-03-15", "limit": { "context": 163840, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek: DeepSeek V3 0324", "open_weights": true, "reasoning": true, "release_date": "2025-03-24", "temperature": true, "tool_call": true }, "deepseek/deepseek-chat-v3.1": { "attachment": false, "cost": { "input": 0.15, "output": 0.75 }, "description": "DeepSeek: DeepSeek V3.1 is an AI model provided by kilo.", "id": "deepseek/deepseek-chat-v3.1", "last_updated": "2025-08-21", "limit": { "context": 32768, "output": 7168 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek: DeepSeek V3.1", "open_weights": true, "reasoning": true, "release_date": "2025-08-21", "temperature": true, "tool_call": true }, "deepseek/deepseek-r1": { "attachment": false, "cost": { "input": 0.7, "output": 2.5 }, "description": "DeepSeek: R1 is an AI model provided by kilo.", "id": "deepseek/deepseek-r1", "last_updated": "2025-01-20", "limit": { "context": 64000, "output": 16000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek: R1", "open_weights": true, "reasoning": true, "release_date": "2025-01-20", "temperature": true, "tool_call": true }, "deepseek/deepseek-r1-0528": { "attachment": false, "cost": { "cache_read": 0.2, "input": 0.45, "output": 2.15 }, "description": "DeepSeek: R1 0528 is an AI model provided by kilo.", "id": "deepseek/deepseek-r1-0528", "last_updated": "2026-03-15", "limit": { "context": 163840, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek: R1 0528", "open_weights": true, "reasoning": true, "release_date": "2025-05-28", "temperature": true, "tool_call": true }, "deepseek/deepseek-r1-distill-llama-70b": { "attachment": false, "cost": { "cache_read": 0.015, "input": 0.7, "output": 0.8 }, "description": "DeepSeek: R1 Distill Llama 70B is an AI model provided by kilo.", "id": "deepseek/deepseek-r1-distill-llama-70b", "last_updated": "2026-03-15", "limit": { "context": 131072, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek: R1 Distill Llama 70B", "open_weights": true, "reasoning": true, "release_date": "2025-01-23", "temperature": true, "tool_call": false }, "deepseek/deepseek-r1-distill-qwen-32b": { "attachment": false, "cost": { "input": 0.29, "output": 0.29 }, "description": "DeepSeek: R1 Distill Qwen 32B is an AI model provided by kilo.", "id": "deepseek/deepseek-r1-distill-qwen-32b", "last_updated": "2025-11-25", "limit": { "context": 32768, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek: R1 Distill Qwen 32B", "open_weights": true, "reasoning": true, "release_date": "2025-01-01", "temperature": true, "tool_call": false }, "deepseek/deepseek-v3.1-terminus": { "attachment": false, "cost": { "cache_read": 0.13, "input": 0.21, "output": 0.79 }, "description": "DeepSeek: DeepSeek V3.1 Terminus is an AI model provided by kilo.", "id": "deepseek/deepseek-v3.1-terminus", "last_updated": "2025-09-22", "limit": { "context": 163840, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek: DeepSeek V3.1 Terminus", "open_weights": true, "reasoning": true, "release_date": "2025-09-22", "temperature": true, "tool_call": true }, "deepseek/deepseek-v3.2": { "attachment": false, "cost": { "cache_read": 0.125, "input": 0.26, "output": 0.38 }, "description": "DeepSeek: DeepSeek V3.2 is an AI model provided by kilo.", "id": "deepseek/deepseek-v3.2", "last_updated": "2026-03-15", "limit": { "context": 163840, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek: DeepSeek V3.2", "open_weights": true, "reasoning": true, "release_date": "2025-12-01", "temperature": true, "tool_call": true }, "deepseek/deepseek-v3.2-exp": { "attachment": false, "cost": { "input": 0.27, "output": 0.41 }, "description": "DeepSeek: DeepSeek V3.2 Exp is an AI model provided by kilo.", "id": "deepseek/deepseek-v3.2-exp", "last_updated": "2025-09-29", "limit": { "context": 163840, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek: DeepSeek V3.2 Exp", "open_weights": true, "reasoning": true, "release_date": "2025-01-01", "temperature": true, "tool_call": true }, "deepseek/deepseek-v3.2-speciale": { "attachment": false, "cost": { "cache_read": 0.135, "input": 0.4, "output": 1.2 }, "description": "DeepSeek: DeepSeek V3.2 Speciale is an AI model provided by kilo.", "id": "deepseek/deepseek-v3.2-speciale", "last_updated": "2026-03-15", "limit": { "context": 163840, "output": 163840 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek: DeepSeek V3.2 Speciale", "open_weights": true, "reasoning": true, "release_date": "2025-12-01", "temperature": true, "tool_call": false }, "deepseek/deepseek-v4-flash": { "attachment": false, "cost": { "cache_read": 0.0028, "input": 0.14, "output": 0.28 }, "description": "DeepSeek: DeepSeek V4 Flash is an AI model provided by kilo.", "id": "deepseek/deepseek-v4-flash", "last_updated": "2026-05-01", "limit": { "context": 1048576, "output": 384000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek: DeepSeek V4 Flash", "open_weights": false, "reasoning": true, "release_date": "2026-04-24", "temperature": true, "tool_call": true }, "deepseek/deepseek-v4-pro": { "attachment": false, "cost": { "cache_read": 0.003625, "input": 0.435, "output": 0.87 }, "description": "DeepSeek: DeepSeek V4 Pro is an AI model provided by kilo.", "id": "deepseek/deepseek-v4-pro", "last_updated": "2026-05-01", "limit": { "context": 1048576, "output": 384000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek: DeepSeek V4 Pro", "open_weights": false, "reasoning": true, "release_date": "2026-04-24", "temperature": true, "tool_call": true }, "essentialai/rnj-1-instruct": { "attachment": false, "cost": { "input": 0.15, "output": 0.15 }, "description": "EssentialAI: Rnj 1 Instruct is an AI model provided by kilo.", "id": "essentialai/rnj-1-instruct", "last_updated": "2026-03-15", "limit": { "context": 32768, "output": 6554 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "EssentialAI: Rnj 1 Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-12-05", "temperature": true, "tool_call": true }, "google/gemini-2.0-flash-001": { "attachment": true, "cost": { "cache_read": 0.025, "cache_write": 0.083333, "input": 0.1, "output": 0.4 }, "description": "Google: Gemini 2.0 Flash is an AI model provided by kilo.", "id": "google/gemini-2.0-flash-001", "last_updated": "2026-03-15", "limit": { "context": 1048576, "output": 8192 }, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "name": "Google: Gemini 2.0 Flash", "open_weights": false, "reasoning": false, "release_date": "2024-12-11", "temperature": true, "tool_call": true }, "google/gemini-2.0-flash-lite-001": { "attachment": true, "cost": { "input": 0.075, "output": 0.3 }, "description": "Google: Gemini 2.0 Flash Lite is an AI model provided by kilo.", "id": "google/gemini-2.0-flash-lite-001", "last_updated": "2026-03-15", "limit": { "context": 1048576, "output": 8192 }, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "name": "Google: Gemini 2.0 Flash Lite", "open_weights": false, "reasoning": false, "release_date": "2024-12-11", "temperature": true, "tool_call": true }, "google/gemini-2.5-flash": { "attachment": true, "cost": { "cache_read": 0.03, "cache_write": 0.083333, "input": 0.3, "output": 2.5, "reasoning": 2.5 }, "description": "Google: Gemini 2.5 Flash is an AI model provided by kilo.", "id": "google/gemini-2.5-flash", "last_updated": "2026-03-15", "limit": { "context": 1048576, "output": 65535 }, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "name": "Google: Gemini 2.5 Flash", "open_weights": false, "reasoning": true, "release_date": "2025-07-17", "temperature": true, "tool_call": true }, "google/gemini-2.5-flash-image": { "attachment": true, "cost": { "input": 0.3, "output": 2.5 }, "description": "Google: Nano Banana (Gemini 2.5 Flash Image) is an AI model provided by kilo.", "id": "google/gemini-2.5-flash-image", "last_updated": "2026-03-15", "limit": { "context": 32768, "output": 32768 }, "modalities": { "input": [ "image", "text" ], "output": [ "image", "text" ] }, "name": "Google: Nano Banana (Gemini 2.5 Flash Image)", "open_weights": false, "reasoning": false, "release_date": "2025-10-08", "temperature": true, "tool_call": false }, "google/gemini-2.5-flash-lite": { "attachment": true, "cost": { "cache_read": 0.01, "cache_write": 0.083333, "input": 0.1, "output": 0.4, "reasoning": 0.4 }, "description": "Google: Gemini 2.5 Flash Lite is an AI model provided by kilo.", "id": "google/gemini-2.5-flash-lite", "last_updated": "2026-03-15", "limit": { "context": 1048576, "output": 65535 }, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "name": "Google: Gemini 2.5 Flash Lite", "open_weights": false, "reasoning": true, "release_date": "2025-06-17", "temperature": true, "tool_call": true }, "google/gemini-2.5-flash-lite-preview-09-2025": { "attachment": true, "cost": { "cache_read": 0.01, "cache_write": 0.083333, "input": 0.1, "output": 0.4, "reasoning": 0.4 }, "description": "Google: Gemini 2.5 Flash Lite Preview 09-2025 is an AI model provided by kilo.", "id": "google/gemini-2.5-flash-lite-preview-09-2025", "last_updated": "2026-03-15", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "name": "Google: Gemini 2.5 Flash Lite Preview 09-2025", "open_weights": false, "reasoning": true, "release_date": "2025-09-25", "temperature": true, "tool_call": true }, "google/gemini-2.5-pro": { "attachment": true, "cost": { "cache_read": 0.125, "cache_write": 0.375, "input": 1.25, "output": 10, "reasoning": 10 }, "description": "Google: Gemini 2.5 Pro is an AI model provided by kilo.", "id": "google/gemini-2.5-pro", "last_updated": "2026-03-15", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "name": "Google: Gemini 2.5 Pro", "open_weights": false, "reasoning": true, "release_date": "2025-03-20", "temperature": true, "tool_call": true }, "google/gemini-2.5-pro-preview": { "attachment": true, "cost": { "cache_read": 0.125, "cache_write": 0.375, "input": 1.25, "output": 10, "reasoning": 10 }, "description": "Google: Gemini 2.5 Pro Preview 06-05 is an AI model provided by kilo.", "id": "google/gemini-2.5-pro-preview", "last_updated": "2026-03-15", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "audio", "image", "pdf", "text" ], "output": [ "text" ] }, "name": "Google: Gemini 2.5 Pro Preview 06-05", "open_weights": false, "reasoning": true, "release_date": "2025-06-05", "temperature": true, "tool_call": true }, "google/gemini-2.5-pro-preview-05-06": { "attachment": true, "cost": { "cache_read": 0.125, "cache_write": 0.375, "input": 1.25, "output": 10, "reasoning": 10 }, "description": "Google: Gemini 2.5 Pro Preview 05-06 is an AI model provided by kilo.", "id": "google/gemini-2.5-pro-preview-05-06", "last_updated": "2026-03-15", "limit": { "context": 1048576, "output": 65535 }, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "name": "Google: Gemini 2.5 Pro Preview 05-06", "open_weights": false, "reasoning": true, "release_date": "2025-05-06", "temperature": true, "tool_call": true }, "google/gemini-3-flash-preview": { "attachment": true, "cost": { "cache_read": 0.05, "cache_write": 0.083333, "input": 0.5, "output": 3, "reasoning": 3 }, "description": "Google: Gemini 3 Flash Preview is an AI model provided by kilo.", "id": "google/gemini-3-flash-preview", "last_updated": "2026-03-15", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "name": "Google: Gemini 3 Flash Preview", "open_weights": false, "reasoning": true, "release_date": "2025-12-17", "temperature": true, "tool_call": true }, "google/gemini-3-pro-image-preview": { "attachment": true, "cost": { "input": 2, "output": 12, "reasoning": 12 }, "description": "Google: Nano Banana Pro (Gemini 3 Pro Image Preview) is an AI model provided by kilo.", "id": "google/gemini-3-pro-image-preview", "last_updated": "2026-03-15", "limit": { "context": 65536, "output": 32768 }, "modalities": { "input": [ "image", "text" ], "output": [ "image", "text" ] }, "name": "Google: Nano Banana Pro (Gemini 3 Pro Image Preview)", "open_weights": false, "reasoning": true, "release_date": "2025-11-20", "temperature": true, "tool_call": false }, "google/gemini-3.1-flash-image-preview": { "attachment": true, "cost": { "input": 0.5, "output": 3 }, "description": "Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview) is an AI model provided by kilo.", "id": "google/gemini-3.1-flash-image-preview", "last_updated": "2026-03-15", "limit": { "context": 65536, "output": 65536 }, "modalities": { "input": [ "image", "text" ], "output": [ "image", "text" ] }, "name": "Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)", "open_weights": false, "reasoning": true, "release_date": "2026-02-26", "temperature": true, "tool_call": false }, "google/gemini-3.1-flash-lite-preview": { "attachment": true, "cost": { "input": 0.25, "output": 1.5, "reasoning": 1.5 }, "description": "Google: Gemini 3.1 Flash Lite Preview is an AI model provided by kilo.", "id": "google/gemini-3.1-flash-lite-preview", "last_updated": "2026-03-15", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "name": "Google: Gemini 3.1 Flash Lite Preview", "open_weights": false, "reasoning": true, "release_date": "2026-03-03", "temperature": true, "tool_call": true }, "google/gemini-3.1-pro-preview": { "attachment": true, "cost": { "input": 2, "output": 12, "reasoning": 12 }, "description": "Google: Gemini 3.1 Pro Preview is an AI model provided by kilo.", "id": "google/gemini-3.1-pro-preview", "last_updated": "2026-03-15", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "name": "Google: Gemini 3.1 Pro Preview", "open_weights": false, "reasoning": true, "release_date": "2026-02-19", "temperature": true, "tool_call": true }, "google/gemini-3.1-pro-preview-customtools": { "attachment": true, "cost": { "input": 2, "output": 12, "reasoning": 12 }, "description": "Google: Gemini 3.1 Pro Preview Custom Tools is an AI model provided by kilo.", "id": "google/gemini-3.1-pro-preview-customtools", "last_updated": "2026-03-15", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "text" ] }, "name": "Google: Gemini 3.1 Pro Preview Custom Tools", "open_weights": false, "reasoning": true, "release_date": "2026-02-26", "temperature": true, "tool_call": true }, "google/gemma-2-27b-it": { "attachment": false, "cost": { "input": 0.65, "output": 0.65 }, "description": "Google: Gemma 2 27B is an AI model provided by kilo.", "id": "google/gemma-2-27b-it", "last_updated": "2024-06-24", "limit": { "context": 8192, "output": 2048 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Google: Gemma 2 27B", "open_weights": true, "reasoning": false, "release_date": "2024-06-24", "temperature": true, "tool_call": false }, "google/gemma-3-12b-it": { "attachment": true, "cost": { "cache_read": 0.015, "input": 0.04, "output": 0.13 }, "description": "Google: Gemma 3 12B is an AI model provided by kilo.", "id": "google/gemma-3-12b-it", "last_updated": "2026-03-15", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "name": "Google: Gemma 3 12B", "open_weights": true, "reasoning": false, "release_date": "2025-03-13", "temperature": true, "tool_call": false }, "google/gemma-3-27b-it": { "attachment": true, "cost": { "cache_read": 0.02, "input": 0.03, "output": 0.11 }, "description": "Google: Gemma 3 27B is an AI model provided by kilo.", "id": "google/gemma-3-27b-it", "last_updated": "2026-03-15", "limit": { "context": 128000, "output": 65536 }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "name": "Google: Gemma 3 27B", "open_weights": true, "reasoning": false, "release_date": "2025-03-12", "temperature": true, "tool_call": true }, "google/gemma-3-4b-it": { "attachment": true, "cost": { "input": 0.04, "output": 0.08 }, "description": "Google: Gemma 3 4B is an AI model provided by kilo.", "id": "google/gemma-3-4b-it", "last_updated": "2026-03-15", "limit": { "context": 131072, "output": 19200 }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "name": "Google: Gemma 3 4B", "open_weights": true, "reasoning": false, "release_date": "2025-03-13", "temperature": true, "tool_call": false }, "google/gemma-3n-e4b-it": { "attachment": false, "cost": { "input": 0.02, "output": 0.04 }, "description": "Google: Gemma 3n 4B is an AI model provided by kilo.", "id": "google/gemma-3n-e4b-it", "last_updated": "2025-05-20", "limit": { "context": 32768, "output": 6554 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Google: Gemma 3n 4B", "open_weights": true, "reasoning": false, "release_date": "2025-05-20", "temperature": true, "tool_call": false }, "google/gemma-4-26b-a4b-it": { "attachment": true, "cost": { "input": 0.12, "output": 0.4 }, "description": "Google: Gemma 4 26B A4B is an AI model provided by kilo.", "id": "google/gemma-4-26b-a4b-it", "last_updated": "2026-04-11", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "name": "Google: Gemma 4 26B A4B", "open_weights": true, "reasoning": true, "release_date": "2026-04-03", "temperature": true, "tool_call": true }, "google/gemma-4-31b-it": { "attachment": true, "cost": { "input": 0.14, "output": 0.4 }, "description": "Google: Gemma 4 31B is an AI model provided by kilo.", "id": "google/gemma-4-31b-it", "last_updated": "2026-04-11", "limit": { "context": 262144, "output": 131072 }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "name": "Google: Gemma 4 31B", "open_weights": true, "reasoning": true, "release_date": "2026-04-02", "temperature": true, "tool_call": true }, "google/lyria-3-clip-preview": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Google: Lyria 3 Clip Preview is an AI model provided by kilo.", "id": "google/lyria-3-clip-preview", "last_updated": "2026-04-11", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "image", "text" ], "output": [ "audio", "text" ] }, "name": "Google: Lyria 3 Clip Preview", "open_weights": false, "reasoning": false, "release_date": "2026-03-30", "temperature": true, "tool_call": false }, "google/lyria-3-pro-preview": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Google: Lyria 3 Pro Preview is an AI model provided by kilo.", "id": "google/lyria-3-pro-preview", "last_updated": "2026-04-11", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "image", "text" ], "output": [ "audio", "text" ] }, "name": "Google: Lyria 3 Pro Preview", "open_weights": false, "reasoning": false, "release_date": "2026-03-30", "temperature": true, "tool_call": false }, "gryphe/mythomax-l2-13b": { "attachment": false, "cost": { "input": 0.06, "output": 0.06 }, "description": "MythoMax 13B is an AI model provided by kilo.", "id": "gryphe/mythomax-l2-13b", "last_updated": "2024-04-25", "limit": { "context": 4096, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MythoMax 13B", "open_weights": true, "reasoning": false, "release_date": "2024-04-25", "temperature": true, "tool_call": false }, "ibm-granite/granite-4.0-h-micro": { "attachment": false, "cost": { "input": 0.017, "output": 0.11 }, "description": "IBM: Granite 4.0 Micro is an AI model provided by kilo.", "id": "ibm-granite/granite-4.0-h-micro", "last_updated": "2026-03-15", "limit": { "context": 131000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "IBM: Granite 4.0 Micro", "open_weights": true, "reasoning": false, "release_date": "2025-10-20", "temperature": true, "tool_call": false }, "ibm-granite/granite-4.1-8b": { "attachment": false, "cost": { "cache_read": 0.05, "input": 0.05, "output": 0.1 }, "description": "IBM: Granite 4.1 8B is an AI model provided by kilo.", "id": "ibm-granite/granite-4.1-8b", "last_updated": "2026-05-01", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "IBM: Granite 4.1 8B", "open_weights": false, "reasoning": false, "release_date": "2026-04-30", "temperature": true, "tool_call": true }, "inception/mercury-2": { "attachment": false, "cost": { "cache_read": 0.025, "input": 0.25, "output": 0.75 }, "description": "Inception: Mercury 2 is an AI model provided by kilo.", "id": "inception/mercury-2", "last_updated": "2026-02-24", "limit": { "context": 128000, "output": 50000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Inception: Mercury 2", "open_weights": false, "reasoning": true, "release_date": "2026-02-24", "temperature": true, "tool_call": true }, "inclusionai/ling-2.6-1t:free": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "inclusionAI: Ling-2.6-1T (free) is an AI model provided by kilo.", "id": "inclusionai/ling-2.6-1t:free", "last_updated": "2026-05-01", "limit": { "context": 262144, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "inclusionAI: Ling-2.6-1T (free)", "open_weights": false, "reasoning": false, "release_date": "2026-04-23", "temperature": true, "tool_call": true }, "inclusionai/ling-2.6-flash": { "attachment": false, "cost": { "cache_read": 0.016, "input": 0.08, "output": 0.24 }, "description": "inclusionAI: Ling-2.6 Flash is an AI model provided by kilo.", "id": "inclusionai/ling-2.6-flash", "last_updated": "2026-05-01", "limit": { "context": 262144, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "inclusionAI: Ling-2.6 Flash", "open_weights": false, "reasoning": false, "release_date": "2026-04-21", "temperature": true, "tool_call": true }, "inflection/inflection-3-pi": { "attachment": false, "cost": { "input": 2.5, "output": 10 }, "description": "Inflection: Inflection 3 Pi is an AI model provided by kilo.", "id": "inflection/inflection-3-pi", "last_updated": "2026-03-15", "limit": { "context": 8000, "output": 1024 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Inflection: Inflection 3 Pi", "open_weights": false, "reasoning": false, "release_date": "2024-10-11", "temperature": true, "tool_call": false }, "inflection/inflection-3-productivity": { "attachment": false, "cost": { "input": 2.5, "output": 10 }, "description": "Inflection: Inflection 3 Productivity is an AI model provided by kilo.", "id": "inflection/inflection-3-productivity", "last_updated": "2026-03-15", "limit": { "context": 8000, "output": 1024 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Inflection: Inflection 3 Productivity", "open_weights": false, "reasoning": false, "release_date": "2024-10-11", "temperature": true, "tool_call": false }, "kilo-auto/balanced": { "attachment": false, "cost": { "input": 0.6, "output": 3 }, "description": "Kilo Auto Balanced is an AI model provided by kilo.", "id": "kilo-auto/balanced", "last_updated": "2026-03-15", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kilo Auto Balanced", "open_weights": false, "reasoning": true, "release_date": "2026-03-15", "temperature": true, "tool_call": true }, "kilo-auto/free": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Kilo Auto Free is an AI model provided by kilo.", "id": "kilo-auto/free", "last_updated": "2026-03-15", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kilo Auto Free", "open_weights": false, "reasoning": true, "release_date": "2026-03-15", "temperature": true, "tool_call": true }, "kilo-auto/frontier": { "attachment": true, "cost": { "input": 5, "output": 25 }, "description": "Kilo Auto Frontier is an AI model provided by kilo.", "id": "kilo-auto/frontier", "last_updated": "2026-03-15", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "name": "Kilo Auto Frontier", "open_weights": false, "reasoning": true, "release_date": "2026-03-15", "temperature": true, "tool_call": true }, "kilo-auto/small": { "attachment": true, "cost": { "input": 0.05, "output": 0.4 }, "description": "Kilo Auto Small is an AI model provided by kilo.", "id": "kilo-auto/small", "last_updated": "2026-03-15", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "name": "Kilo Auto Small", "open_weights": false, "reasoning": true, "release_date": "2026-03-15", "temperature": true, "tool_call": true }, "kwaipilot/kat-coder-pro-v2": { "attachment": false, "cost": { "cache_read": 0.06, "input": 0.3, "output": 1.2 }, "description": "Kwaipilot: KAT-Coder-Pro V2 is an AI model provided by kilo.", "id": "kwaipilot/kat-coder-pro-v2", "last_updated": "2026-04-11", "limit": { "context": 256000, "output": 80000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kwaipilot: KAT-Coder-Pro V2", "open_weights": true, "reasoning": false, "release_date": "2026-03-27", "temperature": true, "tool_call": true }, "liquid/lfm-2-24b-a2b": { "attachment": false, "cost": { "input": 0.03, "output": 0.12 }, "description": "LiquidAI: LFM2-24B-A2B is an AI model provided by kilo.", "id": "liquid/lfm-2-24b-a2b", "last_updated": "2026-03-15", "limit": { "context": 32768, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "LiquidAI: LFM2-24B-A2B", "open_weights": true, "reasoning": false, "release_date": "2026-02-26", "temperature": true, "tool_call": false }, "mancer/weaver": { "attachment": false, "cost": { "input": 0.75, "output": 1 }, "description": "Mancer: Weaver (alpha) is an AI model provided by kilo.", "id": "mancer/weaver", "last_updated": "2026-03-15", "limit": { "context": 8000, "output": 2000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mancer: Weaver (alpha)", "open_weights": false, "reasoning": false, "release_date": "2023-08-02", "temperature": true, "tool_call": false }, "meta-llama/llama-3-70b-instruct": { "attachment": false, "cost": { "input": 0.51, "output": 0.74 }, "description": "Meta: Llama 3 70B Instruct is an AI model provided by kilo.", "id": "meta-llama/llama-3-70b-instruct", "last_updated": "2024-07-23", "limit": { "context": 8192, "output": 8000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Meta: Llama 3 70B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-07-23", "temperature": true, "tool_call": false }, "meta-llama/llama-3-8b-instruct": { "attachment": false, "cost": { "input": 0.03, "output": 0.04 }, "description": "Meta: Llama 3 8B Instruct is an AI model provided by kilo.", "id": "meta-llama/llama-3-8b-instruct", "last_updated": "2025-04-03", "limit": { "context": 8192, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Meta: Llama 3 8B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-04-25", "temperature": true, "tool_call": true }, "meta-llama/llama-3.1-70b-instruct": { "attachment": false, "cost": { "input": 0.4, "output": 0.4 }, "description": "Meta: Llama 3.1 70B Instruct is an AI model provided by kilo.", "id": "meta-llama/llama-3.1-70b-instruct", "last_updated": "2024-07-23", "limit": { "context": 131072, "output": 26215 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Meta: Llama 3.1 70B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-07-16", "temperature": true, "tool_call": true }, "meta-llama/llama-3.1-8b-instruct": { "attachment": false, "cost": { "input": 0.02, "output": 0.05 }, "description": "Meta: Llama 3.1 8B Instruct is an AI model provided by kilo.", "id": "meta-llama/llama-3.1-8b-instruct", "last_updated": "2025-12-23", "limit": { "context": 16384, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Meta: Llama 3.1 8B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-07-23", "temperature": true, "tool_call": true }, "meta-llama/llama-3.2-11b-vision-instruct": { "attachment": true, "cost": { "input": 0.049, "output": 0.049 }, "description": "Meta: Llama 3.2 11B Vision Instruct is an AI model provided by kilo.", "id": "meta-llama/llama-3.2-11b-vision-instruct", "last_updated": "2024-09-25", "limit": { "context": 131072, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Meta: Llama 3.2 11B Vision Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-09-25", "temperature": true, "tool_call": false }, "meta-llama/llama-3.2-1b-instruct": { "attachment": false, "cost": { "input": 0.027, "output": 0.2 }, "description": "Meta: Llama 3.2 1B Instruct is an AI model provided by kilo.", "id": "meta-llama/llama-3.2-1b-instruct", "last_updated": "2026-01-27", "limit": { "context": 60000, "output": 12000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Meta: Llama 3.2 1B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-09-18", "temperature": true, "tool_call": false }, "meta-llama/llama-3.2-3b-instruct": { "attachment": false, "cost": { "input": 0.051, "output": 0.34 }, "description": "Meta: Llama 3.2 3B Instruct is an AI model provided by kilo.", "id": "meta-llama/llama-3.2-3b-instruct", "last_updated": "2026-03-15", "limit": { "context": 80000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Meta: Llama 3.2 3B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-09-18", "temperature": true, "tool_call": false }, "meta-llama/llama-3.3-70b-instruct": { "attachment": false, "cost": { "input": 0.1, "output": 0.32 }, "description": "Meta: Llama 3.3 70B Instruct is an AI model provided by kilo.", "id": "meta-llama/llama-3.3-70b-instruct", "last_updated": "2026-02-04", "limit": { "context": 131072, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Meta: Llama 3.3 70B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-08-01", "temperature": true, "tool_call": true }, "meta-llama/llama-4-maverick": { "attachment": true, "cost": { "input": 0.15, "output": 0.6 }, "description": "Meta: Llama 4 Maverick is an AI model provided by kilo.", "id": "meta-llama/llama-4-maverick", "last_updated": "2025-12-24", "limit": { "context": 1048576, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Meta: Llama 4 Maverick", "open_weights": true, "reasoning": false, "release_date": "2025-04-05", "temperature": true, "tool_call": true }, "meta-llama/llama-4-scout": { "attachment": true, "cost": { "input": 0.08, "output": 0.3 }, "description": "Meta: Llama 4 Scout is an AI model provided by kilo.", "id": "meta-llama/llama-4-scout", "last_updated": "2025-04-05", "limit": { "context": 327680, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Meta: Llama 4 Scout", "open_weights": true, "reasoning": false, "release_date": "2025-04-05", "temperature": true, "tool_call": true }, "meta-llama/llama-guard-3-8b": { "attachment": false, "cost": { "input": 0.02, "output": 0.06 }, "description": "Llama Guard 3 8B is an AI model provided by kilo.", "id": "meta-llama/llama-guard-3-8b", "last_updated": "2026-02-04", "limit": { "context": 131072, "output": 26215 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama Guard 3 8B", "open_weights": true, "reasoning": false, "release_date": "2024-04-18", "temperature": true, "tool_call": false }, "meta-llama/llama-guard-4-12b": { "attachment": true, "cost": { "input": 0.18, "output": 0.18 }, "description": "Meta: Llama Guard 4 12B is an AI model provided by kilo.", "id": "meta-llama/llama-guard-4-12b", "last_updated": "2025-04-05", "limit": { "context": 163840, "output": 32768 }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "name": "Meta: Llama Guard 4 12B", "open_weights": true, "reasoning": false, "release_date": "2025-04-05", "temperature": true, "tool_call": false }, "microsoft/phi-4": { "attachment": false, "cost": { "input": 0.06, "output": 0.14 }, "description": "Microsoft: Phi 4 is an AI model provided by kilo.", "id": "microsoft/phi-4", "last_updated": "2024-12-11", "limit": { "context": 16384, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Microsoft: Phi 4", "open_weights": true, "reasoning": false, "release_date": "2024-12-11", "temperature": true, "tool_call": false }, "microsoft/phi-4-mini-instruct": { "attachment": false, "cost": { "cache_read": 0.08, "input": 0.08, "output": 0.35 }, "description": "Microsoft: Phi 4 Mini Instruct is an AI model provided by kilo.", "id": "microsoft/phi-4-mini-instruct", "last_updated": "2026-05-07", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Microsoft: Phi 4 Mini Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-10-17", "structured_output": true, "temperature": true, "tool_call": false }, "microsoft/wizardlm-2-8x22b": { "attachment": false, "cost": { "input": 0.62, "output": 0.62 }, "description": "WizardLM-2 8x22B is an AI model provided by kilo.", "id": "microsoft/wizardlm-2-8x22b", "last_updated": "2024-04-24", "limit": { "context": 65535, "output": 8000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "WizardLM-2 8x22B", "open_weights": true, "reasoning": false, "release_date": "2024-04-24", "temperature": true, "tool_call": false }, "minimax/minimax-01": { "attachment": true, "cost": { "input": 0.2, "output": 1.1 }, "description": "MiniMax: MiniMax-01 is an AI model provided by kilo.", "id": "minimax/minimax-01", "last_updated": "2025-01-15", "limit": { "context": 1000192, "output": 1000192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "MiniMax: MiniMax-01", "open_weights": true, "reasoning": false, "release_date": "2025-01-15", "temperature": true, "tool_call": false }, "minimax/minimax-m1": { "attachment": false, "cost": { "input": 0.4, "output": 2.2 }, "description": "MiniMax: MiniMax M1 is an AI model provided by kilo.", "id": "minimax/minimax-m1", "last_updated": "2025-06-17", "limit": { "context": 1000000, "output": 40000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax: MiniMax M1", "open_weights": true, "reasoning": true, "release_date": "2025-06-17", "temperature": true, "tool_call": true }, "minimax/minimax-m2": { "attachment": false, "cost": { "cache_read": 0.03, "input": 0.255, "output": 1 }, "description": "MiniMax: MiniMax M2 is an AI model provided by kilo.", "id": "minimax/minimax-m2", "last_updated": "2026-03-15", "limit": { "context": 196608, "output": 196608 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax: MiniMax M2", "open_weights": true, "reasoning": true, "release_date": "2025-10-23", "temperature": true, "tool_call": true }, "minimax/minimax-m2-her": { "attachment": false, "cost": { "input": 0.3, "output": 1.2 }, "description": "MiniMax: MiniMax M2-her is an AI model provided by kilo.", "id": "minimax/minimax-m2-her", "last_updated": "2026-03-15", "limit": { "context": 65536, "output": 2048 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax: MiniMax M2-her", "open_weights": true, "reasoning": false, "release_date": "2026-01-23", "temperature": true, "tool_call": false }, "minimax/minimax-m2.1": { "attachment": false, "cost": { "cache_read": 0.03, "input": 0.27, "output": 0.95 }, "description": "MiniMax: MiniMax M2.1 is an AI model provided by kilo.", "id": "minimax/minimax-m2.1", "last_updated": "2025-12-23", "limit": { "context": 196608, "output": 39322 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax: MiniMax M2.1", "open_weights": true, "reasoning": true, "release_date": "2025-12-23", "temperature": true, "tool_call": true }, "minimax/minimax-m2.5": { "attachment": false, "cost": { "cache_read": 0.029, "input": 0.25, "output": 1.2 }, "description": "MiniMax: MiniMax M2.5 is an AI model provided by kilo.", "id": "minimax/minimax-m2.5", "last_updated": "2026-03-15", "limit": { "context": 196608, "output": 196608 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax: MiniMax M2.5", "open_weights": true, "reasoning": true, "release_date": "2026-02-12", "temperature": true, "tool_call": true }, "minimax/minimax-m2.7": { "attachment": false, "cost": { "cache_read": 0.06, "input": 0.3, "output": 1.2 }, "description": "MiniMax: MiniMax M2.7 is an AI model provided by kilo.", "family": "minimax-m2.7", "id": "minimax/minimax-m2.7", "last_updated": "2026-03-18", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax: MiniMax M2.7", "open_weights": true, "reasoning": true, "release_date": "2026-03-18", "temperature": true, "tool_call": true }, "mistralai/codestral-2508": { "attachment": false, "cost": { "input": 0.3, "output": 0.9 }, "description": "Mistral: Codestral 2508 is an AI model provided by kilo.", "id": "mistralai/codestral-2508", "last_updated": "2025-08-01", "limit": { "context": 256000, "output": 51200 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral: Codestral 2508", "open_weights": true, "reasoning": false, "release_date": "2025-08-01", "temperature": true, "tool_call": true }, "mistralai/devstral-2512": { "attachment": false, "cost": { "cache_read": 0.025, "input": 0.4, "output": 2 }, "description": "Mistral: Devstral 2 2512 is an AI model provided by kilo.", "id": "mistralai/devstral-2512", "last_updated": "2026-03-15", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral: Devstral 2 2512", "open_weights": true, "reasoning": false, "release_date": "2025-09-12", "temperature": true, "tool_call": true }, "mistralai/devstral-medium": { "attachment": false, "cost": { "input": 0.4, "output": 2 }, "description": "Mistral: Devstral Medium is an AI model provided by kilo.", "id": "mistralai/devstral-medium", "last_updated": "2025-07-10", "limit": { "context": 131072, "output": 26215 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral: Devstral Medium", "open_weights": true, "reasoning": false, "release_date": "2025-07-10", "temperature": true, "tool_call": true }, "mistralai/devstral-small": { "attachment": false, "cost": { "input": 0.1, "output": 0.3 }, "description": "Mistral: Devstral Small 1.1 is an AI model provided by kilo.", "id": "mistralai/devstral-small", "last_updated": "2025-07-10", "limit": { "context": 131072, "output": 26215 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral: Devstral Small 1.1", "open_weights": true, "reasoning": false, "release_date": "2025-05-07", "temperature": true, "tool_call": true }, "mistralai/ministral-14b-2512": { "attachment": true, "cost": { "input": 0.2, "output": 0.2 }, "description": "Mistral: Ministral 3 14B 2512 is an AI model provided by kilo.", "id": "mistralai/ministral-14b-2512", "last_updated": "2025-12-16", "limit": { "context": 262144, "output": 52429 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Mistral: Ministral 3 14B 2512", "open_weights": false, "reasoning": false, "release_date": "2025-12-16", "temperature": true, "tool_call": true }, "mistralai/ministral-3b-2512": { "attachment": true, "cost": { "input": 0.1, "output": 0.1 }, "description": "Mistral: Ministral 3 3B 2512 is an AI model provided by kilo.", "id": "mistralai/ministral-3b-2512", "last_updated": "2026-03-15", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "name": "Mistral: Ministral 3 3B 2512", "open_weights": true, "reasoning": false, "release_date": "2025-12-02", "temperature": true, "tool_call": true }, "mistralai/ministral-8b-2512": { "attachment": true, "cost": { "input": 0.15, "output": 0.15 }, "description": "Mistral: Ministral 3 8B 2512 is an AI model provided by kilo.", "id": "mistralai/ministral-8b-2512", "last_updated": "2026-03-15", "limit": { "context": 262144, "output": 32768 }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "name": "Mistral: Ministral 3 8B 2512", "open_weights": true, "reasoning": false, "release_date": "2025-12-02", "temperature": true, "tool_call": true }, "mistralai/mistral-7b-instruct-v0.1": { "attachment": false, "cost": { "input": 0.11, "output": 0.19 }, "description": "Mistral: Mistral 7B Instruct v0.1 is an AI model provided by kilo.", "id": "mistralai/mistral-7b-instruct-v0.1", "last_updated": "2025-04-03", "limit": { "context": 2824, "output": 565 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral: Mistral 7B Instruct v0.1", "open_weights": false, "reasoning": false, "release_date": "2025-04-03", "temperature": true, "tool_call": false }, "mistralai/mistral-large": { "attachment": false, "cost": { "input": 2, "output": 6 }, "description": "Mistral Large is an AI model provided by kilo.", "id": "mistralai/mistral-large", "last_updated": "2025-12-02", "limit": { "context": 128000, "output": 25600 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral Large", "open_weights": true, "reasoning": false, "release_date": "2024-07-24", "temperature": true, "tool_call": true }, "mistralai/mistral-large-2407": { "attachment": false, "cost": { "input": 2, "output": 6 }, "description": "Mistral Large 2407 is an AI model provided by kilo.", "id": "mistralai/mistral-large-2407", "last_updated": "2026-03-15", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral Large 2407", "open_weights": true, "reasoning": false, "release_date": "2024-11-19", "temperature": true, "tool_call": true }, "mistralai/mistral-large-2411": { "attachment": false, "cost": { "input": 2, "output": 6 }, "description": "Mistral Large 2411 is an AI model provided by kilo.", "id": "mistralai/mistral-large-2411", "last_updated": "2024-11-04", "limit": { "context": 131072, "output": 26215 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral Large 2411", "open_weights": true, "reasoning": false, "release_date": "2024-07-24", "temperature": true, "tool_call": true }, "mistralai/mistral-large-2512": { "attachment": true, "cost": { "input": 0.5, "output": 1.5 }, "description": "Mistral: Mistral Large 3 2512 is an AI model provided by kilo.", "id": "mistralai/mistral-large-2512", "last_updated": "2025-12-16", "limit": { "context": 262144, "output": 52429 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Mistral: Mistral Large 3 2512", "open_weights": true, "reasoning": false, "release_date": "2024-11-01", "temperature": true, "tool_call": true }, "mistralai/mistral-medium-3": { "attachment": true, "cost": { "input": 0.4, "output": 2 }, "description": "Mistral: Mistral Medium 3 is an AI model provided by kilo.", "id": "mistralai/mistral-medium-3", "last_updated": "2025-05-07", "limit": { "context": 131072, "output": 26215 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Mistral: Mistral Medium 3", "open_weights": false, "reasoning": false, "release_date": "2025-05-07", "temperature": true, "tool_call": true }, "mistralai/mistral-medium-3-5": { "attachment": true, "cost": { "input": 1.5, "output": 7.5 }, "description": "Mistral: Mistral Medium 3.5 is an AI model provided by kilo.", "id": "mistralai/mistral-medium-3-5", "last_updated": "2026-05-07", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "name": "Mistral: Mistral Medium 3.5", "open_weights": false, "reasoning": true, "release_date": "2026-04-30", "structured_output": true, "temperature": true, "tool_call": true }, "mistralai/mistral-medium-3.1": { "attachment": true, "cost": { "input": 0.4, "output": 2 }, "description": "Mistral: Mistral Medium 3.1 is an AI model provided by kilo.", "id": "mistralai/mistral-medium-3.1", "last_updated": "2025-08-12", "limit": { "context": 131072, "output": 26215 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Mistral: Mistral Medium 3.1", "open_weights": false, "reasoning": false, "release_date": "2025-08-12", "temperature": true, "tool_call": true }, "mistralai/mistral-nemo": { "attachment": false, "cost": { "input": 0.02, "output": 0.04 }, "description": "Mistral: Mistral Nemo is an AI model provided by kilo.", "id": "mistralai/mistral-nemo", "last_updated": "2024-07-30", "limit": { "context": 131072, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral: Mistral Nemo", "open_weights": true, "reasoning": false, "release_date": "2024-07-01", "temperature": true, "tool_call": true }, "mistralai/mistral-saba": { "attachment": false, "cost": { "input": 0.2, "output": 0.6 }, "description": "Mistral: Saba is an AI model provided by kilo.", "id": "mistralai/mistral-saba", "last_updated": "2026-03-15", "limit": { "context": 32768, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral: Saba", "open_weights": true, "reasoning": false, "release_date": "2025-02-17", "temperature": true, "tool_call": true }, "mistralai/mistral-small-24b-instruct-2501": { "attachment": false, "cost": { "input": 0.05, "output": 0.08 }, "description": "Mistral: Mistral Small 3 is an AI model provided by kilo.", "id": "mistralai/mistral-small-24b-instruct-2501", "last_updated": "2026-01-10", "limit": { "context": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral: Mistral Small 3", "open_weights": true, "reasoning": false, "release_date": "2025-12-29", "temperature": true, "tool_call": true }, "mistralai/mistral-small-2603": { "attachment": true, "cost": { "cache_read": 0.015, "input": 0.15, "output": 0.6 }, "description": "Mistral: Mistral Small 4 is an AI model provided by kilo.", "id": "mistralai/mistral-small-2603", "last_updated": "2026-04-11", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "name": "Mistral: Mistral Small 4", "open_weights": true, "reasoning": true, "release_date": "2026-03-16", "temperature": true, "tool_call": true }, "mistralai/mistral-small-3.1-24b-instruct": { "attachment": true, "cost": { "cache_read": 0.015, "input": 0.35, "output": 0.56 }, "description": "Mistral: Mistral Small 3.1 24B is an AI model provided by kilo.", "id": "mistralai/mistral-small-3.1-24b-instruct", "last_updated": "2026-03-15", "limit": { "context": 128000, "output": 131072 }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "name": "Mistral: Mistral Small 3.1 24B", "open_weights": true, "reasoning": false, "release_date": "2025-03-17", "temperature": true, "tool_call": false }, "mistralai/mistral-small-3.2-24b-instruct": { "attachment": true, "cost": { "cache_read": 0.03, "input": 0.06, "output": 0.18 }, "description": "Mistral: Mistral Small 3.2 24B is an AI model provided by kilo.", "id": "mistralai/mistral-small-3.2-24b-instruct", "last_updated": "2025-06-20", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "name": "Mistral: Mistral Small 3.2 24B", "open_weights": true, "reasoning": false, "release_date": "2025-06-20", "temperature": true, "tool_call": true }, "mistralai/mixtral-8x22b-instruct": { "attachment": false, "cost": { "input": 2, "output": 6 }, "description": "Mistral: Mixtral 8x22B Instruct is an AI model provided by kilo.", "id": "mistralai/mixtral-8x22b-instruct", "last_updated": "2024-04-17", "limit": { "context": 65536, "output": 13108 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral: Mixtral 8x22B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-04-17", "temperature": true, "tool_call": true }, "mistralai/mixtral-8x7b-instruct": { "attachment": false, "cost": { "input": 0.54, "output": 0.54 }, "description": "Mistral: Mixtral 8x7B Instruct is an AI model provided by kilo.", "id": "mistralai/mixtral-8x7b-instruct", "last_updated": "2026-03-15", "limit": { "context": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral: Mixtral 8x7B Instruct", "open_weights": true, "reasoning": false, "release_date": "2023-12-10", "temperature": true, "tool_call": true }, "mistralai/pixtral-large-2411": { "attachment": true, "cost": { "input": 2, "output": 6 }, "description": "Mistral: Pixtral Large 2411 is an AI model provided by kilo.", "id": "mistralai/pixtral-large-2411", "last_updated": "2026-03-15", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "name": "Mistral: Pixtral Large 2411", "open_weights": true, "reasoning": false, "release_date": "2024-11-19", "temperature": true, "tool_call": true }, "mistralai/voxtral-small-24b-2507": { "attachment": false, "cost": { "input": 0.1, "output": 0.3 }, "description": "Mistral: Voxtral Small 24B 2507 is an AI model provided by kilo.", "id": "mistralai/voxtral-small-24b-2507", "last_updated": "2025-07-01", "limit": { "context": 32000, "output": 6400 }, "modalities": { "input": [ "text", "audio" ], "output": [ "text" ] }, "name": "Mistral: Voxtral Small 24B 2507", "open_weights": true, "reasoning": false, "release_date": "2025-07-01", "temperature": true, "tool_call": true }, "moonshotai/kimi-k2": { "attachment": false, "cost": { "input": 0.55, "output": 2.2 }, "description": "MoonshotAI: Kimi K2 0711 is an AI model provided by kilo.", "id": "moonshotai/kimi-k2", "last_updated": "2026-03-15", "limit": { "context": 131000, "output": 26215 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MoonshotAI: Kimi K2 0711", "open_weights": true, "reasoning": false, "release_date": "2025-07-11", "temperature": true, "tool_call": true }, "moonshotai/kimi-k2-0905": { "attachment": false, "cost": { "cache_read": 0.15, "input": 0.4, "output": 2 }, "description": "MoonshotAI: Kimi K2 0905 is an AI model provided by kilo.", "id": "moonshotai/kimi-k2-0905", "last_updated": "2025-09-05", "limit": { "context": 131072, "output": 26215 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MoonshotAI: Kimi K2 0905", "open_weights": true, "reasoning": false, "release_date": "2025-09-05", "temperature": true, "tool_call": true }, "moonshotai/kimi-k2-thinking": { "attachment": false, "cost": { "cache_read": 0.2, "input": 0.47, "output": 2 }, "description": "MoonshotAI: Kimi K2 Thinking is an AI model provided by kilo.", "id": "moonshotai/kimi-k2-thinking", "last_updated": "2026-03-15", "limit": { "context": 131072, "output": 65535 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MoonshotAI: Kimi K2 Thinking", "open_weights": true, "reasoning": true, "release_date": "2025-11-06", "temperature": true, "tool_call": true }, "moonshotai/kimi-k2.5": { "attachment": true, "cost": { "input": 0.45, "output": 2.2 }, "description": "MoonshotAI: Kimi K2.5 is an AI model provided by kilo.", "id": "moonshotai/kimi-k2.5", "last_updated": "2026-03-15", "limit": { "context": 262144, "output": 65535 }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "name": "MoonshotAI: Kimi K2.5", "open_weights": true, "reasoning": true, "release_date": "2026-01-27", "temperature": true, "tool_call": true }, "moonshotai/kimi-k2.6": { "attachment": true, "cost": { "cache_read": 0.375, "input": 0.75, "output": 3.5 }, "description": "MoonshotAI: Kimi K2.6 is an AI model provided by kilo.", "id": "moonshotai/kimi-k2.6", "last_updated": "2026-05-12", "limit": { "context": 262144, "output": 65535 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "MoonshotAI: Kimi K2.6", "open_weights": true, "reasoning": true, "release_date": "2026-04-20", "structured_output": true, "temperature": true, "tool_call": true }, "morph/morph-v3-fast": { "attachment": false, "cost": { "input": 0.8, "output": 1.2 }, "description": "Morph: Morph V3 Fast is an AI model provided by kilo.", "id": "morph/morph-v3-fast", "last_updated": "2024-08-15", "limit": { "context": 81920, "output": 38000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Morph: Morph V3 Fast", "open_weights": false, "reasoning": false, "release_date": "2024-08-15", "temperature": true, "tool_call": false }, "morph/morph-v3-large": { "attachment": false, "cost": { "input": 0.9, "output": 1.9 }, "description": "Morph: Morph V3 Large is an AI model provided by kilo.", "id": "morph/morph-v3-large", "last_updated": "2024-08-15", "limit": { "context": 262144, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Morph: Morph V3 Large", "open_weights": false, "reasoning": false, "release_date": "2024-08-15", "temperature": true, "tool_call": false }, "nex-agi/deepseek-v3.1-nex-n1": { "attachment": false, "cost": { "input": 0.27, "output": 1 }, "description": "Nex AGI: DeepSeek V3.1 Nex N1 is an AI model provided by kilo.", "id": "nex-agi/deepseek-v3.1-nex-n1", "last_updated": "2025-11-25", "limit": { "context": 131072, "output": 163840 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Nex AGI: DeepSeek V3.1 Nex N1", "open_weights": false, "reasoning": false, "release_date": "2025-01-01", "temperature": true, "tool_call": true }, "nousresearch/hermes-2-pro-llama-3-8b": { "attachment": false, "cost": { "input": 0.14, "output": 0.14 }, "description": "NousResearch: Hermes 2 Pro - Llama-3 8B is an AI model provided by kilo.", "id": "nousresearch/hermes-2-pro-llama-3-8b", "last_updated": "2024-06-27", "limit": { "context": 8192, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "NousResearch: Hermes 2 Pro - Llama-3 8B", "open_weights": true, "reasoning": false, "release_date": "2024-05-27", "temperature": true, "tool_call": false }, "nousresearch/hermes-3-llama-3.1-405b": { "attachment": false, "cost": { "input": 1, "output": 1 }, "description": "Nous: Hermes 3 405B Instruct is an AI model provided by kilo.", "id": "nousresearch/hermes-3-llama-3.1-405b", "last_updated": "2024-08-16", "limit": { "context": 131072, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Nous: Hermes 3 405B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-08-16", "temperature": true, "tool_call": false }, "nousresearch/hermes-3-llama-3.1-70b": { "attachment": false, "cost": { "input": 0.3, "output": 0.3 }, "description": "Nous: Hermes 3 70B Instruct is an AI model provided by kilo.", "id": "nousresearch/hermes-3-llama-3.1-70b", "last_updated": "2026-03-15", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Nous: Hermes 3 70B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-08-18", "temperature": true, "tool_call": false }, "nousresearch/hermes-4-405b": { "attachment": false, "cost": { "input": 1, "output": 3 }, "description": "Nous: Hermes 4 405B is an AI model provided by kilo.", "id": "nousresearch/hermes-4-405b", "last_updated": "2025-08-25", "limit": { "context": 131072, "output": 26215 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Nous: Hermes 4 405B", "open_weights": true, "reasoning": true, "release_date": "2025-08-25", "temperature": true, "tool_call": false }, "nousresearch/hermes-4-70b": { "attachment": false, "cost": { "cache_read": 0.055, "input": 0.13, "output": 0.4 }, "description": "Nous: Hermes 4 70B is an AI model provided by kilo.", "id": "nousresearch/hermes-4-70b", "last_updated": "2026-03-15", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Nous: Hermes 4 70B", "open_weights": true, "reasoning": true, "release_date": "2025-08-25", "temperature": true, "tool_call": false }, "nvidia/llama-3.1-nemotron-70b-instruct": { "attachment": false, "cost": { "input": 1.2, "output": 1.2 }, "description": "NVIDIA: Llama 3.1 Nemotron 70B Instruct is an AI model provided by kilo.", "id": "nvidia/llama-3.1-nemotron-70b-instruct", "last_updated": "2024-10-12", "limit": { "context": 131072, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "NVIDIA: Llama 3.1 Nemotron 70B Instruct", "open_weights": false, "reasoning": false, "release_date": "2024-10-12", "temperature": true, "tool_call": true }, "nvidia/llama-3.3-nemotron-super-49b-v1.5": { "attachment": false, "cost": { "input": 0.1, "output": 0.4 }, "description": "NVIDIA: Llama 3.3 Nemotron Super 49B V1.5 is an AI model provided by kilo.", "id": "nvidia/llama-3.3-nemotron-super-49b-v1.5", "last_updated": "2025-03-16", "limit": { "context": 131072, "output": 26215 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "NVIDIA: Llama 3.3 Nemotron Super 49B V1.5", "open_weights": false, "reasoning": true, "release_date": "2025-03-16", "temperature": true, "tool_call": true }, "nvidia/nemotron-3-nano-30b-a3b": { "attachment": false, "cost": { "input": 0.05, "output": 0.2 }, "description": "NVIDIA: Nemotron 3 Nano 30B A3B is an AI model provided by kilo.", "id": "nvidia/nemotron-3-nano-30b-a3b", "last_updated": "2026-02-04", "limit": { "context": 262144, "output": 52429 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "NVIDIA: Nemotron 3 Nano 30B A3B", "open_weights": true, "reasoning": true, "release_date": "2024-12", "temperature": true, "tool_call": true }, "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "NVIDIA: Nemotron 3 Nano Omni (free) is an AI model provided by kilo.", "id": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free", "last_updated": "2026-05-01", "limit": { "context": 256000, "output": 65536 }, "modalities": { "input": [ "text", "audio", "image", "video" ], "output": [ "text" ] }, "name": "NVIDIA: Nemotron 3 Nano Omni (free)", "open_weights": false, "reasoning": true, "release_date": "2026-04-28", "temperature": true, "tool_call": true }, "nvidia/nemotron-3-super-120b-a12b": { "attachment": false, "cost": { "cache_read": 0.1, "input": 0.1, "output": 0.5 }, "description": "NVIDIA: Nemotron 3 Super is an AI model provided by kilo.", "id": "nvidia/nemotron-3-super-120b-a12b", "last_updated": "2026-04-11", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "NVIDIA: Nemotron 3 Super", "open_weights": true, "reasoning": true, "release_date": "2026-03-11", "temperature": true, "tool_call": true }, "nvidia/nemotron-3-super-120b-a12b:free": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "NVIDIA: Nemotron 3 Super (free) is an AI model provided by kilo.", "id": "nvidia/nemotron-3-super-120b-a12b:free", "last_updated": "2026-03-15", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "NVIDIA: Nemotron 3 Super (free)", "open_weights": true, "reasoning": true, "release_date": "2026-03-12", "temperature": true, "tool_call": true }, "nvidia/nemotron-nano-9b-v2": { "attachment": false, "cost": { "input": 0.04, "output": 0.16 }, "description": "NVIDIA: Nemotron Nano 9B V2 is an AI model provided by kilo.", "id": "nvidia/nemotron-nano-9b-v2", "last_updated": "2025-08-18", "limit": { "context": 131072, "output": 26215 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "NVIDIA: Nemotron Nano 9B V2", "open_weights": true, "reasoning": true, "release_date": "2025-08-18", "temperature": true, "tool_call": true }, "openai/gpt-3.5-turbo": { "attachment": false, "cost": { "input": 0.5, "output": 1.5 }, "description": "OpenAI: GPT-3.5 Turbo is an AI model provided by kilo.", "id": "openai/gpt-3.5-turbo", "last_updated": "2023-11-06", "limit": { "context": 16385, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "OpenAI: GPT-3.5 Turbo", "open_weights": false, "reasoning": false, "release_date": "2023-03-01", "temperature": true, "tool_call": true }, "openai/gpt-3.5-turbo-0613": { "attachment": false, "cost": { "input": 1, "output": 2 }, "description": "OpenAI: GPT-3.5 Turbo (older v0613) is an AI model provided by kilo.", "id": "openai/gpt-3.5-turbo-0613", "last_updated": "2023-06-13", "limit": { "context": 4095, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "OpenAI: GPT-3.5 Turbo (older v0613)", "open_weights": false, "reasoning": false, "release_date": "2023-06-13", "temperature": true, "tool_call": true }, "openai/gpt-3.5-turbo-16k": { "attachment": false, "cost": { "input": 3, "output": 4 }, "description": "OpenAI: GPT-3.5 Turbo 16k is an AI model provided by kilo.", "id": "openai/gpt-3.5-turbo-16k", "last_updated": "2026-03-15", "limit": { "context": 16385, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "OpenAI: GPT-3.5 Turbo 16k", "open_weights": false, "reasoning": false, "release_date": "2023-08-28", "temperature": true, "tool_call": true }, "openai/gpt-3.5-turbo-instruct": { "attachment": false, "cost": { "input": 1.5, "output": 2 }, "description": "OpenAI: GPT-3.5 Turbo Instruct is an AI model provided by kilo.", "id": "openai/gpt-3.5-turbo-instruct", "last_updated": "2023-09-21", "limit": { "context": 4095, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "OpenAI: GPT-3.5 Turbo Instruct", "open_weights": false, "reasoning": false, "release_date": "2023-03-01", "temperature": true, "tool_call": false }, "openai/gpt-4": { "attachment": false, "cost": { "input": 30, "output": 60 }, "description": "OpenAI: GPT-4 is an AI model provided by kilo.", "id": "openai/gpt-4", "last_updated": "2024-04-09", "limit": { "context": 8191, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "OpenAI: GPT-4", "open_weights": false, "reasoning": false, "release_date": "2023-03-14", "temperature": true, "tool_call": true }, "openai/gpt-4-0314": { "attachment": false, "cost": { "input": 30, "output": 60 }, "description": "OpenAI: GPT-4 (older v0314) is an AI model provided by kilo.", "id": "openai/gpt-4-0314", "last_updated": "2026-03-15", "limit": { "context": 8191, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "OpenAI: GPT-4 (older v0314)", "open_weights": false, "reasoning": false, "release_date": "2023-05-28", "temperature": true, "tool_call": true }, "openai/gpt-4-1106-preview": { "attachment": false, "cost": { "input": 10, "output": 30 }, "description": "OpenAI: GPT-4 Turbo (older v1106) is an AI model provided by kilo.", "id": "openai/gpt-4-1106-preview", "last_updated": "2026-03-15", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "OpenAI: GPT-4 Turbo (older v1106)", "open_weights": false, "reasoning": false, "release_date": "2023-11-06", "temperature": true, "tool_call": true }, "openai/gpt-4-turbo": { "attachment": true, "cost": { "input": 10, "output": 30 }, "description": "OpenAI: GPT-4 Turbo is an AI model provided by kilo.", "id": "openai/gpt-4-turbo", "last_updated": "2024-04-09", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "OpenAI: GPT-4 Turbo", "open_weights": false, "reasoning": false, "release_date": "2023-09-13", "temperature": true, "tool_call": true }, "openai/gpt-4-turbo-preview": { "attachment": false, "cost": { "input": 10, "output": 30 }, "description": "OpenAI: GPT-4 Turbo Preview is an AI model provided by kilo.", "id": "openai/gpt-4-turbo-preview", "last_updated": "2026-03-15", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "OpenAI: GPT-4 Turbo Preview", "open_weights": false, "reasoning": false, "release_date": "2024-01-25", "temperature": true, "tool_call": true }, "openai/gpt-4.1": { "attachment": true, "cost": { "cache_read": 0.5, "input": 2, "output": 8 }, "description": "OpenAI: GPT-4.1 is an AI model provided by kilo.", "id": "openai/gpt-4.1", "last_updated": "2026-03-15", "limit": { "context": 1047576, "output": 32768 }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "name": "OpenAI: GPT-4.1", "open_weights": false, "reasoning": false, "release_date": "2025-04-14", "temperature": true, "tool_call": true }, "openai/gpt-4.1-mini": { "attachment": true, "cost": { "cache_read": 0.1, "input": 0.4, "output": 1.6 }, "description": "OpenAI: GPT-4.1 Mini is an AI model provided by kilo.", "id": "openai/gpt-4.1-mini", "last_updated": "2026-03-15", "limit": { "context": 1047576, "output": 32768 }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "name": "OpenAI: GPT-4.1 Mini", "open_weights": false, "reasoning": false, "release_date": "2025-04-14", "temperature": true, "tool_call": true }, "openai/gpt-4.1-nano": { "attachment": true, "cost": { "cache_read": 0.025, "input": 0.1, "output": 0.4 }, "description": "OpenAI: GPT-4.1 Nano is an AI model provided by kilo.", "id": "openai/gpt-4.1-nano", "last_updated": "2026-03-15", "limit": { "context": 1047576, "output": 32768 }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "name": "OpenAI: GPT-4.1 Nano", "open_weights": false, "reasoning": false, "release_date": "2025-04-14", "temperature": true, "tool_call": true }, "openai/gpt-4o": { "attachment": true, "cost": { "cache_read": 1.25, "input": 2.5, "output": 10 }, "description": "OpenAI: GPT-4o is an AI model provided by kilo.", "id": "openai/gpt-4o", "last_updated": "2026-03-15", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "name": "OpenAI: GPT-4o", "open_weights": false, "reasoning": false, "release_date": "2024-05-13", "temperature": true, "tool_call": true }, "openai/gpt-4o-2024-05-13": { "attachment": true, "cost": { "input": 5, "output": 15 }, "description": "OpenAI: GPT-4o (2024-05-13) is an AI model provided by kilo.", "id": "openai/gpt-4o-2024-05-13", "last_updated": "2026-03-15", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "name": "OpenAI: GPT-4o (2024-05-13)", "open_weights": false, "reasoning": false, "release_date": "2024-05-13", "temperature": true, "tool_call": true }, "openai/gpt-4o-2024-08-06": { "attachment": true, "cost": { "cache_read": 1.25, "input": 2.5, "output": 10 }, "description": "OpenAI: GPT-4o (2024-08-06) is an AI model provided by kilo.", "id": "openai/gpt-4o-2024-08-06", "last_updated": "2026-03-15", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "name": "OpenAI: GPT-4o (2024-08-06)", "open_weights": false, "reasoning": false, "release_date": "2024-08-06", "temperature": true, "tool_call": true }, "openai/gpt-4o-2024-11-20": { "attachment": true, "cost": { "cache_read": 1.25, "input": 2.5, "output": 10 }, "description": "OpenAI: GPT-4o (2024-11-20) is an AI model provided by kilo.", "id": "openai/gpt-4o-2024-11-20", "last_updated": "2026-03-15", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "name": "OpenAI: GPT-4o (2024-11-20)", "open_weights": false, "reasoning": false, "release_date": "2024-11-20", "temperature": true, "tool_call": true }, "openai/gpt-4o-audio-preview": { "attachment": false, "cost": { "input": 2.5, "output": 10 }, "description": "OpenAI: GPT-4o Audio is an AI model provided by kilo.", "id": "openai/gpt-4o-audio-preview", "last_updated": "2026-03-15", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "audio", "text" ], "output": [ "audio", "text" ] }, "name": "OpenAI: GPT-4o Audio", "open_weights": false, "reasoning": false, "release_date": "2025-08-15", "temperature": true, "tool_call": true }, "openai/gpt-4o-mini": { "attachment": true, "cost": { "cache_read": 0.075, "input": 0.15, "output": 0.6 }, "description": "OpenAI: GPT-4o-mini is an AI model provided by kilo.", "id": "openai/gpt-4o-mini", "last_updated": "2026-03-15", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "name": "OpenAI: GPT-4o-mini", "open_weights": false, "reasoning": false, "release_date": "2024-07-18", "temperature": true, "tool_call": true }, "openai/gpt-4o-mini-2024-07-18": { "attachment": true, "cost": { "input": 0.15, "output": 0.6 }, "description": "OpenAI: GPT-4o-mini (2024-07-18) is an AI model provided by kilo.", "id": "openai/gpt-4o-mini-2024-07-18", "last_updated": "2026-03-15", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "name": "OpenAI: GPT-4o-mini (2024-07-18)", "open_weights": false, "reasoning": false, "release_date": "2024-07-18", "temperature": true, "tool_call": true }, "openai/gpt-4o-mini-search-preview": { "attachment": false, "cost": { "input": 0.15, "output": 0.6 }, "description": "OpenAI: GPT-4o-mini Search Preview is an AI model provided by kilo.", "id": "openai/gpt-4o-mini-search-preview", "last_updated": "2025-01", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "OpenAI: GPT-4o-mini Search Preview", "open_weights": false, "reasoning": false, "release_date": "2025-01", "temperature": false, "tool_call": false }, "openai/gpt-4o-search-preview": { "attachment": false, "cost": { "input": 2.5, "output": 10 }, "description": "OpenAI: GPT-4o Search Preview is an AI model provided by kilo.", "id": "openai/gpt-4o-search-preview", "last_updated": "2026-03-15", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "OpenAI: GPT-4o Search Preview", "open_weights": false, "reasoning": false, "release_date": "2025-03-13", "tool_call": false }, "openai/gpt-5": { "attachment": true, "cost": { "cache_read": 0.125, "input": 1.25, "output": 10 }, "description": "OpenAI: GPT-5 is an AI model provided by kilo.", "id": "openai/gpt-5", "last_updated": "2026-03-15", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "name": "OpenAI: GPT-5", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "temperature": false, "tool_call": true }, "openai/gpt-5-chat": { "attachment": true, "cost": { "cache_read": 0.125, "input": 1.25, "output": 10 }, "description": "OpenAI: GPT-5 Chat is an AI model provided by kilo.", "id": "openai/gpt-5-chat", "last_updated": "2026-03-15", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "name": "OpenAI: GPT-5 Chat", "open_weights": false, "reasoning": false, "release_date": "2025-08-07", "temperature": false, "tool_call": false }, "openai/gpt-5-codex": { "attachment": true, "cost": { "cache_read": 0.125, "input": 1.25, "output": 10 }, "description": "OpenAI: GPT-5 Codex is an AI model provided by kilo.", "id": "openai/gpt-5-codex", "last_updated": "2025-09-15", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "OpenAI: GPT-5 Codex", "open_weights": false, "reasoning": true, "release_date": "2025-09-15", "temperature": false, "tool_call": true }, "openai/gpt-5-image": { "attachment": true, "cost": { "input": 10, "output": 10 }, "description": "OpenAI: GPT-5 Image is an AI model provided by kilo.", "id": "openai/gpt-5-image", "last_updated": "2026-03-15", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "image", "text" ] }, "name": "OpenAI: GPT-5 Image", "open_weights": false, "reasoning": true, "release_date": "2025-10-14", "temperature": true, "tool_call": true }, "openai/gpt-5-image-mini": { "attachment": true, "cost": { "input": 2.5, "output": 2 }, "description": "OpenAI: GPT-5 Image Mini is an AI model provided by kilo.", "id": "openai/gpt-5-image-mini", "last_updated": "2026-03-15", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "image", "text" ] }, "name": "OpenAI: GPT-5 Image Mini", "open_weights": false, "reasoning": true, "release_date": "2025-10-16", "temperature": true, "tool_call": true }, "openai/gpt-5-mini": { "attachment": true, "cost": { "cache_read": 0.025, "input": 0.25, "output": 2 }, "description": "OpenAI: GPT-5 Mini is an AI model provided by kilo.", "id": "openai/gpt-5-mini", "last_updated": "2026-03-15", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "name": "OpenAI: GPT-5 Mini", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "temperature": false, "tool_call": true }, "openai/gpt-5-nano": { "attachment": true, "cost": { "cache_read": 0.005, "input": 0.05, "output": 0.4 }, "description": "OpenAI: GPT-5 Nano is an AI model provided by kilo.", "id": "openai/gpt-5-nano", "last_updated": "2026-03-15", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "name": "OpenAI: GPT-5 Nano", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "temperature": false, "tool_call": true }, "openai/gpt-5-pro": { "attachment": true, "cost": { "input": 15, "output": 120 }, "description": "OpenAI: GPT-5 Pro is an AI model provided by kilo.", "id": "openai/gpt-5-pro", "last_updated": "2026-03-15", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "name": "OpenAI: GPT-5 Pro", "open_weights": false, "reasoning": true, "release_date": "2025-10-06", "temperature": false, "tool_call": true }, "openai/gpt-5.1": { "attachment": true, "cost": { "cache_read": 0.125, "input": 1.25, "output": 10 }, "description": "OpenAI: GPT-5.1 is an AI model provided by kilo.", "id": "openai/gpt-5.1", "last_updated": "2026-03-15", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "name": "OpenAI: GPT-5.1", "open_weights": false, "reasoning": true, "release_date": "2025-11-13", "temperature": false, "tool_call": true }, "openai/gpt-5.1-chat": { "attachment": true, "cost": { "cache_read": 0.125, "input": 1.25, "output": 10 }, "description": "OpenAI: GPT-5.1 Chat is an AI model provided by kilo.", "id": "openai/gpt-5.1-chat", "last_updated": "2026-03-15", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "name": "OpenAI: GPT-5.1 Chat", "open_weights": false, "reasoning": false, "release_date": "2025-11-13", "temperature": false, "tool_call": true }, "openai/gpt-5.1-codex": { "attachment": true, "cost": { "cache_read": 0.125, "input": 1.25, "output": 10 }, "description": "OpenAI: GPT-5.1-Codex is an AI model provided by kilo.", "id": "openai/gpt-5.1-codex", "last_updated": "2025-11-13", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "OpenAI: GPT-5.1-Codex", "open_weights": false, "reasoning": true, "release_date": "2025-11-13", "temperature": false, "tool_call": true }, "openai/gpt-5.1-codex-max": { "attachment": true, "cost": { "cache_read": 0.125, "input": 1.25, "output": 10 }, "description": "OpenAI: GPT-5.1-Codex-Max is an AI model provided by kilo.", "id": "openai/gpt-5.1-codex-max", "last_updated": "2025-11-13", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "OpenAI: GPT-5.1-Codex-Max", "open_weights": false, "reasoning": true, "release_date": "2025-11-13", "temperature": false, "tool_call": true }, "openai/gpt-5.1-codex-mini": { "attachment": true, "cost": { "cache_read": 0.025, "input": 0.25, "output": 2 }, "description": "OpenAI: GPT-5.1-Codex-Mini is an AI model provided by kilo.", "id": "openai/gpt-5.1-codex-mini", "last_updated": "2025-11-13", "limit": { "context": 400000, "output": 100000 }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "name": "OpenAI: GPT-5.1-Codex-Mini", "open_weights": false, "reasoning": true, "release_date": "2025-11-13", "temperature": false, "tool_call": true }, "openai/gpt-5.2": { "attachment": true, "cost": { "cache_read": 0.175, "input": 1.75, "output": 14 }, "description": "OpenAI: GPT-5.2 is an AI model provided by kilo.", "id": "openai/gpt-5.2", "last_updated": "2026-03-15", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "name": "OpenAI: GPT-5.2", "open_weights": false, "reasoning": true, "release_date": "2025-12-11", "temperature": false, "tool_call": true }, "openai/gpt-5.2-chat": { "attachment": true, "cost": { "cache_read": 0.175, "input": 1.75, "output": 14 }, "description": "OpenAI: GPT-5.2 Chat is an AI model provided by kilo.", "id": "openai/gpt-5.2-chat", "last_updated": "2026-03-15", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "name": "OpenAI: GPT-5.2 Chat", "open_weights": false, "reasoning": false, "release_date": "2025-12-11", "temperature": false, "tool_call": true }, "openai/gpt-5.2-codex": { "attachment": true, "cost": { "cache_read": 0.175, "input": 1.75, "output": 14 }, "description": "OpenAI: GPT-5.2-Codex is an AI model provided by kilo.", "id": "openai/gpt-5.2-codex", "last_updated": "2026-01-14", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "OpenAI: GPT-5.2-Codex", "open_weights": false, "reasoning": true, "release_date": "2026-01-14", "temperature": false, "tool_call": true }, "openai/gpt-5.2-pro": { "attachment": true, "cost": { "input": 21, "output": 168 }, "description": "OpenAI: GPT-5.2 Pro is an AI model provided by kilo.", "id": "openai/gpt-5.2-pro", "last_updated": "2026-03-15", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "name": "OpenAI: GPT-5.2 Pro", "open_weights": false, "reasoning": true, "release_date": "2025-12-11", "temperature": false, "tool_call": true }, "openai/gpt-5.3-chat": { "attachment": true, "cost": { "input": 1.75, "output": 14 }, "description": "OpenAI: GPT-5.3 Chat is an AI model provided by kilo.", "id": "openai/gpt-5.3-chat", "last_updated": "2026-03-15", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "name": "OpenAI: GPT-5.3 Chat", "open_weights": false, "reasoning": false, "release_date": "2026-03-04", "tool_call": true }, "openai/gpt-5.3-codex": { "attachment": true, "cost": { "input": 1.75, "output": 14 }, "description": "OpenAI: GPT-5.3-Codex is an AI model provided by kilo.", "id": "openai/gpt-5.3-codex", "last_updated": "2026-03-15", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "name": "OpenAI: GPT-5.3-Codex", "open_weights": false, "reasoning": true, "release_date": "2026-02-25", "tool_call": true }, "openai/gpt-5.4": { "attachment": true, "cost": { "input": 2.5, "output": 15 }, "description": "OpenAI: GPT-5.4 is an AI model provided by kilo.", "id": "openai/gpt-5.4", "last_updated": "2026-03-15", "limit": { "context": 1050000, "output": 128000 }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "name": "OpenAI: GPT-5.4", "open_weights": false, "reasoning": true, "release_date": "2026-03-06", "tool_call": true }, "openai/gpt-5.4-image-2": { "attachment": true, "cost": { "cache_read": 2, "input": 8, "output": 15 }, "description": "OpenAI: GPT-5.4 Image 2 is an AI model provided by kilo.", "id": "openai/gpt-5.4-image-2", "last_updated": "2026-05-01", "limit": { "context": 272000, "output": 128000 }, "modalities": { "input": [ "image", "text", "pdf" ], "output": [ "image", "text" ] }, "name": "OpenAI: GPT-5.4 Image 2", "open_weights": false, "reasoning": true, "release_date": "2026-04-21", "temperature": false, "tool_call": false }, "openai/gpt-5.4-mini": { "attachment": true, "cost": { "cache_read": 0.075, "input": 0.75, "output": 4.5 }, "description": "OpenAI: GPT-5.4 Mini is an AI model provided by kilo.", "id": "openai/gpt-5.4-mini", "last_updated": "2026-04-11", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "name": "OpenAI: GPT-5.4 Mini", "open_weights": false, "reasoning": true, "release_date": "2026-03-17", "temperature": false, "tool_call": true }, "openai/gpt-5.4-nano": { "attachment": true, "cost": { "cache_read": 0.02, "input": 0.2, "output": 1.25 }, "description": "OpenAI: GPT-5.4 Nano is an AI model provided by kilo.", "id": "openai/gpt-5.4-nano", "last_updated": "2026-04-11", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "name": "OpenAI: GPT-5.4 Nano", "open_weights": false, "reasoning": true, "release_date": "2026-03-17", "temperature": false, "tool_call": true }, "openai/gpt-5.4-pro": { "attachment": true, "cost": { "input": 30, "output": 180 }, "description": "OpenAI: GPT-5.4 Pro is an AI model provided by kilo.", "id": "openai/gpt-5.4-pro", "last_updated": "2026-03-15", "limit": { "context": 1050000, "output": 128000 }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "name": "OpenAI: GPT-5.4 Pro", "open_weights": false, "reasoning": true, "release_date": "2026-03-06", "tool_call": true }, "openai/gpt-5.5": { "attachment": true, "cost": { "cache_read": 0.5, "input": 5, "output": 30 }, "description": "OpenAI: GPT-5.5 is an AI model provided by kilo.", "id": "openai/gpt-5.5", "last_updated": "2026-05-01", "limit": { "context": 1050000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "OpenAI: GPT-5.5", "open_weights": false, "reasoning": true, "release_date": "2026-04-24", "temperature": false, "tool_call": true }, "openai/gpt-5.5-pro": { "attachment": true, "cost": { "input": 30, "output": 180 }, "description": "OpenAI: GPT-5.5 Pro is an AI model provided by kilo.", "id": "openai/gpt-5.5-pro", "last_updated": "2026-05-01", "limit": { "context": 1050000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "OpenAI: GPT-5.5 Pro", "open_weights": false, "reasoning": true, "release_date": "2026-04-24", "temperature": false, "tool_call": true }, "openai/gpt-audio": { "attachment": false, "cost": { "input": 2.5, "output": 10 }, "description": "OpenAI: GPT Audio is an AI model provided by kilo.", "id": "openai/gpt-audio", "last_updated": "2026-03-15", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "audio", "text" ], "output": [ "audio", "text" ] }, "name": "OpenAI: GPT Audio", "open_weights": false, "reasoning": false, "release_date": "2026-01-20", "temperature": true, "tool_call": false }, "openai/gpt-audio-mini": { "attachment": false, "cost": { "input": 0.6, "output": 2.4 }, "description": "OpenAI: GPT Audio Mini is an AI model provided by kilo.", "id": "openai/gpt-audio-mini", "last_updated": "2026-03-15", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "audio", "text" ], "output": [ "audio", "text" ] }, "name": "OpenAI: GPT Audio Mini", "open_weights": false, "reasoning": false, "release_date": "2026-01-20", "temperature": true, "tool_call": false }, "openai/gpt-chat-latest": { "attachment": true, "cost": { "cache_read": 0.5, "input": 5, "output": 30 }, "description": "OpenAI: GPT Chat Latest is an AI model provided by kilo.", "id": "openai/gpt-chat-latest", "last_updated": "2026-05-07", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "name": "OpenAI: GPT Chat Latest", "open_weights": false, "reasoning": true, "release_date": "2026-05-05", "structured_output": true, "temperature": false, "tool_call": true }, "openai/gpt-oss-120b": { "attachment": false, "cost": { "input": 0.039, "output": 0.19 }, "description": "OpenAI: gpt-oss-120b is an AI model provided by kilo.", "id": "openai/gpt-oss-120b", "last_updated": "2025-08-05", "limit": { "context": 131072, "output": 26215 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "OpenAI: gpt-oss-120b", "open_weights": true, "reasoning": true, "release_date": "2025-08-05", "temperature": true, "tool_call": true }, "openai/gpt-oss-20b": { "attachment": false, "cost": { "input": 0.03, "output": 0.14 }, "description": "OpenAI: gpt-oss-20b is an AI model provided by kilo.", "id": "openai/gpt-oss-20b", "last_updated": "2025-08-05", "limit": { "context": 131072, "output": 26215 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "OpenAI: gpt-oss-20b", "open_weights": true, "reasoning": true, "release_date": "2025-08-05", "temperature": true, "tool_call": true }, "openai/gpt-oss-safeguard-20b": { "attachment": false, "cost": { "cache_read": 0.037, "input": 0.075, "output": 0.3 }, "description": "OpenAI: gpt-oss-safeguard-20b is an AI model provided by kilo.", "id": "openai/gpt-oss-safeguard-20b", "last_updated": "2025-10-29", "limit": { "context": 131072, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "OpenAI: gpt-oss-safeguard-20b", "open_weights": false, "reasoning": true, "release_date": "2025-10-29", "temperature": true, "tool_call": true }, "openai/o1": { "attachment": true, "cost": { "cache_read": 7.5, "input": 15, "output": 60 }, "description": "OpenAI: o1 is an AI model provided by kilo.", "id": "openai/o1", "last_updated": "2026-03-15", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "name": "OpenAI: o1", "open_weights": false, "reasoning": false, "release_date": "2024-12-05", "temperature": false, "tool_call": true }, "openai/o1-pro": { "attachment": true, "cost": { "input": 150, "output": 600 }, "description": "OpenAI: o1-pro is an AI model provided by kilo.", "id": "openai/o1-pro", "last_updated": "2026-03-15", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "name": "OpenAI: o1-pro", "open_weights": false, "reasoning": true, "release_date": "2025-03-19", "temperature": false, "tool_call": false }, "openai/o3": { "attachment": true, "cost": { "cache_read": 0.5, "input": 2, "output": 8 }, "description": "OpenAI: o3 is an AI model provided by kilo.", "id": "openai/o3", "last_updated": "2026-03-15", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "name": "OpenAI: o3", "open_weights": false, "reasoning": true, "release_date": "2025-04-16", "temperature": false, "tool_call": true }, "openai/o3-deep-research": { "attachment": true, "cost": { "cache_read": 2.5, "input": 10, "output": 40 }, "description": "OpenAI: o3 Deep Research is an AI model provided by kilo.", "id": "openai/o3-deep-research", "last_updated": "2026-03-15", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "name": "OpenAI: o3 Deep Research", "open_weights": false, "reasoning": true, "release_date": "2024-06-26", "temperature": true, "tool_call": true }, "openai/o3-mini": { "attachment": true, "cost": { "cache_read": 0.55, "input": 1.1, "output": 4.4 }, "description": "OpenAI: o3 Mini is an AI model provided by kilo.", "id": "openai/o3-mini", "last_updated": "2026-03-15", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "name": "OpenAI: o3 Mini", "open_weights": false, "reasoning": false, "release_date": "2024-12-20", "temperature": false, "tool_call": true }, "openai/o3-mini-high": { "attachment": true, "cost": { "cache_read": 0.55, "input": 1.1, "output": 4.4 }, "description": "OpenAI: o3 Mini High is an AI model provided by kilo.", "id": "openai/o3-mini-high", "last_updated": "2026-03-15", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "pdf", "text" ], "output": [ "text" ] }, "name": "OpenAI: o3 Mini High", "open_weights": false, "reasoning": false, "release_date": "2025-01-31", "temperature": false, "tool_call": true }, "openai/o3-pro": { "attachment": true, "cost": { "input": 20, "output": 80 }, "description": "OpenAI: o3 Pro is an AI model provided by kilo.", "id": "openai/o3-pro", "last_updated": "2026-03-15", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "name": "OpenAI: o3 Pro", "open_weights": false, "reasoning": true, "release_date": "2025-04-16", "temperature": false, "tool_call": true }, "openai/o4-mini": { "attachment": true, "cost": { "cache_read": 0.275, "input": 1.1, "output": 4.4 }, "description": "OpenAI: o4 Mini is an AI model provided by kilo.", "id": "openai/o4-mini", "last_updated": "2026-03-15", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "name": "OpenAI: o4 Mini", "open_weights": false, "reasoning": true, "release_date": "2025-04-16", "temperature": false, "tool_call": true }, "openai/o4-mini-deep-research": { "attachment": true, "cost": { "cache_read": 0.5, "input": 2, "output": 8 }, "description": "OpenAI: o4 Mini Deep Research is an AI model provided by kilo.", "id": "openai/o4-mini-deep-research", "last_updated": "2026-03-15", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "name": "OpenAI: o4 Mini Deep Research", "open_weights": false, "reasoning": true, "release_date": "2024-06-26", "temperature": true, "tool_call": true }, "openai/o4-mini-high": { "attachment": true, "cost": { "input": 1.1, "output": 4.4 }, "description": "OpenAI: o4 Mini High is an AI model provided by kilo.", "id": "openai/o4-mini-high", "last_updated": "2026-03-15", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "name": "OpenAI: o4 Mini High", "open_weights": false, "reasoning": true, "release_date": "2025-04-17", "tool_call": true }, "openrouter/auto": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Auto Router is an AI model provided by kilo.", "id": "openrouter/auto", "last_updated": "2026-03-15", "limit": { "context": 2000000, "output": 32768 }, "modalities": { "input": [ "audio", "image", "pdf", "text", "video" ], "output": [ "image", "text" ] }, "name": "Auto Router", "open_weights": false, "reasoning": true, "release_date": "2026-03-15", "temperature": true, "tool_call": true }, "openrouter/bodybuilder": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Body Builder (beta) is an AI model provided by kilo.", "id": "openrouter/bodybuilder", "last_updated": "2026-03-15", "limit": { "context": 128000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Body Builder (beta)", "open_weights": false, "reasoning": false, "release_date": "2026-03-15", "status": "beta", "tool_call": false }, "openrouter/free": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Free Models Router is an AI model provided by kilo.", "id": "openrouter/free", "last_updated": "2026-03-15", "limit": { "context": 200000, "output": 32768 }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "name": "Free Models Router", "open_weights": false, "reasoning": true, "release_date": "2026-02-01", "temperature": true, "tool_call": true }, "openrouter/owl-alpha": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Owl Alpha is an AI model provided by kilo.", "id": "openrouter/owl-alpha", "last_updated": "2026-04-30", "limit": { "context": 1048756, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Owl Alpha", "open_weights": false, "reasoning": true, "release_date": "2026-04-28", "status": "alpha", "structured_output": true, "temperature": true, "tool_call": true }, "openrouter/pareto-code": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Pareto Code Router is an AI model provided by kilo.", "id": "openrouter/pareto-code", "last_updated": "2026-05-01", "limit": { "context": 200000, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Pareto Code Router", "open_weights": false, "reasoning": false, "release_date": "2026-04-21", "temperature": false, "tool_call": false }, "perplexity/sonar": { "attachment": true, "cost": { "input": 1, "output": 1 }, "description": "Perplexity: Sonar is an AI model provided by kilo.", "id": "perplexity/sonar", "last_updated": "2025-09-01", "limit": { "context": 127072, "output": 25415 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Perplexity: Sonar", "open_weights": false, "reasoning": false, "release_date": "2024-01-01", "temperature": true, "tool_call": false }, "perplexity/sonar-deep-research": { "attachment": false, "cost": { "input": 2, "output": 8 }, "description": "Perplexity: Sonar Deep Research is an AI model provided by kilo.", "id": "perplexity/sonar-deep-research", "last_updated": "2025-01-27", "limit": { "context": 128000, "output": 25600 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Perplexity: Sonar Deep Research", "open_weights": false, "reasoning": true, "release_date": "2025-01-27", "temperature": true, "tool_call": false }, "perplexity/sonar-pro": { "attachment": true, "cost": { "input": 3, "output": 15 }, "description": "Perplexity: Sonar Pro is an AI model provided by kilo.", "id": "perplexity/sonar-pro", "last_updated": "2025-09-01", "limit": { "context": 200000, "output": 8000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Perplexity: Sonar Pro", "open_weights": false, "reasoning": false, "release_date": "2024-01-01", "temperature": true, "tool_call": false }, "perplexity/sonar-pro-search": { "attachment": true, "cost": { "input": 3, "output": 15 }, "description": "Perplexity: Sonar Pro Search is an AI model provided by kilo.", "id": "perplexity/sonar-pro-search", "last_updated": "2026-03-15", "limit": { "context": 200000, "output": 8000 }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "name": "Perplexity: Sonar Pro Search", "open_weights": false, "reasoning": true, "release_date": "2025-10-31", "temperature": true, "tool_call": false }, "perplexity/sonar-reasoning-pro": { "attachment": true, "cost": { "input": 2, "output": 8 }, "description": "Perplexity: Sonar Reasoning Pro is an AI model provided by kilo.", "id": "perplexity/sonar-reasoning-pro", "last_updated": "2025-09-01", "limit": { "context": 128000, "output": 25600 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Perplexity: Sonar Reasoning Pro", "open_weights": false, "reasoning": true, "release_date": "2024-01-01", "temperature": true, "tool_call": false }, "poolside/laguna-m.1:free": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Poolside: Laguna M.1 (free) is an AI model provided by kilo.", "id": "poolside/laguna-m.1:free", "last_updated": "2026-05-01", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Poolside: Laguna M.1 (free)", "open_weights": false, "reasoning": true, "release_date": "2026-04-28", "temperature": true, "tool_call": true }, "poolside/laguna-xs.2:free": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Poolside: Laguna XS.2 (free) is an AI model provided by kilo.", "id": "poolside/laguna-xs.2:free", "last_updated": "2026-05-01", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Poolside: Laguna XS.2 (free)", "open_weights": false, "reasoning": true, "release_date": "2026-04-28", "temperature": true, "tool_call": true }, "prime-intellect/intellect-3": { "attachment": false, "cost": { "input": 0.2, "output": 1.1 }, "description": "Prime Intellect: INTELLECT-3 is an AI model provided by kilo.", "id": "prime-intellect/intellect-3", "last_updated": "2026-02-04", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Prime Intellect: INTELLECT-3", "open_weights": true, "reasoning": true, "release_date": "2025-11-26", "temperature": true, "tool_call": true }, "qwen/qwen-2.5-72b-instruct": { "attachment": false, "cost": { "input": 0.12, "output": 0.39 }, "description": "Qwen2.5 72B Instruct is an AI model provided by kilo.", "id": "qwen/qwen-2.5-72b-instruct", "last_updated": "2026-01-10", "limit": { "context": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen2.5 72B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-09", "temperature": true, "tool_call": true }, "qwen/qwen-2.5-7b-instruct": { "attachment": false, "cost": { "input": 0.04, "output": 0.1 }, "description": "Qwen: Qwen2.5 7B Instruct is an AI model provided by kilo.", "id": "qwen/qwen-2.5-7b-instruct", "last_updated": "2025-04-16", "limit": { "context": 32768, "output": 6554 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen: Qwen2.5 7B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-09", "temperature": true, "tool_call": true }, "qwen/qwen-2.5-coder-32b-instruct": { "attachment": false, "cost": { "cache_read": 0.015, "input": 0.2, "output": 0.2 }, "description": "Qwen2.5 Coder 32B Instruct is an AI model provided by kilo.", "id": "qwen/qwen-2.5-coder-32b-instruct", "last_updated": "2026-03-15", "limit": { "context": 32768, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen2.5 Coder 32B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-11-11", "temperature": true, "tool_call": false }, "qwen/qwen-max": { "attachment": false, "cost": { "cache_read": 0.32, "input": 1.04, "output": 4.16 }, "description": "Qwen: Qwen-Max is an AI model provided by kilo.", "id": "qwen/qwen-max", "last_updated": "2026-03-15", "limit": { "context": 32768, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen: Qwen-Max ", "open_weights": false, "reasoning": false, "release_date": "2024-04-03", "temperature": true, "tool_call": true }, "qwen/qwen-plus": { "attachment": false, "cost": { "cache_read": 0.08, "input": 0.4, "output": 1.2 }, "description": "Qwen: Qwen-Plus is an AI model provided by kilo.", "id": "qwen/qwen-plus", "last_updated": "2025-09-11", "limit": { "context": 1000000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen: Qwen-Plus", "open_weights": false, "reasoning": false, "release_date": "2024-01-25", "temperature": true, "tool_call": true }, "qwen/qwen-plus-2025-07-28": { "attachment": false, "cost": { "input": 0.26, "output": 0.78 }, "description": "Qwen: Qwen Plus 0728 is an AI model provided by kilo.", "id": "qwen/qwen-plus-2025-07-28", "last_updated": "2026-03-15", "limit": { "context": 1000000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen: Qwen Plus 0728", "open_weights": true, "reasoning": false, "release_date": "2025-09-09", "temperature": true, "tool_call": true }, "qwen/qwen-plus-2025-07-28:thinking": { "attachment": false, "cost": { "input": 0.26, "output": 0.78 }, "description": "Qwen: Qwen Plus 0728 (thinking) is an AI model provided by kilo.", "id": "qwen/qwen-plus-2025-07-28:thinking", "last_updated": "2026-03-15", "limit": { "context": 1000000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen: Qwen Plus 0728 (thinking)", "open_weights": true, "reasoning": true, "release_date": "2025-09-09", "temperature": true, "tool_call": true }, "qwen/qwen-turbo": { "attachment": false, "cost": { "cache_read": 0.01, "input": 0.0325, "output": 0.13 }, "description": "Qwen: Qwen-Turbo is an AI model provided by kilo.", "id": "qwen/qwen-turbo", "last_updated": "2026-03-15", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen: Qwen-Turbo", "open_weights": false, "reasoning": false, "release_date": "2024-11-01", "temperature": true, "tool_call": true }, "qwen/qwen-vl-max": { "attachment": true, "cost": { "input": 0.8, "output": 3.2 }, "description": "Qwen: Qwen VL Max is an AI model provided by kilo.", "id": "qwen/qwen-vl-max", "last_updated": "2025-08-13", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen: Qwen VL Max", "open_weights": false, "reasoning": false, "release_date": "2024-04-08", "temperature": true, "tool_call": true }, "qwen/qwen-vl-plus": { "attachment": true, "cost": { "cache_read": 0.042, "input": 0.1365, "output": 0.4095 }, "description": "Qwen: Qwen VL Plus is an AI model provided by kilo.", "id": "qwen/qwen-vl-plus", "last_updated": "2026-03-15", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "name": "Qwen: Qwen VL Plus", "open_weights": false, "reasoning": false, "release_date": "2024-01-25", "temperature": true, "tool_call": false }, "qwen/qwen2.5-vl-72b-instruct": { "attachment": true, "cost": { "cache_read": 0.075, "input": 0.8, "output": 0.8 }, "description": "Qwen: Qwen2.5 VL 72B Instruct is an AI model provided by kilo.", "id": "qwen/qwen2.5-vl-72b-instruct", "last_updated": "2026-03-15", "limit": { "context": 32768, "output": 32768 }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "name": "Qwen: Qwen2.5 VL 72B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-02-01", "temperature": true, "tool_call": false }, "qwen/qwen3-14b": { "attachment": false, "cost": { "cache_read": 0.025, "input": 0.06, "output": 0.24 }, "description": "Qwen: Qwen3 14B is an AI model provided by kilo.", "id": "qwen/qwen3-14b", "last_updated": "2026-03-15", "limit": { "context": 40960, "output": 40960 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen: Qwen3 14B", "open_weights": true, "reasoning": true, "release_date": "2025-04", "temperature": true, "tool_call": true }, "qwen/qwen3-235b-a22b": { "attachment": false, "cost": { "cache_read": 0.15, "input": 0.455, "output": 1.82 }, "description": "Qwen: Qwen3 235B A22B is an AI model provided by kilo.", "id": "qwen/qwen3-235b-a22b", "last_updated": "2026-03-15", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen: Qwen3 235B A22B", "open_weights": true, "reasoning": true, "release_date": "2024-12-01", "temperature": true, "tool_call": true }, "qwen/qwen3-235b-a22b-2507": { "attachment": false, "cost": { "input": 0.071, "output": 0.1 }, "description": "Qwen: Qwen3 235B A22B Instruct 2507 is an AI model provided by kilo.", "id": "qwen/qwen3-235b-a22b-2507", "last_updated": "2026-01", "limit": { "context": 262144, "output": 52429 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen: Qwen3 235B A22B Instruct 2507", "open_weights": true, "reasoning": true, "release_date": "2025-04", "temperature": true, "tool_call": true }, "qwen/qwen3-235b-a22b-thinking-2507": { "attachment": false, "cost": { "input": 0.11, "output": 0.6 }, "description": "Qwen: Qwen3 235B A22B Thinking 2507 is an AI model provided by kilo.", "id": "qwen/qwen3-235b-a22b-thinking-2507", "last_updated": "2026-03-15", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen: Qwen3 235B A22B Thinking 2507", "open_weights": true, "reasoning": true, "release_date": "2025-07-25", "temperature": true, "tool_call": true }, "qwen/qwen3-30b-a3b": { "attachment": false, "cost": { "cache_read": 0.03, "input": 0.08, "output": 0.28 }, "description": "Qwen: Qwen3 30B A3B is an AI model provided by kilo.", "id": "qwen/qwen3-30b-a3b", "last_updated": "2026-03-15", "limit": { "context": 40960, "output": 40960 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen: Qwen3 30B A3B", "open_weights": true, "reasoning": true, "release_date": "2025-04", "temperature": true, "tool_call": true }, "qwen/qwen3-30b-a3b-instruct-2507": { "attachment": false, "cost": { "cache_read": 0.04, "input": 0.09, "output": 0.3 }, "description": "Qwen: Qwen3 30B A3B Instruct 2507 is an AI model provided by kilo.", "id": "qwen/qwen3-30b-a3b-instruct-2507", "last_updated": "2026-03-15", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen: Qwen3 30B A3B Instruct 2507", "open_weights": true, "reasoning": false, "release_date": "2025-07-29", "temperature": true, "tool_call": true }, "qwen/qwen3-30b-a3b-thinking-2507": { "attachment": false, "cost": { "input": 0.051, "output": 0.34 }, "description": "Qwen: Qwen3 30B A3B Thinking 2507 is an AI model provided by kilo.", "id": "qwen/qwen3-30b-a3b-thinking-2507", "last_updated": "2025-07-29", "limit": { "context": 32768, "output": 6554 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen: Qwen3 30B A3B Thinking 2507", "open_weights": true, "reasoning": true, "release_date": "2025-07-29", "temperature": true, "tool_call": true }, "qwen/qwen3-32b": { "attachment": false, "cost": { "cache_read": 0.04, "input": 0.08, "output": 0.24 }, "description": "Qwen: Qwen3 32B is an AI model provided by kilo.", "id": "qwen/qwen3-32b", "last_updated": "2026-02-04", "limit": { "context": 40960, "output": 40960 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen: Qwen3 32B", "open_weights": true, "reasoning": true, "release_date": "2024-12-01", "temperature": true, "tool_call": true }, "qwen/qwen3-8b": { "attachment": false, "cost": { "cache_read": 0.05, "input": 0.05, "output": 0.4 }, "description": "Qwen: Qwen3 8B is an AI model provided by kilo.", "id": "qwen/qwen3-8b", "last_updated": "2026-03-15", "limit": { "context": 40960, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen: Qwen3 8B", "open_weights": true, "reasoning": true, "release_date": "2025-04", "temperature": true, "tool_call": true }, "qwen/qwen3-coder": { "attachment": false, "cost": { "cache_read": 0.022, "input": 0.22, "output": 1 }, "description": "Qwen: Qwen3 Coder 480B A35B is an AI model provided by kilo.", "id": "qwen/qwen3-coder", "last_updated": "2025-07-23", "limit": { "context": 262144, "output": 52429 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen: Qwen3 Coder 480B A35B", "open_weights": true, "reasoning": false, "release_date": "2025-07-23", "temperature": true, "tool_call": true }, "qwen/qwen3-coder-30b-a3b-instruct": { "attachment": false, "cost": { "input": 0.07, "output": 0.27 }, "description": "Qwen: Qwen3 Coder 30B A3B Instruct is an AI model provided by kilo.", "id": "qwen/qwen3-coder-30b-a3b-instruct", "last_updated": "2025-07-31", "limit": { "context": 160000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen: Qwen3 Coder 30B A3B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-07-31", "temperature": true, "tool_call": true }, "qwen/qwen3-coder-flash": { "attachment": false, "cost": { "cache_read": 0.06, "input": 0.195, "output": 0.975 }, "description": "Qwen: Qwen3 Coder Flash is an AI model provided by kilo.", "id": "qwen/qwen3-coder-flash", "last_updated": "2026-03-15", "limit": { "context": 1000000, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen: Qwen3 Coder Flash", "open_weights": false, "reasoning": false, "release_date": "2025-07-23", "temperature": true, "tool_call": true }, "qwen/qwen3-coder-next": { "attachment": false, "cost": { "cache_read": 0.035, "input": 0.12, "output": 0.75 }, "description": "Qwen: Qwen3 Coder Next is an AI model provided by kilo.", "id": "qwen/qwen3-coder-next", "last_updated": "2026-03-15", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen: Qwen3 Coder Next", "open_weights": true, "reasoning": false, "release_date": "2026-02-02", "temperature": true, "tool_call": true }, "qwen/qwen3-coder-plus": { "attachment": false, "cost": { "cache_read": 0.2, "input": 0.65, "output": 3.25 }, "description": "Qwen: Qwen3 Coder Plus is an AI model provided by kilo.", "id": "qwen/qwen3-coder-plus", "last_updated": "2026-03-15", "limit": { "context": 1000000, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen: Qwen3 Coder Plus", "open_weights": true, "reasoning": false, "release_date": "2025-07-01", "temperature": true, "tool_call": true }, "qwen/qwen3-max": { "attachment": false, "cost": { "cache_read": 0.24, "input": 1.2, "output": 6 }, "description": "Qwen: Qwen3 Max is an AI model provided by kilo.", "id": "qwen/qwen3-max", "last_updated": "2026-03-15", "limit": { "context": 262144, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen: Qwen3 Max", "open_weights": false, "reasoning": false, "release_date": "2025-09-05", "temperature": true, "tool_call": true }, "qwen/qwen3-max-thinking": { "attachment": false, "cost": { "input": 0.78, "output": 3.9 }, "description": "Qwen: Qwen3 Max Thinking is an AI model provided by kilo.", "id": "qwen/qwen3-max-thinking", "last_updated": "2026-03-15", "limit": { "context": 262144, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen: Qwen3 Max Thinking", "open_weights": false, "reasoning": true, "release_date": "2026-01-23", "temperature": true, "tool_call": true }, "qwen/qwen3-next-80b-a3b-instruct": { "attachment": false, "cost": { "input": 0.09, "output": 1.1 }, "description": "Qwen: Qwen3 Next 80B A3B Instruct is an AI model provided by kilo.", "id": "qwen/qwen3-next-80b-a3b-instruct", "last_updated": "2026-03-15", "limit": { "context": 131072, "output": 52429 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen: Qwen3 Next 80B A3B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-09-11", "temperature": true, "tool_call": true }, "qwen/qwen3-next-80b-a3b-thinking": { "attachment": false, "cost": { "input": 0.0975, "output": 0.78 }, "description": "Qwen: Qwen3 Next 80B A3B Thinking is an AI model provided by kilo.", "id": "qwen/qwen3-next-80b-a3b-thinking", "last_updated": "2026-03-15", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen: Qwen3 Next 80B A3B Thinking", "open_weights": true, "reasoning": true, "release_date": "2025-09-11", "temperature": true, "tool_call": true }, "qwen/qwen3-vl-235b-a22b-instruct": { "attachment": true, "cost": { "cache_read": 0.11, "input": 0.2, "output": 0.88 }, "description": "Qwen: Qwen3 VL 235B A22B Instruct is an AI model provided by kilo.", "id": "qwen/qwen3-vl-235b-a22b-instruct", "last_updated": "2026-01-10", "limit": { "context": 262144, "output": 52429 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen: Qwen3 VL 235B A22B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-09-23", "temperature": true, "tool_call": true }, "qwen/qwen3-vl-235b-a22b-thinking": { "attachment": true, "cost": { "input": 0.26, "output": 2.6 }, "description": "Qwen: Qwen3 VL 235B A22B Thinking is an AI model provided by kilo.", "id": "qwen/qwen3-vl-235b-a22b-thinking", "last_updated": "2026-03-15", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "name": "Qwen: Qwen3 VL 235B A22B Thinking", "open_weights": true, "reasoning": true, "release_date": "2025-09-24", "temperature": true, "tool_call": true }, "qwen/qwen3-vl-30b-a3b-instruct": { "attachment": true, "cost": { "input": 0.13, "output": 0.52 }, "description": "Qwen: Qwen3 VL 30B A3B Instruct is an AI model provided by kilo.", "id": "qwen/qwen3-vl-30b-a3b-instruct", "last_updated": "2025-11-25", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen: Qwen3 VL 30B A3B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-10-05", "temperature": true, "tool_call": true }, "qwen/qwen3-vl-30b-a3b-thinking": { "attachment": true, "cost": { "input": 0.13, "output": 1.56 }, "description": "Qwen: Qwen3 VL 30B A3B Thinking is an AI model provided by kilo.", "id": "qwen/qwen3-vl-30b-a3b-thinking", "last_updated": "2026-03-15", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "name": "Qwen: Qwen3 VL 30B A3B Thinking", "open_weights": true, "reasoning": true, "release_date": "2025-10-11", "temperature": true, "tool_call": true }, "qwen/qwen3-vl-32b-instruct": { "attachment": true, "cost": { "input": 0.104, "output": 0.416 }, "description": "Qwen: Qwen3 VL 32B Instruct is an AI model provided by kilo.", "id": "qwen/qwen3-vl-32b-instruct", "last_updated": "2025-11-25", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen: Qwen3 VL 32B Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-10-21", "temperature": true, "tool_call": true }, "qwen/qwen3-vl-8b-instruct": { "attachment": true, "cost": { "input": 0.08, "output": 0.5 }, "description": "Qwen: Qwen3 VL 8B Instruct is an AI model provided by kilo.", "id": "qwen/qwen3-vl-8b-instruct", "last_updated": "2025-11-25", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "name": "Qwen: Qwen3 VL 8B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-10-15", "temperature": true, "tool_call": true }, "qwen/qwen3-vl-8b-thinking": { "attachment": true, "cost": { "input": 0.117, "output": 1.365 }, "description": "Qwen: Qwen3 VL 8B Thinking is an AI model provided by kilo.", "id": "qwen/qwen3-vl-8b-thinking", "last_updated": "2025-11-25", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "name": "Qwen: Qwen3 VL 8B Thinking", "open_weights": false, "reasoning": true, "release_date": "2025-10-15", "temperature": true, "tool_call": true }, "qwen/qwen3.5-122b-a10b": { "attachment": true, "cost": { "input": 0.26, "output": 2.08 }, "description": "Qwen: Qwen3.5-122B-A10B is an AI model provided by kilo.", "id": "qwen/qwen3.5-122b-a10b", "last_updated": "2026-03-15", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "name": "Qwen: Qwen3.5-122B-A10B", "open_weights": true, "reasoning": true, "release_date": "2026-02-26", "temperature": true, "tool_call": true }, "qwen/qwen3.5-27b": { "attachment": true, "cost": { "input": 0.195, "output": 1.56 }, "description": "Qwen: Qwen3.5-27B is an AI model provided by kilo.", "id": "qwen/qwen3.5-27b", "last_updated": "2026-03-15", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "name": "Qwen: Qwen3.5-27B", "open_weights": true, "reasoning": true, "release_date": "2026-02-26", "temperature": true, "tool_call": true }, "qwen/qwen3.5-35b-a3b": { "attachment": true, "cost": { "input": 0.1625, "output": 1.3 }, "description": "Qwen: Qwen3.5-35B-A3B is an AI model provided by kilo.", "id": "qwen/qwen3.5-35b-a3b", "last_updated": "2026-03-15", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "name": "Qwen: Qwen3.5-35B-A3B", "open_weights": true, "reasoning": true, "release_date": "2026-02-26", "temperature": true, "tool_call": true }, "qwen/qwen3.5-397b-a17b": { "attachment": true, "cost": { "input": 0.39, "output": 2.34 }, "description": "Qwen: Qwen3.5 397B A17B is an AI model provided by kilo.", "id": "qwen/qwen3.5-397b-a17b", "last_updated": "2026-03-15", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "name": "Qwen: Qwen3.5 397B A17B", "open_weights": false, "reasoning": true, "release_date": "2026-02-15", "temperature": true, "tool_call": true }, "qwen/qwen3.5-9b": { "attachment": true, "cost": { "input": 0.05, "output": 0.15 }, "description": "Qwen: Qwen3.5-9B is an AI model provided by kilo.", "id": "qwen/qwen3.5-9b", "last_updated": "2026-03-15", "limit": { "context": 256000, "output": 32768 }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "name": "Qwen: Qwen3.5-9B", "open_weights": true, "reasoning": true, "release_date": "2026-03-10", "temperature": true, "tool_call": true }, "qwen/qwen3.5-flash-02-23": { "attachment": true, "cost": { "input": 0.1, "output": 0.4 }, "description": "Qwen: Qwen3.5-Flash is an AI model provided by kilo.", "id": "qwen/qwen3.5-flash-02-23", "last_updated": "2026-03-15", "limit": { "context": 1000000, "output": 65536 }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "name": "Qwen: Qwen3.5-Flash", "open_weights": true, "reasoning": true, "release_date": "2026-02-26", "temperature": true, "tool_call": true }, "qwen/qwen3.5-plus-02-15": { "attachment": true, "cost": { "input": 0.26, "output": 1.56 }, "description": "Qwen: Qwen3.5 Plus 2026-02-15 is an AI model provided by kilo.", "id": "qwen/qwen3.5-plus-02-15", "last_updated": "2026-03-15", "limit": { "context": 1000000, "output": 65536 }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "name": "Qwen: Qwen3.5 Plus 2026-02-15", "open_weights": false, "reasoning": true, "release_date": "2026-02-15", "temperature": true, "tool_call": true }, "qwen/qwen3.5-plus-20260420": { "attachment": true, "cost": { "input": 0.4, "output": 2.4 }, "description": "Qwen: Qwen3.5 Plus 2026-04-20 is an AI model provided by kilo.", "id": "qwen/qwen3.5-plus-20260420", "last_updated": "2026-05-01", "limit": { "context": 1000000, "output": 65536 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen: Qwen3.5 Plus 2026-04-20", "open_weights": false, "reasoning": true, "release_date": "2026-04-27", "temperature": true, "tool_call": true }, "qwen/qwen3.6-27b": { "attachment": true, "cost": { "input": 0.325, "output": 3.25 }, "description": "Qwen: Qwen3.6 27B is an AI model provided by kilo.", "id": "qwen/qwen3.6-27b", "last_updated": "2026-05-01", "limit": { "context": 256000, "output": 65536 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen: Qwen3.6 27B", "open_weights": false, "reasoning": true, "release_date": "2026-04-27", "temperature": true, "tool_call": true }, "qwen/qwen3.6-35b-a3b": { "attachment": true, "cost": { "cache_read": 0.1612, "input": 0.1612, "output": 0.96525 }, "description": "Qwen: Qwen3.6 35B A3B is an AI model provided by kilo.", "id": "qwen/qwen3.6-35b-a3b", "last_updated": "2026-05-01", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen: Qwen3.6 35B A3B", "open_weights": false, "reasoning": true, "release_date": "2026-04-27", "temperature": true, "tool_call": false }, "qwen/qwen3.6-flash": { "attachment": true, "cost": { "cache_write": 0.3125, "input": 0.25, "output": 1.5 }, "description": "Qwen: Qwen3.6 Flash is an AI model provided by kilo.", "id": "qwen/qwen3.6-flash", "last_updated": "2026-05-01", "limit": { "context": 1000000, "output": 65536 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen: Qwen3.6 Flash", "open_weights": false, "reasoning": true, "release_date": "2026-04-27", "temperature": true, "tool_call": true }, "qwen/qwen3.6-max-preview": { "attachment": false, "cost": { "cache_write": 1.3, "input": 1.04, "output": 6.24 }, "description": "Qwen: Qwen3.6 Max Preview is an AI model provided by kilo.", "id": "qwen/qwen3.6-max-preview", "last_updated": "2026-05-01", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen: Qwen3.6 Max Preview", "open_weights": false, "reasoning": true, "release_date": "2026-04-27", "temperature": true, "tool_call": true }, "qwen/qwen3.6-plus": { "attachment": true, "cost": { "cache_read": 0.0325, "cache_write": 0.40625, "input": 0.325, "output": 1.95 }, "description": "Qwen: Qwen3.6 Plus is an AI model provided by kilo.", "id": "qwen/qwen3.6-plus", "last_updated": "2026-04-11", "limit": { "context": 1000000, "output": 65536 }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "name": "Qwen: Qwen3.6 Plus", "open_weights": false, "reasoning": true, "release_date": "2025-08-26", "temperature": true, "tool_call": true }, "rekaai/reka-edge": { "attachment": true, "cost": { "input": 0.1, "output": 0.1 }, "description": "Reka Edge is an AI model provided by kilo.", "id": "rekaai/reka-edge", "last_updated": "2026-04-11", "limit": { "context": 16384, "output": 16384 }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "name": "Reka Edge", "open_weights": true, "reasoning": false, "release_date": "2026-03-20", "temperature": true, "tool_call": true }, "rekaai/reka-flash-3": { "attachment": false, "cost": { "input": 0.1, "output": 0.2 }, "description": "Reka Flash 3 is an AI model provided by kilo.", "id": "rekaai/reka-flash-3", "last_updated": "2026-04-11", "limit": { "context": 65536, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Reka Flash 3", "open_weights": true, "reasoning": true, "release_date": "2025-03-12", "temperature": true, "tool_call": false }, "relace/relace-apply-3": { "attachment": false, "cost": { "input": 0.85, "output": 1.25 }, "description": "Relace: Relace Apply 3 is an AI model provided by kilo.", "id": "relace/relace-apply-3", "last_updated": "2026-03-15", "limit": { "context": 256000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Relace: Relace Apply 3", "open_weights": false, "reasoning": false, "release_date": "2025-09-26", "tool_call": false }, "relace/relace-search": { "attachment": false, "cost": { "input": 1, "output": 3 }, "description": "Relace: Relace Search is an AI model provided by kilo.", "id": "relace/relace-search", "last_updated": "2026-03-15", "limit": { "context": 256000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Relace: Relace Search", "open_weights": false, "reasoning": false, "release_date": "2025-12-09", "temperature": true, "tool_call": true }, "sao10k/l3-euryale-70b": { "attachment": false, "cost": { "input": 1.48, "output": 1.48 }, "description": "Sao10k: Llama 3 Euryale 70B v2.1 is an AI model provided by kilo.", "id": "sao10k/l3-euryale-70b", "last_updated": "2026-03-15", "limit": { "context": 8192, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Sao10k: Llama 3 Euryale 70B v2.1", "open_weights": true, "reasoning": false, "release_date": "2024-06-18", "temperature": true, "tool_call": true }, "sao10k/l3-lunaris-8b": { "attachment": false, "cost": { "input": 0.04, "output": 0.05 }, "description": "Sao10K: Llama 3 8B Lunaris is an AI model provided by kilo.", "id": "sao10k/l3-lunaris-8b", "last_updated": "2026-03-15", "limit": { "context": 8192, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Sao10K: Llama 3 8B Lunaris", "open_weights": true, "reasoning": false, "release_date": "2024-08-13", "temperature": true, "tool_call": false }, "sao10k/l3.1-70b-hanami-x1": { "attachment": false, "cost": { "input": 3, "output": 3 }, "description": "Sao10K: Llama 3.1 70B Hanami x1 is an AI model provided by kilo.", "id": "sao10k/l3.1-70b-hanami-x1", "last_updated": "2026-03-15", "limit": { "context": 16000, "output": 16000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Sao10K: Llama 3.1 70B Hanami x1", "open_weights": true, "reasoning": false, "release_date": "2025-01-08", "temperature": true, "tool_call": false }, "sao10k/l3.1-euryale-70b": { "attachment": false, "cost": { "input": 0.85, "output": 0.85 }, "description": "Sao10K: Llama 3.1 Euryale 70B v2.2 is an AI model provided by kilo.", "id": "sao10k/l3.1-euryale-70b", "last_updated": "2026-03-15", "limit": { "context": 131072, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Sao10K: Llama 3.1 Euryale 70B v2.2", "open_weights": true, "reasoning": false, "release_date": "2024-08-28", "temperature": true, "tool_call": true }, "sao10k/l3.3-euryale-70b": { "attachment": false, "cost": { "input": 0.65, "output": 0.75 }, "description": "Sao10K: Llama 3.3 Euryale 70B is an AI model provided by kilo.", "id": "sao10k/l3.3-euryale-70b", "last_updated": "2026-03-15", "limit": { "context": 131072, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Sao10K: Llama 3.3 Euryale 70B", "open_weights": true, "reasoning": false, "release_date": "2024-12-18", "temperature": true, "tool_call": false }, "stepfun/step-3.5-flash": { "attachment": false, "cost": { "cache_read": 0.02, "input": 0.1, "output": 0.3 }, "description": "StepFun: Step 3.5 Flash is an AI model provided by kilo.", "id": "stepfun/step-3.5-flash", "last_updated": "2026-01-29", "limit": { "context": 256000, "output": 256000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "StepFun: Step 3.5 Flash", "open_weights": true, "reasoning": true, "release_date": "2026-01-29", "temperature": true, "tool_call": true }, "stepfun/step-3.5-flash:free": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "StepFun: Step 3.5 Flash (free) is an AI model provided by kilo.", "id": "stepfun/step-3.5-flash:free", "last_updated": "2026-05-01", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "StepFun: Step 3.5 Flash (free)", "open_weights": false, "reasoning": true, "release_date": "2025-08-26", "temperature": true, "tool_call": true }, "switchpoint/router": { "attachment": false, "cost": { "input": 0.85, "output": 3.4 }, "description": "Switchpoint Router is an AI model provided by kilo.", "id": "switchpoint/router", "last_updated": "2026-03-15", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Switchpoint Router", "open_weights": false, "reasoning": true, "release_date": "2025-07-12", "temperature": true, "tool_call": false }, "tencent/hunyuan-a13b-instruct": { "attachment": false, "cost": { "input": 0.14, "output": 0.57 }, "description": "Tencent: Hunyuan A13B Instruct is an AI model provided by kilo.", "id": "tencent/hunyuan-a13b-instruct", "last_updated": "2025-11-25", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Tencent: Hunyuan A13B Instruct", "open_weights": false, "reasoning": true, "release_date": "2025-06-30", "temperature": true, "tool_call": false }, "tencent/hy3-preview:free": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Tencent: Hy3 Preview (free) is an AI model provided by kilo.", "id": "tencent/hy3-preview:free", "last_updated": "2026-05-01", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Tencent: Hy3 Preview (free)", "open_weights": false, "reasoning": true, "release_date": "2026-04-22", "temperature": true, "tool_call": true }, "thedrummer/cydonia-24b-v4.1": { "attachment": false, "cost": { "input": 0.3, "output": 0.5 }, "description": "TheDrummer: Cydonia 24B V4.1 is an AI model provided by kilo.", "id": "thedrummer/cydonia-24b-v4.1", "last_updated": "2026-03-15", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "TheDrummer: Cydonia 24B V4.1", "open_weights": true, "reasoning": false, "release_date": "2025-09-27", "temperature": true, "tool_call": false }, "thedrummer/rocinante-12b": { "attachment": false, "cost": { "input": 0.17, "output": 0.43 }, "description": "TheDrummer: Rocinante 12B is an AI model provided by kilo.", "id": "thedrummer/rocinante-12b", "last_updated": "2026-03-15", "limit": { "context": 32768, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "TheDrummer: Rocinante 12B", "open_weights": true, "reasoning": false, "release_date": "2024-09-30", "temperature": true, "tool_call": true }, "thedrummer/skyfall-36b-v2": { "attachment": false, "cost": { "input": 0.55, "output": 0.8 }, "description": "TheDrummer: Skyfall 36B V2 is an AI model provided by kilo.", "id": "thedrummer/skyfall-36b-v2", "last_updated": "2026-03-15", "limit": { "context": 32768, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "TheDrummer: Skyfall 36B V2", "open_weights": true, "reasoning": false, "release_date": "2025-03-11", "temperature": true, "tool_call": false }, "thedrummer/unslopnemo-12b": { "attachment": false, "cost": { "input": 0.4, "output": 0.4 }, "description": "TheDrummer: UnslopNemo 12B is an AI model provided by kilo.", "id": "thedrummer/unslopnemo-12b", "last_updated": "2026-03-15", "limit": { "context": 32768, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "TheDrummer: UnslopNemo 12B", "open_weights": true, "reasoning": false, "release_date": "2024-11-09", "temperature": true, "tool_call": true }, "tngtech/deepseek-r1t2-chimera": { "attachment": false, "cost": { "cache_read": 0.125, "input": 0.25, "output": 0.85 }, "description": "TNG: DeepSeek R1T2 Chimera is an AI model provided by kilo.", "id": "tngtech/deepseek-r1t2-chimera", "last_updated": "2025-07-08", "limit": { "context": 163840, "output": 163840 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "TNG: DeepSeek R1T2 Chimera", "open_weights": true, "reasoning": true, "release_date": "2025-07-08", "temperature": true, "tool_call": true }, "undi95/remm-slerp-l2-13b": { "attachment": false, "cost": { "input": 0.45, "output": 0.65 }, "description": "ReMM SLERP 13B is an AI model provided by kilo.", "id": "undi95/remm-slerp-l2-13b", "last_updated": "2026-03-15", "limit": { "context": 6144, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "ReMM SLERP 13B", "open_weights": true, "reasoning": false, "release_date": "2023-07-22", "temperature": true, "tool_call": false }, "upstage/solar-pro-3": { "attachment": false, "cost": { "input": 0.15, "output": 0.6 }, "description": "Upstage: Solar Pro 3 is an AI model provided by kilo.", "id": "upstage/solar-pro-3", "last_updated": "2026-03-15", "limit": { "context": 128000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Upstage: Solar Pro 3", "open_weights": false, "reasoning": true, "release_date": "2026-01-27", "temperature": true, "tool_call": true }, "writer/palmyra-x5": { "attachment": false, "cost": { "input": 0.6, "output": 6 }, "description": "Writer: Palmyra X5 is an AI model provided by kilo.", "id": "writer/palmyra-x5", "last_updated": "2025-04-28", "limit": { "context": 1040000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Writer: Palmyra X5", "open_weights": false, "reasoning": false, "release_date": "2025-04-28", "temperature": true, "tool_call": false }, "x-ai/grok-3": { "attachment": false, "cost": { "cache_read": 0.75, "input": 3, "output": 15 }, "description": "xAI: Grok 3 is an AI model provided by kilo.", "id": "x-ai/grok-3", "last_updated": "2025-02-17", "limit": { "context": 131072, "output": 26215 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "xAI: Grok 3", "open_weights": false, "reasoning": false, "release_date": "2025-02-17", "temperature": true, "tool_call": true }, "x-ai/grok-3-beta": { "attachment": false, "cost": { "cache_read": 0.75, "input": 3, "output": 15 }, "description": "xAI: Grok 3 Beta is an AI model provided by kilo.", "id": "x-ai/grok-3-beta", "last_updated": "2025-02-17", "limit": { "context": 131072, "output": 26215 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "xAI: Grok 3 Beta", "open_weights": false, "reasoning": false, "release_date": "2025-02-17", "temperature": true, "tool_call": true }, "x-ai/grok-3-mini": { "attachment": false, "cost": { "cache_read": 0.075, "input": 0.3, "output": 0.5 }, "description": "xAI: Grok 3 Mini is an AI model provided by kilo.", "id": "x-ai/grok-3-mini", "last_updated": "2025-02-17", "limit": { "context": 131072, "output": 26215 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "xAI: Grok 3 Mini", "open_weights": false, "reasoning": true, "release_date": "2025-02-17", "temperature": true, "tool_call": true }, "x-ai/grok-3-mini-beta": { "attachment": false, "cost": { "cache_read": 0.075, "input": 0.3, "output": 0.5 }, "description": "xAI: Grok 3 Mini Beta is an AI model provided by kilo.", "id": "x-ai/grok-3-mini-beta", "last_updated": "2025-02-17", "limit": { "context": 131072, "output": 26215 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "xAI: Grok 3 Mini Beta", "open_weights": false, "reasoning": true, "release_date": "2025-02-17", "temperature": true, "tool_call": true }, "x-ai/grok-4": { "attachment": true, "cost": { "cache_read": 0.75, "input": 3, "output": 15 }, "description": "xAI: Grok 4 is an AI model provided by kilo.", "id": "x-ai/grok-4", "last_updated": "2025-07-09", "limit": { "context": 256000, "output": 51200 }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "name": "xAI: Grok 4", "open_weights": false, "reasoning": true, "release_date": "2025-07-09", "temperature": true, "tool_call": true }, "x-ai/grok-4-fast": { "attachment": true, "cost": { "cache_read": 0.05, "input": 0.2, "output": 0.5 }, "description": "xAI: Grok 4 Fast is an AI model provided by kilo.", "id": "x-ai/grok-4-fast", "last_updated": "2025-08-19", "limit": { "context": 2000000, "output": 30000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "xAI: Grok 4 Fast", "open_weights": false, "reasoning": true, "release_date": "2025-08-19", "temperature": true, "tool_call": true }, "x-ai/grok-4.1-fast": { "attachment": true, "cost": { "cache_read": 0.05, "input": 0.2, "output": 0.5 }, "description": "xAI: Grok 4.1 Fast is an AI model provided by kilo.", "id": "x-ai/grok-4.1-fast", "last_updated": "2025-11-19", "limit": { "context": 2000000, "output": 30000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "xAI: Grok 4.1 Fast", "open_weights": false, "reasoning": true, "release_date": "2025-11-19", "temperature": true, "tool_call": true }, "x-ai/grok-4.20": { "attachment": true, "cost": { "cache_read": 0.2, "input": 2, "output": 6 }, "description": "xAI: Grok 4.20 is an AI model provided by kilo.", "id": "x-ai/grok-4.20", "last_updated": "2026-04-11", "limit": { "context": 2000000, "output": 2000000 }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "name": "xAI: Grok 4.20", "open_weights": false, "reasoning": true, "release_date": "2026-03-31", "temperature": true, "tool_call": true }, "x-ai/grok-4.20-multi-agent": { "attachment": true, "cost": { "cache_read": 0.2, "input": 2, "output": 6 }, "description": "xAI: Grok 4.20 Multi-Agent is an AI model provided by kilo.", "id": "x-ai/grok-4.20-multi-agent", "last_updated": "2026-04-11", "limit": { "context": 2000000, "output": 2000000 }, "modalities": { "input": [ "image", "pdf", "text" ], "output": [ "text" ] }, "name": "xAI: Grok 4.20 Multi-Agent", "open_weights": false, "reasoning": true, "release_date": "2026-03-31", "temperature": true, "tool_call": false }, "x-ai/grok-4.3": { "attachment": true, "cost": { "cache_read": 0.2, "input": 1.25, "output": 2.5 }, "description": "xAI: Grok 4.3 is an AI model provided by kilo.", "id": "x-ai/grok-4.3", "last_updated": "2026-05-01", "limit": { "context": 1000000, "output": 4096 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "xAI: Grok 4.3", "open_weights": false, "reasoning": true, "release_date": "2026-05-01", "temperature": true, "tool_call": true }, "x-ai/grok-code-fast-1": { "attachment": false, "cost": { "cache_read": 0.02, "input": 0.2, "output": 1.5 }, "description": "xAI: Grok Code Fast 1 is an AI model provided by kilo.", "id": "x-ai/grok-code-fast-1", "last_updated": "2025-08-26", "limit": { "context": 256000, "output": 10000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "xAI: Grok Code Fast 1", "open_weights": false, "reasoning": true, "release_date": "2025-08-26", "temperature": true, "tool_call": true }, "x-ai/grok-code-fast-1:optimized:free": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "xAI: Grok Code Fast 1 Optimized (experimental, free) is an AI model provided by kilo.", "id": "x-ai/grok-code-fast-1:optimized:free", "last_updated": "2026-03-15", "limit": { "context": 256000, "output": 10000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "xAI: Grok Code Fast 1 Optimized (experimental, free)", "open_weights": false, "reasoning": true, "release_date": "2025-08-27", "temperature": true, "tool_call": true }, "xiaomi/mimo-v2-flash": { "attachment": false, "cost": { "cache_read": 0.045, "input": 0.09, "output": 0.29 }, "description": "Xiaomi: MiMo-V2-Flash is an AI model provided by kilo.", "family": "mimo", "id": "xiaomi/mimo-v2-flash", "knowledge": "2024-12-01", "last_updated": "2026-02-04", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Xiaomi: MiMo-V2-Flash", "open_weights": true, "reasoning": true, "release_date": "2025-12-16", "temperature": true, "tool_call": true }, "xiaomi/mimo-v2-omni": { "attachment": true, "cost": { "cache_read": 0.08, "input": 0.4, "output": 2 }, "description": "Xiaomi: MiMo-V2-Omni is an AI model provided by kilo.", "family": "mimo", "id": "xiaomi/mimo-v2-omni", "knowledge": "2024-12", "last_updated": "2026-03-18", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Xiaomi: MiMo-V2-Omni", "open_weights": false, "reasoning": true, "release_date": "2026-03-18", "temperature": true, "tool_call": true }, "xiaomi/mimo-v2-pro": { "attachment": false, "cost": { "cache_read": 0.2, "context_over_200k": { "cache_read": 0.4, "input": 2, "output": 6 }, "input": 1, "output": 3, "tiers": [ { "cache_read": 0.4, "input": 2, "output": 6, "tier": { "size": 256000, "type": "context" } } ] }, "description": "Xiaomi: MiMo-V2-Pro is an AI model provided by kilo.", "family": "mimo", "id": "xiaomi/mimo-v2-pro", "knowledge": "2024-12", "last_updated": "2026-03-18", "limit": { "context": 1048576, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Xiaomi: MiMo-V2-Pro", "open_weights": false, "reasoning": true, "release_date": "2026-03-18", "temperature": true, "tool_call": true }, "xiaomi/mimo-v2.5": { "attachment": true, "cost": { "cache_read": 0.08, "context_over_200k": { "cache_read": 0.16, "input": 0.8, "output": 4 }, "input": 0.4, "output": 2, "tiers": [ { "cache_read": 0.16, "input": 0.8, "output": 4, "tier": { "size": 256000, "type": "context" } } ] }, "description": "Xiaomi: MiMo-V2.5 is an AI model provided by kilo.", "family": "mimo", "id": "xiaomi/mimo-v2.5", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-12", "last_updated": "2026-04-22", "limit": { "context": 1048576, "output": 131072 }, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "name": "Xiaomi: MiMo-V2.5", "open_weights": true, "reasoning": true, "release_date": "2026-04-22", "temperature": true, "tool_call": true }, "xiaomi/mimo-v2.5-pro": { "attachment": false, "cost": { "cache_read": 0.2, "context_over_200k": { "cache_read": 0.4, "input": 2, "output": 6 }, "input": 1, "output": 3, "tiers": [ { "cache_read": 0.4, "input": 2, "output": 6, "tier": { "size": 256000, "type": "context" } } ] }, "description": "Xiaomi: MiMo V2.5 Pro is an AI model provided by kilo.", "family": "mimo", "id": "xiaomi/mimo-v2.5-pro", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-12", "last_updated": "2026-04-22", "limit": { "context": 1048576, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Xiaomi: MiMo V2.5 Pro", "open_weights": true, "reasoning": true, "release_date": "2026-04-22", "temperature": true, "tool_call": true }, "z-ai/glm-4-32b": { "attachment": false, "cost": { "input": 0.1, "output": 0.1 }, "description": "Z.ai: GLM 4 32B is an AI model provided by kilo.", "id": "z-ai/glm-4-32b", "last_updated": "2026-03-15", "limit": { "context": 128000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Z.ai: GLM 4 32B ", "open_weights": true, "reasoning": false, "release_date": "2025-07-25", "temperature": true, "tool_call": true }, "z-ai/glm-4.5": { "attachment": false, "cost": { "cache_read": 0.175, "input": 0.6, "output": 2.2 }, "description": "Z.ai: GLM 4.5 is an AI model provided by kilo.", "id": "z-ai/glm-4.5", "last_updated": "2026-03-15", "limit": { "context": 131072, "output": 98304 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Z.ai: GLM 4.5", "open_weights": true, "reasoning": true, "release_date": "2025-07-28", "temperature": true, "tool_call": true }, "z-ai/glm-4.5-air": { "attachment": false, "cost": { "cache_read": 0.025, "input": 0.13, "output": 0.85 }, "description": "Z.ai: GLM 4.5 Air is an AI model provided by kilo.", "id": "z-ai/glm-4.5-air", "last_updated": "2025-07-28", "limit": { "context": 131072, "output": 98304 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Z.ai: GLM 4.5 Air", "open_weights": true, "reasoning": true, "release_date": "2025-07-28", "temperature": true, "tool_call": true }, "z-ai/glm-4.5v": { "attachment": true, "cost": { "cache_read": 0.11, "input": 0.6, "output": 1.8 }, "description": "Z.ai: GLM 4.5V is an AI model provided by kilo.", "id": "z-ai/glm-4.5v", "last_updated": "2025-08-11", "limit": { "context": 65536, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Z.ai: GLM 4.5V", "open_weights": true, "reasoning": true, "release_date": "2025-08-11", "temperature": true, "tool_call": true }, "z-ai/glm-4.6": { "attachment": false, "cost": { "cache_read": 0.175, "input": 0.39, "output": 1.9 }, "description": "Z.ai: GLM 4.6 is an AI model provided by kilo.", "id": "z-ai/glm-4.6", "last_updated": "2026-03-15", "limit": { "context": 204800, "output": 204800 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Z.ai: GLM 4.6", "open_weights": true, "reasoning": true, "release_date": "2025-09-30", "temperature": true, "tool_call": true }, "z-ai/glm-4.6v": { "attachment": true, "cost": { "input": 0.3, "output": 0.9 }, "description": "Z.ai: GLM 4.6V is an AI model provided by kilo.", "id": "z-ai/glm-4.6v", "last_updated": "2026-01-10", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "name": "Z.ai: GLM 4.6V", "open_weights": true, "reasoning": true, "release_date": "2025-09-30", "temperature": true, "tool_call": true }, "z-ai/glm-4.7": { "attachment": false, "cost": { "cache_read": 0.2, "input": 0.38, "output": 1.98 }, "description": "Z.ai: GLM 4.7 is an AI model provided by kilo.", "id": "z-ai/glm-4.7", "last_updated": "2026-03-15", "limit": { "context": 202752, "output": 65535 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Z.ai: GLM 4.7", "open_weights": true, "reasoning": true, "release_date": "2025-12-22", "temperature": true, "tool_call": true }, "z-ai/glm-4.7-flash": { "attachment": false, "cost": { "cache_read": 0.01, "input": 0.06, "output": 0.4 }, "description": "Z.ai: GLM 4.7 Flash is an AI model provided by kilo.", "id": "z-ai/glm-4.7-flash", "last_updated": "2026-01-19", "limit": { "context": 202752, "output": 40551 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Z.ai: GLM 4.7 Flash", "open_weights": true, "reasoning": true, "release_date": "2026-01-19", "temperature": true, "tool_call": true }, "z-ai/glm-5": { "attachment": false, "cost": { "input": 0.72, "output": 2.3 }, "description": "Z.ai: GLM 5 is an AI model provided by kilo.", "id": "z-ai/glm-5", "last_updated": "2026-03-15", "limit": { "context": 202752, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Z.ai: GLM 5", "open_weights": true, "reasoning": true, "release_date": "2026-02-12", "temperature": true, "tool_call": true }, "z-ai/glm-5-turbo": { "attachment": false, "cost": { "cache_read": 0.24, "input": 1.2, "output": 4 }, "description": "Z.ai: GLM 5 Turbo is an AI model provided by kilo.", "id": "z-ai/glm-5-turbo", "last_updated": "2026-04-11", "limit": { "context": 202752, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Z.ai: GLM 5 Turbo", "open_weights": true, "reasoning": true, "release_date": "2026-03-15", "temperature": true, "tool_call": true }, "z-ai/glm-5.1": { "attachment": false, "cost": { "input": 1.26, "output": 3.96 }, "description": "Z.ai: GLM 5.1 is an AI model provided by kilo.", "id": "z-ai/glm-5.1", "last_updated": "2026-03-27", "limit": { "context": 202752, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Z.ai: GLM 5.1", "open_weights": true, "reasoning": true, "release_date": "2026-03-27", "temperature": true, "tool_call": true }, "z-ai/glm-5v-turbo": { "attachment": true, "cost": { "cache_read": 0.24, "input": 1.2, "output": 4 }, "description": "Z.ai: GLM 5V Turbo is an AI model provided by kilo.", "id": "z-ai/glm-5v-turbo", "last_updated": "2026-04-11", "limit": { "context": 202752, "output": 131072 }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "name": "Z.ai: GLM 5V Turbo", "open_weights": true, "reasoning": true, "release_date": "2026-04-01", "temperature": true, "tool_call": true }, "~anthropic/claude-haiku-latest": { "attachment": true, "cost": { "cache_read": 0.1, "cache_write": 1.25, "input": 1, "output": 5 }, "description": "Anthropic: Claude Haiku Latest is an AI model provided by kilo.", "id": "~anthropic/claude-haiku-latest", "last_updated": "2026-05-01", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Anthropic: Claude Haiku Latest", "open_weights": false, "reasoning": true, "release_date": "2026-04-27", "temperature": true, "tool_call": true }, "~anthropic/claude-opus-latest": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "input": 5, "output": 25 }, "description": "Anthropic: Claude Opus Latest is an AI model provided by kilo.", "id": "~anthropic/claude-opus-latest", "last_updated": "2026-05-01", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Anthropic: Claude Opus Latest", "open_weights": false, "reasoning": true, "release_date": "2026-04-16", "temperature": false, "tool_call": true }, "~anthropic/claude-sonnet-latest": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Anthropic: Claude Sonnet Latest is an AI model provided by kilo.", "id": "~anthropic/claude-sonnet-latest", "last_updated": "2026-05-01", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Anthropic: Claude Sonnet Latest", "open_weights": false, "reasoning": true, "release_date": "2026-04-27", "temperature": true, "tool_call": true }, "~google/gemini-flash-latest": { "attachment": true, "cost": { "cache_read": 0.05, "cache_write": 0.08333333333333334, "input": 0.5, "output": 3 }, "description": "Google: Gemini Flash Latest is an AI model provided by kilo.", "id": "~google/gemini-flash-latest", "last_updated": "2026-05-01", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Google: Gemini Flash Latest", "open_weights": false, "reasoning": true, "release_date": "2026-04-27", "temperature": true, "tool_call": true }, "~google/gemini-pro-latest": { "attachment": true, "cost": { "cache_read": 0.2, "cache_write": 0.375, "input": 2, "output": 12 }, "description": "Google: Gemini Pro Latest is an AI model provided by kilo.", "id": "~google/gemini-pro-latest", "last_updated": "2026-05-01", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Google: Gemini Pro Latest", "open_weights": false, "reasoning": true, "release_date": "2026-04-27", "temperature": true, "tool_call": true }, "~moonshotai/kimi-latest": { "attachment": true, "cost": { "cache_read": 0.14, "input": 0.74, "output": 3.49 }, "description": "MoonshotAI: Kimi Latest is an AI model provided by kilo.", "id": "~moonshotai/kimi-latest", "last_updated": "2026-05-01", "limit": { "context": 262142, "output": 262142 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "MoonshotAI: Kimi Latest", "open_weights": false, "reasoning": true, "release_date": "2026-04-27", "temperature": true, "tool_call": true }, "~openai/gpt-latest": { "attachment": true, "cost": { "cache_read": 0.5, "input": 5, "output": 30 }, "description": "OpenAI: GPT Latest is an AI model provided by kilo.", "id": "~openai/gpt-latest", "last_updated": "2026-05-01", "limit": { "context": 1050000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "OpenAI: GPT Latest", "open_weights": false, "reasoning": true, "release_date": "2026-04-27", "temperature": false, "tool_call": true }, "~openai/gpt-mini-latest": { "attachment": true, "cost": { "cache_read": 0.075, "input": 0.75, "output": 4.5 }, "description": "OpenAI: GPT Mini Latest is an AI model provided by kilo.", "id": "~openai/gpt-mini-latest", "last_updated": "2026-05-01", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "OpenAI: GPT Mini Latest", "open_weights": false, "reasoning": true, "release_date": "2026-04-27", "temperature": false, "tool_call": true } }, "name": "Kilo Gateway", "npm": "@ai-sdk/openai-compatible" }, "kimi-for-coding": { "api": "https://api.kimi.com/coding/v1", "doc": "https://www.kimi.com/coding/docs/en/third-party-agents.html", "env": [ "KIMI_API_KEY" ], "iconURL": "https://models.dev/logos/kimi-for-coding.svg", "id": "kimi-for-coding", "models": { "k2p5": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "Kimi K2.5 is an AI model provided by kimi-for-coding.", "family": "kimi-thinking", "id": "k2p5", "knowledge": "2025-01", "last_updated": "2026-01", "limit": { "context": 262144, "output": 32768 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Kimi K2.5", "open_weights": true, "reasoning": true, "release_date": "2026-01", "structured_output": true, "temperature": true, "tool_call": true }, "k2p6": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "Kimi K2.6 is an AI model provided by kimi-for-coding.", "family": "kimi-thinking", "id": "k2p6", "knowledge": "2025-01", "last_updated": "2026-04", "limit": { "context": 262144, "output": 32768 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Kimi K2.6", "open_weights": true, "reasoning": true, "release_date": "2026-04", "structured_output": true, "temperature": true, "tool_call": true }, "kimi-k2-thinking": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "Kimi K2 Thinking is an AI model provided by kimi-for-coding.", "family": "kimi-thinking", "id": "kimi-k2-thinking", "knowledge": "2025-07", "last_updated": "2025-12", "limit": { "context": 262144, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 Thinking", "open_weights": true, "reasoning": true, "release_date": "2025-11", "structured_output": true, "temperature": true, "tool_call": true } }, "name": "Kimi For Coding", "npm": "@ai-sdk/anthropic" }, "kuae-cloud-coding-plan": { "api": "https://coding-plan-endpoint.kuaecloud.net/v1", "doc": "https://docs.mthreads.com/kuaecloud/kuaecloud-doc-online/coding_plan/", "env": [ "KUAE_API_KEY" ], "iconURL": "https://models.dev/logos/kuae-cloud-coding-plan.svg", "id": "kuae-cloud-coding-plan", "models": { "GLM-4.7": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "GLM-4.7 is an AI model provided by kuae-cloud-coding-plan.", "family": "glm", "id": "GLM-4.7", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-04", "last_updated": "2025-12-22", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.7", "open_weights": true, "reasoning": true, "release_date": "2025-12-22", "temperature": true, "tool_call": true } }, "name": "KUAE Cloud Coding Plan", "npm": "@ai-sdk/openai-compatible" }, "llama": { "api": "https://api.llama.com/compat/v1/", "doc": "https://llama.developer.meta.com/docs/models", "env": [ "LLAMA_API_KEY" ], "iconURL": "https://models.dev/logos/llama.svg", "id": "llama", "lobeIcon": "Meta.Color", "models": { "cerebras-llama-4-maverick-17b-128e-instruct": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Cerebras-Llama-4-Maverick-17B-128E-Instruct is an AI model provided by llama.", "family": "llama", "id": "cerebras-llama-4-maverick-17b-128e-instruct", "knowledge": "2025-01", "last_updated": "2025-04-05", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Cerebras-Llama-4-Maverick-17B-128E-Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-04-05", "temperature": true, "tool_call": true }, "cerebras-llama-4-scout-17b-16e-instruct": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Cerebras-Llama-4-Scout-17B-16E-Instruct is an AI model provided by llama.", "family": "llama", "id": "cerebras-llama-4-scout-17b-16e-instruct", "knowledge": "2025-01", "last_updated": "2025-04-05", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Cerebras-Llama-4-Scout-17B-16E-Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-04-05", "temperature": true, "tool_call": true }, "groq-llama-4-maverick-17b-128e-instruct": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Groq-Llama-4-Maverick-17B-128E-Instruct is an AI model provided by llama.", "family": "llama", "id": "groq-llama-4-maverick-17b-128e-instruct", "knowledge": "2025-01", "last_updated": "2025-04-05", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Groq-Llama-4-Maverick-17B-128E-Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-04-05", "temperature": true, "tool_call": true }, "llama-3.3-70b-instruct": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Llama-3.3-70B-Instruct is an AI model provided by llama.", "family": "llama", "id": "llama-3.3-70b-instruct", "knowledge": "2023-12", "last_updated": "2024-12-06", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama-3.3-70B-Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-12-06", "temperature": true, "tool_call": true }, "llama-3.3-8b-instruct": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Llama-3.3-8B-Instruct is an AI model provided by llama.", "family": "llama", "id": "llama-3.3-8b-instruct", "knowledge": "2023-12", "last_updated": "2024-12-06", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama-3.3-8B-Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-12-06", "temperature": true, "tool_call": true }, "llama-4-maverick-17b-128e-instruct-fp8": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Llama-4-Maverick-17B-128E-Instruct-FP8 is an AI model provided by llama.", "family": "llama", "id": "llama-4-maverick-17b-128e-instruct-fp8", "knowledge": "2024-08", "last_updated": "2025-04-05", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Llama-4-Maverick-17B-128E-Instruct-FP8", "open_weights": true, "reasoning": false, "release_date": "2025-04-05", "temperature": true, "tool_call": true }, "llama-4-scout-17b-16e-instruct-fp8": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Llama-4-Scout-17B-16E-Instruct-FP8 is an AI model provided by llama.", "family": "llama", "id": "llama-4-scout-17b-16e-instruct-fp8", "knowledge": "2024-08", "last_updated": "2025-04-05", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Llama-4-Scout-17B-16E-Instruct-FP8", "open_weights": true, "reasoning": false, "release_date": "2025-04-05", "temperature": true, "tool_call": true } }, "name": "Llama", "npm": "@ai-sdk/openai-compatible" }, "llmgateway": { "api": "https://api.llmgateway.io/v1", "doc": "https://llmgateway.io/docs", "env": [ "LLMGATEWAY_API_KEY" ], "iconURL": "https://models.dev/logos/llmgateway.svg", "id": "llmgateway", "models": { "auto": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Auto Route is an AI model provided by llmgateway.", "family": "auto", "id": "auto", "last_updated": "2024-01-01", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Auto Route", "open_weights": false, "reasoning": false, "release_date": "2024-01-01", "structured_output": true, "temperature": true, "tool_call": true }, "claude-3-5-haiku": { "attachment": false, "cost": { "cache_read": 0.08, "input": 0.8, "output": 4 }, "description": "Claude 3.5 Haiku is an AI model provided by llmgateway.", "family": "claude", "id": "claude-3-5-haiku", "last_updated": "2024-10-22", "limit": { "context": 200000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Claude 3.5 Haiku", "open_weights": false, "reasoning": false, "release_date": "2024-10-22", "status": "deprecated", "structured_output": false, "temperature": true, "tool_call": true }, "claude-3-5-sonnet-20241022": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 3.5 v2 is an AI model provided by llmgateway.", "family": "claude-sonnet", "id": "claude-3-5-sonnet-20241022", "knowledge": "2024-04-30", "last_updated": "2024-10-22", "limit": { "context": 200000, "output": 8192 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 3.5 v2", "open_weights": false, "reasoning": false, "release_date": "2024-10-22", "temperature": true, "tool_call": true }, "claude-3-7-sonnet": { "attachment": false, "cost": { "cache_read": 0.3, "input": 3, "output": 15 }, "description": "Claude 3.7 Sonnet is an AI model provided by llmgateway.", "family": "claude", "id": "claude-3-7-sonnet", "last_updated": "2025-02-24", "limit": { "context": 200000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Claude 3.7 Sonnet", "open_weights": false, "reasoning": true, "release_date": "2025-02-24", "structured_output": false, "temperature": true, "tool_call": true }, "claude-3-7-sonnet-20250219": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 3.7 is an AI model provided by llmgateway.", "family": "claude-sonnet", "id": "claude-3-7-sonnet-20250219", "knowledge": "2024-10-31", "last_updated": "2025-02-19", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 3.7", "open_weights": false, "reasoning": true, "release_date": "2025-02-19", "temperature": true, "tool_call": true }, "claude-3-opus": { "attachment": true, "cost": { "cache_read": 1.5, "input": 15, "output": 75 }, "description": "Claude 3 Opus is an AI model provided by llmgateway.", "family": "claude", "id": "claude-3-opus", "last_updated": "2024-03-04", "limit": { "context": 200000, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Claude 3 Opus", "open_weights": false, "reasoning": false, "release_date": "2024-03-04", "structured_output": false, "temperature": true, "tool_call": true }, "claude-haiku-4-5": { "attachment": true, "cost": { "cache_read": 0.1, "cache_write": 1.25, "input": 1, "output": 5 }, "description": "Claude Haiku 4.5 (latest) is an AI model provided by llmgateway.", "family": "claude-haiku", "id": "claude-haiku-4-5", "knowledge": "2025-02-28", "last_updated": "2025-10-15", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Haiku 4.5 (latest)", "open_weights": false, "reasoning": true, "release_date": "2025-10-15", "temperature": true, "tool_call": true }, "claude-haiku-4-5-20251001": { "attachment": true, "cost": { "cache_read": 0.1, "cache_write": 1.25, "input": 1, "output": 5 }, "description": "Claude Haiku 4.5 is an AI model provided by llmgateway.", "family": "claude-haiku", "id": "claude-haiku-4-5-20251001", "knowledge": "2025-02-28", "last_updated": "2025-10-15", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Haiku 4.5", "open_weights": false, "reasoning": true, "release_date": "2025-10-15", "temperature": true, "tool_call": true }, "claude-opus-4-1-20250805": { "attachment": true, "cost": { "cache_read": 1.5, "cache_write": 18.75, "input": 15, "output": 75 }, "description": "Claude Opus 4.1 is an AI model provided by llmgateway.", "family": "claude-opus", "id": "claude-opus-4-1-20250805", "knowledge": "2025-03-31", "last_updated": "2025-08-05", "limit": { "context": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.1", "open_weights": false, "reasoning": true, "release_date": "2025-08-05", "temperature": true, "tool_call": true }, "claude-opus-4-20250514": { "attachment": true, "cost": { "cache_read": 1.5, "cache_write": 18.75, "input": 15, "output": 75 }, "description": "Claude Opus 4 is an AI model provided by llmgateway.", "family": "claude-opus", "id": "claude-opus-4-20250514", "knowledge": "2025-03-31", "last_updated": "2025-05-22", "limit": { "context": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4", "open_weights": false, "reasoning": true, "release_date": "2025-05-22", "temperature": true, "tool_call": true }, "claude-opus-4-5-20251101": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "input": 5, "output": 25 }, "description": "Claude Opus 4.5 is an AI model provided by llmgateway.", "family": "claude-opus", "id": "claude-opus-4-5-20251101", "knowledge": "2025-03-31", "last_updated": "2025-11-01", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.5", "open_weights": false, "reasoning": true, "release_date": "2025-11-01", "temperature": true, "tool_call": true }, "claude-opus-4-6": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "input": 5, "output": 25 }, "description": "Claude Opus 4.6 is an AI model provided by llmgateway.", "family": "claude-opus", "id": "claude-opus-4-6", "knowledge": "2025-05-31", "last_updated": "2026-03-13", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.6", "open_weights": false, "reasoning": true, "release_date": "2026-02-05", "temperature": true, "tool_call": true }, "claude-opus-4-7": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "input": 5, "output": 25 }, "description": "Claude Opus 4.7 is an AI model provided by llmgateway.", "family": "claude-opus", "id": "claude-opus-4-7", "knowledge": "2026-01-31", "last_updated": "2026-04-16", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.7", "open_weights": false, "reasoning": true, "release_date": "2026-04-16", "temperature": false, "tool_call": true }, "claude-sonnet-4-20250514": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 4 is an AI model provided by llmgateway.", "family": "claude-sonnet", "id": "claude-sonnet-4-20250514", "knowledge": "2025-03-31", "last_updated": "2025-05-22", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4", "open_weights": false, "reasoning": true, "release_date": "2025-05-22", "temperature": true, "tool_call": true }, "claude-sonnet-4-5": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 4.5 (latest) is an AI model provided by llmgateway.", "family": "claude-sonnet", "id": "claude-sonnet-4-5", "knowledge": "2025-07-31", "last_updated": "2025-09-29", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.5 (latest)", "open_weights": false, "reasoning": true, "release_date": "2025-09-29", "temperature": true, "tool_call": true }, "claude-sonnet-4-5-20250929": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 4.5 is an AI model provided by llmgateway.", "family": "claude-sonnet", "id": "claude-sonnet-4-5-20250929", "knowledge": "2025-07-31", "last_updated": "2025-09-29", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.5", "open_weights": false, "reasoning": true, "release_date": "2025-09-29", "temperature": true, "tool_call": true }, "claude-sonnet-4-6": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 4.6 is an AI model provided by llmgateway.", "family": "claude-sonnet", "id": "claude-sonnet-4-6", "knowledge": "2025-08-31", "last_updated": "2026-03-13", "limit": { "context": 1000000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.6", "open_weights": false, "reasoning": true, "release_date": "2026-02-17", "temperature": true, "tool_call": true }, "codestral-2508": { "attachment": false, "cost": { "input": 0.3, "output": 0.9 }, "description": "Codestral is an AI model provided by llmgateway.", "family": "mistral", "id": "codestral-2508", "last_updated": "2025-07-30", "limit": { "context": 256000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Codestral", "open_weights": true, "reasoning": false, "release_date": "2025-07-30", "structured_output": true, "temperature": true, "tool_call": false }, "custom": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Custom Model is an AI model provided by llmgateway.", "family": "auto", "id": "custom", "last_updated": "2024-01-01", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Custom Model", "open_weights": false, "reasoning": false, "release_date": "2024-01-01", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek-r1-0528": { "attachment": false, "cost": { "input": 0.8, "output": 2.4 }, "description": "DeepSeek R1 (0528) is an AI model provided by llmgateway.", "family": "deepseek", "id": "deepseek-r1-0528", "last_updated": "2025-05-28", "limit": { "context": 64000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek R1 (0528)", "open_weights": true, "reasoning": true, "release_date": "2025-05-28", "status": "beta", "structured_output": false, "temperature": true, "tool_call": false }, "deepseek-v3.1": { "attachment": true, "cost": { "cache_read": 0.11, "input": 0.56, "output": 1.68 }, "description": "DeepSeek V3.1 is an AI model provided by llmgateway.", "family": "deepseek", "id": "deepseek-v3.1", "last_updated": "2025-08-21", "limit": { "context": 128000, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "DeepSeek V3.1", "open_weights": true, "reasoning": true, "release_date": "2025-08-21", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek-v3.2": { "attachment": true, "cost": { "cache_read": 0.03, "input": 0.28, "output": 0.42 }, "description": "DeepSeek V3.2 is an AI model provided by llmgateway.", "family": "deepseek", "id": "deepseek-v3.2", "last_updated": "2025-09-29", "limit": { "context": 163840, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "DeepSeek V3.2", "open_weights": true, "reasoning": true, "release_date": "2025-09-29", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek-v4-flash": { "attachment": false, "cost": { "cache_read": 0.028, "input": 0.14, "output": 0.28 }, "description": "DeepSeek V4 Flash is an AI model provided by llmgateway.", "family": "deepseek-flash", "id": "deepseek-v4-flash", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-05", "last_updated": "2026-04-24", "limit": { "context": 1000000, "output": 384000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V4 Flash", "open_weights": true, "reasoning": true, "release_date": "2026-04-24", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek-v4-pro": { "attachment": false, "cost": { "cache_read": 0.145, "input": 1.74, "output": 3.48 }, "description": "DeepSeek V4 Pro is an AI model provided by llmgateway.", "family": "deepseek-thinking", "id": "deepseek-v4-pro", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-05", "last_updated": "2026-04-24", "limit": { "context": 1000000, "output": 384000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V4 Pro", "open_weights": true, "reasoning": true, "release_date": "2026-04-24", "structured_output": true, "temperature": true, "tool_call": true }, "devstral-2512": { "attachment": false, "cost": { "input": 0.4, "output": 2 }, "description": "Devstral 2 is an AI model provided by llmgateway.", "family": "devstral", "id": "devstral-2512", "knowledge": "2025-12", "last_updated": "2025-12-09", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Devstral 2", "open_weights": true, "reasoning": false, "release_date": "2025-12-09", "temperature": true, "tool_call": true }, "devstral-small-2507": { "attachment": false, "cost": { "input": 0.1, "output": 0.3 }, "description": "Devstral Small is an AI model provided by llmgateway.", "family": "devstral", "id": "devstral-small-2507", "knowledge": "2025-05", "last_updated": "2025-07-10", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Devstral Small", "open_weights": true, "reasoning": false, "release_date": "2025-07-10", "temperature": true, "tool_call": true }, "gemini-2.0-flash": { "attachment": true, "cost": { "cache_read": 0.025, "input": 0.1, "output": 0.4 }, "description": "Gemini 2.0 Flash is an AI model provided by llmgateway.", "family": "gemini-flash", "id": "gemini-2.0-flash", "knowledge": "2024-06", "last_updated": "2024-12-11", "limit": { "context": 1048576, "output": 8192 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.0 Flash", "open_weights": false, "reasoning": false, "release_date": "2024-12-11", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-2.0-flash-lite": { "attachment": true, "cost": { "input": 0.075, "output": 0.3 }, "description": "Gemini 2.0 Flash Lite is an AI model provided by llmgateway.", "family": "gemini-flash-lite", "id": "gemini-2.0-flash-lite", "knowledge": "2024-06", "last_updated": "2024-12-11", "limit": { "context": 1048576, "output": 8192 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.0 Flash Lite", "open_weights": false, "reasoning": false, "release_date": "2024-12-11", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-2.5-flash": { "attachment": true, "cost": { "cache_read": 0.03, "input": 0.3, "input_audio": 1, "output": 2.5 }, "description": "Gemini 2.5 Flash is an AI model provided by llmgateway.", "family": "gemini-flash", "id": "gemini-2.5-flash", "knowledge": "2025-01", "last_updated": "2025-06-05", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Flash", "open_weights": false, "reasoning": true, "release_date": "2025-03-20", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-2.5-flash-lite": { "attachment": true, "cost": { "cache_read": 0.01, "input": 0.1, "input_audio": 0.3, "output": 0.4 }, "description": "Gemini 2.5 Flash Lite is an AI model provided by llmgateway.", "family": "gemini-flash-lite", "id": "gemini-2.5-flash-lite", "knowledge": "2025-01", "last_updated": "2025-06-17", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Flash Lite", "open_weights": false, "reasoning": true, "release_date": "2025-06-17", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-2.5-flash-lite-preview-09-2025": { "attachment": true, "cost": { "cache_read": 0.025, "input": 0.1, "output": 0.4 }, "description": "Gemini 2.5 Flash Lite Preview 09-25 is an AI model provided by llmgateway.", "family": "gemini-flash-lite", "id": "gemini-2.5-flash-lite-preview-09-2025", "knowledge": "2025-01", "last_updated": "2025-09-25", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Flash Lite Preview 09-25", "open_weights": false, "reasoning": true, "release_date": "2025-09-25", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-2.5-pro": { "attachment": true, "cost": { "cache_read": 0.125, "context_over_200k": { "cache_read": 0.25, "input": 2.5, "output": 15 }, "input": 1.25, "output": 10, "tiers": [ { "cache_read": 0.25, "input": 2.5, "output": 15, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Gemini 2.5 Pro is an AI model provided by llmgateway.", "family": "gemini-pro", "id": "gemini-2.5-pro", "knowledge": "2025-01", "last_updated": "2025-06-05", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Pro", "open_weights": false, "reasoning": true, "release_date": "2025-03-20", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-3-flash-preview": { "attachment": true, "cost": { "cache_read": 0.05, "input": 0.5, "input_audio": 1, "output": 3 }, "description": "Gemini 3 Flash Preview is an AI model provided by llmgateway.", "family": "gemini-flash", "id": "gemini-3-flash-preview", "knowledge": "2025-01", "last_updated": "2025-12-17", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "name": "Gemini 3 Flash Preview", "open_weights": false, "reasoning": true, "release_date": "2025-12-17", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-3.1-flash-lite": { "attachment": true, "cost": { "cache_read": 0.025, "input": 0.25, "input_audio": 0.5, "output": 1.5 }, "description": "Gemini 3.1 Flash Lite is an AI model provided by llmgateway.", "family": "gemini-flash-lite", "id": "gemini-3.1-flash-lite", "knowledge": "2025-01", "last_updated": "2026-05-07", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "name": "Gemini 3.1 Flash Lite", "open_weights": false, "reasoning": true, "release_date": "2026-05-07", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-3.1-flash-lite-preview": { "attachment": true, "cost": { "cache_read": 0.025, "input": 0.25, "input_audio": 0.5, "output": 1.5 }, "description": "Gemini 3.1 Flash Lite Preview is an AI model provided by llmgateway.", "family": "gemini-flash-lite", "id": "gemini-3.1-flash-lite-preview", "knowledge": "2025-01", "last_updated": "2026-03-03", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "name": "Gemini 3.1 Flash Lite Preview", "open_weights": false, "reasoning": true, "release_date": "2026-03-03", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-3.1-pro-preview": { "attachment": true, "cost": { "cache_read": 0.2, "context_over_200k": { "cache_read": 0.4, "input": 4, "output": 18 }, "input": 2, "output": 12, "tiers": [ { "cache_read": 0.4, "input": 4, "output": 18, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Gemini 3.1 Pro Preview is an AI model provided by llmgateway.", "family": "gemini-pro", "id": "gemini-3.1-pro-preview", "knowledge": "2025-01", "last_updated": "2026-02-19", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "name": "Gemini 3.1 Pro Preview", "open_weights": false, "reasoning": true, "release_date": "2026-02-19", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-pro-latest": { "attachment": true, "cost": { "cache_read": 0.2, "input": 2, "output": 12 }, "description": "Gemini Pro Latest is an AI model provided by llmgateway.", "family": "gemini", "id": "gemini-pro-latest", "last_updated": "2026-02-27", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemini Pro Latest", "open_weights": false, "reasoning": true, "release_date": "2026-02-27", "structured_output": true, "temperature": true, "tool_call": true }, "gemma-2-27b-it-together": { "attachment": false, "cost": { "input": 0.08, "output": 0.08 }, "description": "Gemma 2 27B IT is an AI model provided by llmgateway.", "family": "gemma", "id": "gemma-2-27b-it-together", "last_updated": "2024-06-27", "limit": { "context": 8192, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Gemma 2 27B IT", "open_weights": true, "reasoning": false, "release_date": "2024-06-27", "structured_output": false, "temperature": true, "tool_call": false }, "gemma-3-12b-it": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Gemma 3 12B is an AI model provided by llmgateway.", "family": "gemma", "id": "gemma-3-12b-it", "knowledge": "2024-10", "last_updated": "2025-03-13", "limit": { "context": 32768, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemma 3 12B", "open_weights": true, "reasoning": false, "release_date": "2025-03-13", "structured_output": true, "temperature": true, "tool_call": false }, "gemma-3-1b-it": { "attachment": false, "cost": { "input": 0.08, "output": 0.3 }, "description": "Gemma 3 1B IT is an AI model provided by llmgateway.", "family": "gemma", "id": "gemma-3-1b-it", "last_updated": "2025-03-12", "limit": { "context": 1000000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Gemma 3 1B IT", "open_weights": true, "reasoning": false, "release_date": "2025-03-12", "structured_output": false, "temperature": true, "tool_call": false }, "gemma-3-27b": { "attachment": true, "cost": { "input": 0.27, "output": 0.27 }, "description": "Gemma 3 27B is an AI model provided by llmgateway.", "family": "gemma", "id": "gemma-3-27b", "last_updated": "2025-03-12", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemma 3 27B", "open_weights": true, "reasoning": false, "release_date": "2025-03-12", "structured_output": false, "temperature": true, "tool_call": false }, "gemma-3-4b-it": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Gemma 3 4B is an AI model provided by llmgateway.", "family": "gemma", "id": "gemma-3-4b-it", "knowledge": "2024-10", "last_updated": "2025-03-13", "limit": { "context": 32768, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemma 3 4B", "open_weights": true, "reasoning": false, "release_date": "2025-03-13", "temperature": true, "tool_call": false }, "gemma-3n-e2b-it": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Gemma 3n 2B is an AI model provided by llmgateway.", "family": "gemma", "id": "gemma-3n-e2b-it", "knowledge": "2024-10", "last_updated": "2025-07-09", "limit": { "context": 8192, "output": 2000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Gemma 3n 2B", "open_weights": true, "reasoning": false, "release_date": "2025-07-09", "temperature": true, "tool_call": false }, "gemma-3n-e4b-it": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Gemma 3n 4B is an AI model provided by llmgateway.", "family": "gemma", "id": "gemma-3n-e4b-it", "knowledge": "2024-10", "last_updated": "2025-05-20", "limit": { "context": 8192, "output": 2000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Gemma 3n 4B", "open_weights": true, "reasoning": false, "release_date": "2025-05-20", "temperature": true, "tool_call": false }, "glm-4-32b-0414-128k": { "attachment": false, "cost": { "input": 0.1, "output": 0.1 }, "description": "GLM-4 32B (0414-128k) is an AI model provided by llmgateway.", "family": "glm", "id": "glm-4-32b-0414-128k", "last_updated": "2025-04-14", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4 32B (0414-128k)", "open_weights": false, "reasoning": false, "release_date": "2025-04-14", "structured_output": true, "temperature": true, "tool_call": true }, "glm-4.5": { "attachment": false, "cost": { "cache_read": 0.11, "cache_write": 0, "input": 0.6, "output": 2.2 }, "description": "GLM-4.5 is an AI model provided by llmgateway.", "family": "glm", "id": "glm-4.5", "knowledge": "2025-04", "last_updated": "2025-07-28", "limit": { "context": 131072, "output": 98304 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.5", "open_weights": true, "reasoning": true, "release_date": "2025-07-28", "temperature": true, "tool_call": true }, "glm-4.5-air": { "attachment": false, "cost": { "cache_read": 0.03, "cache_write": 0, "input": 0.2, "output": 1.1 }, "description": "GLM-4.5-Air is an AI model provided by llmgateway.", "family": "glm-air", "id": "glm-4.5-air", "knowledge": "2025-04", "last_updated": "2025-07-28", "limit": { "context": 131072, "output": 98304 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.5-Air", "open_weights": true, "reasoning": true, "release_date": "2025-07-28", "temperature": true, "tool_call": true }, "glm-4.5-airx": { "attachment": false, "cost": { "cache_read": 0.22, "input": 1.1, "output": 4.5 }, "description": "GLM-4.5 AirX is an AI model provided by llmgateway.", "family": "glm", "id": "glm-4.5-airx", "last_updated": "2025-07-28", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.5 AirX", "open_weights": false, "reasoning": false, "release_date": "2025-07-28", "structured_output": true, "temperature": true, "tool_call": true }, "glm-4.5-flash": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "GLM-4.5-Flash is an AI model provided by llmgateway.", "family": "glm-flash", "id": "glm-4.5-flash", "knowledge": "2025-04", "last_updated": "2025-07-28", "limit": { "context": 131072, "output": 98304 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.5-Flash", "open_weights": true, "reasoning": true, "release_date": "2025-07-28", "temperature": true, "tool_call": true }, "glm-4.5-x": { "attachment": false, "cost": { "cache_read": 0.45, "input": 2.2, "output": 8.9 }, "description": "GLM-4.5 X is an AI model provided by llmgateway.", "family": "glm", "id": "glm-4.5-x", "last_updated": "2025-07-28", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.5 X", "open_weights": false, "reasoning": true, "release_date": "2025-07-28", "status": "beta", "structured_output": true, "temperature": true, "tool_call": true }, "glm-4.5v": { "attachment": true, "cost": { "input": 0.6, "output": 1.8 }, "description": "GLM-4.5V is an AI model provided by llmgateway.", "family": "glm", "id": "glm-4.5v", "knowledge": "2025-04", "last_updated": "2025-08-11", "limit": { "context": 64000, "output": 16384 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "GLM-4.5V", "open_weights": true, "reasoning": true, "release_date": "2025-08-11", "temperature": true, "tool_call": true }, "glm-4.6": { "attachment": false, "cost": { "cache_read": 0.11, "cache_write": 0, "input": 0.6, "output": 2.2 }, "description": "GLM-4.6 is an AI model provided by llmgateway.", "family": "glm", "id": "glm-4.6", "knowledge": "2025-04", "last_updated": "2025-09-30", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.6", "open_weights": true, "reasoning": true, "release_date": "2025-09-30", "temperature": true, "tool_call": true }, "glm-4.6v": { "attachment": true, "cost": { "input": 0.3, "output": 0.9 }, "description": "GLM-4.6V is an AI model provided by llmgateway.", "family": "glm", "id": "glm-4.6v", "knowledge": "2025-04", "last_updated": "2025-12-08", "limit": { "context": 128000, "output": 32768 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "GLM-4.6V", "open_weights": true, "reasoning": true, "release_date": "2025-12-08", "temperature": true, "tool_call": true }, "glm-4.6v-flash": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "GLM-4.6V Flash is an AI model provided by llmgateway.", "family": "glm", "id": "glm-4.6v-flash", "last_updated": "2025-12-08", "limit": { "context": 128000, "output": 16000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GLM-4.6V Flash", "open_weights": true, "reasoning": true, "release_date": "2025-12-08", "status": "beta", "structured_output": true, "temperature": true, "tool_call": true }, "glm-4.6v-flashx": { "attachment": true, "cost": { "cache_read": 0, "input": 0.04, "output": 0.4 }, "description": "GLM-4.6V FlashX is an AI model provided by llmgateway.", "family": "glm", "id": "glm-4.6v-flashx", "last_updated": "2025-12-08", "limit": { "context": 128000, "output": 16000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GLM-4.6V FlashX", "open_weights": false, "reasoning": true, "release_date": "2025-12-08", "structured_output": true, "temperature": true, "tool_call": true }, "glm-4.7": { "attachment": false, "cost": { "cache_read": 0.11, "cache_write": 0, "input": 0.6, "output": 2.2 }, "description": "GLM-4.7 is an AI model provided by llmgateway.", "family": "glm", "id": "glm-4.7", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-04", "last_updated": "2025-12-22", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.7", "open_weights": true, "reasoning": true, "release_date": "2025-12-22", "temperature": true, "tool_call": true }, "glm-4.7-flash": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "GLM-4.7-Flash is an AI model provided by llmgateway.", "family": "glm-flash", "id": "glm-4.7-flash", "knowledge": "2025-04", "last_updated": "2026-01-19", "limit": { "context": 200000, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.7-Flash", "open_weights": true, "reasoning": true, "release_date": "2026-01-19", "temperature": true, "tool_call": true }, "glm-4.7-flashx": { "attachment": false, "cost": { "cache_read": 0.01, "cache_write": 0, "input": 0.07, "output": 0.4 }, "description": "GLM-4.7-FlashX is an AI model provided by llmgateway.", "family": "glm-flash", "id": "glm-4.7-flashx", "knowledge": "2025-04", "last_updated": "2026-01-19", "limit": { "context": 200000, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.7-FlashX", "open_weights": true, "reasoning": true, "release_date": "2026-01-19", "temperature": true, "tool_call": true }, "glm-5": { "attachment": false, "cost": { "cache_read": 0.2, "cache_write": 0, "input": 1, "output": 3.2 }, "description": "GLM-5 is an AI model provided by llmgateway.", "family": "glm", "id": "glm-5", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-02-11", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5", "open_weights": true, "reasoning": true, "release_date": "2026-02-11", "temperature": true, "tool_call": true }, "glm-5.1": { "attachment": false, "cost": { "cache_read": 1.3, "cache_write": 0, "input": 6, "output": 24 }, "description": "GLM-5.1 is an AI model provided by llmgateway.", "family": "glm", "id": "glm-5.1", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-03-27", "limit": { "context": 200000, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5.1", "open_weights": false, "reasoning": true, "release_date": "2026-03-27", "structured_output": true, "temperature": true, "tool_call": true }, "gpt-3.5-turbo": { "attachment": false, "cost": { "cache_read": 1.25, "input": 0.5, "output": 1.5 }, "description": "GPT-3.5-turbo is an AI model provided by llmgateway.", "family": "gpt", "id": "gpt-3.5-turbo", "knowledge": "2021-09-01", "last_updated": "2023-11-06", "limit": { "context": 16385, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT-3.5-turbo", "open_weights": false, "reasoning": false, "release_date": "2023-03-01", "structured_output": false, "temperature": true, "tool_call": false }, "gpt-4": { "attachment": true, "cost": { "input": 30, "output": 60 }, "description": "GPT-4 is an AI model provided by llmgateway.", "family": "gpt", "id": "gpt-4", "knowledge": "2023-11", "last_updated": "2024-04-09", "limit": { "context": 8192, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT-4", "open_weights": false, "reasoning": false, "release_date": "2023-11-06", "structured_output": false, "temperature": true, "tool_call": true }, "gpt-4-turbo": { "attachment": true, "cost": { "input": 10, "output": 30 }, "description": "GPT-4 Turbo is an AI model provided by llmgateway.", "family": "gpt", "id": "gpt-4-turbo", "knowledge": "2023-12", "last_updated": "2024-04-09", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4 Turbo", "open_weights": false, "reasoning": false, "release_date": "2023-11-06", "structured_output": false, "temperature": true, "tool_call": true }, "gpt-4.1": { "attachment": true, "cost": { "cache_read": 0.5, "input": 2, "output": 8 }, "description": "GPT-4.1 is an AI model provided by llmgateway.", "family": "gpt", "id": "gpt-4.1", "knowledge": "2024-04", "last_updated": "2025-04-14", "limit": { "context": 1047576, "output": 32768 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-4.1", "open_weights": false, "reasoning": false, "release_date": "2025-04-14", "structured_output": true, "temperature": true, "tool_call": true }, "gpt-4.1-mini": { "attachment": true, "cost": { "cache_read": 0.1, "input": 0.4, "output": 1.6 }, "description": "GPT-4.1 mini is an AI model provided by llmgateway.", "family": "gpt-mini", "id": "gpt-4.1-mini", "knowledge": "2024-04", "last_updated": "2025-04-14", "limit": { "context": 1047576, "output": 32768 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-4.1 mini", "open_weights": false, "reasoning": false, "release_date": "2025-04-14", "structured_output": true, "temperature": true, "tool_call": true }, "gpt-4.1-nano": { "attachment": true, "cost": { "cache_read": 0.03, "input": 0.1, "output": 0.4 }, "description": "GPT-4.1 nano is an AI model provided by llmgateway.", "family": "gpt-nano", "id": "gpt-4.1-nano", "knowledge": "2024-04", "last_updated": "2025-04-14", "limit": { "context": 1047576, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4.1 nano", "open_weights": false, "reasoning": false, "release_date": "2025-04-14", "structured_output": true, "temperature": true, "tool_call": true }, "gpt-4o": { "attachment": true, "cost": { "cache_read": 1.25, "input": 2.5, "output": 10 }, "description": "GPT-4o is an AI model provided by llmgateway.", "family": "gpt", "id": "gpt-4o", "knowledge": "2023-09", "last_updated": "2024-08-06", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-4o", "open_weights": false, "reasoning": false, "release_date": "2024-05-13", "structured_output": true, "temperature": true, "tool_call": true }, "gpt-4o-mini": { "attachment": true, "cost": { "cache_read": 0.08, "input": 0.15, "output": 0.6 }, "description": "GPT-4o mini is an AI model provided by llmgateway.", "family": "gpt-mini", "id": "gpt-4o-mini", "knowledge": "2023-09", "last_updated": "2024-07-18", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-4o mini", "open_weights": false, "reasoning": false, "release_date": "2024-07-18", "structured_output": true, "temperature": true, "tool_call": true }, "gpt-4o-mini-search-preview": { "attachment": true, "cost": { "input": 0.15, "output": 0.6 }, "description": "GPT-4o Mini Search Preview is an AI model provided by llmgateway.", "family": "gpt", "id": "gpt-4o-mini-search-preview", "last_updated": "2024-10-01", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4o Mini Search Preview", "open_weights": false, "reasoning": false, "release_date": "2024-10-01", "structured_output": false, "temperature": true, "tool_call": false }, "gpt-4o-search-preview": { "attachment": true, "cost": { "input": 2.5, "output": 10 }, "description": "GPT-4o Search Preview is an AI model provided by llmgateway.", "family": "gpt", "id": "gpt-4o-search-preview", "last_updated": "2024-10-01", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4o Search Preview", "open_weights": false, "reasoning": false, "release_date": "2024-10-01", "structured_output": false, "temperature": true, "tool_call": false }, "gpt-5": { "attachment": true, "cost": { "cache_read": 0.125, "input": 1.25, "output": 10 }, "description": "GPT-5 is an AI model provided by llmgateway.", "family": "gpt", "id": "gpt-5", "knowledge": "2024-09-30", "last_updated": "2025-08-07", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5-chat-latest": { "attachment": true, "cost": { "input": 1.25, "output": 10 }, "description": "GPT-5 Chat (latest) is an AI model provided by llmgateway.", "family": "gpt-codex", "id": "gpt-5-chat-latest", "knowledge": "2024-09-30", "last_updated": "2025-08-07", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5 Chat (latest)", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "structured_output": true, "temperature": true, "tool_call": false }, "gpt-5-mini": { "attachment": true, "cost": { "cache_read": 0.025, "input": 0.25, "output": 2 }, "description": "GPT-5 Mini is an AI model provided by llmgateway.", "family": "gpt-mini", "id": "gpt-5-mini", "knowledge": "2024-05-30", "last_updated": "2025-08-07", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5 Mini", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5-nano": { "attachment": true, "cost": { "cache_read": 0.005, "input": 0.05, "output": 0.4 }, "description": "GPT-5 Nano is an AI model provided by llmgateway.", "family": "gpt-nano", "id": "gpt-5-nano", "knowledge": "2024-05-30", "last_updated": "2025-08-07", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5 Nano", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5-pro": { "attachment": true, "cost": { "input": 15, "output": 120 }, "description": "GPT-5 Pro is an AI model provided by llmgateway.", "family": "gpt-pro", "id": "gpt-5-pro", "knowledge": "2024-09-30", "last_updated": "2025-10-06", "limit": { "context": 400000, "input": 272000, "output": 272000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5 Pro", "open_weights": false, "reasoning": true, "release_date": "2025-10-06", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.1": { "attachment": true, "cost": { "cache_read": 0.13, "input": 1.25, "output": 10 }, "description": "GPT-5.1 is an AI model provided by llmgateway.", "family": "gpt", "id": "gpt-5.1", "knowledge": "2024-09-30", "last_updated": "2025-11-13", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.1", "open_weights": false, "reasoning": true, "release_date": "2025-11-13", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.1-codex": { "attachment": true, "cost": { "cache_read": 0.125, "input": 1.25, "output": 10 }, "description": "GPT-5.1 Codex is an AI model provided by llmgateway.", "family": "gpt-codex", "id": "gpt-5.1-codex", "knowledge": "2024-09-30", "last_updated": "2025-11-13", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.1 Codex", "open_weights": false, "reasoning": true, "release_date": "2025-11-13", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.1-codex-mini": { "attachment": true, "cost": { "cache_read": 0.025, "input": 0.25, "output": 2 }, "description": "GPT-5.1 Codex mini is an AI model provided by llmgateway.", "family": "gpt-codex", "id": "gpt-5.1-codex-mini", "knowledge": "2024-09-30", "last_updated": "2025-11-13", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.1 Codex mini", "open_weights": false, "reasoning": true, "release_date": "2025-11-13", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.2": { "attachment": true, "cost": { "cache_read": 0.175, "input": 1.75, "output": 14 }, "description": "GPT-5.2 is an AI model provided by llmgateway.", "family": "gpt", "id": "gpt-5.2", "knowledge": "2025-08-31", "last_updated": "2025-12-11", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.2", "open_weights": false, "reasoning": true, "release_date": "2025-12-11", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.2-chat-latest": { "attachment": true, "cost": { "cache_read": 0.175, "input": 1.75, "output": 14 }, "description": "GPT-5.2 Chat is an AI model provided by llmgateway.", "family": "gpt-codex", "id": "gpt-5.2-chat-latest", "knowledge": "2025-08-31", "last_updated": "2025-12-11", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.2 Chat", "open_weights": false, "reasoning": true, "release_date": "2025-12-11", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.2-codex": { "attachment": true, "cost": { "cache_read": 0.175, "input": 1.75, "output": 14 }, "description": "GPT-5.2 Codex is an AI model provided by llmgateway.", "family": "gpt-codex", "id": "gpt-5.2-codex", "knowledge": "2025-08-31", "last_updated": "2025-12-11", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.2 Codex", "open_weights": false, "reasoning": true, "release_date": "2025-12-11", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.2-pro": { "attachment": true, "cost": { "input": 21, "output": 168 }, "description": "GPT-5.2 Pro is an AI model provided by llmgateway.", "family": "gpt-pro", "id": "gpt-5.2-pro", "knowledge": "2025-08-31", "last_updated": "2025-12-11", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.2 Pro", "open_weights": false, "reasoning": true, "release_date": "2025-12-11", "structured_output": false, "temperature": false, "tool_call": true }, "gpt-5.3-chat-latest": { "attachment": true, "cost": { "cache_read": 0.175, "input": 1.75, "output": 14 }, "description": "GPT-5.3 Chat (latest) is an AI model provided by llmgateway.", "family": "gpt", "id": "gpt-5.3-chat-latest", "knowledge": "2025-08-31", "last_updated": "2026-03-03", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.3 Chat (latest)", "open_weights": false, "reasoning": false, "release_date": "2026-03-03", "structured_output": true, "temperature": true, "tool_call": true }, "gpt-5.3-codex": { "attachment": true, "cost": { "cache_read": 0.175, "input": 1.75, "output": 14 }, "description": "GPT-5.3 Codex is an AI model provided by llmgateway.", "family": "gpt-codex", "id": "gpt-5.3-codex", "knowledge": "2025-08-31", "last_updated": "2026-02-05", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.3 Codex", "open_weights": false, "reasoning": true, "release_date": "2026-02-05", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.4": { "attachment": true, "cost": { "cache_read": 0.25, "input": 2.5, "output": 15 }, "description": "GPT-5.4 is an AI model provided by llmgateway.", "family": "gpt", "id": "gpt-5.4", "knowledge": "2025-08-31", "last_updated": "2026-03-05", "limit": { "context": 1050000, "input": 922000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.4", "open_weights": false, "reasoning": true, "release_date": "2026-03-05", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.4-mini": { "attachment": true, "cost": { "cache_read": 0.075, "input": 0.75, "output": 4.5 }, "description": "GPT-5.4 mini is an AI model provided by llmgateway.", "family": "gpt-mini", "id": "gpt-5.4-mini", "knowledge": "2025-08-31", "last_updated": "2026-03-17", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.4 mini", "open_weights": false, "reasoning": true, "release_date": "2026-03-17", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.4-nano": { "attachment": true, "cost": { "cache_read": 0.02, "input": 0.2, "output": 1.25 }, "description": "GPT-5.4 nano is an AI model provided by llmgateway.", "family": "gpt-nano", "id": "gpt-5.4-nano", "knowledge": "2025-08-31", "last_updated": "2026-03-17", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.4 nano", "open_weights": false, "reasoning": true, "release_date": "2026-03-17", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.4-pro": { "attachment": true, "cost": { "input": 30, "output": 180 }, "description": "GPT-5.4 Pro is an AI model provided by llmgateway.", "family": "gpt-pro", "id": "gpt-5.4-pro", "knowledge": "2025-08-31", "last_updated": "2026-03-05", "limit": { "context": 1050000, "input": 922000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.4 Pro", "open_weights": false, "reasoning": true, "release_date": "2026-03-05", "structured_output": false, "temperature": false, "tool_call": true }, "gpt-5.5": { "attachment": true, "cost": { "cache_read": 0.5, "context_over_200k": { "cache_read": 1, "input": 10, "output": 45 }, "input": 5, "output": 30, "tiers": [ { "cache_read": 1, "input": 10, "output": 45, "tier": { "size": 272000, "type": "context" } } ] }, "description": "GPT-5.5 is an AI model provided by llmgateway.", "experimental": { "modes": { "fast": { "cost": { "cache_read": 1.25, "input": 12.5, "output": 75 }, "provider": { "body": { "service_tier": "priority" } } } } }, "family": "gpt", "id": "gpt-5.5", "knowledge": "2025-12-01", "last_updated": "2026-04-23", "limit": { "context": 1050000, "input": 922000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.5", "open_weights": false, "reasoning": true, "release_date": "2026-04-23", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.5-pro": { "attachment": true, "cost": { "context_over_200k": { "input": 60, "output": 270 }, "input": 30, "output": 180, "tiers": [ { "input": 60, "output": 270, "tier": { "size": 272000, "type": "context" } } ] }, "description": "GPT-5.5 Pro is an AI model provided by llmgateway.", "family": "gpt-pro", "id": "gpt-5.5-pro", "knowledge": "2025-12-01", "last_updated": "2026-04-23", "limit": { "context": 1050000, "input": 922000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.5 Pro", "open_weights": false, "reasoning": true, "release_date": "2026-04-23", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-oss-120b": { "attachment": false, "cost": { "input": 0.15, "output": 0.75 }, "description": "GPT OSS 120B is an AI model provided by llmgateway.", "family": "gpt-oss", "id": "gpt-oss-120b", "last_updated": "2025-08-05", "limit": { "context": 131072, "output": 32766 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT OSS 120B", "open_weights": false, "reasoning": true, "release_date": "2025-08-05", "structured_output": true, "temperature": true, "tool_call": true }, "gpt-oss-20b": { "attachment": false, "cost": { "input": 0.1, "output": 0.5 }, "description": "GPT OSS 20B is an AI model provided by llmgateway.", "family": "gpt-oss", "id": "gpt-oss-20b", "last_updated": "2025-08-05", "limit": { "context": 131072, "output": 32766 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT OSS 20B", "open_weights": false, "reasoning": true, "release_date": "2025-08-05", "structured_output": true, "temperature": true, "tool_call": true }, "grok-3": { "attachment": false, "cost": { "cache_read": 0.75, "input": 3, "output": 15 }, "description": "Grok 3 is an AI model provided by llmgateway.", "family": "grok", "id": "grok-3", "knowledge": "2024-11", "last_updated": "2025-02-17", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok 3", "open_weights": false, "reasoning": false, "release_date": "2025-02-17", "temperature": true, "tool_call": true }, "grok-4": { "attachment": false, "cost": { "cache_read": 0.75, "input": 3, "output": 15, "reasoning": 15 }, "description": "Grok 4 is an AI model provided by llmgateway.", "family": "grok", "id": "grok-4", "knowledge": "2025-07", "last_updated": "2025-07-09", "limit": { "context": 256000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok 4", "open_weights": false, "reasoning": true, "release_date": "2025-07-09", "temperature": true, "tool_call": true }, "grok-4-0709": { "attachment": false, "cost": { "input": 3, "output": 15 }, "description": "Grok 4 (0709) is an AI model provided by llmgateway.", "family": "grok", "id": "grok-4-0709", "last_updated": "2025-07-09", "limit": { "context": 256000, "output": 256000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok 4 (0709)", "open_weights": false, "reasoning": false, "release_date": "2025-07-09", "structured_output": true, "temperature": true, "tool_call": true }, "grok-4-1-fast": { "attachment": true, "cost": { "cache_read": 0.05, "input": 0.2, "output": 0.5 }, "description": "Grok 4.1 Fast is an AI model provided by llmgateway.", "family": "grok", "id": "grok-4-1-fast", "knowledge": "2025-07", "last_updated": "2025-11-19", "limit": { "context": 2000000, "output": 30000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 4.1 Fast", "open_weights": false, "reasoning": true, "release_date": "2025-11-19", "temperature": true, "tool_call": true }, "grok-4-1-fast-non-reasoning": { "attachment": true, "cost": { "cache_read": 0.05, "input": 0.2, "output": 0.5 }, "description": "Grok 4.1 Fast (Non-Reasoning) is an AI model provided by llmgateway.", "family": "grok", "id": "grok-4-1-fast-non-reasoning", "knowledge": "2025-07", "last_updated": "2025-11-19", "limit": { "context": 2000000, "output": 30000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 4.1 Fast (Non-Reasoning)", "open_weights": false, "reasoning": false, "release_date": "2025-11-19", "temperature": true, "tool_call": true }, "grok-4-1-fast-reasoning": { "attachment": true, "cost": { "cache_read": 0.05, "input": 0.2, "output": 0.5 }, "description": "Grok 4.1 Fast Reasoning is an AI model provided by llmgateway.", "family": "grok", "id": "grok-4-1-fast-reasoning", "last_updated": "2025-11-19", "limit": { "context": 2000000, "output": 30000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 4.1 Fast Reasoning", "open_weights": false, "reasoning": true, "release_date": "2025-11-19", "structured_output": true, "temperature": true, "tool_call": true }, "grok-4-20-beta-0309-non-reasoning": { "attachment": true, "cost": { "cache_read": 0.2, "context_over_200k": { "cache_read": 0.4, "input": 4, "output": 12 }, "input": 2, "output": 6, "tiers": [ { "cache_read": 0.4, "input": 4, "output": 12, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Grok 4.20 (Non-Reasoning) is an AI model provided by llmgateway.", "family": "grok", "id": "grok-4-20-beta-0309-non-reasoning", "last_updated": "2026-03-09", "limit": { "context": 2000000, "output": 30000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 4.20 (Non-Reasoning)", "open_weights": false, "reasoning": false, "release_date": "2026-03-09", "temperature": true, "tool_call": true }, "grok-4-20-beta-0309-reasoning": { "attachment": true, "cost": { "cache_read": 0.2, "context_over_200k": { "cache_read": 0.4, "input": 4, "output": 12 }, "input": 2, "output": 6, "tiers": [ { "cache_read": 0.4, "input": 4, "output": 12, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Grok 4.20 (Reasoning) is an AI model provided by llmgateway.", "family": "grok", "id": "grok-4-20-beta-0309-reasoning", "last_updated": "2026-03-09", "limit": { "context": 2000000, "output": 30000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 4.20 (Reasoning)", "open_weights": false, "reasoning": true, "release_date": "2026-03-09", "temperature": true, "tool_call": true }, "grok-4-3": { "attachment": true, "cost": { "cache_read": 0.2, "context_over_200k": { "cache_read": 0.4, "input": 2.5, "output": 5 }, "input": 1.25, "output": 2.5, "tiers": [ { "cache_read": 0.4, "input": 2.5, "output": 5, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Grok 4.3 is an AI model provided by llmgateway.", "family": "grok", "id": "grok-4-3", "last_updated": "2026-05-01", "limit": { "context": 1000000, "output": 30000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 4.3", "open_weights": false, "reasoning": true, "release_date": "2026-05-01", "temperature": true, "tool_call": true }, "grok-4-fast": { "attachment": true, "cost": { "cache_read": 0.05, "input": 0.2, "output": 0.5 }, "description": "Grok 4 Fast is an AI model provided by llmgateway.", "family": "grok", "id": "grok-4-fast", "knowledge": "2025-07", "last_updated": "2025-09-19", "limit": { "context": 2000000, "output": 30000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 4 Fast", "open_weights": false, "reasoning": true, "release_date": "2025-09-19", "temperature": true, "tool_call": true }, "grok-4-fast-non-reasoning": { "attachment": true, "cost": { "cache_read": 0.05, "input": 0.2, "output": 0.5 }, "description": "Grok 4 Fast (Non-Reasoning) is an AI model provided by llmgateway.", "family": "grok", "id": "grok-4-fast-non-reasoning", "knowledge": "2025-07", "last_updated": "2025-09-19", "limit": { "context": 2000000, "output": 30000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 4 Fast (Non-Reasoning)", "open_weights": false, "reasoning": false, "release_date": "2025-09-19", "temperature": true, "tool_call": true }, "grok-4-fast-reasoning": { "attachment": true, "cost": { "cache_read": 0.05, "input": 0.2, "output": 0.5 }, "description": "Grok 4 Fast Reasoning is an AI model provided by llmgateway.", "family": "grok", "id": "grok-4-fast-reasoning", "last_updated": "2025-07-09", "limit": { "context": 2000000, "output": 30000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 4 Fast Reasoning", "open_weights": false, "reasoning": true, "release_date": "2025-07-09", "structured_output": true, "temperature": true, "tool_call": true }, "grok-code-fast-1": { "attachment": false, "cost": { "cache_read": 0.02, "input": 0.2, "output": 1.5 }, "description": "Grok Code Fast 1 is an AI model provided by llmgateway.", "family": "grok", "id": "grok-code-fast-1", "knowledge": "2023-10", "last_updated": "2025-08-28", "limit": { "context": 256000, "output": 10000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok Code Fast 1", "open_weights": false, "reasoning": true, "release_date": "2025-08-28", "temperature": true, "tool_call": true }, "hermes-2-pro-llama-3-8b": { "attachment": false, "cost": { "input": 0.14, "output": 0.14 }, "description": "Hermes 2 Pro Llama 3 8B is an AI model provided by llmgateway.", "family": "hermes", "id": "hermes-2-pro-llama-3-8b", "last_updated": "2024-05-27", "limit": { "context": 8192, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Hermes 2 Pro Llama 3 8B", "open_weights": true, "reasoning": false, "release_date": "2024-05-27", "structured_output": false, "temperature": true, "tool_call": false }, "kimi-k2": { "attachment": false, "cost": { "cache_read": 0.5, "input": 1, "output": 3 }, "description": "Kimi K2 is an AI model provided by llmgateway.", "family": "kimi", "id": "kimi-k2", "last_updated": "2025-07-11", "limit": { "context": 131072, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2", "open_weights": true, "reasoning": false, "release_date": "2025-07-11", "structured_output": true, "temperature": true, "tool_call": true }, "kimi-k2-thinking": { "attachment": false, "cost": { "cache_read": 0.15, "input": 0.6, "output": 2.5 }, "description": "Kimi K2 Thinking is an AI model provided by llmgateway.", "family": "kimi-thinking", "id": "kimi-k2-thinking", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-08", "last_updated": "2025-11-06", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 Thinking", "open_weights": true, "reasoning": true, "release_date": "2025-11-06", "temperature": true, "tool_call": true }, "kimi-k2-thinking-turbo": { "attachment": false, "cost": { "cache_read": 0.15, "input": 1.15, "output": 8 }, "description": "Kimi K2 Thinking Turbo is an AI model provided by llmgateway.", "family": "kimi-thinking", "id": "kimi-k2-thinking-turbo", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-08", "last_updated": "2025-11-06", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 Thinking Turbo", "open_weights": true, "reasoning": true, "release_date": "2025-11-06", "temperature": true, "tool_call": true }, "kimi-k2.5": { "attachment": false, "cost": { "cache_read": 0.1, "input": 0.6, "output": 3 }, "description": "Kimi K2.5 is an AI model provided by llmgateway.", "family": "kimi-k2.5", "id": "kimi-k2.5", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-01", "last_updated": "2026-01", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Kimi K2.5", "open_weights": true, "reasoning": true, "release_date": "2026-01", "structured_output": true, "temperature": false, "tool_call": true }, "kimi-k2.6": { "attachment": true, "cost": { "cache_read": 0.16, "input": 0.95, "output": 4 }, "description": "Kimi K2.6 is an AI model provided by llmgateway.", "family": "kimi-k2.6", "id": "kimi-k2.6", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-01", "last_updated": "2026-04-21", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Kimi K2.6", "open_weights": true, "reasoning": true, "release_date": "2026-04-21", "structured_output": true, "temperature": true, "tool_call": true }, "llama-3-70b-instruct": { "attachment": false, "cost": { "input": 0.51, "output": 0.74 }, "description": "Llama 3 70B Instruct is an AI model provided by llmgateway.", "family": "llama", "id": "llama-3-70b-instruct", "last_updated": "2024-04-18", "limit": { "context": 8192, "output": 8000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3 70B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-04-18", "structured_output": true, "temperature": true, "tool_call": false }, "llama-3-8b-instruct": { "attachment": false, "cost": { "input": 0.04, "output": 0.04 }, "description": "Llama 3 8B Instruct is an AI model provided by llmgateway.", "family": "llama", "id": "llama-3-8b-instruct", "last_updated": "2025-04-03", "limit": { "context": 8192, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3 8B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-04-03", "structured_output": true, "temperature": true, "tool_call": false }, "llama-3.1-70b-instruct": { "attachment": false, "cost": { "input": 0.72, "output": 0.72 }, "description": "Llama 3.1 70B Instruct is an AI model provided by llmgateway.", "family": "llama", "id": "llama-3.1-70b-instruct", "last_updated": "2024-07-23", "limit": { "context": 128000, "output": 2048 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.1 70B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-07-23", "status": "beta", "structured_output": false, "temperature": true, "tool_call": false }, "llama-3.1-8b-instruct": { "attachment": false, "cost": { "input": 0.22, "output": 0.22 }, "description": "Llama 3.1 8B Instruct is an AI model provided by llmgateway.", "family": "llama", "id": "llama-3.1-8b-instruct", "last_updated": "2024-07-23", "limit": { "context": 128000, "output": 2048 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.1 8B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-07-23", "status": "beta", "structured_output": true, "temperature": true, "tool_call": true }, "llama-3.1-nemotron-ultra-253b": { "attachment": false, "cost": { "input": 0.6, "output": 1.8 }, "description": "Llama 3.1 Nemotron Ultra 253B is an AI model provided by llmgateway.", "family": "llama", "id": "llama-3.1-nemotron-ultra-253b", "last_updated": "2025-04-07", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.1 Nemotron Ultra 253B", "open_weights": true, "reasoning": false, "release_date": "2025-04-07", "structured_output": true, "temperature": true, "tool_call": false }, "llama-3.2-11b-instruct": { "attachment": false, "cost": { "input": 0.07, "output": 0.33 }, "description": "Llama 3.2 11B Instruct is an AI model provided by llmgateway.", "family": "llama", "id": "llama-3.2-11b-instruct", "last_updated": "2024-09-25", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.2 11B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-09-25", "structured_output": true, "temperature": true, "tool_call": false }, "llama-3.2-3b-instruct": { "attachment": false, "cost": { "input": 0.03, "output": 0.05 }, "description": "Llama 3.2 3B Instruct is an AI model provided by llmgateway.", "family": "llama", "id": "llama-3.2-3b-instruct", "last_updated": "2024-09-18", "limit": { "context": 32768, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.2 3B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-09-18", "structured_output": true, "temperature": true, "tool_call": false }, "llama-3.3-70b-instruct": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Llama-3.3-70B-Instruct is an AI model provided by llmgateway.", "family": "llama", "id": "llama-3.3-70b-instruct", "knowledge": "2023-12", "last_updated": "2024-12-06", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama-3.3-70B-Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-12-06", "temperature": true, "tool_call": true }, "llama-4-maverick-17b-instruct": { "attachment": true, "cost": { "input": 0.24, "output": 0.97 }, "description": "Llama 4 Maverick 17B Instruct is an AI model provided by llmgateway.", "family": "llama", "id": "llama-4-maverick-17b-instruct", "last_updated": "2025-04-05", "limit": { "context": 8192, "output": 2048 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Llama 4 Maverick 17B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-04-05", "structured_output": false, "temperature": true, "tool_call": false }, "llama-4-scout": { "attachment": false, "cost": { "input": 0.18, "output": 0.59 }, "description": "Llama 4 Scout is an AI model provided by llmgateway.", "family": "llama", "id": "llama-4-scout", "last_updated": "2025-04-05", "limit": { "context": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 4 Scout", "open_weights": true, "reasoning": false, "release_date": "2025-04-05", "status": "beta", "structured_output": false, "temperature": true, "tool_call": true }, "llama-4-scout-17b-instruct": { "attachment": true, "cost": { "input": 0.17, "output": 0.66 }, "description": "Llama 4 Scout 17B Instruct is an AI model provided by llmgateway.", "family": "llama", "id": "llama-4-scout-17b-instruct", "last_updated": "2025-04-05", "limit": { "context": 8192, "output": 2048 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Llama 4 Scout 17B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-04-05", "structured_output": false, "temperature": true, "tool_call": false }, "mimo-v2-flash": { "attachment": false, "cost": { "cache_read": 0.01, "input": 0.1, "output": 0.3 }, "description": "MiMo-V2-Flash is an AI model provided by llmgateway.", "family": "mimo", "id": "mimo-v2-flash", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-12-01", "last_updated": "2026-02-04", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiMo-V2-Flash", "open_weights": true, "reasoning": true, "release_date": "2025-12-16", "temperature": true, "tool_call": true }, "mimo-v2-omni": { "attachment": true, "cost": { "cache_read": 0.08, "input": 0.4, "output": 2 }, "description": "MiMo-V2-Omni is an AI model provided by llmgateway.", "family": "mimo", "id": "mimo-v2-omni", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-12", "last_updated": "2026-03-18", "limit": { "context": 262144, "output": 131072 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "MiMo-V2-Omni", "open_weights": false, "reasoning": true, "release_date": "2026-03-18", "temperature": true, "tool_call": true }, "mimo-v2-pro": { "attachment": false, "cost": { "cache_read": 0.2, "context_over_200k": { "cache_read": 0.4, "input": 2, "output": 6 }, "input": 1, "output": 3, "tiers": [ { "cache_read": 0.4, "input": 2, "output": 6, "tier": { "size": 256000, "type": "context" } } ] }, "description": "MiMo-V2-Pro is an AI model provided by llmgateway.", "family": "mimo", "id": "mimo-v2-pro", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-12", "last_updated": "2026-03-18", "limit": { "context": 1048576, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiMo-V2-Pro", "open_weights": false, "reasoning": true, "release_date": "2026-03-18", "temperature": true, "tool_call": true }, "mimo-v2.5": { "attachment": true, "cost": { "cache_read": 0.08, "context_over_200k": { "cache_read": 0.16, "input": 0.8, "output": 4 }, "input": 0.4, "output": 2, "tiers": [ { "cache_read": 0.16, "input": 0.8, "output": 4, "tier": { "size": 256000, "type": "context" } } ] }, "description": "MiMo-V2.5 is an AI model provided by llmgateway.", "family": "mimo", "id": "mimo-v2.5", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-12", "last_updated": "2026-04-22", "limit": { "context": 1048576, "output": 131072 }, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "name": "MiMo-V2.5", "open_weights": true, "reasoning": true, "release_date": "2026-04-22", "temperature": true, "tool_call": true }, "mimo-v2.5-pro": { "attachment": false, "cost": { "cache_read": 0.2, "context_over_200k": { "cache_read": 0.4, "input": 2, "output": 6 }, "input": 1, "output": 3, "tiers": [ { "cache_read": 0.4, "input": 2, "output": 6, "tier": { "size": 256000, "type": "context" } } ] }, "description": "MiMo-V2.5-Pro is an AI model provided by llmgateway.", "family": "mimo", "id": "mimo-v2.5-pro", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-12", "last_updated": "2026-04-22", "limit": { "context": 1048576, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiMo-V2.5-Pro", "open_weights": true, "reasoning": true, "release_date": "2026-04-22", "temperature": true, "tool_call": true }, "minimax-m2": { "attachment": false, "cost": { "input": 0.3, "output": 1.2 }, "description": "MiniMax-M2 is an AI model provided by llmgateway.", "family": "minimax", "id": "minimax-m2", "last_updated": "2025-10-27", "limit": { "context": 196608, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2", "open_weights": true, "reasoning": true, "release_date": "2025-10-27", "temperature": true, "tool_call": true }, "minimax-m2.1": { "attachment": false, "cost": { "input": 0.3, "output": 1.2 }, "description": "MiniMax-M2.1 is an AI model provided by llmgateway.", "family": "minimax", "id": "minimax-m2.1", "last_updated": "2025-12-23", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.1", "open_weights": true, "reasoning": true, "release_date": "2025-12-23", "temperature": true, "tool_call": true }, "minimax-m2.1-lightning": { "attachment": false, "cost": { "input": 0.12, "output": 0.48 }, "description": "MiniMax M2.1 Lightning is an AI model provided by llmgateway.", "family": "minimax", "id": "minimax-m2.1-lightning", "last_updated": "2025-12-23", "limit": { "context": 196608, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M2.1 Lightning", "open_weights": true, "reasoning": true, "release_date": "2025-12-23", "structured_output": false, "temperature": true, "tool_call": false }, "minimax-m2.5": { "attachment": false, "cost": { "cache_read": 0.03, "cache_write": 0.375, "input": 0.3, "output": 1.2 }, "description": "MiniMax-M2.5 is an AI model provided by llmgateway.", "family": "minimax", "id": "minimax-m2.5", "last_updated": "2026-02-12", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.5", "open_weights": true, "reasoning": true, "release_date": "2026-02-12", "temperature": true, "tool_call": true }, "minimax-m2.5-highspeed": { "attachment": false, "cost": { "cache_read": 0.06, "cache_write": 0.375, "input": 0.6, "output": 2.4 }, "description": "MiniMax-M2.5-highspeed is an AI model provided by llmgateway.", "family": "minimax", "id": "minimax-m2.5-highspeed", "last_updated": "2026-02-13", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.5-highspeed", "open_weights": true, "reasoning": true, "release_date": "2026-02-13", "temperature": true, "tool_call": true }, "minimax-m2.7": { "attachment": false, "cost": { "cache_read": 0.06, "cache_write": 0.375, "input": 0.3, "output": 1.2 }, "description": "MiniMax-M2.7 is an AI model provided by llmgateway.", "family": "minimax", "id": "minimax-m2.7", "last_updated": "2026-03-18", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.7", "open_weights": true, "reasoning": true, "release_date": "2026-03-18", "temperature": true, "tool_call": true }, "minimax-m2.7-highspeed": { "attachment": false, "cost": { "cache_read": 0.06, "cache_write": 0.375, "input": 0.6, "output": 2.4 }, "description": "MiniMax-M2.7-highspeed is an AI model provided by llmgateway.", "family": "minimax", "id": "minimax-m2.7-highspeed", "last_updated": "2026-03-18", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.7-highspeed", "open_weights": true, "reasoning": true, "release_date": "2026-03-18", "temperature": true, "tool_call": true }, "minimax-text-01": { "attachment": false, "cost": { "input": 0.2, "output": 1.1 }, "description": "MiniMax Text 01 is an AI model provided by llmgateway.", "family": "minimax", "id": "minimax-text-01", "last_updated": "2025-01-15", "limit": { "context": 1000000, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax Text 01", "open_weights": true, "reasoning": true, "release_date": "2025-01-15", "structured_output": false, "temperature": true, "tool_call": false }, "ministral-14b-2512": { "attachment": true, "cost": { "input": 0.2, "output": 0.2 }, "description": "Ministral 14B is an AI model provided by llmgateway.", "family": "mistral", "id": "ministral-14b-2512", "last_updated": "2025-12-02", "limit": { "context": 262144, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Ministral 14B", "open_weights": true, "reasoning": false, "release_date": "2025-12-02", "structured_output": true, "temperature": true, "tool_call": false }, "ministral-3b-2512": { "attachment": true, "cost": { "input": 0.1, "output": 0.1 }, "description": "Ministral 3B is an AI model provided by llmgateway.", "family": "mistral", "id": "ministral-3b-2512", "last_updated": "2025-12-02", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Ministral 3B", "open_weights": true, "reasoning": false, "release_date": "2025-12-02", "structured_output": true, "temperature": true, "tool_call": false }, "ministral-8b-2512": { "attachment": true, "cost": { "input": 0.15, "output": 0.15 }, "description": "Ministral 8B is an AI model provided by llmgateway.", "family": "mistral", "id": "ministral-8b-2512", "last_updated": "2025-12-02", "limit": { "context": 262144, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Ministral 8B", "open_weights": true, "reasoning": false, "release_date": "2025-12-02", "structured_output": true, "temperature": true, "tool_call": false }, "mistral-large-2512": { "attachment": true, "cost": { "input": 0.5, "output": 1.5 }, "description": "Mistral Large 3 is an AI model provided by llmgateway.", "family": "mistral-large", "id": "mistral-large-2512", "knowledge": "2024-11", "last_updated": "2025-12-02", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Mistral Large 3", "open_weights": true, "reasoning": false, "release_date": "2024-11-01", "temperature": true, "tool_call": true }, "mistral-large-latest": { "attachment": true, "cost": { "input": 0.5, "output": 1.5 }, "description": "Mistral Large (latest) is an AI model provided by llmgateway.", "family": "mistral-large", "id": "mistral-large-latest", "knowledge": "2024-11", "last_updated": "2025-12-02", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Mistral Large (latest)", "open_weights": true, "reasoning": false, "release_date": "2024-11-01", "temperature": true, "tool_call": true }, "mistral-small-2506": { "attachment": false, "cost": { "input": 0.1, "output": 0.3 }, "description": "Mistral Small 3.2 is an AI model provided by llmgateway.", "family": "mistral-small", "id": "mistral-small-2506", "knowledge": "2025-03", "last_updated": "2025-06-20", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Mistral Small 3.2", "open_weights": true, "reasoning": false, "release_date": "2025-06-20", "temperature": true, "tool_call": true }, "o1": { "attachment": true, "cost": { "cache_read": 7.5, "input": 15, "output": 60 }, "description": "o1 is an AI model provided by llmgateway.", "family": "o", "id": "o1", "knowledge": "2023-09", "last_updated": "2024-12-05", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "o1", "open_weights": false, "reasoning": true, "release_date": "2024-12-05", "structured_output": true, "temperature": false, "tool_call": true }, "o3": { "attachment": true, "cost": { "cache_read": 0.5, "input": 2, "output": 8 }, "description": "o3 is an AI model provided by llmgateway.", "family": "o", "id": "o3", "knowledge": "2024-05", "last_updated": "2025-04-16", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "o3", "open_weights": false, "reasoning": true, "release_date": "2025-04-16", "structured_output": true, "temperature": false, "tool_call": true }, "o3-mini": { "attachment": false, "cost": { "cache_read": 0.55, "input": 1.1, "output": 4.4 }, "description": "o3-mini is an AI model provided by llmgateway.", "family": "o-mini", "id": "o3-mini", "knowledge": "2024-05", "last_updated": "2025-01-29", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "o3-mini", "open_weights": false, "reasoning": true, "release_date": "2024-12-20", "structured_output": true, "temperature": false, "tool_call": true }, "o4-mini": { "attachment": true, "cost": { "cache_read": 0.28, "input": 1.1, "output": 4.4 }, "description": "o4-mini is an AI model provided by llmgateway.", "family": "o-mini", "id": "o4-mini", "knowledge": "2024-05", "last_updated": "2025-04-16", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "o4-mini", "open_weights": false, "reasoning": true, "release_date": "2025-04-16", "structured_output": true, "temperature": false, "tool_call": true }, "pixtral-large-latest": { "attachment": true, "cost": { "input": 2, "output": 6 }, "description": "Pixtral Large (latest) is an AI model provided by llmgateway.", "family": "pixtral", "id": "pixtral-large-latest", "knowledge": "2024-11", "last_updated": "2024-11-04", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Pixtral Large (latest)", "open_weights": true, "reasoning": false, "release_date": "2024-11-01", "temperature": true, "tool_call": true }, "qwen-coder-plus": { "attachment": false, "cost": { "input": 0.5, "output": 1 }, "description": "Qwen Coder Plus is an AI model provided by llmgateway.", "family": "qwen", "id": "qwen-coder-plus", "last_updated": "2024-09-18", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen Coder Plus", "open_weights": false, "reasoning": false, "release_date": "2024-09-18", "structured_output": true, "temperature": true, "tool_call": true }, "qwen-flash": { "attachment": false, "cost": { "input": 0.05, "output": 0.4 }, "description": "Qwen Flash is an AI model provided by llmgateway.", "family": "qwen", "id": "qwen-flash", "knowledge": "2024-04", "last_updated": "2025-07-28", "limit": { "context": 1000000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen Flash", "open_weights": false, "reasoning": true, "release_date": "2025-07-28", "temperature": true, "tool_call": true }, "qwen-max": { "attachment": false, "cost": { "input": 1.6, "output": 6.4 }, "description": "Qwen Max is an AI model provided by llmgateway.", "family": "qwen", "id": "qwen-max", "knowledge": "2024-04", "last_updated": "2025-01-25", "limit": { "context": 32768, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen Max", "open_weights": false, "reasoning": false, "release_date": "2024-04-03", "temperature": true, "tool_call": true }, "qwen-max-latest": { "attachment": true, "cost": { "input": 1.6, "output": 6.4 }, "description": "Qwen Max Latest is an AI model provided by llmgateway.", "family": "qwen", "id": "qwen-max-latest", "last_updated": "2025-01-25", "limit": { "context": 32768, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen Max Latest", "open_weights": false, "reasoning": false, "release_date": "2025-01-25", "structured_output": true, "temperature": true, "tool_call": true }, "qwen-omni-turbo": { "attachment": false, "cost": { "input": 0.07, "input_audio": 4.44, "output": 0.27, "output_audio": 8.89 }, "description": "Qwen-Omni Turbo is an AI model provided by llmgateway.", "family": "qwen", "id": "qwen-omni-turbo", "knowledge": "2024-04", "last_updated": "2025-03-26", "limit": { "context": 32768, "output": 2048 }, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text", "audio" ] }, "name": "Qwen-Omni Turbo", "open_weights": false, "reasoning": false, "release_date": "2025-01-19", "temperature": true, "tool_call": true }, "qwen-plus": { "attachment": false, "cost": { "input": 0.4, "output": 1.2, "reasoning": 4 }, "description": "Qwen Plus is an AI model provided by llmgateway.", "family": "qwen", "id": "qwen-plus", "knowledge": "2024-04", "last_updated": "2025-09-11", "limit": { "context": 1000000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen Plus", "open_weights": false, "reasoning": true, "release_date": "2024-01-25", "temperature": true, "tool_call": true }, "qwen-plus-latest": { "attachment": true, "cost": { "input": 0.3, "output": 0.9 }, "description": "Qwen Plus Latest is an AI model provided by llmgateway.", "family": "qwen", "id": "qwen-plus-latest", "last_updated": "2025-01-25", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen Plus Latest", "open_weights": false, "reasoning": false, "release_date": "2025-01-25", "structured_output": true, "temperature": true, "tool_call": true }, "qwen-turbo": { "attachment": false, "cost": { "input": 0.05, "output": 0.2, "reasoning": 0.5 }, "description": "Qwen Turbo is an AI model provided by llmgateway.", "family": "qwen", "id": "qwen-turbo", "knowledge": "2024-04", "last_updated": "2025-04-28", "limit": { "context": 1000000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen Turbo", "open_weights": false, "reasoning": true, "release_date": "2024-11-01", "temperature": true, "tool_call": true }, "qwen-vl-max": { "attachment": false, "cost": { "input": 0.8, "output": 3.2 }, "description": "Qwen-VL Max is an AI model provided by llmgateway.", "family": "qwen", "id": "qwen-vl-max", "knowledge": "2024-04", "last_updated": "2025-08-13", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen-VL Max", "open_weights": false, "reasoning": false, "release_date": "2024-04-08", "temperature": true, "tool_call": true }, "qwen-vl-plus": { "attachment": false, "cost": { "input": 0.21, "output": 0.63 }, "description": "Qwen-VL Plus is an AI model provided by llmgateway.", "family": "qwen", "id": "qwen-vl-plus", "knowledge": "2024-04", "last_updated": "2025-08-15", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen-VL Plus", "open_weights": false, "reasoning": false, "release_date": "2024-01-25", "temperature": true, "tool_call": true }, "qwen2-5-vl-32b-instruct": { "attachment": true, "cost": { "input": 0.3, "output": 0.3 }, "description": "Qwen2.5 VL 32B Instruct is an AI model provided by llmgateway.", "family": "qwen", "id": "qwen2-5-vl-32b-instruct", "last_updated": "2025-03-15", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen2.5 VL 32B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-03-15", "structured_output": true, "temperature": true, "tool_call": true }, "qwen2-5-vl-72b-instruct": { "attachment": false, "cost": { "input": 2.8, "output": 8.4 }, "description": "Qwen2.5-VL 72B Instruct is an AI model provided by llmgateway.", "family": "qwen", "id": "qwen2-5-vl-72b-instruct", "knowledge": "2024-04", "last_updated": "2024-09", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen2.5-VL 72B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-09", "temperature": true, "tool_call": true }, "qwen25-coder-7b": { "attachment": false, "cost": { "input": 0.05, "output": 0.05 }, "description": "Qwen2.5 Coder 7B is an AI model provided by llmgateway.", "family": "qwen", "id": "qwen25-coder-7b", "last_updated": "2024-09-19", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen2.5 Coder 7B", "open_weights": true, "reasoning": false, "release_date": "2024-09-19", "structured_output": true, "temperature": true, "tool_call": false }, "qwen3-235b-a22b-fp8": { "attachment": false, "cost": { "input": 0.5, "output": 2.5 }, "description": "Qwen3 235B A22B FP8 is an AI model provided by llmgateway.", "family": "qwen", "id": "qwen3-235b-a22b-fp8", "last_updated": "2025-04-28", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 235B A22B FP8", "open_weights": true, "reasoning": true, "release_date": "2025-04-28", "structured_output": true, "temperature": true, "tool_call": true }, "qwen3-235b-a22b-instruct-2507": { "attachment": false, "cost": { "input": 0.8, "output": 2.4 }, "description": "Qwen3 235B A22B Instruct (2507) is an AI model provided by llmgateway.", "family": "qwen", "id": "qwen3-235b-a22b-instruct-2507", "last_updated": "2025-07-08", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 235B A22B Instruct (2507)", "open_weights": true, "reasoning": false, "release_date": "2025-07-08", "structured_output": true, "temperature": true, "tool_call": true }, "qwen3-235b-a22b-thinking-2507": { "attachment": false, "cost": { "input": 0.8, "output": 2.4 }, "description": "Qwen3 235B A22B Thinking (2507) is an AI model provided by llmgateway.", "family": "qwen", "id": "qwen3-235b-a22b-thinking-2507", "last_updated": "2025-07-08", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 235B A22B Thinking (2507)", "open_weights": true, "reasoning": true, "release_date": "2025-07-08", "structured_output": true, "temperature": true, "tool_call": true }, "qwen3-30b-a3b-fp8": { "attachment": false, "cost": { "input": 0.1, "output": 0.1 }, "description": "Qwen3 30B A3B FP8 is an AI model provided by llmgateway.", "family": "qwen", "id": "qwen3-30b-a3b-fp8", "last_updated": "2025-04-28", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 30B A3B FP8", "open_weights": true, "reasoning": true, "release_date": "2025-04-28", "structured_output": true, "temperature": true, "tool_call": true }, "qwen3-30b-a3b-instruct-2507": { "attachment": false, "cost": { "input": 0.1, "output": 0.1 }, "description": "Qwen3 30B A3B Instruct (2507) is an AI model provided by llmgateway.", "family": "qwen", "id": "qwen3-30b-a3b-instruct-2507", "last_updated": "2025-07-08", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 30B A3B Instruct (2507)", "open_weights": true, "reasoning": false, "release_date": "2025-07-08", "structured_output": true, "temperature": true, "tool_call": true }, "qwen3-30b-a3b-thinking-2507": { "attachment": false, "cost": { "input": 0.1, "output": 0.1 }, "description": "Qwen3 30B A3B Thinking (2507) is an AI model provided by llmgateway.", "family": "qwen", "id": "qwen3-30b-a3b-thinking-2507", "last_updated": "2025-07-08", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 30B A3B Thinking (2507)", "open_weights": true, "reasoning": true, "release_date": "2025-07-08", "structured_output": true, "temperature": true, "tool_call": true }, "qwen3-32b": { "attachment": false, "cost": { "input": 0.7, "output": 2.8, "reasoning": 8.4 }, "description": "Qwen3 32B is an AI model provided by llmgateway.", "family": "qwen", "id": "qwen3-32b", "knowledge": "2025-04", "last_updated": "2025-04", "limit": { "context": 131072, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 32B", "open_weights": true, "reasoning": true, "release_date": "2025-04", "temperature": true, "tool_call": true }, "qwen3-32b-fp8": { "attachment": false, "cost": { "input": 0.1, "output": 0.1 }, "description": "Qwen3 32B FP8 is an AI model provided by llmgateway.", "family": "qwen", "id": "qwen3-32b-fp8", "last_updated": "2025-04-28", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 32B FP8", "open_weights": true, "reasoning": true, "release_date": "2025-04-28", "structured_output": true, "temperature": true, "tool_call": true }, "qwen3-4b-fp8": { "attachment": false, "cost": { "input": 0.03, "output": 0.05 }, "description": "Qwen3 4B FP8 is an AI model provided by llmgateway.", "family": "qwen", "id": "qwen3-4b-fp8", "last_updated": "2025-04-28", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 4B FP8", "open_weights": true, "reasoning": true, "release_date": "2025-04-28", "structured_output": true, "temperature": true, "tool_call": true }, "qwen3-coder-30b-a3b-instruct": { "attachment": false, "cost": { "input": 0.45, "output": 2.25 }, "description": "Qwen3-Coder 30B-A3B Instruct is an AI model provided by llmgateway.", "family": "qwen", "id": "qwen3-coder-30b-a3b-instruct", "knowledge": "2025-04", "last_updated": "2025-04", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3-Coder 30B-A3B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-04", "temperature": true, "tool_call": true }, "qwen3-coder-480b-a35b-instruct": { "attachment": false, "cost": { "input": 1.5, "output": 7.5 }, "description": "Qwen3-Coder 480B-A35B Instruct is an AI model provided by llmgateway.", "family": "qwen", "id": "qwen3-coder-480b-a35b-instruct", "knowledge": "2025-04", "last_updated": "2025-04", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3-Coder 480B-A35B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-04", "temperature": true, "tool_call": true }, "qwen3-coder-flash": { "attachment": false, "cost": { "input": 0.3, "output": 1.5 }, "description": "Qwen3 Coder Flash is an AI model provided by llmgateway.", "family": "qwen", "id": "qwen3-coder-flash", "knowledge": "2025-04", "last_updated": "2025-07-28", "limit": { "context": 1000000, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Coder Flash", "open_weights": false, "reasoning": false, "release_date": "2025-07-28", "temperature": true, "tool_call": true }, "qwen3-coder-next": { "attachment": false, "cost": { "input": 0.8, "output": 4 }, "description": "Qwen3 Coder Next is an AI model provided by llmgateway.", "family": "qwen", "id": "qwen3-coder-next", "last_updated": "2025-10-15", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Coder Next", "open_weights": false, "reasoning": true, "release_date": "2025-10-15", "structured_output": true, "temperature": true, "tool_call": true }, "qwen3-coder-plus": { "attachment": false, "cost": { "input": 1, "output": 5 }, "description": "Qwen3 Coder Plus is an AI model provided by llmgateway.", "family": "qwen", "id": "qwen3-coder-plus", "knowledge": "2025-04", "last_updated": "2025-07-23", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Coder Plus", "open_weights": true, "reasoning": false, "release_date": "2025-07-23", "temperature": true, "tool_call": true }, "qwen3-max": { "attachment": false, "cost": { "input": 1.2, "output": 6 }, "description": "Qwen3 Max is an AI model provided by llmgateway.", "family": "qwen", "id": "qwen3-max", "knowledge": "2025-04", "last_updated": "2025-09-23", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Max", "open_weights": false, "reasoning": false, "release_date": "2025-09-23", "temperature": true, "tool_call": true }, "qwen3-max-2026-01-23": { "attachment": true, "cost": { "cache_read": 0.6, "input": 3, "output": 15 }, "description": "Qwen3 Max (2026-01-23) is an AI model provided by llmgateway.", "family": "qwen", "id": "qwen3-max-2026-01-23", "last_updated": "2026-01-23", "limit": { "context": 256000, "output": 32800 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen3 Max (2026-01-23)", "open_weights": false, "reasoning": true, "release_date": "2026-01-23", "structured_output": true, "temperature": true, "tool_call": true }, "qwen3-next-80b-a3b-instruct": { "attachment": false, "cost": { "input": 0.5, "output": 2 }, "description": "Qwen3-Next 80B-A3B Instruct is an AI model provided by llmgateway.", "family": "qwen", "id": "qwen3-next-80b-a3b-instruct", "knowledge": "2025-04", "last_updated": "2025-09", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3-Next 80B-A3B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-09", "temperature": true, "tool_call": true }, "qwen3-next-80b-a3b-thinking": { "attachment": false, "cost": { "input": 0.5, "output": 6 }, "description": "Qwen3-Next 80B-A3B (Thinking) is an AI model provided by llmgateway.", "family": "qwen", "id": "qwen3-next-80b-a3b-thinking", "knowledge": "2025-04", "last_updated": "2025-09", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3-Next 80B-A3B (Thinking)", "open_weights": true, "reasoning": true, "release_date": "2025-09", "temperature": true, "tool_call": true }, "qwen3-vl-235b-a22b-instruct": { "attachment": true, "cost": { "input": 0.8, "output": 2.4 }, "description": "Qwen3 VL 235B A22B Instruct is an AI model provided by llmgateway.", "family": "qwen", "id": "qwen3-vl-235b-a22b-instruct", "last_updated": "2025-09-15", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen3 VL 235B A22B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-09-15", "structured_output": true, "temperature": true, "tool_call": true }, "qwen3-vl-235b-a22b-thinking": { "attachment": true, "cost": { "input": 0.8, "output": 2.4 }, "description": "Qwen3 VL 235B A22B Thinking is an AI model provided by llmgateway.", "family": "qwen", "id": "qwen3-vl-235b-a22b-thinking", "last_updated": "2025-09-15", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen3 VL 235B A22B Thinking", "open_weights": true, "reasoning": true, "release_date": "2025-09-15", "structured_output": true, "temperature": true, "tool_call": true }, "qwen3-vl-30b-a3b-instruct": { "attachment": true, "cost": { "input": 0.1, "output": 0.1 }, "description": "Qwen3 VL 30B A3B Instruct is an AI model provided by llmgateway.", "family": "qwen", "id": "qwen3-vl-30b-a3b-instruct", "last_updated": "2025-10-02", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen3 VL 30B A3B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-10-02", "structured_output": true, "temperature": true, "tool_call": true }, "qwen3-vl-30b-a3b-thinking": { "attachment": true, "cost": { "input": 0.1, "output": 0.1 }, "description": "Qwen3 VL 30B A3B Thinking is an AI model provided by llmgateway.", "family": "qwen", "id": "qwen3-vl-30b-a3b-thinking", "last_updated": "2025-10-02", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen3 VL 30B A3B Thinking", "open_weights": true, "reasoning": true, "release_date": "2025-10-02", "structured_output": true, "temperature": true, "tool_call": true }, "qwen3-vl-8b-instruct": { "attachment": true, "cost": { "input": 0.1, "output": 0.1 }, "description": "Qwen3 VL 8B Instruct is an AI model provided by llmgateway.", "family": "qwen", "id": "qwen3-vl-8b-instruct", "last_updated": "2025-08-19", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen3 VL 8B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-08-19", "structured_output": false, "temperature": true, "tool_call": false }, "qwen3-vl-flash": { "attachment": true, "cost": { "cache_read": 0.01, "input": 0.05, "output": 0.4 }, "description": "Qwen3 VL Flash is an AI model provided by llmgateway.", "family": "qwen", "id": "qwen3-vl-flash", "last_updated": "2025-10-09", "limit": { "context": 1000000, "output": 32000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen3 VL Flash", "open_weights": false, "reasoning": false, "release_date": "2025-10-09", "structured_output": true, "temperature": true, "tool_call": true }, "qwen3-vl-plus": { "attachment": false, "cost": { "input": 0.2, "output": 1.6, "reasoning": 4.8 }, "description": "Qwen3-VL Plus is an AI model provided by llmgateway.", "family": "qwen", "id": "qwen3-vl-plus", "knowledge": "2025-04", "last_updated": "2025-09-23", "limit": { "context": 262144, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen3-VL Plus", "open_weights": false, "reasoning": true, "release_date": "2025-09-23", "temperature": true, "tool_call": true }, "qwen3.6-35b-a3b": { "attachment": true, "cost": { "input": 0.248, "output": 1.485 }, "description": "Qwen3.6 35B-A3B is an AI model provided by llmgateway.", "family": "qwen", "id": "qwen3.6-35b-a3b", "last_updated": "2026-04-17", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text" ] }, "name": "Qwen3.6 35B-A3B", "open_weights": true, "reasoning": true, "release_date": "2026-04-17", "structured_output": true, "temperature": true, "tool_call": true }, "qwen3.6-max-preview": { "attachment": false, "cost": { "cache_read": 0.13, "cache_write": 1.625, "input": 1.3, "output": 7.8 }, "description": "Qwen3.6 Max Preview is an AI model provided by llmgateway.", "family": "qwen", "id": "qwen3.6-max-preview", "knowledge": "2025-04", "last_updated": "2026-04-20", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3.6 Max Preview", "open_weights": false, "reasoning": true, "release_date": "2026-04-20", "temperature": true, "tool_call": true }, "qwen3.6-plus": { "attachment": false, "cost": { "cache_read": 0.05, "cache_write": 0.625, "context_over_200k": { "cache_read": 0.2, "cache_write": 2.5, "input": 2, "output": 6 }, "input": 0.5, "output": 3, "tiers": [ { "cache_read": 0.2, "cache_write": 2.5, "input": 2, "output": 6, "tier": { "size": 256000, "type": "context" } } ] }, "description": "Qwen3.6 Plus is an AI model provided by llmgateway.", "family": "qwen", "id": "qwen3.6-plus", "knowledge": "2025-04", "last_updated": "2026-04-02", "limit": { "context": 1000000, "output": 65536 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen3.6 Plus", "open_weights": false, "reasoning": true, "release_date": "2026-04-02", "temperature": true, "tool_call": true }, "qwen35-397b-a17b": { "attachment": true, "cost": { "input": 0.6, "output": 3.6 }, "description": "Qwen3.5 397B-A17B is an AI model provided by llmgateway.", "family": "qwen", "id": "qwen35-397b-a17b", "last_updated": "2026-02-15", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text" ] }, "name": "Qwen3.5 397B-A17B", "open_weights": true, "reasoning": true, "release_date": "2026-02-15", "structured_output": true, "temperature": true, "tool_call": true }, "qwq-plus": { "attachment": false, "cost": { "input": 0.8, "output": 2.4 }, "description": "QwQ Plus is an AI model provided by llmgateway.", "family": "qwen", "id": "qwq-plus", "knowledge": "2024-04", "last_updated": "2025-03-05", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "QwQ Plus", "open_weights": false, "reasoning": true, "release_date": "2025-03-05", "temperature": true, "tool_call": true }, "seed-1-6-250615": { "attachment": true, "cost": { "cache_read": 0.05, "input": 0.25, "output": 2 }, "description": "Seed 1.6 (250615) is an AI model provided by llmgateway.", "family": "seed", "id": "seed-1-6-250615", "last_updated": "2025-06-25", "limit": { "context": 256000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Seed 1.6 (250615)", "open_weights": true, "reasoning": true, "release_date": "2025-06-25", "structured_output": true, "temperature": true, "tool_call": true }, "seed-1-6-250915": { "attachment": true, "cost": { "cache_read": 0.05, "input": 0.25, "output": 2 }, "description": "Seed 1.6 (250915) is an AI model provided by llmgateway.", "family": "seed", "id": "seed-1-6-250915", "last_updated": "2025-09-15", "limit": { "context": 256000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Seed 1.6 (250915)", "open_weights": true, "reasoning": true, "release_date": "2025-09-15", "structured_output": true, "temperature": true, "tool_call": true }, "seed-1-6-flash-250715": { "attachment": true, "cost": { "cache_read": 0.01, "input": 0.07, "output": 0.3 }, "description": "Seed 1.6 Flash (250715) is an AI model provided by llmgateway.", "family": "seed", "id": "seed-1-6-flash-250715", "last_updated": "2025-07-26", "limit": { "context": 256000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Seed 1.6 Flash (250715)", "open_weights": true, "reasoning": true, "release_date": "2025-07-26", "structured_output": true, "temperature": true, "tool_call": true }, "seed-1-8-251228": { "attachment": true, "cost": { "cache_read": 0.05, "input": 0.25, "output": 2 }, "description": "Seed 1.8 (251228) is an AI model provided by llmgateway.", "family": "seed", "id": "seed-1-8-251228", "last_updated": "2025-12-18", "limit": { "context": 256000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Seed 1.8 (251228)", "open_weights": true, "reasoning": true, "release_date": "2025-12-18", "structured_output": true, "temperature": true, "tool_call": true }, "sonar": { "attachment": false, "cost": { "input": 1, "output": 1 }, "description": "Sonar is an AI model provided by llmgateway.", "family": "sonar", "id": "sonar", "knowledge": "2025-09-01", "last_updated": "2025-09-01", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Sonar", "open_weights": false, "reasoning": false, "release_date": "2024-01-01", "temperature": true, "tool_call": false }, "sonar-pro": { "attachment": true, "cost": { "input": 3, "output": 15 }, "description": "Sonar Pro is an AI model provided by llmgateway.", "family": "sonar-pro", "id": "sonar-pro", "knowledge": "2025-09-01", "last_updated": "2025-09-01", "limit": { "context": 200000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Sonar Pro", "open_weights": false, "reasoning": false, "release_date": "2024-01-01", "temperature": true, "tool_call": false }, "sonar-reasoning-pro": { "attachment": true, "cost": { "input": 2, "output": 8 }, "description": "Sonar Reasoning Pro is an AI model provided by llmgateway.", "family": "sonar-reasoning", "id": "sonar-reasoning-pro", "knowledge": "2025-09-01", "last_updated": "2025-09-01", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Sonar Reasoning Pro", "open_weights": false, "reasoning": true, "release_date": "2024-01-01", "temperature": true, "tool_call": false } }, "name": "LLM Gateway", "npm": "@ai-sdk/openai-compatible" }, "lmstudio": { "api": "http://127.0.0.1:1234/v1", "doc": "https://lmstudio.ai/models", "env": [ "LMSTUDIO_API_KEY" ], "iconURL": "https://models.dev/logos/lmstudio.svg", "id": "lmstudio", "lobeIcon": "LMStudio", "models": { "openai/gpt-oss-20b": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "GPT OSS 20B is an AI model provided by lmstudio.", "family": "gpt-oss", "id": "openai/gpt-oss-20b", "last_updated": "2025-08-05", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT OSS 20B", "open_weights": true, "reasoning": true, "release_date": "2025-08-05", "temperature": true, "tool_call": true }, "qwen/qwen3-30b-a3b-2507": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Qwen3 30B A3B 2507 is an AI model provided by lmstudio.", "family": "qwen", "id": "qwen/qwen3-30b-a3b-2507", "knowledge": "2025-04", "last_updated": "2025-07-30", "limit": { "context": 262144, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 30B A3B 2507", "open_weights": true, "reasoning": false, "release_date": "2025-07-30", "temperature": true, "tool_call": true }, "qwen/qwen3-coder-30b": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Qwen3 Coder 30B is an AI model provided by lmstudio.", "family": "qwen", "id": "qwen/qwen3-coder-30b", "knowledge": "2025-04", "last_updated": "2025-07-23", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Coder 30B", "open_weights": true, "reasoning": false, "release_date": "2025-07-23", "temperature": true, "tool_call": true } }, "name": "LMStudio", "npm": "@ai-sdk/openai-compatible" }, "lucidquery": { "api": "https://lucidquery.com/api/v1", "doc": "https://lucidquery.com/api/docs", "env": [ "LUCIDQUERY_API_KEY" ], "iconURL": "https://models.dev/logos/lucidquery.svg", "id": "lucidquery", "models": { "lucidnova-rf1-100b": { "attachment": true, "cost": { "input": 2, "output": 5 }, "description": "LucidNova RF1 100B is an AI model provided by lucidquery.", "family": "nova", "id": "lucidnova-rf1-100b", "knowledge": "2025-09-16", "last_updated": "2025-09-10", "limit": { "context": 120000, "output": 8000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "LucidNova RF1 100B", "open_weights": false, "reasoning": true, "release_date": "2024-12-28", "temperature": false, "tool_call": true }, "lucidquery-nexus-coder": { "attachment": true, "cost": { "input": 2, "output": 5 }, "description": "LucidQuery Nexus Coder is an AI model provided by lucidquery.", "family": "lucid", "id": "lucidquery-nexus-coder", "knowledge": "2025-08-01", "last_updated": "2025-09-01", "limit": { "context": 250000, "output": 60000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "LucidQuery Nexus Coder", "open_weights": false, "reasoning": true, "release_date": "2025-09-01", "temperature": false, "tool_call": true } }, "name": "LucidQuery AI", "npm": "@ai-sdk/openai-compatible" }, "meganova": { "api": "https://api.meganova.ai/v1", "doc": "https://docs.meganova.ai", "env": [ "MEGANOVA_API_KEY" ], "iconURL": "https://models.dev/logos/meganova.svg", "id": "meganova", "models": { "MiniMaxAI/MiniMax-M2.1": { "attachment": false, "cost": { "input": 0.28, "output": 1.2 }, "description": "MiniMax M2.1 is an AI model provided by meganova.", "family": "minimax", "id": "MiniMaxAI/MiniMax-M2.1", "interleaved": { "field": "reasoning_content" }, "last_updated": "2025-12-23", "limit": { "context": 196608, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M2.1", "open_weights": true, "reasoning": true, "release_date": "2025-12-23", "temperature": true, "tool_call": true }, "MiniMaxAI/MiniMax-M2.5": { "attachment": false, "cost": { "input": 0.3, "output": 1.2 }, "description": "MiniMax M2.5 is an AI model provided by meganova.", "family": "minimax", "id": "MiniMaxAI/MiniMax-M2.5", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-02-12", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M2.5", "open_weights": true, "reasoning": true, "release_date": "2026-02-12", "temperature": true, "tool_call": true }, "Qwen/Qwen2.5-VL-32B-Instruct": { "attachment": true, "cost": { "input": 0.2, "output": 0.6 }, "description": "Qwen2.5 VL 32B Instruct is an AI model provided by meganova.", "family": "qwen", "id": "Qwen/Qwen2.5-VL-32B-Instruct", "last_updated": "2025-03-24", "limit": { "context": 16384, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen2.5 VL 32B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-03-24", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-235B-A22B-Instruct-2507": { "attachment": false, "cost": { "input": 0.09, "output": 0.6 }, "description": "Qwen3 235B A22B Instruct 2507 is an AI model provided by meganova.", "family": "qwen", "id": "Qwen/Qwen3-235B-A22B-Instruct-2507", "last_updated": "2025-07-23", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 235B A22B Instruct 2507", "open_weights": true, "reasoning": false, "release_date": "2025-07-23", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3.5-Plus": { "attachment": false, "cost": { "input": 0.4, "output": 2.4, "reasoning": 2.4 }, "description": "Qwen3.5 Plus is an AI model provided by meganova.", "family": "qwen", "id": "Qwen/Qwen3.5-Plus", "knowledge": "2025-04", "last_updated": "2026-02", "limit": { "context": 1000000, "output": 65536 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen3.5 Plus", "open_weights": false, "reasoning": true, "release_date": "2026-02", "temperature": true, "tool_call": true }, "XiaomiMiMo/MiMo-V2-Flash": { "attachment": false, "cost": { "input": 0.1, "output": 0.3 }, "description": "MiMo V2 Flash is an AI model provided by meganova.", "family": "mimo", "id": "XiaomiMiMo/MiMo-V2-Flash", "knowledge": "2024-12-01", "last_updated": "2025-12-17", "limit": { "context": 262144, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiMo V2 Flash", "open_weights": true, "reasoning": true, "release_date": "2025-12-17", "temperature": true, "tool_call": true }, "deepseek-ai/DeepSeek-R1-0528": { "attachment": false, "cost": { "input": 0.5, "output": 2.15 }, "description": "DeepSeek R1 0528 is an AI model provided by meganova.", "family": "deepseek-thinking", "id": "deepseek-ai/DeepSeek-R1-0528", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-07", "last_updated": "2025-05-28", "limit": { "context": 163840, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek R1 0528", "open_weights": true, "reasoning": true, "release_date": "2025-05-28", "temperature": true, "tool_call": false }, "deepseek-ai/DeepSeek-V3-0324": { "attachment": false, "cost": { "input": 0.25, "output": 0.88 }, "description": "DeepSeek V3 0324 is an AI model provided by meganova.", "family": "deepseek", "id": "deepseek-ai/DeepSeek-V3-0324", "last_updated": "2025-03-24", "limit": { "context": 163840, "output": 163840 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3 0324", "open_weights": true, "reasoning": false, "release_date": "2025-03-24", "temperature": true, "tool_call": true }, "deepseek-ai/DeepSeek-V3.1": { "attachment": false, "cost": { "input": 0.27, "output": 1 }, "description": "DeepSeek V3.1 is an AI model provided by meganova.", "family": "deepseek", "id": "deepseek-ai/DeepSeek-V3.1", "last_updated": "2025-08-25", "limit": { "context": 164000, "output": 164000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3.1", "open_weights": true, "reasoning": false, "release_date": "2025-08-25", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek-ai/DeepSeek-V3.2": { "attachment": false, "cost": { "input": 0.26, "output": 0.38 }, "description": "DeepSeek V3.2 is an AI model provided by meganova.", "family": "deepseek", "id": "deepseek-ai/DeepSeek-V3.2", "last_updated": "2025-12-03", "limit": { "context": 164000, "output": 164000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3.2", "open_weights": true, "reasoning": false, "release_date": "2025-12-03", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek-ai/DeepSeek-V3.2-Exp": { "attachment": false, "cost": { "input": 0.27, "output": 0.4 }, "description": "DeepSeek V3.2 Exp is an AI model provided by meganova.", "family": "deepseek", "id": "deepseek-ai/DeepSeek-V3.2-Exp", "last_updated": "2025-10-10", "limit": { "context": 164000, "output": 164000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3.2 Exp", "open_weights": true, "reasoning": false, "release_date": "2025-10-10", "structured_output": true, "temperature": true, "tool_call": true }, "meta-llama/Llama-3.3-70B-Instruct": { "attachment": false, "cost": { "input": 0.1, "output": 0.3 }, "description": "Llama 3.3 70B Instruct is an AI model provided by meganova.", "family": "llama", "id": "meta-llama/Llama-3.3-70B-Instruct", "last_updated": "2024-12-06", "limit": { "context": 131072, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-12-06", "temperature": true, "tool_call": true }, "mistralai/Mistral-Nemo-Instruct-2407": { "attachment": false, "cost": { "input": 0.02, "output": 0.04 }, "description": "Mistral Nemo Instruct 2407 is an AI model provided by meganova.", "family": "mistral", "id": "mistralai/Mistral-Nemo-Instruct-2407", "last_updated": "2024-07-18", "limit": { "context": 131072, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral Nemo Instruct 2407", "open_weights": true, "reasoning": false, "release_date": "2024-07-18", "structured_output": true, "temperature": true, "tool_call": true }, "mistralai/Mistral-Small-3.2-24B-Instruct-2506": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Mistral Small 3.2 24B Instruct is an AI model provided by meganova.", "family": "mistral-small", "id": "mistralai/Mistral-Small-3.2-24B-Instruct-2506", "knowledge": "2024-10", "last_updated": "2025-06-20", "limit": { "context": 32768, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Mistral Small 3.2 24B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-06-20", "structured_output": true, "temperature": true, "tool_call": true }, "moonshotai/Kimi-K2-Thinking": { "attachment": false, "cost": { "input": 0.6, "output": 2.6 }, "description": "Kimi K2 Thinking is an AI model provided by meganova.", "family": "kimi-thinking", "id": "moonshotai/Kimi-K2-Thinking", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-08", "last_updated": "2025-11-06", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 Thinking", "open_weights": true, "reasoning": true, "release_date": "2025-11-06", "temperature": true, "tool_call": true }, "moonshotai/Kimi-K2.5": { "attachment": false, "cost": { "input": 0.45, "output": 2.8 }, "description": "Kimi K2.5 is an AI model provided by meganova.", "family": "kimi", "id": "moonshotai/Kimi-K2.5", "interleaved": { "field": "reasoning_content" }, "knowledge": "2026-01", "last_updated": "2026-01-27", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Kimi K2.5", "open_weights": true, "reasoning": true, "release_date": "2026-01-27", "temperature": true, "tool_call": true }, "zai-org/GLM-4.6": { "attachment": false, "cost": { "input": 0.45, "output": 1.9 }, "description": "GLM-4.6 is an AI model provided by meganova.", "family": "glm", "id": "zai-org/GLM-4.6", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-04", "last_updated": "2025-09-30", "limit": { "context": 202752, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.6", "open_weights": true, "reasoning": true, "release_date": "2025-09-30", "temperature": true, "tool_call": true }, "zai-org/GLM-4.7": { "attachment": false, "cost": { "input": 0.2, "output": 0.8 }, "description": "GLM-4.7 is an AI model provided by meganova.", "family": "glm", "id": "zai-org/GLM-4.7", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-04", "last_updated": "2025-12-22", "limit": { "context": 202752, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.7", "open_weights": true, "reasoning": true, "release_date": "2025-12-22", "temperature": true, "tool_call": true }, "zai-org/GLM-5": { "attachment": false, "cost": { "input": 0.8, "output": 2.56 }, "description": "GLM-5 is an AI model provided by meganova.", "family": "glm", "id": "zai-org/GLM-5", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-02-11", "limit": { "context": 202752, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5", "open_weights": true, "reasoning": true, "release_date": "2026-02-11", "temperature": true, "tool_call": true } }, "name": "Meganova", "npm": "@ai-sdk/openai-compatible" }, "midjourney": { "id": "midjourney", "lobeIcon": "Midjourney", "models": {} }, "minimax": { "api": "https://platform.minimaxi.com/document/对话", "doc": "https://platform.minimax.io/docs/guides/quickstart", "env": [ "MINIMAX_API_KEY" ], "iconURL": "https://models.dev/logos/minimax.svg", "id": "minimax", "lobeIcon": "Minimax.Color", "models": { "MiniMax-M2": { "attachment": false, "cost": { "input": 0.3, "output": 1.2 }, "description": "MiniMax-M2 is an AI model provided by minimax.", "family": "minimax", "id": "MiniMax-M2", "last_updated": "2025-10-27", "limit": { "context": 196608, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2", "open_weights": true, "reasoning": true, "release_date": "2025-10-27", "temperature": true, "tool_call": true }, "MiniMax-M2.1": { "attachment": false, "cost": { "input": 0.3, "output": 1.2 }, "description": "MiniMax-M2.1 is an AI model provided by minimax.", "family": "minimax", "id": "MiniMax-M2.1", "last_updated": "2025-12-23", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.1", "open_weights": true, "reasoning": true, "release_date": "2025-12-23", "temperature": true, "tool_call": true }, "MiniMax-M2.5": { "attachment": false, "cost": { "cache_read": 0.03, "cache_write": 0.375, "input": 0.3, "output": 1.2 }, "description": "MiniMax-M2.5 is an AI model provided by minimax.", "family": "minimax", "id": "MiniMax-M2.5", "last_updated": "2026-02-12", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.5", "open_weights": true, "reasoning": true, "release_date": "2026-02-12", "temperature": true, "tool_call": true }, "MiniMax-M2.5-highspeed": { "attachment": false, "cost": { "cache_read": 0.06, "cache_write": 0.375, "input": 0.6, "output": 2.4 }, "description": "MiniMax-M2.5-highspeed is an AI model provided by minimax.", "family": "minimax", "id": "MiniMax-M2.5-highspeed", "last_updated": "2026-02-13", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.5-highspeed", "open_weights": true, "reasoning": true, "release_date": "2026-02-13", "temperature": true, "tool_call": true }, "MiniMax-M2.7": { "attachment": false, "cost": { "cache_read": 0.06, "cache_write": 0.375, "input": 0.3, "output": 1.2 }, "description": "MiniMax-M2.7 is an AI model provided by minimax.", "family": "minimax", "id": "MiniMax-M2.7", "last_updated": "2026-03-18", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.7", "open_weights": true, "reasoning": true, "release_date": "2026-03-18", "temperature": true, "tool_call": true }, "MiniMax-M2.7-highspeed": { "attachment": false, "cost": { "cache_read": 0.06, "cache_write": 0.375, "input": 0.6, "output": 2.4 }, "description": "MiniMax-M2.7-highspeed is an AI model provided by minimax.", "family": "minimax", "id": "MiniMax-M2.7-highspeed", "last_updated": "2026-03-18", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.7-highspeed", "open_weights": true, "reasoning": true, "release_date": "2026-03-18", "temperature": true, "tool_call": true } }, "name": "MiniMax (minimax.io)", "npm": "@ai-sdk/anthropic" }, "minimax-cn": { "api": "https://api.minimaxi.com/anthropic/v1", "doc": "https://platform.minimaxi.com/docs/guides/quickstart", "env": [ "MINIMAX_API_KEY" ], "iconURL": "https://models.dev/logos/minimax-cn.svg", "id": "minimax-cn", "models": { "MiniMax-M2": { "attachment": false, "cost": { "input": 0.3, "output": 1.2 }, "description": "MiniMax-M2 is an AI model provided by minimax-cn.", "family": "minimax", "id": "MiniMax-M2", "last_updated": "2025-10-27", "limit": { "context": 196608, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2", "open_weights": true, "reasoning": true, "release_date": "2025-10-27", "temperature": true, "tool_call": true }, "MiniMax-M2.1": { "attachment": false, "cost": { "input": 0.3, "output": 1.2 }, "description": "MiniMax-M2.1 is an AI model provided by minimax-cn.", "family": "minimax", "id": "MiniMax-M2.1", "last_updated": "2025-12-23", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.1", "open_weights": true, "reasoning": true, "release_date": "2025-12-23", "temperature": true, "tool_call": true }, "MiniMax-M2.5": { "attachment": false, "cost": { "cache_read": 0.03, "cache_write": 0.375, "input": 0.3, "output": 1.2 }, "description": "MiniMax-M2.5 is an AI model provided by minimax-cn.", "family": "minimax", "id": "MiniMax-M2.5", "last_updated": "2026-02-12", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.5", "open_weights": true, "reasoning": true, "release_date": "2026-02-12", "temperature": true, "tool_call": true }, "MiniMax-M2.5-highspeed": { "attachment": false, "cost": { "cache_read": 0.06, "cache_write": 0.375, "input": 0.6, "output": 2.4 }, "description": "MiniMax-M2.5-highspeed is an AI model provided by minimax-cn.", "family": "minimax", "id": "MiniMax-M2.5-highspeed", "last_updated": "2026-02-13", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.5-highspeed", "open_weights": true, "reasoning": true, "release_date": "2026-02-13", "temperature": true, "tool_call": true }, "MiniMax-M2.7": { "attachment": false, "cost": { "cache_read": 0.06, "cache_write": 0.375, "input": 0.3, "output": 1.2 }, "description": "MiniMax-M2.7 is an AI model provided by minimax-cn.", "family": "minimax", "id": "MiniMax-M2.7", "last_updated": "2026-03-18", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.7", "open_weights": true, "reasoning": true, "release_date": "2026-03-18", "temperature": true, "tool_call": true }, "MiniMax-M2.7-highspeed": { "attachment": false, "cost": { "cache_read": 0.06, "cache_write": 0.375, "input": 0.6, "output": 2.4 }, "description": "MiniMax-M2.7-highspeed is an AI model provided by minimax-cn.", "family": "minimax", "id": "MiniMax-M2.7-highspeed", "last_updated": "2026-03-18", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.7-highspeed", "open_weights": true, "reasoning": true, "release_date": "2026-03-18", "temperature": true, "tool_call": true } }, "name": "MiniMax (minimaxi.com)", "npm": "@ai-sdk/anthropic" }, "minimax-cn-coding-plan": { "api": "https://api.minimaxi.com/anthropic/v1", "doc": "https://platform.minimaxi.com/docs/coding-plan/intro", "env": [ "MINIMAX_API_KEY" ], "iconURL": "https://models.dev/logos/minimax-cn-coding-plan.svg", "id": "minimax-cn-coding-plan", "models": { "MiniMax-M2": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "MiniMax-M2 is an AI model provided by minimax-cn-coding-plan.", "family": "minimax", "id": "MiniMax-M2", "last_updated": "2025-10-27", "limit": { "context": 196608, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2", "open_weights": true, "reasoning": true, "release_date": "2025-10-27", "temperature": true, "tool_call": true }, "MiniMax-M2.1": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "MiniMax-M2.1 is an AI model provided by minimax-cn-coding-plan.", "family": "minimax", "id": "MiniMax-M2.1", "last_updated": "2025-12-23", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.1", "open_weights": true, "reasoning": true, "release_date": "2025-12-23", "temperature": true, "tool_call": true }, "MiniMax-M2.5": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "MiniMax-M2.5 is an AI model provided by minimax-cn-coding-plan.", "family": "minimax", "id": "MiniMax-M2.5", "last_updated": "2026-02-12", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.5", "open_weights": true, "reasoning": true, "release_date": "2026-02-12", "temperature": true, "tool_call": true }, "MiniMax-M2.5-highspeed": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "MiniMax-M2.5-highspeed is an AI model provided by minimax-cn-coding-plan.", "family": "minimax", "id": "MiniMax-M2.5-highspeed", "last_updated": "2026-02-13", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.5-highspeed", "open_weights": true, "reasoning": true, "release_date": "2026-02-13", "temperature": true, "tool_call": true }, "MiniMax-M2.7": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "MiniMax-M2.7 is an AI model provided by minimax-cn-coding-plan.", "family": "minimax", "id": "MiniMax-M2.7", "last_updated": "2026-03-18", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.7", "open_weights": true, "reasoning": true, "release_date": "2026-03-18", "temperature": true, "tool_call": true }, "MiniMax-M2.7-highspeed": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "MiniMax-M2.7-highspeed is an AI model provided by minimax-cn-coding-plan.", "family": "minimax", "id": "MiniMax-M2.7-highspeed", "last_updated": "2026-03-18", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.7-highspeed", "open_weights": true, "reasoning": true, "release_date": "2026-03-18", "temperature": true, "tool_call": true } }, "name": "MiniMax Coding Plan (minimaxi.com)", "npm": "@ai-sdk/anthropic" }, "minimax-coding-plan": { "api": "https://api.minimax.io/anthropic/v1", "doc": "https://platform.minimax.io/docs/coding-plan/intro", "env": [ "MINIMAX_API_KEY" ], "iconURL": "https://models.dev/logos/minimax-coding-plan.svg", "id": "minimax-coding-plan", "models": { "MiniMax-M2": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "MiniMax-M2 is an AI model provided by minimax-coding-plan.", "family": "minimax", "id": "MiniMax-M2", "last_updated": "2025-10-27", "limit": { "context": 196608, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2", "open_weights": true, "reasoning": true, "release_date": "2025-10-27", "temperature": true, "tool_call": true }, "MiniMax-M2.1": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "MiniMax-M2.1 is an AI model provided by minimax-coding-plan.", "family": "minimax", "id": "MiniMax-M2.1", "last_updated": "2025-12-23", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.1", "open_weights": true, "reasoning": true, "release_date": "2025-12-23", "temperature": true, "tool_call": true }, "MiniMax-M2.5": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "MiniMax-M2.5 is an AI model provided by minimax-coding-plan.", "family": "minimax", "id": "MiniMax-M2.5", "last_updated": "2026-02-12", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.5", "open_weights": true, "reasoning": true, "release_date": "2026-02-12", "temperature": true, "tool_call": true }, "MiniMax-M2.5-highspeed": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "MiniMax-M2.5-highspeed is an AI model provided by minimax-coding-plan.", "family": "minimax", "id": "MiniMax-M2.5-highspeed", "last_updated": "2026-02-13", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.5-highspeed", "open_weights": true, "reasoning": true, "release_date": "2026-02-13", "temperature": true, "tool_call": true }, "MiniMax-M2.7": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "MiniMax-M2.7 is an AI model provided by minimax-coding-plan.", "family": "minimax", "id": "MiniMax-M2.7", "last_updated": "2026-03-18", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.7", "open_weights": true, "reasoning": true, "release_date": "2026-03-18", "temperature": true, "tool_call": true }, "MiniMax-M2.7-highspeed": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "MiniMax-M2.7-highspeed is an AI model provided by minimax-coding-plan.", "family": "minimax", "id": "MiniMax-M2.7-highspeed", "last_updated": "2026-03-18", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.7-highspeed", "open_weights": true, "reasoning": true, "release_date": "2026-03-18", "temperature": true, "tool_call": true } }, "name": "MiniMax Coding Plan (minimax.io)", "npm": "@ai-sdk/anthropic" }, "mistral": { "doc": "https://docs.mistral.ai/getting-started/models/", "env": [ "MISTRAL_API_KEY" ], "iconURL": "https://models.dev/logos/mistral.svg", "id": "mistral", "lobeIcon": "Mistral.Color", "models": { "codestral-latest": { "attachment": false, "cost": { "input": 0.3, "output": 0.9 }, "description": "Codestral (latest) is an AI model provided by mistral.", "family": "codestral", "id": "codestral-latest", "knowledge": "2024-10", "last_updated": "2025-01-04", "limit": { "context": 256000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Codestral (latest)", "open_weights": true, "reasoning": false, "release_date": "2024-05-29", "temperature": true, "tool_call": true }, "devstral-2512": { "attachment": false, "cost": { "input": 0.4, "output": 2 }, "description": "Devstral 2 is an AI model provided by mistral.", "family": "devstral", "id": "devstral-2512", "knowledge": "2025-12", "last_updated": "2025-12-09", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Devstral 2", "open_weights": true, "reasoning": false, "release_date": "2025-12-09", "temperature": true, "tool_call": true }, "devstral-medium-2507": { "attachment": false, "cost": { "input": 0.4, "output": 2 }, "description": "Devstral Medium is an AI model provided by mistral.", "family": "devstral", "id": "devstral-medium-2507", "knowledge": "2025-05", "last_updated": "2025-07-10", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Devstral Medium", "open_weights": true, "reasoning": false, "release_date": "2025-07-10", "temperature": true, "tool_call": true }, "devstral-medium-latest": { "attachment": false, "cost": { "input": 0.4, "output": 2 }, "description": "Devstral 2 (latest) is an AI model provided by mistral.", "family": "devstral", "id": "devstral-medium-latest", "knowledge": "2025-12", "last_updated": "2025-12-02", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Devstral 2 (latest)", "open_weights": true, "reasoning": false, "release_date": "2025-12-02", "temperature": true, "tool_call": true }, "devstral-small-2505": { "attachment": false, "cost": { "input": 0.1, "output": 0.3 }, "description": "Devstral Small 2505 is an AI model provided by mistral.", "family": "devstral", "id": "devstral-small-2505", "knowledge": "2025-05", "last_updated": "2025-05-07", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Devstral Small 2505", "open_weights": true, "reasoning": false, "release_date": "2025-05-07", "temperature": true, "tool_call": true }, "devstral-small-2507": { "attachment": false, "cost": { "input": 0.1, "output": 0.3 }, "description": "Devstral Small is an AI model provided by mistral.", "family": "devstral", "id": "devstral-small-2507", "knowledge": "2025-05", "last_updated": "2025-07-10", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Devstral Small", "open_weights": true, "reasoning": false, "release_date": "2025-07-10", "temperature": true, "tool_call": true }, "labs-devstral-small-2512": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Devstral Small 2 is an AI model provided by mistral.", "family": "devstral", "id": "labs-devstral-small-2512", "knowledge": "2025-12", "last_updated": "2025-12-09", "limit": { "context": 256000, "output": 256000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Devstral Small 2", "open_weights": true, "reasoning": false, "release_date": "2025-12-09", "temperature": true, "tool_call": true }, "magistral-medium-latest": { "attachment": false, "cost": { "input": 2, "output": 5 }, "description": "Magistral Medium (latest) is an AI model provided by mistral.", "family": "magistral-medium", "id": "magistral-medium-latest", "knowledge": "2025-06", "last_updated": "2025-03-20", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Magistral Medium (latest)", "open_weights": true, "reasoning": true, "release_date": "2025-03-17", "temperature": true, "tool_call": true }, "magistral-small": { "attachment": false, "cost": { "input": 0.5, "output": 1.5 }, "description": "Magistral Small is an AI model provided by mistral.", "family": "magistral-small", "id": "magistral-small", "knowledge": "2025-06", "last_updated": "2025-03-17", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Magistral Small", "open_weights": true, "reasoning": true, "release_date": "2025-03-17", "temperature": true, "tool_call": true }, "ministral-3b-latest": { "attachment": false, "cost": { "input": 0.04, "output": 0.04 }, "description": "Ministral 3B (latest) is an AI model provided by mistral.", "family": "ministral", "id": "ministral-3b-latest", "knowledge": "2024-10", "last_updated": "2024-10-04", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Ministral 3B (latest)", "open_weights": true, "reasoning": false, "release_date": "2024-10-01", "temperature": true, "tool_call": true }, "ministral-8b-latest": { "attachment": false, "cost": { "input": 0.1, "output": 0.1 }, "description": "Ministral 8B (latest) is an AI model provided by mistral.", "family": "ministral", "id": "ministral-8b-latest", "knowledge": "2024-10", "last_updated": "2024-10-04", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Ministral 8B (latest)", "open_weights": true, "reasoning": false, "release_date": "2024-10-01", "temperature": true, "tool_call": true }, "mistral-embed": { "attachment": false, "cost": { "input": 0.1, "output": 0 }, "description": "Mistral Embed is an AI model provided by mistral.", "family": "mistral-embed", "id": "mistral-embed", "last_updated": "2023-12-11", "limit": { "context": 8000, "output": 3072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral Embed", "open_weights": false, "reasoning": false, "release_date": "2023-12-11", "temperature": false, "tool_call": false }, "mistral-large-2411": { "attachment": false, "cost": { "input": 2, "output": 6 }, "description": "Mistral Large 2.1 is an AI model provided by mistral.", "family": "mistral-large", "id": "mistral-large-2411", "knowledge": "2024-11", "last_updated": "2024-11-04", "limit": { "context": 131072, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral Large 2.1", "open_weights": true, "reasoning": false, "release_date": "2024-11-01", "temperature": true, "tool_call": true }, "mistral-large-2512": { "attachment": true, "cost": { "input": 0.5, "output": 1.5 }, "description": "Mistral Large 3 is an AI model provided by mistral.", "family": "mistral-large", "id": "mistral-large-2512", "knowledge": "2024-11", "last_updated": "2025-12-02", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Mistral Large 3", "open_weights": true, "reasoning": false, "release_date": "2024-11-01", "temperature": true, "tool_call": true }, "mistral-large-latest": { "attachment": true, "cost": { "input": 0.5, "output": 1.5 }, "description": "Mistral Large (latest) is an AI model provided by mistral.", "family": "mistral-large", "id": "mistral-large-latest", "knowledge": "2024-11", "last_updated": "2025-12-02", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Mistral Large (latest)", "open_weights": true, "reasoning": false, "release_date": "2024-11-01", "temperature": true, "tool_call": true }, "mistral-medium-2505": { "attachment": true, "cost": { "input": 0.4, "output": 2 }, "description": "Mistral Medium 3 is an AI model provided by mistral.", "family": "mistral-medium", "id": "mistral-medium-2505", "knowledge": "2025-05", "last_updated": "2025-05-07", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Mistral Medium 3", "open_weights": false, "reasoning": false, "release_date": "2025-05-07", "temperature": true, "tool_call": true }, "mistral-medium-2508": { "attachment": true, "cost": { "input": 0.4, "output": 2 }, "description": "Mistral Medium 3.1 is an AI model provided by mistral.", "family": "mistral-medium", "id": "mistral-medium-2508", "knowledge": "2025-05", "last_updated": "2025-08-12", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Mistral Medium 3.1", "open_weights": false, "reasoning": false, "release_date": "2025-08-12", "temperature": true, "tool_call": true }, "mistral-medium-2604": { "attachment": true, "cost": { "input": 1.5, "output": 7.5 }, "description": "Mistral Medium 3.5 is an AI model provided by mistral.", "family": "mistral-medium", "id": "mistral-medium-2604", "last_updated": "2026-04-29", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Mistral Medium 3.5", "open_weights": true, "reasoning": true, "release_date": "2026-04-29", "structured_output": true, "temperature": true, "tool_call": true }, "mistral-medium-latest": { "attachment": true, "cost": { "input": 1.5, "output": 7.5 }, "description": "Mistral Medium (latest) is an AI model provided by mistral.", "family": "mistral-medium", "id": "mistral-medium-latest", "last_updated": "2026-04-29", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Mistral Medium (latest)", "open_weights": true, "reasoning": true, "release_date": "2026-04-29", "structured_output": true, "temperature": true, "tool_call": true }, "mistral-nemo": { "attachment": false, "cost": { "input": 0.15, "output": 0.15 }, "description": "Mistral Nemo is an AI model provided by mistral.", "family": "mistral-nemo", "id": "mistral-nemo", "knowledge": "2024-07", "last_updated": "2024-07-01", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral Nemo", "open_weights": true, "reasoning": false, "release_date": "2024-07-01", "temperature": true, "tool_call": true }, "mistral-small-2506": { "attachment": false, "cost": { "input": 0.1, "output": 0.3 }, "description": "Mistral Small 3.2 is an AI model provided by mistral.", "family": "mistral-small", "id": "mistral-small-2506", "knowledge": "2025-03", "last_updated": "2025-06-20", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Mistral Small 3.2", "open_weights": true, "reasoning": false, "release_date": "2025-06-20", "temperature": true, "tool_call": true }, "mistral-small-2603": { "attachment": true, "cost": { "input": 0.15, "output": 0.6 }, "description": "Mistral Small 4 is an AI model provided by mistral.", "family": "mistral-small", "id": "mistral-small-2603", "knowledge": "2025-06", "last_updated": "2026-03-16", "limit": { "context": 256000, "output": 256000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Mistral Small 4", "open_weights": true, "reasoning": true, "release_date": "2026-03-16", "temperature": true, "tool_call": true }, "mistral-small-latest": { "attachment": true, "cost": { "input": 0.15, "output": 0.6 }, "description": "Mistral Small (latest) is an AI model provided by mistral.", "family": "mistral-small", "id": "mistral-small-latest", "knowledge": "2025-06", "last_updated": "2026-03-16", "limit": { "context": 256000, "output": 256000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Mistral Small (latest)", "open_weights": true, "reasoning": true, "release_date": "2026-03-16", "temperature": true, "tool_call": true }, "open-mistral-7b": { "attachment": false, "cost": { "input": 0.25, "output": 0.25 }, "description": "Mistral 7B is an AI model provided by mistral.", "family": "mistral", "id": "open-mistral-7b", "knowledge": "2023-12", "last_updated": "2023-09-27", "limit": { "context": 8000, "output": 8000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral 7B", "open_weights": true, "reasoning": false, "release_date": "2023-09-27", "temperature": true, "tool_call": true }, "open-mixtral-8x22b": { "attachment": false, "cost": { "input": 2, "output": 6 }, "description": "Mixtral 8x22B is an AI model provided by mistral.", "family": "mixtral", "id": "open-mixtral-8x22b", "knowledge": "2024-04", "last_updated": "2024-04-17", "limit": { "context": 64000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mixtral 8x22B", "open_weights": true, "reasoning": false, "release_date": "2024-04-17", "temperature": true, "tool_call": true }, "open-mixtral-8x7b": { "attachment": false, "cost": { "input": 0.7, "output": 0.7 }, "description": "Mixtral 8x7B is an AI model provided by mistral.", "family": "mixtral", "id": "open-mixtral-8x7b", "knowledge": "2024-01", "last_updated": "2023-12-11", "limit": { "context": 32000, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mixtral 8x7B", "open_weights": true, "reasoning": false, "release_date": "2023-12-11", "temperature": true, "tool_call": true }, "pixtral-12b": { "attachment": true, "cost": { "input": 0.15, "output": 0.15 }, "description": "Pixtral 12B is an AI model provided by mistral.", "family": "pixtral", "id": "pixtral-12b", "knowledge": "2024-09", "last_updated": "2024-09-01", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Pixtral 12B", "open_weights": true, "reasoning": false, "release_date": "2024-09-01", "temperature": true, "tool_call": true }, "pixtral-large-latest": { "attachment": true, "cost": { "input": 2, "output": 6 }, "description": "Pixtral Large (latest) is an AI model provided by mistral.", "family": "pixtral", "id": "pixtral-large-latest", "knowledge": "2024-11", "last_updated": "2024-11-04", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Pixtral Large (latest)", "open_weights": true, "reasoning": false, "release_date": "2024-11-01", "temperature": true, "tool_call": true } }, "name": "Mistral", "npm": "@ai-sdk/mistral" }, "mixlayer": { "api": "https://models.mixlayer.ai/v1", "doc": "https://docs.mixlayer.com", "env": [ "MIXLAYER_API_KEY" ], "iconURL": "https://models.dev/logos/mixlayer.svg", "id": "mixlayer", "models": { "qwen/qwen3.5-122b-a10b": { "attachment": false, "cost": { "input": 0.4, "output": 3.2 }, "description": "Qwen3.5 122B A10B is an AI model provided by mixlayer.", "family": "qwen", "id": "qwen/qwen3.5-122b-a10b", "last_updated": "2026-03-18", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3.5 122B A10B", "open_weights": true, "reasoning": true, "release_date": "2026-03-18", "temperature": true, "tool_call": true }, "qwen/qwen3.5-27b": { "attachment": false, "cost": { "input": 0.3, "output": 2.4 }, "description": "Qwen3.5 27B is an AI model provided by mixlayer.", "family": "qwen", "id": "qwen/qwen3.5-27b", "last_updated": "2026-03-18", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3.5 27B", "open_weights": true, "reasoning": true, "release_date": "2026-03-18", "temperature": true, "tool_call": true }, "qwen/qwen3.5-35b-a3b": { "attachment": false, "cost": { "input": 0.25, "output": 1.3 }, "description": "Qwen3.5 35B A3B is an AI model provided by mixlayer.", "family": "qwen", "id": "qwen/qwen3.5-35b-a3b", "last_updated": "2026-03-18", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3.5 35B A3B", "open_weights": true, "reasoning": true, "release_date": "2026-03-18", "temperature": true, "tool_call": true }, "qwen/qwen3.5-397b-a17b": { "attachment": false, "cost": { "input": 0.6, "output": 3.6 }, "description": "Qwen3.5 397B A17B is an AI model provided by mixlayer.", "family": "qwen", "id": "qwen/qwen3.5-397b-a17b", "last_updated": "2026-03-18", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3.5 397B A17B", "open_weights": true, "reasoning": true, "release_date": "2026-03-18", "temperature": true, "tool_call": true }, "qwen/qwen3.5-9b": { "attachment": false, "cost": { "input": 0.1, "output": 0.4 }, "description": "Qwen3.5 9B is an AI model provided by mixlayer.", "family": "qwen", "id": "qwen/qwen3.5-9b", "last_updated": "2026-03-18", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3.5 9B", "open_weights": true, "reasoning": true, "release_date": "2026-03-18", "temperature": true, "tool_call": true } }, "name": "Mixlayer", "npm": "@ai-sdk/openai-compatible" }, "moark": { "api": "https://moark.com/v1", "doc": "https://moark.com/docs/openapi/v1#tag/%E6%96%87%E6%9C%AC%E7%94%9F%E6%88%90", "env": [ "MOARK_API_KEY" ], "iconURL": "https://models.dev/logos/moark.svg", "id": "moark", "models": { "GLM-4.7": { "attachment": false, "cost": { "input": 3.5, "output": 14 }, "description": "GLM-4.7 is an AI model provided by moark.", "family": "glm", "id": "GLM-4.7", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-04", "last_updated": "2025-12-22", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.7", "open_weights": true, "reasoning": true, "release_date": "2025-12-22", "temperature": true, "tool_call": true }, "MiniMax-M2.1": { "attachment": false, "cost": { "input": 2.1, "output": 8.4 }, "description": "MiniMax-M2.1 is an AI model provided by moark.", "family": "minimax", "id": "MiniMax-M2.1", "last_updated": "2025-12-23", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.1", "open_weights": true, "reasoning": true, "release_date": "2025-12-23", "temperature": true, "tool_call": true } }, "name": "Moark", "npm": "@ai-sdk/openai-compatible" }, "modelscope": { "api": "https://api-inference.modelscope.cn/v1", "doc": "https://modelscope.cn/docs/model-service/API-Inference/intro", "env": [ "MODELSCOPE_API_KEY" ], "iconURL": "https://models.dev/logos/modelscope.svg", "id": "modelscope", "lobeIcon": "ModelScope", "models": { "Qwen/Qwen3-235B-A22B-Instruct-2507": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Qwen3 235B A22B Instruct 2507 is an AI model provided by modelscope.", "family": "qwen", "id": "Qwen/Qwen3-235B-A22B-Instruct-2507", "knowledge": "2025-04", "last_updated": "2025-07-21", "limit": { "context": 262144, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 235B A22B Instruct 2507", "open_weights": true, "reasoning": false, "release_date": "2025-04-28", "temperature": true, "tool_call": true }, "Qwen/Qwen3-235B-A22B-Thinking-2507": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Qwen3-235B-A22B-Thinking-2507 is an AI model provided by modelscope.", "family": "qwen", "id": "Qwen/Qwen3-235B-A22B-Thinking-2507", "knowledge": "2025-04", "last_updated": "2025-07-25", "limit": { "context": 262144, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3-235B-A22B-Thinking-2507", "open_weights": true, "reasoning": true, "release_date": "2025-07-25", "temperature": true, "tool_call": true }, "Qwen/Qwen3-30B-A3B-Instruct-2507": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Qwen3 30B A3B Instruct 2507 is an AI model provided by modelscope.", "family": "qwen", "id": "Qwen/Qwen3-30B-A3B-Instruct-2507", "knowledge": "2025-04", "last_updated": "2025-07-30", "limit": { "context": 262144, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 30B A3B Instruct 2507", "open_weights": true, "reasoning": false, "release_date": "2025-07-30", "temperature": true, "tool_call": true }, "Qwen/Qwen3-30B-A3B-Thinking-2507": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Qwen3 30B A3B Thinking 2507 is an AI model provided by modelscope.", "family": "qwen", "id": "Qwen/Qwen3-30B-A3B-Thinking-2507", "knowledge": "2025-04", "last_updated": "2025-07-30", "limit": { "context": 262144, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 30B A3B Thinking 2507", "open_weights": true, "reasoning": true, "release_date": "2025-07-30", "temperature": true, "tool_call": true }, "Qwen/Qwen3-Coder-30B-A3B-Instruct": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Qwen3 Coder 30B A3B Instruct is an AI model provided by modelscope.", "family": "qwen", "id": "Qwen/Qwen3-Coder-30B-A3B-Instruct", "knowledge": "2025-04", "last_updated": "2025-07-31", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Coder 30B A3B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-07-31", "temperature": true, "tool_call": true }, "ZhipuAI/GLM-4.5": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "GLM-4.5 is an AI model provided by modelscope.", "family": "glm", "id": "ZhipuAI/GLM-4.5", "knowledge": "2025-04", "last_updated": "2025-07-28", "limit": { "context": 131072, "output": 98304 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.5", "open_weights": true, "reasoning": true, "release_date": "2025-07-28", "temperature": true, "tool_call": true }, "ZhipuAI/GLM-4.6": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "GLM-4.6 is an AI model provided by modelscope.", "family": "glm", "id": "ZhipuAI/GLM-4.6", "knowledge": "2025-07", "last_updated": "2025-09-30", "limit": { "context": 202752, "output": 98304 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.6", "open_weights": true, "reasoning": true, "release_date": "2025-09-30", "temperature": true, "tool_call": true } }, "name": "ModelScope", "npm": "@ai-sdk/openai-compatible" }, "moonshotai": { "api": "https://api.moonshot.ai/v1", "doc": "https://platform.moonshot.ai/docs/api/chat", "env": [ "MOONSHOT_API_KEY" ], "iconURL": "https://models.dev/logos/moonshotai.svg", "id": "moonshotai", "lobeIcon": "Moonshot.Color", "models": { "kimi-k2-0711-preview": { "attachment": false, "cost": { "cache_read": 0.15, "input": 0.6, "output": 2.5 }, "description": "Kimi K2 0711 is an AI model provided by moonshotai.", "family": "kimi", "id": "kimi-k2-0711-preview", "knowledge": "2024-10", "last_updated": "2025-07-14", "limit": { "context": 131072, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 0711", "open_weights": true, "reasoning": false, "release_date": "2025-07-14", "temperature": true, "tool_call": true }, "kimi-k2-0905-preview": { "attachment": false, "cost": { "cache_read": 0.15, "input": 0.6, "output": 2.5 }, "description": "Kimi K2 0905 is an AI model provided by moonshotai.", "family": "kimi", "id": "kimi-k2-0905-preview", "knowledge": "2024-10", "last_updated": "2025-09-05", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 0905", "open_weights": true, "reasoning": false, "release_date": "2025-09-05", "temperature": true, "tool_call": true }, "kimi-k2-thinking": { "attachment": false, "cost": { "cache_read": 0.15, "input": 0.6, "output": 2.5 }, "description": "Kimi K2 Thinking is an AI model provided by moonshotai.", "family": "kimi-thinking", "id": "kimi-k2-thinking", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-08", "last_updated": "2025-11-06", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 Thinking", "open_weights": true, "reasoning": true, "release_date": "2025-11-06", "temperature": true, "tool_call": true }, "kimi-k2-thinking-turbo": { "attachment": false, "cost": { "cache_read": 0.15, "input": 1.15, "output": 8 }, "description": "Kimi K2 Thinking Turbo is an AI model provided by moonshotai.", "family": "kimi-thinking", "id": "kimi-k2-thinking-turbo", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-08", "last_updated": "2025-11-06", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 Thinking Turbo", "open_weights": true, "reasoning": true, "release_date": "2025-11-06", "temperature": true, "tool_call": true }, "kimi-k2-turbo-preview": { "attachment": false, "cost": { "cache_read": 0.6, "input": 2.4, "output": 10 }, "description": "Kimi K2 Turbo is an AI model provided by moonshotai.", "family": "kimi", "id": "kimi-k2-turbo-preview", "knowledge": "2024-10", "last_updated": "2025-09-05", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 Turbo", "open_weights": true, "reasoning": false, "release_date": "2025-09-05", "temperature": true, "tool_call": true }, "kimi-k2.5": { "attachment": false, "cost": { "cache_read": 0.1, "input": 0.6, "output": 3 }, "description": "Kimi K2.5 is an AI model provided by moonshotai.", "family": "kimi-k2.5", "id": "kimi-k2.5", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-01", "last_updated": "2026-01", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Kimi K2.5", "open_weights": true, "reasoning": true, "release_date": "2026-01", "structured_output": true, "temperature": false, "tool_call": true }, "kimi-k2.6": { "attachment": true, "cost": { "cache_read": 0.16, "input": 0.95, "output": 4 }, "description": "Kimi K2.6 is an AI model provided by moonshotai.", "family": "kimi-k2.6", "id": "kimi-k2.6", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-01", "last_updated": "2026-04-21", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Kimi K2.6", "open_weights": true, "reasoning": true, "release_date": "2026-04-21", "structured_output": true, "temperature": true, "tool_call": true } }, "name": "Moonshot AI", "npm": "@ai-sdk/openai-compatible" }, "moonshotai-cn": { "api": "https://api.moonshot.cn/v1", "doc": "https://platform.moonshot.cn/docs/api/chat", "env": [ "MOONSHOT_API_KEY" ], "iconURL": "https://models.dev/logos/moonshotai-cn.svg", "id": "moonshotai-cn", "lobeIcon": "Moonshot.Color", "models": { "kimi-k2-0711-preview": { "attachment": false, "cost": { "cache_read": 0.15, "input": 0.6, "output": 2.5 }, "description": "Kimi K2 0711 is an AI model provided by moonshotai-cn.", "family": "kimi", "id": "kimi-k2-0711-preview", "knowledge": "2024-10", "last_updated": "2025-07-14", "limit": { "context": 131072, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 0711", "open_weights": true, "reasoning": false, "release_date": "2025-07-14", "temperature": true, "tool_call": true }, "kimi-k2-0905-preview": { "attachment": false, "cost": { "cache_read": 0.15, "input": 0.6, "output": 2.5 }, "description": "Kimi K2 0905 is an AI model provided by moonshotai-cn.", "family": "kimi", "id": "kimi-k2-0905-preview", "knowledge": "2024-10", "last_updated": "2025-09-05", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 0905", "open_weights": true, "reasoning": false, "release_date": "2025-09-05", "temperature": true, "tool_call": true }, "kimi-k2-thinking": { "attachment": false, "cost": { "cache_read": 0.15, "input": 0.6, "output": 2.5 }, "description": "Kimi K2 Thinking is an AI model provided by moonshotai-cn.", "family": "kimi-thinking", "id": "kimi-k2-thinking", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-08", "last_updated": "2025-11-06", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 Thinking", "open_weights": true, "reasoning": true, "release_date": "2025-11-06", "temperature": true, "tool_call": true }, "kimi-k2-thinking-turbo": { "attachment": false, "cost": { "cache_read": 0.15, "input": 1.15, "output": 8 }, "description": "Kimi K2 Thinking Turbo is an AI model provided by moonshotai-cn.", "family": "kimi-thinking", "id": "kimi-k2-thinking-turbo", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-08", "last_updated": "2025-11-06", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 Thinking Turbo", "open_weights": true, "reasoning": true, "release_date": "2025-11-06", "temperature": true, "tool_call": true }, "kimi-k2-turbo-preview": { "attachment": false, "cost": { "cache_read": 0.6, "input": 2.4, "output": 10 }, "description": "Kimi K2 Turbo is an AI model provided by moonshotai-cn.", "family": "kimi", "id": "kimi-k2-turbo-preview", "knowledge": "2024-10", "last_updated": "2025-09-05", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 Turbo", "open_weights": true, "reasoning": false, "release_date": "2025-09-05", "temperature": true, "tool_call": true }, "kimi-k2.5": { "attachment": false, "cost": { "cache_read": 0.1, "input": 0.6, "output": 3 }, "description": "Kimi K2.5 is an AI model provided by moonshotai-cn.", "family": "kimi-k2.5", "id": "kimi-k2.5", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-01", "last_updated": "2026-01", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Kimi K2.5", "open_weights": true, "reasoning": true, "release_date": "2026-01", "structured_output": true, "temperature": false, "tool_call": true }, "kimi-k2.6": { "attachment": true, "cost": { "cache_read": 0.16, "input": 0.95, "output": 4 }, "description": "Kimi K2.6 is an AI model provided by moonshotai-cn.", "family": "kimi-k2.6", "id": "kimi-k2.6", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-01", "last_updated": "2026-04-21", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Kimi K2.6", "open_weights": true, "reasoning": true, "release_date": "2026-04-21", "structured_output": true, "temperature": true, "tool_call": true } }, "name": "Moonshot AI (China)", "npm": "@ai-sdk/openai-compatible" }, "morph": { "api": "https://api.morphllm.com/v1", "doc": "https://docs.morphllm.com/api-reference/introduction", "env": [ "MORPH_API_KEY" ], "iconURL": "https://models.dev/logos/morph.svg", "id": "morph", "lobeIcon": "Morph", "models": { "auto": { "attachment": false, "cost": { "input": 0.85, "output": 1.55 }, "description": "Auto is an AI model provided by morph.", "family": "auto", "id": "auto", "last_updated": "2024-06-01", "limit": { "context": 32000, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Auto", "open_weights": false, "reasoning": false, "release_date": "2024-06-01", "temperature": false, "tool_call": false }, "morph-v3-fast": { "attachment": false, "cost": { "input": 0.8, "output": 1.2 }, "description": "Morph v3 Fast is an AI model provided by morph.", "family": "morph", "id": "morph-v3-fast", "last_updated": "2024-08-15", "limit": { "context": 16000, "output": 16000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Morph v3 Fast", "open_weights": false, "reasoning": false, "release_date": "2024-08-15", "temperature": false, "tool_call": false }, "morph-v3-large": { "attachment": false, "cost": { "input": 0.9, "output": 1.9 }, "description": "Morph v3 Large is an AI model provided by morph.", "family": "morph", "id": "morph-v3-large", "last_updated": "2024-08-15", "limit": { "context": 32000, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Morph v3 Large", "open_weights": false, "reasoning": false, "release_date": "2024-08-15", "temperature": false, "tool_call": false } }, "name": "Morph", "npm": "@ai-sdk/openai-compatible" }, "nano-gpt": { "api": "https://nano-gpt.com/api/v1", "doc": "https://docs.nano-gpt.com", "env": [ "NANO_GPT_API_KEY" ], "iconURL": "https://models.dev/logos/nano-gpt.svg", "id": "nano-gpt", "models": { "Alibaba-NLP/Tongyi-DeepResearch-30B-A3B": { "attachment": false, "cost": { "input": 0.08, "output": 0.24000000000000002 }, "description": "Tongyi DeepResearch 30B A3B is an AI model provided by nano-gpt.", "family": "yi", "id": "Alibaba-NLP/Tongyi-DeepResearch-30B-A3B", "last_updated": "2025-08-26", "limit": { "context": 128000, "input": 128000, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Tongyi DeepResearch 30B A3B", "open_weights": false, "reasoning": false, "release_date": "2025-08-26", "structured_output": false, "tool_call": false }, "Baichuan-M2": { "attachment": false, "cost": { "input": 15.73, "output": 15.73 }, "description": "Baichuan M2 32B Medical is an AI model provided by nano-gpt.", "id": "Baichuan-M2", "last_updated": "2025-08-19", "limit": { "context": 32768, "input": 32768, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Baichuan M2 32B Medical", "open_weights": false, "reasoning": false, "release_date": "2025-08-19", "structured_output": false, "tool_call": false }, "Baichuan4-Air": { "attachment": false, "cost": { "input": 0.157, "output": 0.157 }, "description": "Baichuan 4 Air is an AI model provided by nano-gpt.", "id": "Baichuan4-Air", "last_updated": "2025-08-19", "limit": { "context": 32768, "input": 32768, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Baichuan 4 Air", "open_weights": false, "reasoning": false, "release_date": "2025-08-19", "structured_output": false, "tool_call": false }, "Baichuan4-Turbo": { "attachment": false, "cost": { "input": 2.42, "output": 2.42 }, "description": "Baichuan 4 Turbo is an AI model provided by nano-gpt.", "id": "Baichuan4-Turbo", "last_updated": "2025-08-19", "limit": { "context": 128000, "input": 128000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Baichuan 4 Turbo", "open_weights": false, "reasoning": false, "release_date": "2025-08-19", "structured_output": false, "tool_call": false }, "CrucibleLab/L3.3-70B-Loki-V2.0": { "attachment": false, "cost": { "input": 0.49299999999999994, "output": 0.49299999999999994 }, "description": "L3.3 70B Loki v2.0 is an AI model provided by nano-gpt.", "family": "llama", "id": "CrucibleLab/L3.3-70B-Loki-V2.0", "last_updated": "2026-01-22", "limit": { "context": 16384, "input": 16384, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "L3.3 70B Loki v2.0", "open_weights": false, "reasoning": false, "release_date": "2026-01-22", "structured_output": false, "tool_call": false }, "Doctor-Shotgun/MS3.2-24B-Magnum-Diamond": { "attachment": false, "cost": { "input": 0.49299999999999994, "output": 0.49299999999999994 }, "description": "MS3.2 24B Magnum Diamond is an AI model provided by nano-gpt.", "family": "mistral", "id": "Doctor-Shotgun/MS3.2-24B-Magnum-Diamond", "last_updated": "2025-11-24", "limit": { "context": 16384, "input": 16384, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MS3.2 24B Magnum Diamond", "open_weights": false, "reasoning": false, "release_date": "2025-11-24", "structured_output": false, "tool_call": false }, "EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.0": { "attachment": false, "cost": { "input": 2.006, "output": 2.006 }, "description": "EVA Llama 3.33 70B is an AI model provided by nano-gpt.", "family": "llama", "id": "EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.0", "last_updated": "2025-07-26", "limit": { "context": 16384, "input": 16384, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "EVA Llama 3.33 70B", "open_weights": false, "reasoning": false, "release_date": "2025-07-26", "structured_output": false, "tool_call": false }, "EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1": { "attachment": false, "cost": { "input": 2.006, "output": 2.006 }, "description": "EVA-LLaMA-3.33-70B-v0.1 is an AI model provided by nano-gpt.", "family": "llama", "id": "EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1", "last_updated": "2025-09-25", "limit": { "context": 16384, "input": 16384, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "EVA-LLaMA-3.33-70B-v0.1", "open_weights": false, "reasoning": false, "release_date": "2025-09-25", "structured_output": false, "tool_call": false }, "EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2": { "attachment": false, "cost": { "input": 0.7989999999999999, "output": 0.7989999999999999 }, "description": "EVA-Qwen2.5-32B-v0.2 is an AI model provided by nano-gpt.", "family": "qwen", "id": "EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2", "last_updated": "2025-07-26", "limit": { "context": 16384, "input": 16384, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "EVA-Qwen2.5-32B-v0.2", "open_weights": false, "reasoning": false, "release_date": "2025-07-26", "structured_output": false, "tool_call": false }, "EVA-UNIT-01/EVA-Qwen2.5-72B-v0.2": { "attachment": false, "cost": { "input": 0.7989999999999999, "output": 0.7989999999999999 }, "description": "EVA-Qwen2.5-72B-v0.2 is an AI model provided by nano-gpt.", "family": "qwen", "id": "EVA-UNIT-01/EVA-Qwen2.5-72B-v0.2", "last_updated": "2025-09-25", "limit": { "context": 16384, "input": 16384, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "EVA-Qwen2.5-72B-v0.2", "open_weights": false, "reasoning": false, "release_date": "2025-09-25", "structured_output": false, "tool_call": false }, "Envoid/Llama-3.05-NT-Storybreaker-Ministral-70B": { "attachment": false, "cost": { "input": 0.49299999999999994, "output": 0.49299999999999994 }, "description": "Llama 3.05 Storybreaker Ministral 70b is an AI model provided by nano-gpt.", "family": "llama", "id": "Envoid/Llama-3.05-NT-Storybreaker-Ministral-70B", "last_updated": "2024-12-01", "limit": { "context": 16384, "input": 16384, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.05 Storybreaker Ministral 70b", "open_weights": false, "reasoning": false, "release_date": "2024-12-01", "structured_output": false, "tool_call": false }, "Envoid/Llama-3.05-Nemotron-Tenyxchat-Storybreaker-70B": { "attachment": false, "cost": { "input": 0.49299999999999994, "output": 0.49299999999999994 }, "description": "Nemotron Tenyxchat Storybreaker 70b is an AI model provided by nano-gpt.", "family": "nemotron", "id": "Envoid/Llama-3.05-Nemotron-Tenyxchat-Storybreaker-70B", "last_updated": "2024-12-01", "limit": { "context": 16384, "input": 16384, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Nemotron Tenyxchat Storybreaker 70b", "open_weights": false, "reasoning": false, "release_date": "2024-12-01", "structured_output": false, "tool_call": false }, "GLM-4.5-Air-Derestricted": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "GLM 4.5 Air Derestricted is an AI model provided by nano-gpt.", "id": "GLM-4.5-Air-Derestricted", "last_updated": "2025-07-28", "limit": { "context": 202600, "input": 202600, "output": 98304 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.5 Air Derestricted", "open_weights": false, "reasoning": false, "release_date": "2025-07-28", "structured_output": false, "tool_call": false }, "GLM-4.5-Air-Derestricted-Iceblink": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "GLM 4.5 Air Derestricted Iceblink is an AI model provided by nano-gpt.", "id": "GLM-4.5-Air-Derestricted-Iceblink", "last_updated": "2025-07-28", "limit": { "context": 131072, "input": 131072, "output": 98304 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.5 Air Derestricted Iceblink", "open_weights": false, "reasoning": false, "release_date": "2025-07-28", "structured_output": false, "tool_call": false }, "GLM-4.5-Air-Derestricted-Iceblink-ReExtract": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "GLM 4.5 Air Derestricted Iceblink ReExtract is an AI model provided by nano-gpt.", "id": "GLM-4.5-Air-Derestricted-Iceblink-ReExtract", "last_updated": "2025-12-12", "limit": { "context": 131072, "input": 131072, "output": 98304 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.5 Air Derestricted Iceblink ReExtract", "open_weights": false, "reasoning": false, "release_date": "2025-12-12", "structured_output": false, "tool_call": false }, "GLM-4.5-Air-Derestricted-Iceblink-v2": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "GLM 4.5 Air Derestricted Iceblink v2 is an AI model provided by nano-gpt.", "id": "GLM-4.5-Air-Derestricted-Iceblink-v2", "last_updated": "2025-07-28", "limit": { "context": 158600, "input": 158600, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.5 Air Derestricted Iceblink v2", "open_weights": false, "reasoning": false, "release_date": "2025-07-28", "structured_output": false, "tool_call": false }, "GLM-4.5-Air-Derestricted-Iceblink-v2-ReExtract": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "GLM 4.5 Air Derestricted Iceblink v2 ReExtract is an AI model provided by nano-gpt.", "id": "GLM-4.5-Air-Derestricted-Iceblink-v2-ReExtract", "last_updated": "2025-12-12", "limit": { "context": 131072, "input": 131072, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.5 Air Derestricted Iceblink v2 ReExtract", "open_weights": false, "reasoning": false, "release_date": "2025-12-12", "structured_output": false, "tool_call": false }, "GLM-4.5-Air-Derestricted-Steam": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "GLM 4.5 Air Derestricted Steam is an AI model provided by nano-gpt.", "id": "GLM-4.5-Air-Derestricted-Steam", "last_updated": "2025-07-28", "limit": { "context": 220600, "input": 220600, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.5 Air Derestricted Steam", "open_weights": false, "reasoning": false, "release_date": "2025-07-28", "structured_output": false, "tool_call": false }, "GLM-4.5-Air-Derestricted-Steam-ReExtract": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "GLM 4.5 Air Derestricted Steam ReExtract is an AI model provided by nano-gpt.", "id": "GLM-4.5-Air-Derestricted-Steam-ReExtract", "last_updated": "2025-12-12", "limit": { "context": 131072, "input": 131072, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.5 Air Derestricted Steam ReExtract", "open_weights": false, "reasoning": false, "release_date": "2025-12-12", "structured_output": false, "tool_call": false }, "GLM-4.6-Derestricted-v5": { "attachment": false, "cost": { "input": 0.4, "output": 1.5 }, "description": "GLM 4.6 Derestricted v5 is an AI model provided by nano-gpt.", "id": "GLM-4.6-Derestricted-v5", "last_updated": "2025-12-23", "limit": { "context": 131072, "input": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.6 Derestricted v5", "open_weights": false, "reasoning": false, "release_date": "2025-12-23", "structured_output": false, "tool_call": false }, "GalrionSoftworks/MN-LooseCannon-12B-v1": { "attachment": false, "cost": { "input": 0.49299999999999994, "output": 0.49299999999999994 }, "description": "MN-LooseCannon-12B-v1 is an AI model provided by nano-gpt.", "family": "mistral-nemo", "id": "GalrionSoftworks/MN-LooseCannon-12B-v1", "last_updated": "2024-07-01", "limit": { "context": 16384, "input": 16384, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MN-LooseCannon-12B-v1", "open_weights": false, "reasoning": false, "release_date": "2024-07-01", "structured_output": false, "tool_call": false }, "Gemma-3-27B-ArliAI-RPMax-v3": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "Gemma 3 27B RPMax v3 is an AI model provided by nano-gpt.", "id": "Gemma-3-27B-ArliAI-RPMax-v3", "last_updated": "2025-07-03", "limit": { "context": 32768, "input": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Gemma 3 27B RPMax v3", "open_weights": false, "reasoning": false, "release_date": "2025-07-03", "structured_output": false, "tool_call": false }, "Gemma-3-27B-Big-Tiger-v3": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "Gemma 3 27B Big Tiger v3 is an AI model provided by nano-gpt.", "id": "Gemma-3-27B-Big-Tiger-v3", "last_updated": "2025-08-08", "limit": { "context": 32768, "input": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Gemma 3 27B Big Tiger v3", "open_weights": false, "reasoning": false, "release_date": "2025-08-08", "structured_output": false, "tool_call": false }, "Gemma-3-27B-CardProjector-v4": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "Gemma 3 27B CardProjector v4 is an AI model provided by nano-gpt.", "id": "Gemma-3-27B-CardProjector-v4", "last_updated": "2025-03-10", "limit": { "context": 32768, "input": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Gemma 3 27B CardProjector v4", "open_weights": false, "reasoning": false, "release_date": "2025-03-10", "structured_output": false, "tool_call": false }, "Gemma-3-27B-Glitter": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "Gemma 3 27B Glitter is an AI model provided by nano-gpt.", "id": "Gemma-3-27B-Glitter", "last_updated": "2025-03-10", "limit": { "context": 32768, "input": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Gemma 3 27B Glitter", "open_weights": false, "reasoning": false, "release_date": "2025-03-10", "structured_output": false, "tool_call": false }, "Gemma-3-27B-Nidum-Uncensored": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "Gemma 3 27B Nidum Uncensored is an AI model provided by nano-gpt.", "id": "Gemma-3-27B-Nidum-Uncensored", "last_updated": "2025-08-08", "limit": { "context": 32768, "input": 32768, "output": 96000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Gemma 3 27B Nidum Uncensored", "open_weights": false, "reasoning": false, "release_date": "2025-08-08", "structured_output": false, "tool_call": false }, "Gemma-3-27B-it": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "Gemma 3 27B IT is an AI model provided by nano-gpt.", "id": "Gemma-3-27B-it", "last_updated": "2025-03-10", "limit": { "context": 32768, "input": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Gemma 3 27B IT", "open_weights": false, "reasoning": false, "release_date": "2025-03-10", "structured_output": false, "tool_call": false }, "Gemma-3-27B-it-Abliterated": { "attachment": false, "cost": { "input": 0.42, "output": 0.42 }, "description": "Gemma 3 27B IT Abliterated is an AI model provided by nano-gpt.", "id": "Gemma-3-27B-it-Abliterated", "last_updated": "2025-07-03", "limit": { "context": 32768, "input": 32768, "output": 96000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Gemma 3 27B IT Abliterated", "open_weights": false, "reasoning": false, "release_date": "2025-07-03", "structured_output": false, "tool_call": false }, "Gryphe/MythoMax-L2-13b": { "attachment": false, "cost": { "input": 0.1003, "output": 0.1003 }, "description": "MythoMax 13B is an AI model provided by nano-gpt.", "family": "llama", "id": "Gryphe/MythoMax-L2-13b", "last_updated": "2025-08-08", "limit": { "context": 4000, "input": 4000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MythoMax 13B", "open_weights": false, "reasoning": false, "release_date": "2025-08-08", "structured_output": false, "tool_call": false }, "Infermatic/MN-12B-Inferor-v0.0": { "attachment": false, "cost": { "input": 0.25499999999999995, "output": 0.49299999999999994 }, "description": "Mistral Nemo Inferor 12B is an AI model provided by nano-gpt.", "family": "mistral-nemo", "id": "Infermatic/MN-12B-Inferor-v0.0", "last_updated": "2024-07-01", "limit": { "context": 16384, "input": 16384, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral Nemo Inferor 12B", "open_weights": false, "reasoning": false, "release_date": "2024-07-01", "structured_output": false, "tool_call": false }, "KAT-Coder-Air-V1": { "attachment": false, "cost": { "input": 0.1, "output": 0.2 }, "description": "KAT Coder Air V1 is an AI model provided by nano-gpt.", "id": "KAT-Coder-Air-V1", "last_updated": "2025-10-28", "limit": { "context": 128000, "input": 128000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "KAT Coder Air V1", "open_weights": false, "reasoning": false, "release_date": "2025-10-28", "structured_output": false, "tool_call": false }, "KAT-Coder-Exp-72B-1010": { "attachment": false, "cost": { "input": 0.1, "output": 0.2 }, "description": "KAT Coder Exp 72B 1010 is an AI model provided by nano-gpt.", "id": "KAT-Coder-Exp-72B-1010", "last_updated": "2025-10-28", "limit": { "context": 128000, "input": 128000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "KAT Coder Exp 72B 1010", "open_weights": false, "reasoning": false, "release_date": "2025-10-28", "structured_output": false, "tool_call": false }, "KAT-Coder-Pro-V1": { "attachment": false, "cost": { "input": 1.5, "output": 6 }, "description": "KAT Coder Pro V1 is an AI model provided by nano-gpt.", "id": "KAT-Coder-Pro-V1", "last_updated": "2025-10-28", "limit": { "context": 256000, "input": 256000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "KAT Coder Pro V1", "open_weights": false, "reasoning": false, "release_date": "2025-10-28", "structured_output": false, "tool_call": false }, "LLM360/K2-Think": { "attachment": false, "cost": { "input": 0.17, "output": 0.68 }, "description": "K2-Think is an AI model provided by nano-gpt.", "family": "kimi-thinking", "id": "LLM360/K2-Think", "last_updated": "2025-07-26", "limit": { "context": 128000, "input": 128000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "K2-Think", "open_weights": false, "reasoning": false, "release_date": "2025-07-26", "structured_output": false, "tool_call": false }, "LatitudeGames/Wayfarer-Large-70B-Llama-3.3": { "attachment": false, "cost": { "input": 0.700000007, "output": 0.700000007 }, "description": "Llama 3.3 70B Wayfarer is an AI model provided by nano-gpt.", "family": "llama", "id": "LatitudeGames/Wayfarer-Large-70B-Llama-3.3", "last_updated": "2025-02-20", "limit": { "context": 16384, "input": 16384, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B Wayfarer", "open_weights": false, "reasoning": false, "release_date": "2025-02-20", "structured_output": false, "tool_call": false }, "Llama-3.3+(3.1v3.3)-70B-Hanami-x1": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "Llama 3.3+ 70B Hanami x1 is an AI model provided by nano-gpt.", "id": "Llama-3.3+(3.1v3.3)-70B-Hanami-x1", "last_updated": "2024-12-06", "limit": { "context": 32768, "input": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3+ 70B Hanami x1", "open_weights": false, "reasoning": false, "release_date": "2024-12-06", "structured_output": false, "tool_call": false }, "Llama-3.3+(3.1v3.3)-70B-New-Dawn-v1.1": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "Llama 3.3+ 70B New Dawn v1.1 is an AI model provided by nano-gpt.", "id": "Llama-3.3+(3.1v3.3)-70B-New-Dawn-v1.1", "last_updated": "2024-12-06", "limit": { "context": 32768, "input": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3+ 70B New Dawn v1.1", "open_weights": false, "reasoning": false, "release_date": "2024-12-06", "structured_output": false, "tool_call": false }, "Llama-3.3+(3v3.3)-70B-TenyxChat-DaybreakStorywriter": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "Llama 3.3+ 70B TenyxChat DaybreakStorywriter is an AI model provided by nano-gpt.", "id": "Llama-3.3+(3v3.3)-70B-TenyxChat-DaybreakStorywriter", "last_updated": "2024-12-06", "limit": { "context": 32768, "input": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3+ 70B TenyxChat DaybreakStorywriter", "open_weights": false, "reasoning": false, "release_date": "2024-12-06", "structured_output": false, "tool_call": false }, "Llama-3.3-70B-Anthrobomination": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "Llama 3.3 70B Anthrobomination is an AI model provided by nano-gpt.", "id": "Llama-3.3-70B-Anthrobomination", "last_updated": "2024-12-06", "limit": { "context": 32768, "input": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B Anthrobomination", "open_weights": false, "reasoning": false, "release_date": "2024-12-06", "structured_output": false, "tool_call": false }, "Llama-3.3-70B-Argunaut-1-SFT": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "Llama 3.3 70B Argunaut 1 SFT is an AI model provided by nano-gpt.", "id": "Llama-3.3-70B-Argunaut-1-SFT", "last_updated": "2024-12-06", "limit": { "context": 32768, "input": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B Argunaut 1 SFT", "open_weights": false, "reasoning": false, "release_date": "2024-12-06", "structured_output": false, "tool_call": false }, "Llama-3.3-70B-ArliAI-RPMax-v1.4": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "Llama 3.3 70B RPMax v1.4 is an AI model provided by nano-gpt.", "id": "Llama-3.3-70B-ArliAI-RPMax-v1.4", "last_updated": "2024-12-06", "limit": { "context": 32768, "input": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B RPMax v1.4", "open_weights": false, "reasoning": false, "release_date": "2024-12-06", "structured_output": false, "tool_call": false }, "Llama-3.3-70B-ArliAI-RPMax-v2": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "Llama 3.3 70B ArliAI RPMax v2 is an AI model provided by nano-gpt.", "id": "Llama-3.3-70B-ArliAI-RPMax-v2", "last_updated": "2025-08-08", "limit": { "context": 32768, "input": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B ArliAI RPMax v2", "open_weights": false, "reasoning": false, "release_date": "2025-08-08", "structured_output": false, "tool_call": false }, "Llama-3.3-70B-ArliAI-RPMax-v3": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "Llama 3.3 70B ArliAI RPMax v3 is an AI model provided by nano-gpt.", "id": "Llama-3.3-70B-ArliAI-RPMax-v3", "last_updated": "2024-12-06", "limit": { "context": 32768, "input": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B ArliAI RPMax v3", "open_weights": false, "reasoning": false, "release_date": "2024-12-06", "structured_output": false, "tool_call": false }, "Llama-3.3-70B-Aurora-Borealis": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "Llama 3.3 70B Aurora Borealis is an AI model provided by nano-gpt.", "id": "Llama-3.3-70B-Aurora-Borealis", "last_updated": "2024-12-06", "limit": { "context": 32768, "input": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B Aurora Borealis", "open_weights": false, "reasoning": false, "release_date": "2024-12-06", "structured_output": false, "tool_call": false }, "Llama-3.3-70B-Bigger-Body": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "Llama 3.3 70B Bigger Body is an AI model provided by nano-gpt.", "id": "Llama-3.3-70B-Bigger-Body", "last_updated": "2024-12-06", "limit": { "context": 32768, "input": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B Bigger Body", "open_weights": false, "reasoning": false, "release_date": "2024-12-06", "structured_output": false, "tool_call": false }, "Llama-3.3-70B-Cirrus-x1": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "Llama 3.3 70B Cirrus x1 is an AI model provided by nano-gpt.", "id": "Llama-3.3-70B-Cirrus-x1", "last_updated": "2024-12-06", "limit": { "context": 32768, "input": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B Cirrus x1", "open_weights": false, "reasoning": false, "release_date": "2024-12-06", "structured_output": false, "tool_call": false }, "Llama-3.3-70B-Cu-Mai-R1": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "Llama 3.3 70B Cu Mai R1 is an AI model provided by nano-gpt.", "id": "Llama-3.3-70B-Cu-Mai-R1", "last_updated": "2024-12-06", "limit": { "context": 32768, "input": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B Cu Mai R1", "open_weights": false, "reasoning": false, "release_date": "2024-12-06", "structured_output": false, "tool_call": false }, "Llama-3.3-70B-Damascus-R1": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "Damascus R1 is an AI model provided by nano-gpt.", "id": "Llama-3.3-70B-Damascus-R1", "last_updated": "2024-12-06", "limit": { "context": 32768, "input": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Damascus R1", "open_weights": false, "reasoning": false, "release_date": "2024-12-06", "structured_output": false, "tool_call": false }, "Llama-3.3-70B-Dark-Ages-v0.1": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "Llama 3.3 70B Dark Ages v0.1 is an AI model provided by nano-gpt.", "id": "Llama-3.3-70B-Dark-Ages-v0.1", "last_updated": "2024-12-06", "limit": { "context": 32768, "input": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B Dark Ages v0.1", "open_weights": false, "reasoning": false, "release_date": "2024-12-06", "structured_output": false, "tool_call": false }, "Llama-3.3-70B-Electra-R1": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "Llama 3.3 70B Electra R1 is an AI model provided by nano-gpt.", "id": "Llama-3.3-70B-Electra-R1", "last_updated": "2024-12-06", "limit": { "context": 32768, "input": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B Electra R1", "open_weights": false, "reasoning": false, "release_date": "2024-12-06", "structured_output": false, "tool_call": false }, "Llama-3.3-70B-Electranova-v1.0": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "Llama 3.3 70B Electranova v1.0 is an AI model provided by nano-gpt.", "id": "Llama-3.3-70B-Electranova-v1.0", "last_updated": "2024-12-06", "limit": { "context": 32768, "input": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B Electranova v1.0", "open_weights": false, "reasoning": false, "release_date": "2024-12-06", "structured_output": false, "tool_call": false }, "Llama-3.3-70B-Fallen-R1-v1": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "Llama 3.3 70B Fallen R1 v1 is an AI model provided by nano-gpt.", "id": "Llama-3.3-70B-Fallen-R1-v1", "last_updated": "2024-12-06", "limit": { "context": 32768, "input": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B Fallen R1 v1", "open_weights": false, "reasoning": false, "release_date": "2024-12-06", "structured_output": false, "tool_call": false }, "Llama-3.3-70B-Fallen-v1": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "Llama 3.3 70B Fallen v1 is an AI model provided by nano-gpt.", "id": "Llama-3.3-70B-Fallen-v1", "last_updated": "2024-12-06", "limit": { "context": 32768, "input": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B Fallen v1", "open_weights": false, "reasoning": false, "release_date": "2024-12-06", "structured_output": false, "tool_call": false }, "Llama-3.3-70B-Forgotten-Abomination-v5.0": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "Llama 3.3 70B Forgotten Abomination v5.0 is an AI model provided by nano-gpt.", "id": "Llama-3.3-70B-Forgotten-Abomination-v5.0", "last_updated": "2024-12-06", "limit": { "context": 32768, "input": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B Forgotten Abomination v5.0", "open_weights": false, "reasoning": false, "release_date": "2024-12-06", "structured_output": false, "tool_call": false }, "Llama-3.3-70B-Forgotten-Safeword-3.6": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "Llama 3.3 70B Forgotten Safeword 3.6 is an AI model provided by nano-gpt.", "id": "Llama-3.3-70B-Forgotten-Safeword-3.6", "last_updated": "2024-12-06", "limit": { "context": 32768, "input": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B Forgotten Safeword 3.6", "open_weights": false, "reasoning": false, "release_date": "2024-12-06", "structured_output": false, "tool_call": false }, "Llama-3.3-70B-GeneticLemonade-Opus": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "Llama 3.3 70B GeneticLemonade Opus is an AI model provided by nano-gpt.", "id": "Llama-3.3-70B-GeneticLemonade-Opus", "last_updated": "2024-12-06", "limit": { "context": 32768, "input": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B GeneticLemonade Opus", "open_weights": false, "reasoning": false, "release_date": "2024-12-06", "structured_output": false, "tool_call": false }, "Llama-3.3-70B-GeneticLemonade-Unleashed-v3": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "Llama 3.3 70B GeneticLemonade Unleashed v3 is an AI model provided by nano-gpt.", "id": "Llama-3.3-70B-GeneticLemonade-Unleashed-v3", "last_updated": "2024-12-06", "limit": { "context": 32768, "input": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B GeneticLemonade Unleashed v3", "open_weights": false, "reasoning": false, "release_date": "2024-12-06", "structured_output": false, "tool_call": false }, "Llama-3.3-70B-Ignition-v0.1": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "Llama 3.3 70B Ignition v0.1 is an AI model provided by nano-gpt.", "id": "Llama-3.3-70B-Ignition-v0.1", "last_updated": "2024-12-06", "limit": { "context": 32768, "input": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B Ignition v0.1", "open_weights": false, "reasoning": false, "release_date": "2024-12-06", "structured_output": false, "tool_call": false }, "Llama-3.3-70B-Incandescent-Malevolence": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "Llama 3.3 70B Incandescent Malevolence is an AI model provided by nano-gpt.", "id": "Llama-3.3-70B-Incandescent-Malevolence", "last_updated": "2024-12-06", "limit": { "context": 32768, "input": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B Incandescent Malevolence", "open_weights": false, "reasoning": false, "release_date": "2024-12-06", "structured_output": false, "tool_call": false }, "Llama-3.3-70B-Legion-V2.1": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "Llama 3.3 70B Legion V2.1 is an AI model provided by nano-gpt.", "id": "Llama-3.3-70B-Legion-V2.1", "last_updated": "2024-12-06", "limit": { "context": 32768, "input": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B Legion V2.1", "open_weights": false, "reasoning": false, "release_date": "2024-12-06", "structured_output": false, "tool_call": false }, "Llama-3.3-70B-MS-Nevoria": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "Llama 3.3 70B MS Nevoria is an AI model provided by nano-gpt.", "id": "Llama-3.3-70B-MS-Nevoria", "last_updated": "2024-12-06", "limit": { "context": 32768, "input": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B MS Nevoria", "open_weights": false, "reasoning": false, "release_date": "2024-12-06", "structured_output": false, "tool_call": false }, "Llama-3.3-70B-Magnum-v4-SE": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "Llama 3.3 70B Magnum v4 SE is an AI model provided by nano-gpt.", "id": "Llama-3.3-70B-Magnum-v4-SE", "last_updated": "2024-12-06", "limit": { "context": 32768, "input": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B Magnum v4 SE", "open_weights": false, "reasoning": false, "release_date": "2024-12-06", "structured_output": false, "tool_call": false }, "Llama-3.3-70B-Magnum-v4-SE-Cirrus-x1-SLERP": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "Llama 3.3 70B Magnum v4 SE Cirrus x1 SLERP is an AI model provided by nano-gpt.", "id": "Llama-3.3-70B-Magnum-v4-SE-Cirrus-x1-SLERP", "last_updated": "2025-07-26", "limit": { "context": 32768, "input": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B Magnum v4 SE Cirrus x1 SLERP", "open_weights": false, "reasoning": false, "release_date": "2025-07-26", "structured_output": false, "tool_call": false }, "Llama-3.3-70B-Mhnnn-x1": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "Llama 3.3 70B Mhnnn x1 is an AI model provided by nano-gpt.", "id": "Llama-3.3-70B-Mhnnn-x1", "last_updated": "2024-12-06", "limit": { "context": 32768, "input": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B Mhnnn x1", "open_weights": false, "reasoning": false, "release_date": "2024-12-06", "structured_output": false, "tool_call": false }, "Llama-3.3-70B-MiraiFanfare": { "attachment": false, "cost": { "input": 0.493, "output": 0.493 }, "description": "Llama 3.3 70b Mirai Fanfare is an AI model provided by nano-gpt.", "id": "Llama-3.3-70B-MiraiFanfare", "last_updated": "2025-07-26", "limit": { "context": 32768, "input": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70b Mirai Fanfare", "open_weights": false, "reasoning": false, "release_date": "2025-07-26", "structured_output": false, "tool_call": false }, "Llama-3.3-70B-Mokume-Gane-R1": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "Llama 3.3 70B Mokume Gane R1 is an AI model provided by nano-gpt.", "id": "Llama-3.3-70B-Mokume-Gane-R1", "last_updated": "2024-12-06", "limit": { "context": 32768, "input": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B Mokume Gane R1", "open_weights": false, "reasoning": false, "release_date": "2024-12-06", "structured_output": false, "tool_call": false }, "Llama-3.3-70B-Nova": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "Llama 3.3 70B Nova is an AI model provided by nano-gpt.", "id": "Llama-3.3-70B-Nova", "last_updated": "2024-12-06", "limit": { "context": 32768, "input": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B Nova", "open_weights": false, "reasoning": false, "release_date": "2024-12-06", "structured_output": false, "tool_call": false }, "Llama-3.3-70B-Predatorial-Extasy": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "Llama 3.3 70B Predatorial Extasy is an AI model provided by nano-gpt.", "id": "Llama-3.3-70B-Predatorial-Extasy", "last_updated": "2024-12-06", "limit": { "context": 32768, "input": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B Predatorial Extasy", "open_weights": false, "reasoning": false, "release_date": "2024-12-06", "structured_output": false, "tool_call": false }, "Llama-3.3-70B-Progenitor-V3.3": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "Llama 3.3 70B Progenitor V3.3 is an AI model provided by nano-gpt.", "id": "Llama-3.3-70B-Progenitor-V3.3", "last_updated": "2025-07-26", "limit": { "context": 32768, "input": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B Progenitor V3.3", "open_weights": false, "reasoning": false, "release_date": "2025-07-26", "structured_output": false, "tool_call": false }, "Llama-3.3-70B-RAWMAW": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "Llama 3.3 70B RAWMAW is an AI model provided by nano-gpt.", "id": "Llama-3.3-70B-RAWMAW", "last_updated": "2024-12-06", "limit": { "context": 32768, "input": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B RAWMAW", "open_weights": false, "reasoning": false, "release_date": "2024-12-06", "structured_output": false, "tool_call": false }, "Llama-3.3-70B-Sapphira-0.1": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "Llama 3.3 70B Sapphira 0.1 is an AI model provided by nano-gpt.", "id": "Llama-3.3-70B-Sapphira-0.1", "last_updated": "2024-12-06", "limit": { "context": 32768, "input": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B Sapphira 0.1", "open_weights": false, "reasoning": false, "release_date": "2024-12-06", "structured_output": false, "tool_call": false }, "Llama-3.3-70B-Sapphira-0.2": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "Llama 3.3 70B Sapphira 0.2 is an AI model provided by nano-gpt.", "id": "Llama-3.3-70B-Sapphira-0.2", "last_updated": "2024-12-06", "limit": { "context": 32768, "input": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B Sapphira 0.2", "open_weights": false, "reasoning": false, "release_date": "2024-12-06", "structured_output": false, "tool_call": false }, "Llama-3.3-70B-Shakudo": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "Llama 3.3 70B Shakudo is an AI model provided by nano-gpt.", "id": "Llama-3.3-70B-Shakudo", "last_updated": "2024-12-06", "limit": { "context": 32768, "input": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B Shakudo", "open_weights": false, "reasoning": false, "release_date": "2024-12-06", "structured_output": false, "tool_call": false }, "Llama-3.3-70B-StrawberryLemonade-v1.0": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "Llama 3.3 70B StrawberryLemonade v1.0 is an AI model provided by nano-gpt.", "id": "Llama-3.3-70B-StrawberryLemonade-v1.0", "last_updated": "2024-12-06", "limit": { "context": 32768, "input": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B StrawberryLemonade v1.0", "open_weights": false, "reasoning": false, "release_date": "2024-12-06", "structured_output": false, "tool_call": false }, "Llama-3.3-70B-Strawberrylemonade-v1.2": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "Llama 3.3 70B StrawberryLemonade v1.2 is an AI model provided by nano-gpt.", "id": "Llama-3.3-70B-Strawberrylemonade-v1.2", "last_updated": "2024-12-06", "limit": { "context": 32768, "input": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B StrawberryLemonade v1.2", "open_weights": false, "reasoning": false, "release_date": "2024-12-06", "structured_output": false, "tool_call": false }, "Llama-3.3-70B-The-Omega-Directive-Unslop-v2.0": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "Llama 3.3 70B Omega Directive Unslop v2.0 is an AI model provided by nano-gpt.", "id": "Llama-3.3-70B-The-Omega-Directive-Unslop-v2.0", "last_updated": "2024-12-06", "limit": { "context": 32768, "input": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B Omega Directive Unslop v2.0", "open_weights": false, "reasoning": false, "release_date": "2024-12-06", "structured_output": false, "tool_call": false }, "Llama-3.3-70B-The-Omega-Directive-Unslop-v2.1": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "Llama 3.3 70B Omega Directive Unslop v2.1 is an AI model provided by nano-gpt.", "id": "Llama-3.3-70B-The-Omega-Directive-Unslop-v2.1", "last_updated": "2024-12-06", "limit": { "context": 32768, "input": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B Omega Directive Unslop v2.1", "open_weights": false, "reasoning": false, "release_date": "2024-12-06", "structured_output": false, "tool_call": false }, "Llama-3.3-70B-Vulpecula-R1": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "Llama 3.3 70B Vulpecula R1 is an AI model provided by nano-gpt.", "id": "Llama-3.3-70B-Vulpecula-R1", "last_updated": "2024-12-06", "limit": { "context": 32768, "input": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B Vulpecula R1", "open_weights": false, "reasoning": false, "release_date": "2024-12-06", "structured_output": false, "tool_call": false }, "Magistral-Small-2506": { "attachment": false, "cost": { "input": 0.4, "output": 1.4 }, "description": "Magistral Small 2506 is an AI model provided by nano-gpt.", "id": "Magistral-Small-2506", "last_updated": "2025-09-25", "limit": { "context": 32768, "input": 32768, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Magistral Small 2506", "open_weights": false, "reasoning": false, "release_date": "2025-09-25", "structured_output": false, "tool_call": false }, "MarinaraSpaghetti/NemoMix-Unleashed-12B": { "attachment": false, "cost": { "input": 0.49299999999999994, "output": 0.49299999999999994 }, "description": "NemoMix 12B Unleashed is an AI model provided by nano-gpt.", "family": "mistral-nemo", "id": "MarinaraSpaghetti/NemoMix-Unleashed-12B", "last_updated": "2024-07-01", "limit": { "context": 32768, "input": 32768, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "NemoMix 12B Unleashed", "open_weights": false, "reasoning": false, "release_date": "2024-07-01", "structured_output": false, "tool_call": false }, "Meta-Llama-3-1-8B-Instruct-FP8": { "attachment": false, "cost": { "input": 0.02, "output": 0.03 }, "description": "Llama 3.1 8B (decentralized) is an AI model provided by nano-gpt.", "id": "Meta-Llama-3-1-8B-Instruct-FP8", "last_updated": "2024-07-23", "limit": { "context": 128000, "input": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.1 8B (decentralized)", "open_weights": false, "reasoning": false, "release_date": "2024-07-23", "structured_output": false, "tool_call": false }, "MiniMax-M1": { "attachment": false, "cost": { "input": 0.1394, "output": 1.3328 }, "description": "MiniMax M1 is an AI model provided by nano-gpt.", "id": "MiniMax-M1", "last_updated": "2025-06-16", "limit": { "context": 1000000, "input": 1000000, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M1", "open_weights": false, "reasoning": false, "release_date": "2025-06-16", "structured_output": false, "tool_call": false }, "MiniMax-M2": { "attachment": false, "cost": { "input": 0.17, "output": 1.53 }, "description": "MiniMax M2 is an AI model provided by nano-gpt.", "id": "MiniMax-M2", "last_updated": "2025-10-25", "limit": { "context": 200000, "input": 200000, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M2", "open_weights": false, "reasoning": true, "release_date": "2025-10-25", "structured_output": false, "tool_call": false }, "MiniMaxAI/MiniMax-M1-80k": { "attachment": false, "cost": { "input": 0.6052, "output": 2.4225000000000003 }, "description": "MiniMax M1 80K is an AI model provided by nano-gpt.", "family": "minimax", "id": "MiniMaxAI/MiniMax-M1-80k", "last_updated": "2025-06-16", "limit": { "context": 1000000, "input": 1000000, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M1 80K", "open_weights": false, "reasoning": false, "release_date": "2025-06-16", "structured_output": false, "tool_call": false }, "Mistral-Nemo-12B-Instruct-2407": { "attachment": true, "cost": { "input": 0.01, "output": 0.01 }, "description": "Mistral Nemo 12B Instruct 2407 is an AI model provided by nano-gpt.", "id": "Mistral-Nemo-12B-Instruct-2407", "last_updated": "2024-07-18", "limit": { "context": 16384, "input": 16384, "output": 16384 }, "modalities": { "input": [ "text", "pdf" ], "output": [ "text" ] }, "name": "Mistral Nemo 12B Instruct 2407", "open_weights": false, "reasoning": false, "release_date": "2024-07-18", "structured_output": false, "tool_call": false }, "NeverSleep/Llama-3-Lumimaid-70B-v0.1": { "attachment": true, "cost": { "input": 2.006, "output": 2.006 }, "description": "Lumimaid 70b is an AI model provided by nano-gpt.", "family": "llama", "id": "NeverSleep/Llama-3-Lumimaid-70B-v0.1", "last_updated": "2024-07-01", "limit": { "context": 16384, "input": 16384, "output": 8192 }, "modalities": { "input": [ "text", "pdf" ], "output": [ "text" ] }, "name": "Lumimaid 70b", "open_weights": false, "reasoning": false, "release_date": "2024-07-01", "structured_output": false, "tool_call": false }, "NeverSleep/Lumimaid-v0.2-70B": { "attachment": false, "cost": { "input": 1, "output": 1.5 }, "description": "Lumimaid v0.2 is an AI model provided by nano-gpt.", "family": "llama", "id": "NeverSleep/Lumimaid-v0.2-70B", "last_updated": "2024-07-01", "limit": { "context": 16384, "input": 16384, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Lumimaid v0.2", "open_weights": false, "reasoning": false, "release_date": "2024-07-01", "structured_output": false, "tool_call": false }, "NousResearch 2/DeepHermes-3-Mistral-24B-Preview": { "attachment": false, "cost": { "input": 0.3, "output": 0.3 }, "description": "DeepHermes-3 Mistral 24B (Preview) is an AI model provided by nano-gpt.", "family": "nousresearch", "id": "NousResearch 2/DeepHermes-3-Mistral-24B-Preview", "last_updated": "2025-05-10", "limit": { "context": 128000, "input": 128000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepHermes-3 Mistral 24B (Preview)", "open_weights": false, "reasoning": false, "release_date": "2025-05-10", "structured_output": false, "tool_call": false }, "NousResearch 2/Hermes-4-70B:thinking": { "attachment": false, "cost": { "input": 0.2006, "output": 0.39949999999999997 }, "description": "Hermes 4 (Thinking) is an AI model provided by nano-gpt.", "family": "nousresearch", "id": "NousResearch 2/Hermes-4-70B:thinking", "last_updated": "2025-09-17", "limit": { "context": 128000, "input": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Hermes 4 (Thinking)", "open_weights": false, "reasoning": false, "release_date": "2025-09-17", "structured_output": false, "tool_call": false }, "NousResearch 2/hermes-3-llama-3.1-70b": { "attachment": false, "cost": { "input": 0.408, "output": 0.408 }, "description": "Hermes 3 70B is an AI model provided by nano-gpt.", "family": "nousresearch", "id": "NousResearch 2/hermes-3-llama-3.1-70b", "last_updated": "2026-01-07", "limit": { "context": 65536, "input": 65536, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Hermes 3 70B", "open_weights": false, "reasoning": false, "release_date": "2026-01-07", "structured_output": false, "tool_call": false }, "NousResearch 2/hermes-4-405b": { "attachment": false, "cost": { "input": 0.3, "output": 1.2 }, "description": "Hermes 4 Large is an AI model provided by nano-gpt.", "family": "nousresearch", "id": "NousResearch 2/hermes-4-405b", "last_updated": "2025-08-26", "limit": { "context": 128000, "input": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Hermes 4 Large", "open_weights": false, "reasoning": false, "release_date": "2025-08-26", "structured_output": true, "tool_call": true }, "NousResearch 2/hermes-4-405b:thinking": { "attachment": false, "cost": { "input": 0.3, "output": 1.2 }, "description": "Hermes 4 Large (Thinking) is an AI model provided by nano-gpt.", "family": "nousresearch", "id": "NousResearch 2/hermes-4-405b:thinking", "last_updated": "2025-01-01", "limit": { "context": 128000, "input": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Hermes 4 Large (Thinking)", "open_weights": false, "reasoning": false, "release_date": "2025-01-01", "structured_output": true, "tool_call": true }, "NousResearch 2/hermes-4-70b": { "attachment": false, "cost": { "input": 0.2006, "output": 0.39949999999999997 }, "description": "Hermes 4 Medium is an AI model provided by nano-gpt.", "family": "nousresearch", "id": "NousResearch 2/hermes-4-70b", "last_updated": "2025-07-03", "limit": { "context": 128000, "input": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Hermes 4 Medium", "open_weights": false, "reasoning": false, "release_date": "2025-07-03", "structured_output": false, "tool_call": false }, "QwQ-32B-ArliAI-RpR-v1": { "attachment": false, "cost": { "input": 0.2, "output": 0.2 }, "description": "QwQ 32b Arli V1 is an AI model provided by nano-gpt.", "id": "QwQ-32B-ArliAI-RpR-v1", "last_updated": "2025-02-17", "limit": { "context": 32768, "input": 32768, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "QwQ 32b Arli V1", "open_weights": false, "reasoning": false, "release_date": "2025-02-17", "structured_output": false, "tool_call": false }, "Qwen2.5-32B-EVA-v0.2": { "attachment": false, "cost": { "input": 0.493, "output": 0.493 }, "description": "Qwen 2.5 32b EVA is an AI model provided by nano-gpt.", "id": "Qwen2.5-32B-EVA-v0.2", "last_updated": "2024-09-01", "limit": { "context": 24576, "input": 24576, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen 2.5 32b EVA", "open_weights": false, "reasoning": false, "release_date": "2024-09-01", "structured_output": false, "tool_call": false }, "ReadyArt/MS3.2-The-Omega-Directive-24B-Unslop-v2.0": { "attachment": false, "cost": { "input": 0.5, "output": 0.5 }, "description": "Omega Directive 24B Unslop v2.0 is an AI model provided by nano-gpt.", "family": "llama", "id": "ReadyArt/MS3.2-The-Omega-Directive-24B-Unslop-v2.0", "last_updated": "2025-12-08", "limit": { "context": 16384, "input": 16384, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Omega Directive 24B Unslop v2.0", "open_weights": false, "reasoning": false, "release_date": "2025-12-08", "structured_output": false, "tool_call": false }, "ReadyArt/The-Omega-Abomination-L-70B-v1.0": { "attachment": false, "cost": { "input": 0.7, "output": 0.95 }, "description": "The Omega Abomination V1 is an AI model provided by nano-gpt.", "family": "llama", "id": "ReadyArt/The-Omega-Abomination-L-70B-v1.0", "last_updated": "2024-12-01", "limit": { "context": 16384, "input": 16384, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "The Omega Abomination V1", "open_weights": false, "reasoning": false, "release_date": "2024-12-01", "structured_output": false, "tool_call": false }, "Salesforce/Llama-xLAM-2-70b-fc-r": { "attachment": false, "cost": { "input": 2.5, "output": 2.5 }, "description": "Llama-xLAM-2 70B fc-r is an AI model provided by nano-gpt.", "family": "llama", "id": "Salesforce/Llama-xLAM-2-70b-fc-r", "last_updated": "2025-04-13", "limit": { "context": 128000, "input": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama-xLAM-2 70B fc-r", "open_weights": false, "reasoning": false, "release_date": "2025-04-13", "structured_output": false, "tool_call": false }, "Sao10K/L3-8B-Stheno-v3.2": { "attachment": false, "cost": { "input": 0.2006, "output": 0.2006 }, "description": "Sao10K Stheno 8b is an AI model provided by nano-gpt.", "family": "llama", "id": "Sao10K/L3-8B-Stheno-v3.2", "last_updated": "2024-11-29", "limit": { "context": 16384, "input": 16384, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Sao10K Stheno 8b", "open_weights": false, "reasoning": false, "release_date": "2024-11-29", "structured_output": false, "tool_call": false }, "Sao10K/L3.1-70B-Euryale-v2.2": { "attachment": false, "cost": { "input": 0.306, "output": 0.357 }, "description": "Llama 3.1 70B Euryale is an AI model provided by nano-gpt.", "family": "llama", "id": "Sao10K/L3.1-70B-Euryale-v2.2", "last_updated": "2024-07-23", "limit": { "context": 20480, "input": 20480, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.1 70B Euryale", "open_weights": false, "reasoning": false, "release_date": "2024-07-23", "structured_output": false, "tool_call": false }, "Sao10K/L3.1-70B-Hanami-x1": { "attachment": false, "cost": { "input": 0.49299999999999994, "output": 0.49299999999999994 }, "description": "Llama 3.1 70B Hanami is an AI model provided by nano-gpt.", "family": "llama", "id": "Sao10K/L3.1-70B-Hanami-x1", "last_updated": "2024-07-23", "limit": { "context": 16384, "input": 16384, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.1 70B Hanami", "open_weights": false, "reasoning": false, "release_date": "2024-07-23", "structured_output": false, "tool_call": false }, "Sao10K/L3.3-70B-Euryale-v2.3": { "attachment": false, "cost": { "input": 0.49299999999999994, "output": 0.49299999999999994 }, "description": "Llama 3.3 70B Euryale is an AI model provided by nano-gpt.", "family": "llama", "id": "Sao10K/L3.3-70B-Euryale-v2.3", "last_updated": "2024-12-06", "limit": { "context": 20480, "input": 20480, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B Euryale", "open_weights": false, "reasoning": false, "release_date": "2024-12-06", "structured_output": false, "tool_call": false }, "Steelskull/L3.3-Cu-Mai-R1-70b": { "attachment": false, "cost": { "input": 0.49299999999999994, "output": 0.49299999999999994 }, "description": "Llama 3.3 70B Cu Mai is an AI model provided by nano-gpt.", "family": "llama", "id": "Steelskull/L3.3-Cu-Mai-R1-70b", "last_updated": "2024-12-06", "limit": { "context": 16384, "input": 16384, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B Cu Mai", "open_weights": false, "reasoning": false, "release_date": "2024-12-06", "structured_output": false, "tool_call": false }, "Steelskull/L3.3-Electra-R1-70b": { "attachment": false, "cost": { "input": 0.69989, "output": 0.69989 }, "description": "Steelskull Electra R1 70b is an AI model provided by nano-gpt.", "family": "llama", "id": "Steelskull/L3.3-Electra-R1-70b", "last_updated": "2024-12-06", "limit": { "context": 16384, "input": 16384, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Steelskull Electra R1 70b", "open_weights": false, "reasoning": false, "release_date": "2024-12-06", "structured_output": false, "tool_call": false }, "Steelskull/L3.3-MS-Evalebis-70b": { "attachment": false, "cost": { "input": 0.49299999999999994, "output": 0.49299999999999994 }, "description": "MS Evalebis 70b is an AI model provided by nano-gpt.", "family": "llama", "id": "Steelskull/L3.3-MS-Evalebis-70b", "last_updated": "2024-12-06", "limit": { "context": 16384, "input": 16384, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MS Evalebis 70b", "open_weights": false, "reasoning": false, "release_date": "2024-12-06", "structured_output": false, "tool_call": false }, "Steelskull/L3.3-MS-Evayale-70B": { "attachment": false, "cost": { "input": 0.49299999999999994, "output": 0.49299999999999994 }, "description": "Evayale 70b is an AI model provided by nano-gpt.", "family": "llama", "id": "Steelskull/L3.3-MS-Evayale-70B", "last_updated": "2024-12-06", "limit": { "context": 16384, "input": 16384, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Evayale 70b ", "open_weights": false, "reasoning": false, "release_date": "2024-12-06", "structured_output": false, "tool_call": false }, "Steelskull/L3.3-MS-Nevoria-70b": { "attachment": false, "cost": { "input": 0.49299999999999994, "output": 0.49299999999999994 }, "description": "Steelskull Nevoria 70b is an AI model provided by nano-gpt.", "family": "llama", "id": "Steelskull/L3.3-MS-Nevoria-70b", "last_updated": "2024-12-06", "limit": { "context": 16384, "input": 16384, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Steelskull Nevoria 70b", "open_weights": false, "reasoning": false, "release_date": "2024-12-06", "structured_output": false, "tool_call": false }, "Steelskull/L3.3-Nevoria-R1-70b": { "attachment": false, "cost": { "input": 0.49299999999999994, "output": 0.49299999999999994 }, "description": "Steelskull Nevoria R1 70b is an AI model provided by nano-gpt.", "family": "llama", "id": "Steelskull/L3.3-Nevoria-R1-70b", "last_updated": "2024-12-06", "limit": { "context": 16384, "input": 16384, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Steelskull Nevoria R1 70b", "open_weights": false, "reasoning": false, "release_date": "2024-12-06", "structured_output": false, "tool_call": false }, "TEE/deepseek-r1-0528": { "attachment": false, "cost": { "input": 2, "output": 2 }, "description": "DeepSeek R1 0528 TEE is an AI model provided by nano-gpt.", "family": "deepseek", "id": "TEE/deepseek-r1-0528", "last_updated": "2025-05-28", "limit": { "context": 128000, "input": 128000, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek R1 0528 TEE", "open_weights": false, "reasoning": false, "release_date": "2025-05-28", "structured_output": false, "tool_call": false }, "TEE/deepseek-v3.1": { "attachment": false, "cost": { "input": 1, "output": 2.5 }, "description": "DeepSeek V3.1 TEE is an AI model provided by nano-gpt.", "family": "deepseek", "id": "TEE/deepseek-v3.1", "last_updated": "2025-08-21", "limit": { "context": 164000, "input": 164000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3.1 TEE", "open_weights": false, "reasoning": false, "release_date": "2025-08-21", "structured_output": false, "tool_call": false }, "TEE/deepseek-v3.2": { "attachment": false, "cost": { "input": 0.5, "output": 1 }, "description": "DeepSeek V3.2 TEE is an AI model provided by nano-gpt.", "family": "deepseek", "id": "TEE/deepseek-v3.2", "last_updated": "2025-12-01", "limit": { "context": 164000, "input": 164000, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3.2 TEE", "open_weights": false, "reasoning": false, "release_date": "2025-12-01", "structured_output": false, "tool_call": false }, "TEE/gemma-3-27b-it": { "attachment": false, "cost": { "input": 0.2, "output": 0.8 }, "description": "Gemma 3 27B TEE is an AI model provided by nano-gpt.", "family": "gemma", "id": "TEE/gemma-3-27b-it", "last_updated": "2025-03-10", "limit": { "context": 131072, "input": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Gemma 3 27B TEE", "open_weights": false, "reasoning": false, "release_date": "2025-03-10", "structured_output": false, "tool_call": false }, "TEE/glm-4.6": { "attachment": false, "cost": { "input": 0.75, "output": 2 }, "description": "GLM 4.6 TEE is an AI model provided by nano-gpt.", "family": "glm", "id": "TEE/glm-4.6", "last_updated": "2025-09-30", "limit": { "context": 203000, "input": 203000, "output": 65535 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.6 TEE", "open_weights": false, "reasoning": false, "release_date": "2025-09-30", "structured_output": false, "tool_call": false }, "TEE/glm-4.7": { "attachment": false, "cost": { "input": 0.85, "output": 3.3 }, "description": "GLM 4.7 TEE is an AI model provided by nano-gpt.", "family": "glm", "id": "TEE/glm-4.7", "last_updated": "2026-01-29", "limit": { "context": 131000, "input": 131000, "output": 65535 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.7 TEE", "open_weights": false, "reasoning": false, "release_date": "2026-01-29", "structured_output": false, "tool_call": false }, "TEE/glm-4.7-flash": { "attachment": false, "cost": { "input": 0.15, "output": 0.5 }, "description": "GLM 4.7 Flash TEE is an AI model provided by nano-gpt.", "family": "glm-flash", "id": "TEE/glm-4.7-flash", "last_updated": "2026-01-19", "limit": { "context": 203000, "input": 203000, "output": 65535 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.7 Flash TEE", "open_weights": false, "reasoning": false, "release_date": "2026-01-19", "structured_output": false, "tool_call": false }, "TEE/glm-5": { "attachment": false, "cost": { "input": 1.2, "output": 3.5 }, "description": "GLM 5 TEE is an AI model provided by nano-gpt.", "family": "glm", "id": "TEE/glm-5", "last_updated": "2026-02-11", "limit": { "context": 203000, "input": 203000, "output": 65535 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 5 TEE", "open_weights": false, "reasoning": false, "release_date": "2026-02-11", "structured_output": false, "tool_call": false }, "TEE/gpt-oss-120b": { "attachment": false, "cost": { "input": 2, "output": 2 }, "description": "GPT-OSS 120B TEE is an AI model provided by nano-gpt.", "family": "gpt-oss", "id": "TEE/gpt-oss-120b", "last_updated": "2025-08-05", "limit": { "context": 131072, "input": 131072, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT-OSS 120B TEE", "open_weights": false, "reasoning": false, "release_date": "2025-08-05", "structured_output": false, "tool_call": false }, "TEE/gpt-oss-20b": { "attachment": false, "cost": { "input": 0.2, "output": 0.8 }, "description": "GPT-OSS 20B TEE is an AI model provided by nano-gpt.", "family": "gpt-oss", "id": "TEE/gpt-oss-20b", "last_updated": "2025-08-05", "limit": { "context": 131072, "input": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT-OSS 20B TEE", "open_weights": false, "reasoning": false, "release_date": "2025-08-05", "structured_output": false, "tool_call": false }, "TEE/kimi-k2-thinking": { "attachment": false, "cost": { "input": 2, "output": 2 }, "description": "Kimi K2 Thinking TEE is an AI model provided by nano-gpt.", "family": "kimi-thinking", "id": "TEE/kimi-k2-thinking", "last_updated": "2025-11-06", "limit": { "context": 128000, "input": 128000, "output": 65535 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 Thinking TEE", "open_weights": false, "reasoning": false, "release_date": "2025-11-06", "structured_output": false, "tool_call": false }, "TEE/kimi-k2.5": { "attachment": false, "cost": { "input": 0.3, "output": 1.9 }, "description": "Kimi K2.5 TEE is an AI model provided by nano-gpt.", "family": "kimi", "id": "TEE/kimi-k2.5", "last_updated": "2026-01-29", "limit": { "context": 128000, "input": 128000, "output": 65535 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2.5 TEE", "open_weights": false, "reasoning": false, "release_date": "2026-01-29", "structured_output": false, "tool_call": false }, "TEE/kimi-k2.5-thinking": { "attachment": false, "cost": { "input": 0.3, "output": 1.9 }, "description": "Kimi K2.5 Thinking TEE is an AI model provided by nano-gpt.", "family": "kimi-thinking", "id": "TEE/kimi-k2.5-thinking", "last_updated": "2026-01-29", "limit": { "context": 128000, "input": 128000, "output": 65535 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2.5 Thinking TEE", "open_weights": false, "reasoning": true, "release_date": "2026-01-29", "structured_output": false, "tool_call": false }, "TEE/llama3-3-70b": { "attachment": false, "cost": { "input": 2, "output": 2 }, "description": "Llama 3.3 70B is an AI model provided by nano-gpt.", "family": "llama", "id": "TEE/llama3-3-70b", "last_updated": "2025-07-03", "limit": { "context": 128000, "input": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B", "open_weights": false, "reasoning": false, "release_date": "2025-07-03", "structured_output": false, "tool_call": false }, "TEE/minimax-m2.1": { "attachment": false, "cost": { "input": 0.3, "output": 1.2 }, "description": "MiniMax M2.1 TEE is an AI model provided by nano-gpt.", "family": "minimax", "id": "TEE/minimax-m2.1", "last_updated": "2025-12-23", "limit": { "context": 200000, "input": 200000, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M2.1 TEE", "open_weights": false, "reasoning": true, "release_date": "2025-12-23", "structured_output": true, "tool_call": true }, "TEE/qwen2.5-vl-72b-instruct": { "attachment": true, "cost": { "input": 0.7, "output": 0.7 }, "description": "Qwen2.5 VL 72B TEE is an AI model provided by nano-gpt.", "family": "qwen", "id": "TEE/qwen2.5-vl-72b-instruct", "last_updated": "2025-02-01", "limit": { "context": 65536, "input": 65536, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen2.5 VL 72B TEE", "open_weights": false, "reasoning": false, "release_date": "2025-02-01", "structured_output": false, "tool_call": false }, "TEE/qwen3-30b-a3b-instruct-2507": { "attachment": false, "cost": { "input": 0.15, "output": 0.44999999999999996 }, "description": "Qwen3 30B A3B Instruct 2507 TEE is an AI model provided by nano-gpt.", "family": "qwen", "id": "TEE/qwen3-30b-a3b-instruct-2507", "last_updated": "2025-07-29", "limit": { "context": 262000, "input": 262000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 30B A3B Instruct 2507 TEE", "open_weights": false, "reasoning": false, "release_date": "2025-07-29", "structured_output": false, "tool_call": false }, "TEE/qwen3-coder": { "attachment": false, "cost": { "input": 1.5, "output": 2 }, "description": "Qwen3 Coder 480B TEE is an AI model provided by nano-gpt.", "family": "qwen", "id": "TEE/qwen3-coder", "last_updated": "2025-07-23", "limit": { "context": 128000, "input": 128000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Coder 480B TEE", "open_weights": false, "reasoning": false, "release_date": "2025-07-23", "structured_output": false, "tool_call": false }, "TEE/qwen3.5-397b-a17b": { "attachment": false, "cost": { "input": 0.6, "output": 3.6 }, "description": "Qwen3.5 397B A17B TEE is an AI model provided by nano-gpt.", "family": "qwen", "id": "TEE/qwen3.5-397b-a17b", "last_updated": "2026-02-28", "limit": { "context": 258048, "input": 258048, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3.5 397B A17B TEE", "open_weights": false, "reasoning": false, "release_date": "2026-02-28", "structured_output": false, "tool_call": false }, "THUDM/GLM-4-32B-0414": { "attachment": false, "cost": { "input": 0.2, "output": 0.2 }, "description": "GLM 4 32B 0414 is an AI model provided by nano-gpt.", "family": "glm", "id": "THUDM/GLM-4-32B-0414", "last_updated": "2025-04-14", "limit": { "context": 128000, "input": 128000, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4 32B 0414", "open_weights": false, "reasoning": false, "release_date": "2025-04-14", "structured_output": false, "tool_call": false }, "THUDM/GLM-4-9B-0414": { "attachment": false, "cost": { "input": 0.2, "output": 0.2 }, "description": "GLM 4 9B 0414 is an AI model provided by nano-gpt.", "family": "glm", "id": "THUDM/GLM-4-9B-0414", "last_updated": "2025-04-14", "limit": { "context": 32000, "input": 32000, "output": 8000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4 9B 0414", "open_weights": false, "reasoning": false, "release_date": "2025-04-14", "structured_output": false, "tool_call": false }, "THUDM/GLM-Z1-32B-0414": { "attachment": false, "cost": { "input": 0.2, "output": 0.2 }, "description": "GLM Z1 32B 0414 is an AI model provided by nano-gpt.", "family": "glm-z", "id": "THUDM/GLM-Z1-32B-0414", "last_updated": "2025-04-15", "limit": { "context": 128000, "input": 128000, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM Z1 32B 0414", "open_weights": false, "reasoning": false, "release_date": "2025-04-15", "structured_output": false, "tool_call": false }, "THUDM/GLM-Z1-9B-0414": { "attachment": false, "cost": { "input": 0.2, "output": 0.2 }, "description": "GLM Z1 9B 0414 is an AI model provided by nano-gpt.", "family": "glm-z", "id": "THUDM/GLM-Z1-9B-0414", "last_updated": "2025-04-14", "limit": { "context": 32000, "input": 32000, "output": 8000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM Z1 9B 0414", "open_weights": false, "reasoning": false, "release_date": "2025-04-14", "structured_output": false, "tool_call": false }, "THUDM/GLM-Z1-Rumination-32B-0414": { "attachment": false, "cost": { "input": 0.2, "output": 0.2 }, "description": "GLM Z1 Rumination 32B 0414 is an AI model provided by nano-gpt.", "family": "glm-z", "id": "THUDM/GLM-Z1-Rumination-32B-0414", "last_updated": "2025-04-15", "limit": { "context": 32000, "input": 32000, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM Z1 Rumination 32B 0414", "open_weights": false, "reasoning": false, "release_date": "2025-04-15", "structured_output": false, "tool_call": false }, "TheDrummer 2/Anubis-70B-v1": { "attachment": false, "cost": { "input": 0.31, "output": 0.31 }, "description": "Anubis 70B v1 is an AI model provided by nano-gpt.", "family": "llama", "id": "TheDrummer 2/Anubis-70B-v1", "last_updated": "2024-07-01", "limit": { "context": 65536, "input": 65536, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Anubis 70B v1", "open_weights": false, "reasoning": false, "release_date": "2024-07-01", "structured_output": false, "tool_call": false }, "TheDrummer 2/Anubis-70B-v1.1": { "attachment": false, "cost": { "input": 0.31, "output": 0.31 }, "description": "Anubis 70B v1.1 is an AI model provided by nano-gpt.", "family": "llama", "id": "TheDrummer 2/Anubis-70B-v1.1", "last_updated": "2024-07-01", "limit": { "context": 131072, "input": 131072, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Anubis 70B v1.1", "open_weights": false, "reasoning": false, "release_date": "2024-07-01", "structured_output": false, "tool_call": false }, "TheDrummer 2/Cydonia-24B-v2": { "attachment": false, "cost": { "input": 0.1003, "output": 0.1207 }, "description": "The Drummer Cydonia 24B v2 is an AI model provided by nano-gpt.", "family": "llama", "id": "TheDrummer 2/Cydonia-24B-v2", "last_updated": "2025-02-17", "limit": { "context": 16384, "input": 16384, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "The Drummer Cydonia 24B v2", "open_weights": false, "reasoning": false, "release_date": "2025-02-17", "structured_output": false, "tool_call": false }, "TheDrummer 2/Cydonia-24B-v4": { "attachment": false, "cost": { "input": 0.2006, "output": 0.2414 }, "description": "The Drummer Cydonia 24B v4 is an AI model provided by nano-gpt.", "family": "llama", "id": "TheDrummer 2/Cydonia-24B-v4", "last_updated": "2025-07-22", "limit": { "context": 16384, "input": 16384, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "The Drummer Cydonia 24B v4", "open_weights": false, "reasoning": false, "release_date": "2025-07-22", "structured_output": false, "tool_call": false }, "TheDrummer 2/Cydonia-24B-v4.1": { "attachment": false, "cost": { "input": 0.1003, "output": 0.1207 }, "description": "The Drummer Cydonia 24B v4.1 is an AI model provided by nano-gpt.", "family": "llama", "id": "TheDrummer 2/Cydonia-24B-v4.1", "last_updated": "2025-08-19", "limit": { "context": 16384, "input": 16384, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "The Drummer Cydonia 24B v4.1", "open_weights": false, "reasoning": false, "release_date": "2025-08-19", "structured_output": false, "tool_call": false }, "TheDrummer 2/Cydonia-24B-v4.3": { "attachment": false, "cost": { "input": 0.1003, "output": 0.1207 }, "description": "The Drummer Cydonia 24B v4.3 is an AI model provided by nano-gpt.", "family": "llama", "id": "TheDrummer 2/Cydonia-24B-v4.3", "last_updated": "2025-12-25", "limit": { "context": 32768, "input": 32768, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "The Drummer Cydonia 24B v4.3", "open_weights": false, "reasoning": false, "release_date": "2025-12-25", "structured_output": false, "tool_call": false }, "TheDrummer 2/Magidonia-24B-v4.3": { "attachment": false, "cost": { "input": 0.1003, "output": 0.1207 }, "description": "The Drummer Magidonia 24B v4.3 is an AI model provided by nano-gpt.", "family": "llama", "id": "TheDrummer 2/Magidonia-24B-v4.3", "last_updated": "2025-12-25", "limit": { "context": 32768, "input": 32768, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "The Drummer Magidonia 24B v4.3", "open_weights": false, "reasoning": false, "release_date": "2025-12-25", "structured_output": false, "tool_call": false }, "TheDrummer 2/Rocinante-12B-v1.1": { "attachment": false, "cost": { "input": 0.408, "output": 0.595 }, "description": "Rocinante 12b is an AI model provided by nano-gpt.", "family": "llama", "id": "TheDrummer 2/Rocinante-12B-v1.1", "last_updated": "2024-07-01", "limit": { "context": 16384, "input": 16384, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Rocinante 12b", "open_weights": false, "reasoning": false, "release_date": "2024-07-01", "structured_output": false, "tool_call": false }, "TheDrummer 2/UnslopNemo-12B-v4.1": { "attachment": true, "cost": { "input": 0.49299999999999994, "output": 0.49299999999999994 }, "description": "UnslopNemo 12b v4 is an AI model provided by nano-gpt.", "family": "llama", "id": "TheDrummer 2/UnslopNemo-12B-v4.1", "last_updated": "2024-07-01", "limit": { "context": 32768, "input": 32768, "output": 8192 }, "modalities": { "input": [ "text", "pdf" ], "output": [ "text" ] }, "name": "UnslopNemo 12b v4", "open_weights": false, "reasoning": false, "release_date": "2024-07-01", "structured_output": false, "tool_call": false }, "TheDrummer 2/skyfall-36b-v2": { "attachment": true, "cost": { "input": 0.49299999999999994, "output": 0.49299999999999994 }, "description": "TheDrummer Skyfall 36B V2 is an AI model provided by nano-gpt.", "family": "llama", "id": "TheDrummer 2/skyfall-36b-v2", "last_updated": "2025-03-10", "limit": { "context": 64000, "input": 64000, "output": 32768 }, "modalities": { "input": [ "text", "pdf" ], "output": [ "text" ] }, "name": "TheDrummer Skyfall 36B V2", "open_weights": false, "reasoning": false, "release_date": "2025-03-10", "structured_output": false, "tool_call": false }, "Tongyi-Zhiwen/QwenLong-L1-32B": { "attachment": false, "cost": { "input": 0.13999999999999999, "output": 0.6 }, "description": "QwenLong L1 32B is an AI model provided by nano-gpt.", "family": "qwen", "id": "Tongyi-Zhiwen/QwenLong-L1-32B", "last_updated": "2025-01-25", "limit": { "context": 128000, "input": 128000, "output": 40960 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "QwenLong L1 32B", "open_weights": false, "reasoning": false, "release_date": "2025-01-25", "structured_output": false, "tool_call": false }, "VongolaChouko/Starcannon-Unleashed-12B-v1.0": { "attachment": false, "cost": { "input": 0.49299999999999994, "output": 0.49299999999999994 }, "description": "Mistral Nemo Starcannon 12b v1 is an AI model provided by nano-gpt.", "family": "mistral-nemo", "id": "VongolaChouko/Starcannon-Unleashed-12B-v1.0", "last_updated": "2024-07-01", "limit": { "context": 16384, "input": 16384, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral Nemo Starcannon 12b v1", "open_weights": false, "reasoning": false, "release_date": "2024-07-01", "structured_output": false, "tool_call": false }, "abacusai/Dracarys-72B-Instruct": { "attachment": false, "cost": { "input": 0.49299999999999994, "output": 0.49299999999999994 }, "description": "Llama 3.1 70B Dracarys 2 is an AI model provided by nano-gpt.", "family": "llama", "id": "abacusai/Dracarys-72B-Instruct", "last_updated": "2025-08-02", "limit": { "context": 16384, "input": 16384, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.1 70B Dracarys 2", "open_weights": false, "reasoning": false, "release_date": "2025-08-02", "structured_output": false, "tool_call": false }, "aion-labs/aion-1.0": { "attachment": false, "cost": { "input": 3.995, "output": 7.99 }, "description": "Aion 1.0 is an AI model provided by nano-gpt.", "family": "llama", "id": "aion-labs/aion-1.0", "last_updated": "2025-02-01", "limit": { "context": 65536, "input": 65536, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Aion 1.0", "open_weights": false, "reasoning": false, "release_date": "2025-02-01", "structured_output": false, "tool_call": false }, "aion-labs/aion-1.0-mini": { "attachment": false, "cost": { "input": 0.7989999999999999, "output": 1.394 }, "description": "Aion 1.0 mini (DeepSeek) is an AI model provided by nano-gpt.", "family": "deepseek", "id": "aion-labs/aion-1.0-mini", "last_updated": "2025-02-20", "limit": { "context": 131072, "input": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Aion 1.0 mini (DeepSeek)", "open_weights": false, "reasoning": false, "release_date": "2025-02-20", "structured_output": false, "tool_call": false }, "aion-labs/aion-rp-llama-3.1-8b": { "attachment": false, "cost": { "input": 0.2006, "output": 0.2006 }, "description": "Llama 3.1 8b (uncensored) is an AI model provided by nano-gpt.", "family": "llama", "id": "aion-labs/aion-rp-llama-3.1-8b", "last_updated": "2024-07-23", "limit": { "context": 32768, "input": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.1 8b (uncensored)", "open_weights": false, "reasoning": false, "release_date": "2024-07-23", "structured_output": false, "tool_call": false }, "alibaba/qwen3.6-flash": { "attachment": false, "cost": { "input": 0.19, "output": 1.16 }, "description": "Qwen3.6 Flash is an AI model provided by nano-gpt.", "family": "qwen3.6", "id": "alibaba/qwen3.6-flash", "last_updated": "2026-04-17", "limit": { "context": 991800, "output": 65536 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen3.6 Flash", "open_weights": false, "reasoning": false, "release_date": "2026-04-17", "structured_output": false, "tool_call": false }, "allenai/molmo-2-8b": { "attachment": true, "cost": { "input": 0.2, "output": 0.2 }, "description": "Molmo 2 8B is an AI model provided by nano-gpt.", "family": "allenai", "id": "allenai/molmo-2-8b", "last_updated": "2026-02-14", "limit": { "context": 36864, "input": 36864, "output": 36864 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Molmo 2 8B", "open_weights": false, "reasoning": false, "release_date": "2026-02-14", "structured_output": false, "tool_call": false }, "allenai/olmo-3-32b-think": { "attachment": false, "cost": { "input": 0.3, "output": 0.44999999999999996 }, "description": "Olmo 3 32B Think is an AI model provided by nano-gpt.", "family": "allenai", "id": "allenai/olmo-3-32b-think", "last_updated": "2025-11-01", "limit": { "context": 128000, "input": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Olmo 3 32B Think", "open_weights": false, "reasoning": true, "release_date": "2025-11-01", "structured_output": false, "tool_call": false }, "allenai/olmo-3.1-32b-instruct": { "attachment": false, "cost": { "input": 0.2, "output": 0.6 }, "description": "Olmo 3.1 32B Instruct is an AI model provided by nano-gpt.", "family": "allenai", "id": "allenai/olmo-3.1-32b-instruct", "last_updated": "2026-01-25", "limit": { "context": 65536, "input": 65536, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Olmo 3.1 32B Instruct", "open_weights": false, "reasoning": false, "release_date": "2026-01-25", "structured_output": false, "tool_call": false }, "allenai/olmo-3.1-32b-think": { "attachment": false, "cost": { "input": 0.15, "output": 0.5 }, "description": "Olmo 3.1 32B Think is an AI model provided by nano-gpt.", "family": "allenai", "id": "allenai/olmo-3.1-32b-think", "last_updated": "2026-01-25", "limit": { "context": 65536, "input": 65536, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Olmo 3.1 32B Think", "open_weights": false, "reasoning": true, "release_date": "2026-01-25", "structured_output": false, "tool_call": false }, "amazon/nova-2-lite-v1": { "attachment": false, "cost": { "input": 0.5099999999999999, "output": 4.25 }, "description": "Amazon Nova 2 Lite is an AI model provided by nano-gpt.", "family": "nova", "id": "amazon/nova-2-lite-v1", "last_updated": "2024-12-03", "limit": { "context": 1000000, "input": 1000000, "output": 65535 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Amazon Nova 2 Lite", "open_weights": false, "reasoning": false, "release_date": "2024-12-03", "structured_output": false, "tool_call": false }, "amazon/nova-lite-v1": { "attachment": false, "cost": { "input": 0.0595, "output": 0.238 }, "description": "Amazon Nova Lite 1.0 is an AI model provided by nano-gpt.", "family": "nova-lite", "id": "amazon/nova-lite-v1", "last_updated": "2024-12-03", "limit": { "context": 300000, "input": 300000, "output": 5120 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Amazon Nova Lite 1.0", "open_weights": false, "reasoning": false, "release_date": "2024-12-03", "structured_output": false, "tool_call": false }, "amazon/nova-micro-v1": { "attachment": false, "cost": { "input": 0.0357, "output": 0.1394 }, "description": "Amazon Nova Micro 1.0 is an AI model provided by nano-gpt.", "family": "nova-micro", "id": "amazon/nova-micro-v1", "last_updated": "2024-12-03", "limit": { "context": 128000, "input": 128000, "output": 5120 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Amazon Nova Micro 1.0", "open_weights": false, "reasoning": false, "release_date": "2024-12-03", "structured_output": false, "tool_call": false }, "amazon/nova-pro-v1": { "attachment": false, "cost": { "input": 0.7989999999999999, "output": 3.1959999999999997 }, "description": "Amazon Nova Pro 1.0 is an AI model provided by nano-gpt.", "family": "nova-pro", "id": "amazon/nova-pro-v1", "last_updated": "2024-12-03", "limit": { "context": 300000, "input": 300000, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Amazon Nova Pro 1.0", "open_weights": false, "reasoning": false, "release_date": "2024-12-03", "structured_output": false, "tool_call": false }, "anthracite-org/magnum-v2-72b": { "attachment": false, "cost": { "input": 2.006, "output": 2.992 }, "description": "Magnum V2 72B is an AI model provided by nano-gpt.", "family": "llama", "id": "anthracite-org/magnum-v2-72b", "last_updated": "2024-07-01", "limit": { "context": 16384, "input": 16384, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Magnum V2 72B", "open_weights": false, "reasoning": false, "release_date": "2024-07-01", "structured_output": false, "tool_call": false }, "anthracite-org/magnum-v4-72b": { "attachment": true, "cost": { "input": 2.006, "output": 2.992 }, "description": "Magnum v4 72B is an AI model provided by nano-gpt.", "family": "llama", "id": "anthracite-org/magnum-v4-72b", "last_updated": "2025-01-01", "limit": { "context": 16384, "input": 16384, "output": 8192 }, "modalities": { "input": [ "text", "pdf" ], "output": [ "text" ] }, "name": "Magnum v4 72B", "open_weights": false, "reasoning": false, "release_date": "2025-01-01", "structured_output": false, "tool_call": false }, "anthropic/claude-opus-4.6": { "attachment": true, "cost": { "input": 4.998, "output": 25.007 }, "description": "Claude 4.6 Opus is an AI model provided by nano-gpt.", "family": "claude-opus", "id": "anthropic/claude-opus-4.6", "last_updated": "2026-02-05", "limit": { "context": 1000000, "input": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude 4.6 Opus", "open_weights": false, "reasoning": true, "release_date": "2026-02-05", "structured_output": true, "tool_call": true }, "anthropic/claude-opus-4.6:thinking": { "attachment": true, "cost": { "input": 4.998, "output": 25.007 }, "description": "Claude 4.6 Opus Thinking is an AI model provided by nano-gpt.", "family": "claude-opus", "id": "anthropic/claude-opus-4.6:thinking", "last_updated": "2026-02-05", "limit": { "context": 1000000, "input": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude 4.6 Opus Thinking", "open_weights": false, "reasoning": true, "release_date": "2026-02-05", "structured_output": true, "tool_call": true }, "anthropic/claude-opus-4.6:thinking:low": { "attachment": true, "cost": { "input": 4.998, "output": 25.007 }, "description": "Claude 4.6 Opus Thinking Low is an AI model provided by nano-gpt.", "family": "claude-opus", "id": "anthropic/claude-opus-4.6:thinking:low", "last_updated": "2026-02-05", "limit": { "context": 1000000, "input": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude 4.6 Opus Thinking Low", "open_weights": false, "reasoning": true, "release_date": "2026-02-05", "structured_output": true, "tool_call": true }, "anthropic/claude-opus-4.6:thinking:max": { "attachment": true, "cost": { "input": 4.998, "output": 25.007 }, "description": "Claude 4.6 Opus Thinking Max is an AI model provided by nano-gpt.", "family": "claude-opus", "id": "anthropic/claude-opus-4.6:thinking:max", "last_updated": "2026-02-05", "limit": { "context": 1000000, "input": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude 4.6 Opus Thinking Max", "open_weights": false, "reasoning": true, "release_date": "2026-02-05", "structured_output": true, "tool_call": true }, "anthropic/claude-opus-4.6:thinking:medium": { "attachment": true, "cost": { "input": 4.998, "output": 25.007 }, "description": "Claude 4.6 Opus Thinking Medium is an AI model provided by nano-gpt.", "family": "claude-opus", "id": "anthropic/claude-opus-4.6:thinking:medium", "last_updated": "2026-02-05", "limit": { "context": 1000000, "input": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude 4.6 Opus Thinking Medium", "open_weights": false, "reasoning": true, "release_date": "2026-02-05", "structured_output": true, "tool_call": true }, "anthropic/claude-sonnet-4.6": { "attachment": true, "cost": { "input": 2.992, "output": 14.993999999999998 }, "description": "Claude Sonnet 4.6 is an AI model provided by nano-gpt.", "family": "claude-sonnet", "id": "anthropic/claude-sonnet-4.6", "knowledge": "2025-08-31", "last_updated": "2026-02-17", "limit": { "context": 1000000, "input": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.6", "open_weights": false, "reasoning": false, "release_date": "2026-02-17", "structured_output": true, "tool_call": true }, "anthropic/claude-sonnet-4.6:thinking": { "attachment": true, "cost": { "input": 2.992, "output": 14.993999999999998 }, "description": "Claude Sonnet 4.6 Thinking is an AI model provided by nano-gpt.", "family": "claude-sonnet", "id": "anthropic/claude-sonnet-4.6:thinking", "knowledge": "2025-08-31", "last_updated": "2026-02-17", "limit": { "context": 1000000, "input": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.6 Thinking", "open_weights": false, "reasoning": true, "release_date": "2026-02-17", "structured_output": true, "tool_call": true }, "arcee-ai/trinity-large": { "attachment": false, "cost": { "input": 0.25, "output": 1 }, "description": "Trinity Large is an AI model provided by nano-gpt.", "family": "trinity", "id": "arcee-ai/trinity-large", "last_updated": "2025-12-01", "limit": { "context": 131072, "input": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Trinity Large", "open_weights": false, "reasoning": false, "release_date": "2025-12-01", "structured_output": false, "tool_call": false }, "arcee-ai/trinity-mini": { "attachment": false, "cost": { "input": 0.045000000000000005, "output": 0.15 }, "description": "Trinity Mini is an AI model provided by nano-gpt.", "family": "trinity-mini", "id": "arcee-ai/trinity-mini", "last_updated": "2025-12-01", "limit": { "context": 131072, "input": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Trinity Mini", "open_weights": false, "reasoning": false, "release_date": "2025-12-01", "structured_output": false, "tool_call": false }, "asi1-mini": { "attachment": true, "cost": { "input": 1, "output": 1 }, "description": "ASI1 Mini is an AI model provided by nano-gpt.", "id": "asi1-mini", "last_updated": "2025-03-25", "limit": { "context": 128000, "input": 128000, "output": 16384 }, "modalities": { "input": [ "text", "pdf" ], "output": [ "text" ] }, "name": "ASI1 Mini", "open_weights": false, "reasoning": false, "release_date": "2025-03-25", "structured_output": false, "tool_call": false }, "auto-model": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Auto model is an AI model provided by nano-gpt.", "id": "auto-model", "last_updated": "2024-06-01", "limit": { "context": 1000000, "input": 1000000, "output": 1000000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Auto model", "open_weights": false, "reasoning": false, "release_date": "2024-06-01", "structured_output": false, "tool_call": false }, "auto-model-basic": { "attachment": false, "cost": { "input": 9.996, "output": 19.992 }, "description": "Auto model (Basic) is an AI model provided by nano-gpt.", "id": "auto-model-basic", "last_updated": "2024-06-01", "limit": { "context": 1000000, "input": 1000000, "output": 1000000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Auto model (Basic)", "open_weights": false, "reasoning": false, "release_date": "2024-06-01", "structured_output": false, "tool_call": false }, "auto-model-premium": { "attachment": false, "cost": { "input": 9.996, "output": 19.992 }, "description": "Auto model (Premium) is an AI model provided by nano-gpt.", "id": "auto-model-premium", "last_updated": "2024-06-01", "limit": { "context": 1000000, "input": 1000000, "output": 1000000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Auto model (Premium)", "open_weights": false, "reasoning": false, "release_date": "2024-06-01", "structured_output": false, "tool_call": false }, "auto-model-standard": { "attachment": false, "cost": { "input": 9.996, "output": 19.992 }, "description": "Auto model (Standard) is an AI model provided by nano-gpt.", "id": "auto-model-standard", "last_updated": "2024-06-01", "limit": { "context": 1000000, "input": 1000000, "output": 1000000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Auto model (Standard)", "open_weights": false, "reasoning": false, "release_date": "2024-06-01", "structured_output": false, "tool_call": false }, "azure-gpt-4-turbo": { "attachment": false, "cost": { "input": 9.996, "output": 30.005 }, "description": "Azure gpt-4-turbo is an AI model provided by nano-gpt.", "id": "azure-gpt-4-turbo", "last_updated": "2024-01-01", "limit": { "context": 128000, "input": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Azure gpt-4-turbo", "open_weights": false, "reasoning": false, "release_date": "2023-11-06", "structured_output": false, "tool_call": false }, "azure-gpt-4o": { "attachment": true, "cost": { "input": 2.499, "output": 9.996 }, "description": "Azure gpt-4o is an AI model provided by nano-gpt.", "id": "azure-gpt-4o", "last_updated": "2024-05-13", "limit": { "context": 128000, "input": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Azure gpt-4o", "open_weights": false, "reasoning": false, "release_date": "2024-05-13", "structured_output": true, "tool_call": true }, "azure-gpt-4o-mini": { "attachment": true, "cost": { "input": 0.1496, "output": 0.595 }, "description": "Azure gpt-4o-mini is an AI model provided by nano-gpt.", "id": "azure-gpt-4o-mini", "last_updated": "2024-07-18", "limit": { "context": 128000, "input": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Azure gpt-4o-mini", "open_weights": false, "reasoning": false, "release_date": "2024-07-18", "structured_output": true, "tool_call": true }, "azure-o1": { "attachment": false, "cost": { "input": 14.994, "output": 59.993 }, "description": "Azure o1 is an AI model provided by nano-gpt.", "id": "azure-o1", "last_updated": "2024-12-17", "limit": { "context": 200000, "input": 200000, "output": 100000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Azure o1", "open_weights": false, "reasoning": false, "release_date": "2024-12-17", "structured_output": false, "tool_call": false }, "azure-o3-mini": { "attachment": false, "cost": { "input": 1.088, "output": 4.3996 }, "description": "Azure o3-mini is an AI model provided by nano-gpt.", "id": "azure-o3-mini", "last_updated": "2025-01-31", "limit": { "context": 200000, "input": 200000, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Azure o3-mini", "open_weights": false, "reasoning": false, "release_date": "2025-01-31", "structured_output": false, "tool_call": false }, "baidu/ernie-4.5-300b-a47b": { "attachment": false, "cost": { "input": 0.35, "output": 1.15 }, "description": "ERNIE 4.5 300B is an AI model provided by nano-gpt.", "family": "ernie", "id": "baidu/ernie-4.5-300b-a47b", "last_updated": "2025-06-30", "limit": { "context": 131072, "input": 131072, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "ERNIE 4.5 300B", "open_weights": false, "reasoning": false, "release_date": "2025-06-30", "structured_output": false, "tool_call": false }, "baidu/ernie-4.5-vl-28b-a3b": { "attachment": true, "cost": { "input": 0.13999999999999999, "output": 0.5599999999999999 }, "description": "ERNIE 4.5 VL 28B is an AI model provided by nano-gpt.", "family": "ernie", "id": "baidu/ernie-4.5-vl-28b-a3b", "last_updated": "2025-06-30", "limit": { "context": 32768, "input": 32768, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "ERNIE 4.5 VL 28B", "open_weights": false, "reasoning": false, "release_date": "2025-06-30", "structured_output": false, "tool_call": false }, "baseten/Kimi-K2-Instruct-FP4": { "attachment": false, "cost": { "input": 0.1, "output": 2 }, "description": "Kimi K2 0711 Instruct FP4 is an AI model provided by nano-gpt.", "family": "kimi", "id": "baseten/Kimi-K2-Instruct-FP4", "last_updated": "2025-07-11", "limit": { "context": 128000, "input": 128000, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 0711 Instruct FP4", "open_weights": false, "reasoning": false, "release_date": "2025-07-11", "structured_output": false, "tool_call": false }, "brave": { "attachment": false, "cost": { "input": 5, "output": 5 }, "description": "Brave (Answers) is an AI model provided by nano-gpt.", "id": "brave", "last_updated": "2024-01-01", "limit": { "context": 8192, "input": 8192, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Brave (Answers)", "open_weights": false, "reasoning": false, "release_date": "2023-03-02", "structured_output": false, "tool_call": false }, "brave-pro": { "attachment": false, "cost": { "input": 5, "output": 5 }, "description": "Brave (Pro) is an AI model provided by nano-gpt.", "id": "brave-pro", "last_updated": "2024-01-01", "limit": { "context": 8192, "input": 8192, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Brave (Pro)", "open_weights": false, "reasoning": false, "release_date": "2023-03-02", "structured_output": false, "tool_call": false }, "brave-research": { "attachment": false, "cost": { "input": 5, "output": 5 }, "description": "Brave (Research) is an AI model provided by nano-gpt.", "id": "brave-research", "last_updated": "2024-01-01", "limit": { "context": 16384, "input": 16384, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Brave (Research)", "open_weights": false, "reasoning": false, "release_date": "2023-03-02", "structured_output": false, "tool_call": false }, "chroma": { "attachment": true, "description": "Chroma is an AI model provided by nano-gpt.", "id": "chroma", "last_updated": "2025-08-12", "limit": { "context": 0, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "name": "Chroma", "open_weights": false, "reasoning": false, "release_date": "2025-08-12", "structured_output": false, "temperature": true, "tool_call": false }, "chutesai/Mistral-Small-3.2-24B-Instruct-2506": { "attachment": false, "cost": { "input": 0.2, "output": 0.4 }, "description": "Mistral Small 3.2 24b Instruct is an AI model provided by nano-gpt.", "family": "chutesai", "id": "chutesai/Mistral-Small-3.2-24B-Instruct-2506", "last_updated": "2025-04-15", "limit": { "context": 128000, "input": 128000, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral Small 3.2 24b Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-04-15", "structured_output": false, "tool_call": false }, "claude-3-5-haiku-20241022": { "attachment": true, "cost": { "input": 0.8, "output": 4 }, "description": "Claude 3.5 Haiku is an AI model provided by nano-gpt.", "id": "claude-3-5-haiku-20241022", "last_updated": "2024-10-22", "limit": { "context": 200000, "input": 200000, "output": 8192 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude 3.5 Haiku", "open_weights": false, "reasoning": false, "release_date": "2024-10-22", "structured_output": true, "tool_call": true }, "claude-3-5-sonnet-20240620": { "attachment": true, "cost": { "input": 2.992, "output": 14.994 }, "description": "Claude 3.5 Sonnet Old is an AI model provided by nano-gpt.", "id": "claude-3-5-sonnet-20240620", "last_updated": "2024-06-20", "limit": { "context": 200000, "input": 200000, "output": 8192 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude 3.5 Sonnet Old", "open_weights": false, "reasoning": false, "release_date": "2024-06-20", "structured_output": true, "tool_call": true }, "claude-3-5-sonnet-20241022": { "attachment": true, "cost": { "input": 2.992, "output": 14.994 }, "description": "Claude 3.5 Sonnet is an AI model provided by nano-gpt.", "id": "claude-3-5-sonnet-20241022", "last_updated": "2025-08-26", "limit": { "context": 200000, "input": 200000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Claude 3.5 Sonnet", "open_weights": false, "reasoning": false, "release_date": "2025-08-26", "structured_output": true, "tool_call": true }, "claude-3-7-sonnet-20250219": { "attachment": true, "cost": { "input": 2.992, "output": 14.994 }, "description": "Claude 3.7 Sonnet is an AI model provided by nano-gpt.", "id": "claude-3-7-sonnet-20250219", "last_updated": "2025-02-19", "limit": { "context": 200000, "input": 200000, "output": 16000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude 3.7 Sonnet", "open_weights": false, "reasoning": false, "release_date": "2025-02-19", "structured_output": true, "tool_call": true }, "claude-3-7-sonnet-reasoner": { "attachment": true, "cost": { "input": 3, "output": 15 }, "description": "Claude 3.7 Sonnet Reasoner is an AI model provided by nano-gpt.", "id": "claude-3-7-sonnet-reasoner", "last_updated": "2025-03-29", "limit": { "context": 128000, "input": 128000, "output": 8192 }, "modalities": { "input": [ "text", "pdf" ], "output": [ "text" ] }, "name": "Claude 3.7 Sonnet Reasoner", "open_weights": false, "reasoning": false, "release_date": "2025-03-29", "structured_output": false, "tool_call": false }, "claude-3-7-sonnet-thinking": { "attachment": true, "cost": { "input": 2.992, "output": 14.994 }, "description": "Claude 3.7 Sonnet Thinking is an AI model provided by nano-gpt.", "id": "claude-3-7-sonnet-thinking", "last_updated": "2025-02-24", "limit": { "context": 200000, "input": 200000, "output": 16000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude 3.7 Sonnet Thinking", "open_weights": false, "reasoning": true, "release_date": "2025-02-24", "structured_output": true, "tool_call": true }, "claude-3-7-sonnet-thinking:1024": { "attachment": true, "cost": { "input": 2.992, "output": 14.994 }, "description": "Claude 3.7 Sonnet Thinking (1K) is an AI model provided by nano-gpt.", "id": "claude-3-7-sonnet-thinking:1024", "last_updated": "2025-02-24", "limit": { "context": 200000, "input": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude 3.7 Sonnet Thinking (1K)", "open_weights": false, "reasoning": true, "release_date": "2025-02-24", "structured_output": true, "tool_call": true }, "claude-3-7-sonnet-thinking:128000": { "attachment": true, "cost": { "input": 2.992, "output": 14.994 }, "description": "Claude 3.7 Sonnet Thinking (128K) is an AI model provided by nano-gpt.", "id": "claude-3-7-sonnet-thinking:128000", "last_updated": "2025-02-24", "limit": { "context": 200000, "input": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude 3.7 Sonnet Thinking (128K)", "open_weights": false, "reasoning": true, "release_date": "2025-02-24", "structured_output": true, "tool_call": true }, "claude-3-7-sonnet-thinking:32768": { "attachment": true, "cost": { "input": 2.992, "output": 14.994 }, "description": "Claude 3.7 Sonnet Thinking (32K) is an AI model provided by nano-gpt.", "id": "claude-3-7-sonnet-thinking:32768", "last_updated": "2025-07-15", "limit": { "context": 200000, "input": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude 3.7 Sonnet Thinking (32K)", "open_weights": false, "reasoning": true, "release_date": "2025-07-15", "structured_output": true, "tool_call": true }, "claude-3-7-sonnet-thinking:8192": { "attachment": true, "cost": { "input": 2.992, "output": 14.994 }, "description": "Claude 3.7 Sonnet Thinking (8K) is an AI model provided by nano-gpt.", "id": "claude-3-7-sonnet-thinking:8192", "last_updated": "2025-02-24", "limit": { "context": 200000, "input": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude 3.7 Sonnet Thinking (8K)", "open_weights": false, "reasoning": true, "release_date": "2025-02-24", "structured_output": true, "tool_call": true }, "claude-haiku-4-5-20251001": { "attachment": true, "cost": { "input": 1, "output": 5 }, "description": "Claude Haiku 4.5 is an AI model provided by nano-gpt.", "id": "claude-haiku-4-5-20251001", "last_updated": "2025-10-15", "limit": { "context": 200000, "input": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Haiku 4.5", "open_weights": false, "reasoning": false, "release_date": "2025-10-15", "structured_output": true, "tool_call": true }, "claude-opus-4-1-20250805": { "attachment": true, "cost": { "input": 14.994, "output": 75.004 }, "description": "Claude 4.1 Opus is an AI model provided by nano-gpt.", "id": "claude-opus-4-1-20250805", "last_updated": "2025-08-05", "limit": { "context": 200000, "input": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude 4.1 Opus", "open_weights": false, "reasoning": false, "release_date": "2025-08-05", "structured_output": true, "tool_call": true }, "claude-opus-4-1-thinking": { "attachment": true, "cost": { "input": 14.994, "output": 75.004 }, "description": "Claude 4.1 Opus Thinking is an AI model provided by nano-gpt.", "id": "claude-opus-4-1-thinking", "last_updated": "2025-05-22", "limit": { "context": 200000, "input": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude 4.1 Opus Thinking", "open_weights": false, "reasoning": true, "release_date": "2025-05-22", "structured_output": true, "tool_call": true }, "claude-opus-4-1-thinking:1024": { "attachment": true, "cost": { "input": 14.994, "output": 75.004 }, "description": "Claude 4.1 Opus Thinking (1K) is an AI model provided by nano-gpt.", "id": "claude-opus-4-1-thinking:1024", "last_updated": "2025-05-22", "limit": { "context": 200000, "input": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude 4.1 Opus Thinking (1K)", "open_weights": false, "reasoning": true, "release_date": "2025-05-22", "structured_output": true, "tool_call": true }, "claude-opus-4-1-thinking:32000": { "attachment": true, "cost": { "input": 14.994, "output": 75.004 }, "description": "Claude 4.1 Opus Thinking (32K) is an AI model provided by nano-gpt.", "id": "claude-opus-4-1-thinking:32000", "last_updated": "2025-05-22", "limit": { "context": 200000, "input": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude 4.1 Opus Thinking (32K)", "open_weights": false, "reasoning": true, "release_date": "2025-05-22", "structured_output": true, "tool_call": true }, "claude-opus-4-1-thinking:32768": { "attachment": true, "cost": { "input": 14.994, "output": 75.004 }, "description": "Claude 4.1 Opus Thinking (32K) is an AI model provided by nano-gpt.", "id": "claude-opus-4-1-thinking:32768", "last_updated": "2025-05-22", "limit": { "context": 200000, "input": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude 4.1 Opus Thinking (32K)", "open_weights": false, "reasoning": true, "release_date": "2025-05-22", "structured_output": true, "tool_call": true }, "claude-opus-4-1-thinking:8192": { "attachment": true, "cost": { "input": 14.994, "output": 75.004 }, "description": "Claude 4.1 Opus Thinking (8K) is an AI model provided by nano-gpt.", "id": "claude-opus-4-1-thinking:8192", "last_updated": "2025-05-22", "limit": { "context": 200000, "input": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude 4.1 Opus Thinking (8K)", "open_weights": false, "reasoning": true, "release_date": "2025-05-22", "structured_output": true, "tool_call": true }, "claude-opus-4-20250514": { "attachment": true, "cost": { "input": 14.994, "output": 75.004 }, "description": "Claude 4 Opus is an AI model provided by nano-gpt.", "id": "claude-opus-4-20250514", "last_updated": "2025-05-14", "limit": { "context": 200000, "input": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude 4 Opus", "open_weights": false, "reasoning": false, "release_date": "2025-05-14", "structured_output": true, "tool_call": true }, "claude-opus-4-5-20251101": { "attachment": true, "cost": { "input": 4.998, "output": 25.007 }, "description": "Claude 4.5 Opus is an AI model provided by nano-gpt.", "id": "claude-opus-4-5-20251101", "last_updated": "2025-11-01", "limit": { "context": 200000, "input": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude 4.5 Opus", "open_weights": false, "reasoning": true, "release_date": "2025-11-01", "structured_output": true, "tool_call": true }, "claude-opus-4-5-20251101:thinking": { "attachment": true, "cost": { "input": 4.998, "output": 25.007 }, "description": "Claude 4.5 Opus Thinking is an AI model provided by nano-gpt.", "id": "claude-opus-4-5-20251101:thinking", "last_updated": "2025-11-01", "limit": { "context": 200000, "input": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude 4.5 Opus Thinking", "open_weights": false, "reasoning": true, "release_date": "2025-11-01", "structured_output": true, "tool_call": true }, "claude-opus-4-thinking": { "attachment": true, "cost": { "input": 14.994, "output": 75.004 }, "description": "Claude 4 Opus Thinking is an AI model provided by nano-gpt.", "id": "claude-opus-4-thinking", "last_updated": "2025-07-15", "limit": { "context": 200000, "input": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude 4 Opus Thinking", "open_weights": false, "reasoning": true, "release_date": "2025-07-15", "structured_output": true, "tool_call": true }, "claude-opus-4-thinking:1024": { "attachment": true, "cost": { "input": 14.994, "output": 75.004 }, "description": "Claude 4 Opus Thinking (1K) is an AI model provided by nano-gpt.", "id": "claude-opus-4-thinking:1024", "last_updated": "2025-05-22", "limit": { "context": 200000, "input": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude 4 Opus Thinking (1K)", "open_weights": false, "reasoning": true, "release_date": "2025-05-22", "structured_output": true, "tool_call": true }, "claude-opus-4-thinking:32000": { "attachment": true, "cost": { "input": 14.994, "output": 75.004 }, "description": "Claude 4 Opus Thinking (32K) is an AI model provided by nano-gpt.", "id": "claude-opus-4-thinking:32000", "last_updated": "2025-05-22", "limit": { "context": 200000, "input": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude 4 Opus Thinking (32K)", "open_weights": false, "reasoning": true, "release_date": "2025-05-22", "structured_output": true, "tool_call": true }, "claude-opus-4-thinking:32768": { "attachment": true, "cost": { "input": 14.994, "output": 75.004 }, "description": "Claude 4 Opus Thinking (32K) is an AI model provided by nano-gpt.", "id": "claude-opus-4-thinking:32768", "last_updated": "2025-05-22", "limit": { "context": 200000, "input": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude 4 Opus Thinking (32K)", "open_weights": false, "reasoning": true, "release_date": "2025-05-22", "structured_output": true, "tool_call": true }, "claude-opus-4-thinking:8192": { "attachment": true, "cost": { "input": 14.994, "output": 75.004 }, "description": "Claude 4 Opus Thinking (8K) is an AI model provided by nano-gpt.", "id": "claude-opus-4-thinking:8192", "last_updated": "2025-05-22", "limit": { "context": 200000, "input": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude 4 Opus Thinking (8K)", "open_weights": false, "reasoning": true, "release_date": "2025-05-22", "structured_output": true, "tool_call": true }, "claude-sonnet-4-20250514": { "attachment": true, "cost": { "input": 2.992, "output": 14.994 }, "description": "Claude 4 Sonnet is an AI model provided by nano-gpt.", "id": "claude-sonnet-4-20250514", "last_updated": "2025-09-29", "limit": { "context": 200000, "input": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude 4 Sonnet", "open_weights": false, "reasoning": false, "release_date": "2025-09-29", "structured_output": true, "tool_call": true }, "claude-sonnet-4-5-20250929": { "attachment": true, "cost": { "input": 2.992, "output": 14.994 }, "description": "Claude Sonnet 4.5 is an AI model provided by nano-gpt.", "id": "claude-sonnet-4-5-20250929", "last_updated": "2025-09-29", "limit": { "context": 1000000, "input": 1000000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.5", "open_weights": false, "reasoning": false, "release_date": "2025-09-29", "structured_output": true, "tool_call": true }, "claude-sonnet-4-5-20250929-thinking": { "attachment": true, "cost": { "input": 2.992, "output": 14.994 }, "description": "Claude Sonnet 4.5 Thinking is an AI model provided by nano-gpt.", "id": "claude-sonnet-4-5-20250929-thinking", "last_updated": "2025-09-29", "limit": { "context": 1000000, "input": 1000000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.5 Thinking", "open_weights": false, "reasoning": true, "release_date": "2025-09-29", "structured_output": true, "tool_call": true }, "claude-sonnet-4-thinking": { "attachment": true, "cost": { "input": 2.992, "output": 14.994 }, "description": "Claude 4 Sonnet Thinking is an AI model provided by nano-gpt.", "id": "claude-sonnet-4-thinking", "last_updated": "2025-02-24", "limit": { "context": 1000000, "input": 1000000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude 4 Sonnet Thinking", "open_weights": false, "reasoning": true, "release_date": "2025-02-24", "structured_output": true, "tool_call": true }, "claude-sonnet-4-thinking:1024": { "attachment": true, "cost": { "input": 2.992, "output": 14.994 }, "description": "Claude 4 Sonnet Thinking (1K) is an AI model provided by nano-gpt.", "id": "claude-sonnet-4-thinking:1024", "last_updated": "2025-05-22", "limit": { "context": 1000000, "input": 1000000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude 4 Sonnet Thinking (1K)", "open_weights": false, "reasoning": true, "release_date": "2025-05-22", "structured_output": true, "tool_call": true }, "claude-sonnet-4-thinking:32768": { "attachment": true, "cost": { "input": 2.992, "output": 14.994 }, "description": "Claude 4 Sonnet Thinking (32K) is an AI model provided by nano-gpt.", "id": "claude-sonnet-4-thinking:32768", "last_updated": "2025-05-22", "limit": { "context": 1000000, "input": 1000000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude 4 Sonnet Thinking (32K)", "open_weights": false, "reasoning": true, "release_date": "2025-05-22", "structured_output": true, "tool_call": true }, "claude-sonnet-4-thinking:64000": { "attachment": true, "cost": { "input": 2.992, "output": 14.994 }, "description": "Claude 4 Sonnet Thinking (64K) is an AI model provided by nano-gpt.", "id": "claude-sonnet-4-thinking:64000", "last_updated": "2025-05-22", "limit": { "context": 1000000, "input": 1000000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude 4 Sonnet Thinking (64K)", "open_weights": false, "reasoning": true, "release_date": "2025-05-22", "structured_output": true, "tool_call": true }, "claude-sonnet-4-thinking:8192": { "attachment": true, "cost": { "input": 2.992, "output": 14.994 }, "description": "Claude 4 Sonnet Thinking (8K) is an AI model provided by nano-gpt.", "id": "claude-sonnet-4-thinking:8192", "last_updated": "2025-05-22", "limit": { "context": 1000000, "input": 1000000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude 4 Sonnet Thinking (8K)", "open_weights": false, "reasoning": true, "release_date": "2025-05-22", "structured_output": true, "tool_call": true }, "cognitivecomputations/dolphin-2.9.2-qwen2-72b": { "attachment": false, "cost": { "input": 0.306, "output": 0.306 }, "description": "Dolphin 72b is an AI model provided by nano-gpt.", "family": "qwen", "id": "cognitivecomputations/dolphin-2.9.2-qwen2-72b", "last_updated": "2025-02-27", "limit": { "context": 8192, "input": 8192, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Dolphin 72b", "open_weights": false, "reasoning": false, "release_date": "2025-02-27", "structured_output": false, "tool_call": false }, "cohere/command-r": { "attachment": false, "cost": { "input": 0.476, "output": 1.428 }, "description": "Cohere: Command R is an AI model provided by nano-gpt.", "family": "command-r", "id": "cohere/command-r", "last_updated": "2024-03-11", "limit": { "context": 128000, "input": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Cohere: Command R", "open_weights": false, "reasoning": false, "release_date": "2024-03-11", "structured_output": false, "tool_call": false }, "cohere/command-r-plus-08-2024": { "attachment": false, "cost": { "input": 2.856, "output": 14.246 }, "description": "Cohere: Command R+ is an AI model provided by nano-gpt.", "family": "command-r", "id": "cohere/command-r-plus-08-2024", "last_updated": "2024-08-30", "limit": { "context": 128000, "input": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Cohere: Command R+", "open_weights": false, "reasoning": false, "release_date": "2024-08-30", "structured_output": false, "tool_call": true }, "command-a-reasoning-08-2025": { "attachment": false, "cost": { "input": 2.5, "output": 10 }, "description": "Cohere Command A (08/2025) is an AI model provided by nano-gpt.", "id": "command-a-reasoning-08-2025", "last_updated": "2025-08-22", "limit": { "context": 256000, "input": 256000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Cohere Command A (08/2025)", "open_weights": false, "reasoning": false, "release_date": "2025-08-22", "structured_output": false, "tool_call": false }, "deepclaude": { "attachment": true, "cost": { "input": 3, "output": 15 }, "description": "DeepClaude is an AI model provided by nano-gpt.", "id": "deepclaude", "last_updated": "2025-02-01", "limit": { "context": 128000, "input": 128000, "output": 8192 }, "modalities": { "input": [ "text", "pdf" ], "output": [ "text" ] }, "name": "DeepClaude", "open_weights": false, "reasoning": false, "release_date": "2025-02-01", "structured_output": false, "tool_call": false }, "deepcogito/cogito-v1-preview-qwen-32B": { "attachment": false, "cost": { "input": 1.7999999999999998, "output": 1.7999999999999998 }, "description": "Cogito v1 Preview Qwen 32B is an AI model provided by nano-gpt.", "family": "qwen", "id": "deepcogito/cogito-v1-preview-qwen-32B", "last_updated": "2025-05-10", "limit": { "context": 128000, "input": 128000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Cogito v1 Preview Qwen 32B", "open_weights": false, "reasoning": false, "release_date": "2025-05-10", "structured_output": false, "tool_call": false }, "deepcogito/cogito-v2.1-671b": { "attachment": false, "cost": { "input": 1.25, "output": 1.25 }, "description": "Cogito v2.1 671B MoE is an AI model provided by nano-gpt.", "family": "cogito", "id": "deepcogito/cogito-v2.1-671b", "last_updated": "2025-11-19", "limit": { "context": 128000, "input": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Cogito v2.1 671B MoE", "open_weights": false, "reasoning": true, "release_date": "2025-11-19", "structured_output": false, "tool_call": false }, "deepseek-ai/DeepSeek-R1-0528": { "attachment": false, "cost": { "input": 0.4, "output": 1.7 }, "description": "DeepSeek R1 0528 is an AI model provided by nano-gpt.", "family": "deepseek", "id": "deepseek-ai/DeepSeek-R1-0528", "last_updated": "2025-05-28", "limit": { "context": 128000, "input": 128000, "output": 163840 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek R1 0528", "open_weights": false, "reasoning": true, "release_date": "2025-05-28", "structured_output": false, "tool_call": false }, "deepseek-ai/DeepSeek-V3.1": { "attachment": true, "cost": { "input": 0.2, "output": 0.7 }, "description": "DeepSeek V3.1 is an AI model provided by nano-gpt.", "family": "deepseek", "id": "deepseek-ai/DeepSeek-V3.1", "last_updated": "2025-07-26", "limit": { "context": 128000, "input": 128000, "output": 65536 }, "modalities": { "input": [ "text", "pdf" ], "output": [ "text" ] }, "name": "DeepSeek V3.1", "open_weights": false, "reasoning": false, "release_date": "2025-07-26", "structured_output": false, "tool_call": false }, "deepseek-ai/DeepSeek-V3.1-Terminus": { "attachment": false, "cost": { "input": 0.25, "output": 0.7 }, "description": "DeepSeek V3.1 Terminus is an AI model provided by nano-gpt.", "family": "deepseek", "id": "deepseek-ai/DeepSeek-V3.1-Terminus", "last_updated": "2025-08-02", "limit": { "context": 128000, "input": 128000, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3.1 Terminus", "open_weights": false, "reasoning": false, "release_date": "2025-08-02", "structured_output": true, "tool_call": true }, "deepseek-ai/DeepSeek-V3.1-Terminus:thinking": { "attachment": false, "cost": { "input": 0.25, "output": 0.7 }, "description": "DeepSeek V3.1 Terminus (Thinking) is an AI model provided by nano-gpt.", "family": "deepseek-thinking", "id": "deepseek-ai/DeepSeek-V3.1-Terminus:thinking", "last_updated": "2025-09-22", "limit": { "context": 128000, "input": 128000, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3.1 Terminus (Thinking)", "open_weights": false, "reasoning": false, "release_date": "2025-09-22", "structured_output": true, "tool_call": true }, "deepseek-ai/DeepSeek-V3.1:thinking": { "attachment": false, "cost": { "input": 0.2, "output": 0.7 }, "description": "DeepSeek V3.1 Thinking is an AI model provided by nano-gpt.", "family": "deepseek-thinking", "id": "deepseek-ai/DeepSeek-V3.1:thinking", "last_updated": "2025-08-21", "limit": { "context": 128000, "input": 128000, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3.1 Thinking", "open_weights": false, "reasoning": false, "release_date": "2025-08-21", "structured_output": false, "tool_call": false }, "deepseek-ai/deepseek-v3.2-exp": { "attachment": false, "cost": { "input": 0.27999999999999997, "output": 0.42000000000000004 }, "description": "DeepSeek V3.2 Exp is an AI model provided by nano-gpt.", "family": "deepseek", "id": "deepseek-ai/deepseek-v3.2-exp", "last_updated": "2025-09-29", "limit": { "context": 163840, "input": 163840, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3.2 Exp", "open_weights": false, "reasoning": false, "release_date": "2025-09-29", "structured_output": false, "tool_call": false }, "deepseek-ai/deepseek-v3.2-exp-thinking": { "attachment": false, "cost": { "input": 0.27999999999999997, "output": 0.42000000000000004 }, "description": "DeepSeek V3.2 Exp Thinking is an AI model provided by nano-gpt.", "family": "deepseek-thinking", "id": "deepseek-ai/deepseek-v3.2-exp-thinking", "last_updated": "2025-09-29", "limit": { "context": 163840, "input": 163840, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3.2 Exp Thinking", "open_weights": false, "reasoning": true, "release_date": "2025-09-29", "structured_output": false, "tool_call": false }, "deepseek-chat": { "attachment": true, "cost": { "input": 0.25, "output": 0.7 }, "description": "DeepSeek V3/Deepseek Chat is an AI model provided by nano-gpt.", "id": "deepseek-chat", "last_updated": "2025-02-27", "limit": { "context": 128000, "input": 128000, "output": 8192 }, "modalities": { "input": [ "text", "pdf" ], "output": [ "text" ] }, "name": "DeepSeek V3/Deepseek Chat", "open_weights": false, "reasoning": false, "release_date": "2025-02-27", "structured_output": true, "tool_call": true }, "deepseek-chat-cheaper": { "attachment": true, "cost": { "input": 0.25, "output": 0.7 }, "description": "DeepSeek V3/Chat Cheaper is an AI model provided by nano-gpt.", "id": "deepseek-chat-cheaper", "last_updated": "2025-04-15", "limit": { "context": 128000, "input": 128000, "output": 8192 }, "modalities": { "input": [ "text", "pdf" ], "output": [ "text" ] }, "name": "DeepSeek V3/Chat Cheaper", "open_weights": false, "reasoning": false, "release_date": "2025-04-15", "structured_output": true, "tool_call": true }, "deepseek-math-v2": { "attachment": false, "cost": { "input": 0.6, "output": 2.2 }, "description": "DeepSeek Math V2 is an AI model provided by nano-gpt.", "id": "deepseek-math-v2", "last_updated": "2025-12-03", "limit": { "context": 128000, "input": 128000, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek Math V2", "open_weights": false, "reasoning": false, "release_date": "2025-12-03", "structured_output": false, "tool_call": false }, "deepseek-r1": { "attachment": false, "cost": { "input": 0.4, "output": 1.7 }, "description": "DeepSeek R1 is an AI model provided by nano-gpt.", "id": "deepseek-r1", "last_updated": "2025-01-20", "limit": { "context": 128000, "input": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek R1", "open_weights": false, "reasoning": true, "release_date": "2025-01-20", "structured_output": false, "tool_call": false }, "deepseek-r1-sambanova": { "attachment": false, "cost": { "input": 4.998, "output": 6.987 }, "description": "DeepSeek R1 Fast is an AI model provided by nano-gpt.", "id": "deepseek-r1-sambanova", "last_updated": "2025-02-20", "limit": { "context": 128000, "input": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek R1 Fast", "open_weights": false, "reasoning": false, "release_date": "2025-02-20", "structured_output": false, "tool_call": false }, "deepseek-reasoner": { "attachment": false, "cost": { "input": 0.4, "output": 1.7 }, "description": "DeepSeek Reasoner is an AI model provided by nano-gpt.", "id": "deepseek-reasoner", "last_updated": "2025-01-20", "limit": { "context": 64000, "input": 64000, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek Reasoner", "open_weights": false, "reasoning": false, "release_date": "2025-01-20", "structured_output": false, "tool_call": false }, "deepseek-reasoner-cheaper": { "attachment": false, "cost": { "input": 0.4, "output": 1.7 }, "description": "Deepseek R1 Cheaper is an AI model provided by nano-gpt.", "id": "deepseek-reasoner-cheaper", "last_updated": "2025-01-20", "limit": { "context": 128000, "input": 128000, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Deepseek R1 Cheaper", "open_weights": false, "reasoning": false, "release_date": "2025-01-20", "structured_output": false, "tool_call": false }, "deepseek-v3-0324": { "attachment": false, "cost": { "input": 0.25, "output": 0.7 }, "description": "DeepSeek Chat 0324 is an AI model provided by nano-gpt.", "id": "deepseek-v3-0324", "last_updated": "2025-03-24", "limit": { "context": 128000, "input": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek Chat 0324", "open_weights": false, "reasoning": false, "release_date": "2025-03-24", "structured_output": true, "tool_call": true }, "deepseek/deepseek-prover-v2-671b": { "attachment": false, "cost": { "input": 1, "output": 2.5 }, "description": "DeepSeek Prover v2 671B is an AI model provided by nano-gpt.", "family": "deepseek", "id": "deepseek/deepseek-prover-v2-671b", "last_updated": "2025-04-30", "limit": { "context": 160000, "input": 160000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek Prover v2 671B", "open_weights": false, "reasoning": false, "release_date": "2025-04-30", "structured_output": false, "tool_call": false }, "deepseek/deepseek-v3.2": { "attachment": true, "cost": { "input": 0.27999999999999997, "output": 0.42000000000000004 }, "description": "DeepSeek V3.2 is an AI model provided by nano-gpt.", "family": "deepseek", "id": "deepseek/deepseek-v3.2", "last_updated": "2025-12-01", "limit": { "context": 163000, "input": 163000, "output": 65536 }, "modalities": { "input": [ "text", "pdf" ], "output": [ "text" ] }, "name": "DeepSeek V3.2", "open_weights": false, "reasoning": false, "release_date": "2025-12-01", "structured_output": true, "tool_call": true }, "deepseek/deepseek-v3.2-speciale": { "attachment": true, "cost": { "input": 0.27999999999999997, "output": 0.42000000000000004 }, "description": "DeepSeek V3.2 Speciale is an AI model provided by nano-gpt.", "family": "deepseek", "id": "deepseek/deepseek-v3.2-speciale", "last_updated": "2025-12-02", "limit": { "context": 163000, "input": 163000, "output": 65536 }, "modalities": { "input": [ "text", "pdf" ], "output": [ "text" ] }, "name": "DeepSeek V3.2 Speciale", "open_weights": false, "reasoning": true, "release_date": "2025-12-02", "structured_output": false, "tool_call": false }, "deepseek/deepseek-v3.2:thinking": { "attachment": true, "cost": { "input": 0.27999999999999997, "output": 0.42000000000000004 }, "description": "DeepSeek V3.2 Thinking is an AI model provided by nano-gpt.", "family": "deepseek", "id": "deepseek/deepseek-v3.2:thinking", "last_updated": "2025-12-01", "limit": { "context": 163000, "input": 163000, "output": 65536 }, "modalities": { "input": [ "text", "pdf" ], "output": [ "text" ] }, "name": "DeepSeek V3.2 Thinking", "open_weights": false, "reasoning": true, "release_date": "2025-12-01", "structured_output": true, "tool_call": true }, "dmind/dmind-1": { "attachment": false, "cost": { "input": 0.3, "output": 0.6 }, "description": "DMind-1 is an AI model provided by nano-gpt.", "family": "gpt", "id": "dmind/dmind-1", "last_updated": "2025-06-01", "limit": { "context": 32768, "input": 32768, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DMind-1", "open_weights": false, "reasoning": false, "release_date": "2025-06-01", "structured_output": false, "tool_call": false }, "dmind/dmind-1-mini": { "attachment": false, "cost": { "input": 0.2, "output": 0.4 }, "description": "DMind-1-Mini is an AI model provided by nano-gpt.", "family": "gpt", "id": "dmind/dmind-1-mini", "last_updated": "2025-06-01", "limit": { "context": 32768, "input": 32768, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DMind-1-Mini", "open_weights": false, "reasoning": false, "release_date": "2025-06-01", "structured_output": false, "tool_call": false }, "doubao-1-5-thinking-pro-250415": { "attachment": true, "cost": { "input": 0.6, "output": 2.4 }, "description": "Doubao 1.5 Thinking Pro is an AI model provided by nano-gpt.", "id": "doubao-1-5-thinking-pro-250415", "last_updated": "2025-04-17", "limit": { "context": 128000, "input": 128000, "output": 16384 }, "modalities": { "input": [ "text", "pdf" ], "output": [ "text" ] }, "name": "Doubao 1.5 Thinking Pro", "open_weights": false, "reasoning": false, "release_date": "2025-04-17", "structured_output": false, "tool_call": false }, "doubao-1-5-thinking-pro-vision-250415": { "attachment": true, "cost": { "input": 0.6, "output": 2.4 }, "description": "Doubao 1.5 Thinking Pro Vision is an AI model provided by nano-gpt.", "id": "doubao-1-5-thinking-pro-vision-250415", "last_updated": "2025-04-15", "limit": { "context": 128000, "input": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Doubao 1.5 Thinking Pro Vision", "open_weights": false, "reasoning": false, "release_date": "2025-04-15", "structured_output": false, "tool_call": false }, "doubao-1-5-thinking-vision-pro-250428": { "attachment": true, "cost": { "input": 0.55, "output": 1.43 }, "description": "Doubao 1.5 Thinking Vision Pro is an AI model provided by nano-gpt.", "id": "doubao-1-5-thinking-vision-pro-250428", "last_updated": "2025-05-15", "limit": { "context": 128000, "input": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Doubao 1.5 Thinking Vision Pro", "open_weights": false, "reasoning": false, "release_date": "2025-05-15", "structured_output": false, "tool_call": false }, "doubao-1.5-pro-256k": { "attachment": false, "cost": { "input": 0.799, "output": 1.445 }, "description": "Doubao 1.5 Pro 256k is an AI model provided by nano-gpt.", "id": "doubao-1.5-pro-256k", "last_updated": "2025-03-12", "limit": { "context": 256000, "input": 256000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Doubao 1.5 Pro 256k", "open_weights": false, "reasoning": false, "release_date": "2025-03-12", "structured_output": false, "tool_call": false }, "doubao-1.5-pro-32k": { "attachment": false, "cost": { "input": 0.1343, "output": 0.3349 }, "description": "Doubao 1.5 Pro 32k is an AI model provided by nano-gpt.", "id": "doubao-1.5-pro-32k", "last_updated": "2025-01-22", "limit": { "context": 32000, "input": 32000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Doubao 1.5 Pro 32k", "open_weights": false, "reasoning": false, "release_date": "2025-01-22", "structured_output": false, "tool_call": false }, "doubao-1.5-vision-pro-32k": { "attachment": true, "cost": { "input": 0.459, "output": 1.377 }, "description": "Doubao 1.5 Vision Pro 32k is an AI model provided by nano-gpt.", "id": "doubao-1.5-vision-pro-32k", "last_updated": "2025-01-22", "limit": { "context": 32000, "input": 32000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Doubao 1.5 Vision Pro 32k", "open_weights": false, "reasoning": false, "release_date": "2025-01-22", "structured_output": false, "tool_call": false }, "doubao-seed-1-6-250615": { "attachment": false, "cost": { "input": 0.204, "output": 0.51 }, "description": "Doubao Seed 1.6 is an AI model provided by nano-gpt.", "id": "doubao-seed-1-6-250615", "last_updated": "2025-06-15", "limit": { "context": 256000, "input": 256000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Doubao Seed 1.6", "open_weights": false, "reasoning": false, "release_date": "2025-06-15", "structured_output": false, "tool_call": false }, "doubao-seed-1-6-flash-250615": { "attachment": false, "cost": { "input": 0.0374, "output": 0.374 }, "description": "Doubao Seed 1.6 Flash is an AI model provided by nano-gpt.", "id": "doubao-seed-1-6-flash-250615", "last_updated": "2025-06-15", "limit": { "context": 256000, "input": 256000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Doubao Seed 1.6 Flash", "open_weights": false, "reasoning": false, "release_date": "2025-06-15", "structured_output": false, "tool_call": false }, "doubao-seed-1-6-thinking-250615": { "attachment": false, "cost": { "input": 0.204, "output": 2.04 }, "description": "Doubao Seed 1.6 Thinking is an AI model provided by nano-gpt.", "id": "doubao-seed-1-6-thinking-250615", "last_updated": "2025-06-15", "limit": { "context": 256000, "input": 256000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Doubao Seed 1.6 Thinking", "open_weights": false, "reasoning": false, "release_date": "2025-06-15", "structured_output": false, "tool_call": false }, "doubao-seed-1-8-251215": { "attachment": false, "cost": { "input": 0.612, "output": 6.12 }, "description": "Doubao Seed 1.8 is an AI model provided by nano-gpt.", "id": "doubao-seed-1-8-251215", "last_updated": "2025-12-15", "limit": { "context": 128000, "input": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Doubao Seed 1.8", "open_weights": false, "reasoning": false, "release_date": "2025-12-15", "structured_output": false, "tool_call": false }, "doubao-seed-2-0-code-preview-260215": { "attachment": false, "cost": { "input": 0.782, "output": 3.893 }, "description": "Doubao Seed 2.0 Code Preview is an AI model provided by nano-gpt.", "id": "doubao-seed-2-0-code-preview-260215", "last_updated": "2026-02-14", "limit": { "context": 256000, "input": 256000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Doubao Seed 2.0 Code Preview", "open_weights": false, "reasoning": false, "release_date": "2026-02-14", "structured_output": false, "tool_call": false }, "doubao-seed-2-0-lite-260215": { "attachment": false, "cost": { "input": 0.1462, "output": 0.8738 }, "description": "Doubao Seed 2.0 Lite is an AI model provided by nano-gpt.", "id": "doubao-seed-2-0-lite-260215", "last_updated": "2026-02-14", "limit": { "context": 256000, "input": 256000, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Doubao Seed 2.0 Lite", "open_weights": false, "reasoning": false, "release_date": "2026-02-14", "structured_output": false, "tool_call": false }, "doubao-seed-2-0-mini-260215": { "attachment": false, "cost": { "input": 0.0493, "output": 0.4845 }, "description": "Doubao Seed 2.0 Mini is an AI model provided by nano-gpt.", "id": "doubao-seed-2-0-mini-260215", "last_updated": "2026-02-14", "limit": { "context": 256000, "input": 256000, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Doubao Seed 2.0 Mini", "open_weights": false, "reasoning": false, "release_date": "2026-02-14", "structured_output": false, "tool_call": false }, "doubao-seed-2-0-pro-260215": { "attachment": false, "cost": { "input": 0.782, "output": 3.876 }, "description": "Doubao Seed 2.0 Pro is an AI model provided by nano-gpt.", "id": "doubao-seed-2-0-pro-260215", "last_updated": "2026-02-14", "limit": { "context": 256000, "input": 256000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Doubao Seed 2.0 Pro", "open_weights": false, "reasoning": false, "release_date": "2026-02-14", "structured_output": false, "tool_call": false }, "doubao-seed-code-preview-latest": { "attachment": false, "cost": { "input": 0.1, "output": 0.4 }, "description": "Doubao Seed Code Preview is an AI model provided by nano-gpt.", "id": "doubao-seed-code-preview-latest", "last_updated": "2025-11-13", "limit": { "context": 256000, "input": 256000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Doubao Seed Code Preview", "open_weights": false, "reasoning": true, "release_date": "2025-11-13", "structured_output": false, "tool_call": false }, "ernie-4.5-8k-preview": { "attachment": false, "cost": { "input": 0.66, "output": 2.6 }, "description": "Ernie 4.5 8k Preview is an AI model provided by nano-gpt.", "id": "ernie-4.5-8k-preview", "last_updated": "2025-03-25", "limit": { "context": 8000, "input": 8000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Ernie 4.5 8k Preview", "open_weights": false, "reasoning": false, "release_date": "2025-03-25", "structured_output": false, "tool_call": false }, "ernie-4.5-turbo-128k": { "attachment": true, "cost": { "input": 0.132, "output": 0.55 }, "description": "Ernie 4.5 Turbo 128k is an AI model provided by nano-gpt.", "id": "ernie-4.5-turbo-128k", "last_updated": "2025-05-08", "limit": { "context": 128000, "input": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Ernie 4.5 Turbo 128k", "open_weights": false, "reasoning": false, "release_date": "2025-05-08", "structured_output": false, "tool_call": false }, "ernie-4.5-turbo-vl-32k": { "attachment": true, "cost": { "input": 0.495, "output": 1.43 }, "description": "Ernie 4.5 Turbo VL 32k is an AI model provided by nano-gpt.", "id": "ernie-4.5-turbo-vl-32k", "last_updated": "2025-05-08", "limit": { "context": 32000, "input": 32000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Ernie 4.5 Turbo VL 32k", "open_weights": false, "reasoning": false, "release_date": "2025-05-08", "structured_output": false, "tool_call": false }, "ernie-5.0-thinking-latest": { "attachment": true, "cost": { "input": 1.1, "output": 2 }, "description": "Ernie 5.0 Thinking is an AI model provided by nano-gpt.", "id": "ernie-5.0-thinking-latest", "last_updated": "2025-11-18", "limit": { "context": 128000, "input": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Ernie 5.0 Thinking", "open_weights": false, "reasoning": true, "release_date": "2025-11-18", "structured_output": false, "tool_call": false }, "ernie-5.0-thinking-preview": { "attachment": true, "cost": { "input": 1.1, "output": 2 }, "description": "Ernie 5.0 Thinking Preview is an AI model provided by nano-gpt.", "id": "ernie-5.0-thinking-preview", "last_updated": "2025-11-18", "limit": { "context": 128000, "input": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Ernie 5.0 Thinking Preview", "open_weights": false, "reasoning": true, "release_date": "2025-11-18", "structured_output": false, "tool_call": false }, "ernie-x1-32k": { "attachment": true, "cost": { "input": 0.33, "output": 1.32 }, "description": "Ernie X1 32k is an AI model provided by nano-gpt.", "id": "ernie-x1-32k", "last_updated": "2025-05-08", "limit": { "context": 32000, "input": 32000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Ernie X1 32k", "open_weights": false, "reasoning": false, "release_date": "2025-05-08", "structured_output": false, "tool_call": false }, "ernie-x1-32k-preview": { "attachment": false, "cost": { "input": 0.33, "output": 1.32 }, "description": "Ernie X1 32k is an AI model provided by nano-gpt.", "id": "ernie-x1-32k-preview", "last_updated": "2025-04-03", "limit": { "context": 32000, "input": 32000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Ernie X1 32k", "open_weights": false, "reasoning": false, "release_date": "2025-04-03", "structured_output": false, "tool_call": false }, "ernie-x1-turbo-32k": { "attachment": true, "cost": { "input": 0.165, "output": 0.66 }, "description": "Ernie X1 Turbo 32k is an AI model provided by nano-gpt.", "id": "ernie-x1-turbo-32k", "last_updated": "2025-05-08", "limit": { "context": 32000, "input": 32000, "output": 16384 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Ernie X1 Turbo 32k", "open_weights": false, "reasoning": false, "release_date": "2025-05-08", "structured_output": false, "tool_call": false }, "ernie-x1.1-preview": { "attachment": true, "cost": { "input": 0.15, "output": 0.6 }, "description": "ERNIE X1.1 is an AI model provided by nano-gpt.", "id": "ernie-x1.1-preview", "last_updated": "2025-09-10", "limit": { "context": 64000, "input": 64000, "output": 8192 }, "modalities": { "input": [ "text", "pdf" ], "output": [ "text" ] }, "name": "ERNIE X1.1", "open_weights": false, "reasoning": false, "release_date": "2025-09-10", "structured_output": false, "tool_call": false }, "essentialai/rnj-1-instruct": { "attachment": false, "cost": { "input": 0.15, "output": 0.15 }, "description": "RNJ-1 Instruct 8B is an AI model provided by nano-gpt.", "family": "rnj", "id": "essentialai/rnj-1-instruct", "last_updated": "2025-12-13", "limit": { "context": 128000, "input": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "RNJ-1 Instruct 8B", "open_weights": false, "reasoning": false, "release_date": "2025-12-13", "structured_output": false, "tool_call": false }, "exa-answer": { "attachment": false, "cost": { "input": 2.5, "output": 2.5 }, "description": "Exa (Answer) is an AI model provided by nano-gpt.", "id": "exa-answer", "last_updated": "2025-06-04", "limit": { "context": 4096, "input": 4096, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Exa (Answer)", "open_weights": false, "reasoning": false, "release_date": "2025-06-04", "structured_output": false, "tool_call": false }, "exa-research": { "attachment": false, "cost": { "input": 2.5, "output": 2.5 }, "description": "Exa (Research) is an AI model provided by nano-gpt.", "id": "exa-research", "last_updated": "2025-06-04", "limit": { "context": 8192, "input": 8192, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Exa (Research)", "open_weights": false, "reasoning": false, "release_date": "2025-06-04", "structured_output": false, "tool_call": false }, "exa-research-pro": { "attachment": false, "cost": { "input": 2.5, "output": 2.5 }, "description": "Exa (Research Pro) is an AI model provided by nano-gpt.", "id": "exa-research-pro", "last_updated": "2025-06-04", "limit": { "context": 16384, "input": 16384, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Exa (Research Pro)", "open_weights": false, "reasoning": false, "release_date": "2025-06-04", "structured_output": false, "tool_call": false }, "failspy/Meta-Llama-3-70B-Instruct-abliterated-v3.5": { "attachment": false, "cost": { "input": 0.7, "output": 0.7 }, "description": "Llama 3 70B abliterated is an AI model provided by nano-gpt.", "family": "llama", "id": "failspy/Meta-Llama-3-70B-Instruct-abliterated-v3.5", "last_updated": "2025-07-26", "limit": { "context": 8192, "input": 8192, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3 70B abliterated", "open_weights": false, "reasoning": false, "release_date": "2025-07-26", "structured_output": false, "tool_call": false }, "fastgpt": { "attachment": false, "cost": { "input": 7.5, "output": 7.5 }, "description": "Web Answer is an AI model provided by nano-gpt.", "id": "fastgpt", "last_updated": "2024-01-01", "limit": { "context": 32768, "input": 32768, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Web Answer", "open_weights": false, "reasoning": false, "release_date": "2023-08-01", "structured_output": false, "tool_call": false }, "featherless-ai/Qwerky-72B": { "attachment": false, "cost": { "input": 0.5, "output": 0.5 }, "description": "Qwerky 72B is an AI model provided by nano-gpt.", "family": "qwerky", "id": "featherless-ai/Qwerky-72B", "last_updated": "2025-03-20", "limit": { "context": 32000, "input": 32000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwerky 72B", "open_weights": false, "reasoning": false, "release_date": "2025-03-20", "structured_output": false, "tool_call": false }, "gemini-2.0-flash-001": { "attachment": true, "cost": { "input": 0.1003, "output": 0.408 }, "description": "Gemini 2.0 Flash is an AI model provided by nano-gpt.", "id": "gemini-2.0-flash-001", "last_updated": "2024-12-11", "limit": { "context": 1000000, "input": 1000000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemini 2.0 Flash", "open_weights": false, "reasoning": false, "release_date": "2024-12-11", "structured_output": true, "tool_call": true }, "gemini-2.0-flash-exp-image-generation": { "attachment": false, "cost": { "input": 0.2, "output": 0.8 }, "description": "Gemini Text + Image is an AI model provided by nano-gpt.", "id": "gemini-2.0-flash-exp-image-generation", "last_updated": "2025-02-19", "limit": { "context": 32767, "input": 32767, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Gemini Text + Image", "open_weights": false, "reasoning": false, "release_date": "2025-02-19", "structured_output": false, "tool_call": false }, "gemini-2.0-flash-lite": { "attachment": true, "cost": { "input": 0.0748, "output": 0.306 }, "description": "Gemini 2.0 Flash Lite is an AI model provided by nano-gpt.", "id": "gemini-2.0-flash-lite", "last_updated": "2024-12-11", "limit": { "context": 1000000, "input": 1000000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemini 2.0 Flash Lite", "open_weights": false, "reasoning": false, "release_date": "2024-12-11", "structured_output": false, "tool_call": false }, "gemini-2.0-flash-thinking-exp-01-21": { "attachment": true, "cost": { "input": 0.306, "output": 1.003 }, "description": "Gemini 2.0 Flash Thinking 0121 is an AI model provided by nano-gpt.", "id": "gemini-2.0-flash-thinking-exp-01-21", "last_updated": "2025-01-21", "limit": { "context": 1000000, "input": 1000000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemini 2.0 Flash Thinking 0121", "open_weights": false, "reasoning": true, "release_date": "2025-01-21", "structured_output": false, "tool_call": false }, "gemini-2.0-flash-thinking-exp-1219": { "attachment": false, "cost": { "input": 0.1003, "output": 0.408 }, "description": "Gemini 2.0 Flash Thinking 1219 is an AI model provided by nano-gpt.", "id": "gemini-2.0-flash-thinking-exp-1219", "last_updated": "2024-12-19", "limit": { "context": 32767, "input": 32767, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Gemini 2.0 Flash Thinking 1219", "open_weights": false, "reasoning": false, "release_date": "2024-12-19", "structured_output": false, "tool_call": false }, "gemini-2.0-pro-exp-02-05": { "attachment": true, "cost": { "input": 1.989, "output": 7.956 }, "description": "Gemini 2.0 Pro 0205 is an AI model provided by nano-gpt.", "id": "gemini-2.0-pro-exp-02-05", "last_updated": "2025-02-05", "limit": { "context": 2097152, "input": 2097152, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemini 2.0 Pro 0205", "open_weights": false, "reasoning": false, "release_date": "2025-02-05", "structured_output": false, "tool_call": false }, "gemini-2.0-pro-reasoner": { "attachment": false, "cost": { "input": 1.292, "output": 4.998 }, "description": "Gemini 2.0 Pro Reasoner is an AI model provided by nano-gpt.", "id": "gemini-2.0-pro-reasoner", "last_updated": "2025-02-05", "limit": { "context": 128000, "input": 128000, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Gemini 2.0 Pro Reasoner", "open_weights": false, "reasoning": false, "release_date": "2025-02-05", "structured_output": false, "tool_call": false }, "gemini-2.5-flash": { "attachment": true, "cost": { "input": 0.3, "output": 2.5 }, "description": "Gemini 2.5 Flash is an AI model provided by nano-gpt.", "id": "gemini-2.5-flash", "last_updated": "2025-06-05", "limit": { "context": 1048756, "input": 1048756, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemini 2.5 Flash", "open_weights": false, "reasoning": true, "release_date": "2025-06-05", "structured_output": false, "tool_call": false }, "gemini-2.5-flash-lite": { "attachment": true, "cost": { "input": 0.1, "output": 0.4 }, "description": "Gemini 2.5 Flash Lite is an AI model provided by nano-gpt.", "id": "gemini-2.5-flash-lite", "last_updated": "2025-06-17", "limit": { "context": 1048756, "input": 1048756, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemini 2.5 Flash Lite", "open_weights": false, "reasoning": true, "release_date": "2025-06-17", "structured_output": false, "tool_call": false }, "gemini-2.5-flash-lite-preview-06-17": { "attachment": true, "cost": { "input": 0.15, "output": 0.6 }, "description": "Gemini 2.5 Flash Lite Preview is an AI model provided by nano-gpt.", "id": "gemini-2.5-flash-lite-preview-06-17", "last_updated": "2025-06-17", "limit": { "context": 1048756, "input": 1048756, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemini 2.5 Flash Lite Preview", "open_weights": false, "reasoning": true, "release_date": "2025-06-17", "structured_output": false, "tool_call": false }, "gemini-2.5-flash-lite-preview-09-2025": { "attachment": true, "cost": { "input": 0.1, "output": 0.4 }, "description": "Gemini 2.5 Flash Lite Preview (09/2025) is an AI model provided by nano-gpt.", "id": "gemini-2.5-flash-lite-preview-09-2025", "last_updated": "2025-09-25", "limit": { "context": 1048756, "input": 1048756, "output": 65536 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Flash Lite Preview (09/2025)", "open_weights": false, "reasoning": true, "release_date": "2025-09-25", "structured_output": true, "tool_call": true }, "gemini-2.5-flash-lite-preview-09-2025-thinking": { "attachment": true, "cost": { "input": 0.1, "output": 0.4 }, "description": "Gemini 2.5 Flash Lite Preview (09/2025) – Thinking is an AI model provided by nano-gpt.", "id": "gemini-2.5-flash-lite-preview-09-2025-thinking", "last_updated": "2025-09-25", "limit": { "context": 1048756, "input": 1048756, "output": 65536 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Flash Lite Preview (09/2025) – Thinking", "open_weights": false, "reasoning": true, "release_date": "2025-09-25", "structured_output": true, "tool_call": true }, "gemini-2.5-flash-nothinking": { "attachment": true, "cost": { "input": 0.3, "output": 2.5 }, "description": "Gemini 2.5 Flash (No Thinking) is an AI model provided by nano-gpt.", "id": "gemini-2.5-flash-nothinking", "last_updated": "2025-06-05", "limit": { "context": 1048756, "input": 1048756, "output": 65536 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Flash (No Thinking)", "open_weights": false, "reasoning": false, "release_date": "2025-06-05", "structured_output": false, "tool_call": false }, "gemini-2.5-flash-preview-04-17": { "attachment": true, "cost": { "input": 0.15, "output": 0.6 }, "description": "Gemini 2.5 Flash Preview is an AI model provided by nano-gpt.", "id": "gemini-2.5-flash-preview-04-17", "last_updated": "2025-04-17", "limit": { "context": 1048756, "input": 1048756, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemini 2.5 Flash Preview", "open_weights": false, "reasoning": true, "release_date": "2025-04-17", "structured_output": false, "tool_call": false }, "gemini-2.5-flash-preview-04-17:thinking": { "attachment": true, "cost": { "input": 0.15, "output": 3.5 }, "description": "Gemini 2.5 Flash Preview Thinking is an AI model provided by nano-gpt.", "id": "gemini-2.5-flash-preview-04-17:thinking", "last_updated": "2025-04-17", "limit": { "context": 1048756, "input": 1048756, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemini 2.5 Flash Preview Thinking", "open_weights": false, "reasoning": true, "release_date": "2025-04-17", "structured_output": false, "tool_call": false }, "gemini-2.5-flash-preview-05-20": { "attachment": true, "cost": { "input": 0.15, "output": 0.6 }, "description": "Gemini 2.5 Flash 0520 is an AI model provided by nano-gpt.", "id": "gemini-2.5-flash-preview-05-20", "last_updated": "2025-05-20", "limit": { "context": 1048000, "input": 1048000, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemini 2.5 Flash 0520", "open_weights": false, "reasoning": false, "release_date": "2025-05-20", "structured_output": false, "tool_call": false }, "gemini-2.5-flash-preview-05-20:thinking": { "attachment": true, "cost": { "input": 0.15, "output": 3.5 }, "description": "Gemini 2.5 Flash 0520 Thinking is an AI model provided by nano-gpt.", "id": "gemini-2.5-flash-preview-05-20:thinking", "last_updated": "2025-05-20", "limit": { "context": 1048000, "input": 1048000, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemini 2.5 Flash 0520 Thinking", "open_weights": false, "reasoning": true, "release_date": "2025-05-20", "structured_output": false, "tool_call": false }, "gemini-2.5-flash-preview-09-2025": { "attachment": true, "cost": { "input": 0.3, "output": 2.5 }, "description": "Gemini 2.5 Flash Preview (09/2025) is an AI model provided by nano-gpt.", "id": "gemini-2.5-flash-preview-09-2025", "last_updated": "2025-09-25", "limit": { "context": 1048756, "input": 1048756, "output": 65536 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Flash Preview (09/2025)", "open_weights": false, "reasoning": true, "release_date": "2025-09-25", "structured_output": true, "tool_call": true }, "gemini-2.5-flash-preview-09-2025-thinking": { "attachment": true, "cost": { "input": 0.3, "output": 2.5 }, "description": "Gemini 2.5 Flash Preview (09/2025) – Thinking is an AI model provided by nano-gpt.", "id": "gemini-2.5-flash-preview-09-2025-thinking", "last_updated": "2025-09-25", "limit": { "context": 1048756, "input": 1048756, "output": 65536 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Flash Preview (09/2025) – Thinking", "open_weights": false, "reasoning": true, "release_date": "2025-09-25", "structured_output": true, "tool_call": true }, "gemini-2.5-pro": { "attachment": true, "cost": { "input": 2.5, "output": 10 }, "description": "Gemini 2.5 Pro is an AI model provided by nano-gpt.", "id": "gemini-2.5-pro", "last_updated": "2025-06-05", "limit": { "context": 1048756, "input": 1048756, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemini 2.5 Pro", "open_weights": false, "reasoning": true, "release_date": "2025-06-05", "structured_output": false, "tool_call": false }, "gemini-2.5-pro-exp-03-25": { "attachment": true, "cost": { "input": 2.5, "output": 10 }, "description": "Gemini 2.5 Pro Experimental 0325 is an AI model provided by nano-gpt.", "id": "gemini-2.5-pro-exp-03-25", "last_updated": "2025-03-25", "limit": { "context": 1048756, "input": 1048756, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemini 2.5 Pro Experimental 0325", "open_weights": false, "reasoning": true, "release_date": "2025-03-25", "structured_output": false, "tool_call": false }, "gemini-2.5-pro-preview-03-25": { "attachment": true, "cost": { "input": 2.5, "output": 10 }, "description": "Gemini 2.5 Pro Preview 0325 is an AI model provided by nano-gpt.", "id": "gemini-2.5-pro-preview-03-25", "last_updated": "2025-03-25", "limit": { "context": 1048756, "input": 1048756, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemini 2.5 Pro Preview 0325", "open_weights": false, "reasoning": true, "release_date": "2025-03-25", "structured_output": false, "tool_call": false }, "gemini-2.5-pro-preview-05-06": { "attachment": true, "cost": { "input": 2.5, "output": 10 }, "description": "Gemini 2.5 Pro Preview 0506 is an AI model provided by nano-gpt.", "id": "gemini-2.5-pro-preview-05-06", "last_updated": "2025-05-06", "limit": { "context": 1048756, "input": 1048756, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemini 2.5 Pro Preview 0506", "open_weights": false, "reasoning": true, "release_date": "2025-05-06", "structured_output": false, "tool_call": false }, "gemini-2.5-pro-preview-06-05": { "attachment": true, "cost": { "input": 2.5, "output": 10 }, "description": "Gemini 2.5 Pro Preview 0605 is an AI model provided by nano-gpt.", "id": "gemini-2.5-pro-preview-06-05", "last_updated": "2025-06-05", "limit": { "context": 1048756, "input": 1048756, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemini 2.5 Pro Preview 0605", "open_weights": false, "reasoning": true, "release_date": "2025-06-05", "structured_output": false, "tool_call": false }, "gemini-3-pro-image-preview": { "attachment": true, "cost": { "input": 2, "output": 12 }, "description": "Gemini 3 Pro Image is an AI model provided by nano-gpt.", "id": "gemini-3-pro-image-preview", "last_updated": "2025-11-18", "limit": { "context": 1048756, "input": 1048756, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemini 3 Pro Image", "open_weights": false, "reasoning": false, "release_date": "2025-11-18", "structured_output": false, "tool_call": false }, "gemini-3-pro-preview": { "attachment": true, "cost": { "input": 2, "output": 12 }, "description": "Gemini 3 Pro is an AI model provided by nano-gpt.", "id": "gemini-3-pro-preview", "last_updated": "2025-11-18", "limit": { "context": 1048756, "input": 1048756, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemini 3 Pro", "open_weights": false, "reasoning": true, "release_date": "2025-11-18", "structured_output": true, "tool_call": true }, "gemini-3-pro-preview-thinking": { "attachment": true, "cost": { "input": 2, "output": 12 }, "description": "Gemini 3 Pro Thinking is an AI model provided by nano-gpt.", "id": "gemini-3-pro-preview-thinking", "last_updated": "2025-11-18", "limit": { "context": 1048756, "input": 1048756, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemini 3 Pro Thinking", "open_weights": false, "reasoning": true, "release_date": "2025-11-18", "structured_output": true, "tool_call": true }, "gemini-exp-1206": { "attachment": true, "cost": { "input": 1.258, "output": 4.998 }, "description": "Gemini 2.0 Pro 1206 is an AI model provided by nano-gpt.", "id": "gemini-exp-1206", "last_updated": "2024-12-06", "limit": { "context": 2097152, "input": 2097152, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemini 2.0 Pro 1206", "open_weights": false, "reasoning": false, "release_date": "2024-12-06", "structured_output": false, "tool_call": false }, "glm-4": { "attachment": false, "cost": { "input": 14.994, "output": 14.994 }, "description": "GLM-4 is an AI model provided by nano-gpt.", "id": "glm-4", "last_updated": "2024-01-16", "limit": { "context": 128000, "input": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4", "open_weights": false, "reasoning": false, "release_date": "2024-01-16", "structured_output": false, "tool_call": false }, "glm-4-air": { "attachment": false, "cost": { "input": 0.2006, "output": 0.2006 }, "description": "GLM-4 Air is an AI model provided by nano-gpt.", "id": "glm-4-air", "last_updated": "2024-06-05", "limit": { "context": 128000, "input": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4 Air", "open_weights": false, "reasoning": false, "release_date": "2024-06-05", "structured_output": false, "tool_call": false }, "glm-4-air-0111": { "attachment": false, "cost": { "input": 0.1394, "output": 0.1394 }, "description": "GLM 4 Air 0111 is an AI model provided by nano-gpt.", "id": "glm-4-air-0111", "last_updated": "2025-01-11", "limit": { "context": 128000, "input": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4 Air 0111", "open_weights": false, "reasoning": false, "release_date": "2025-01-11", "structured_output": false, "tool_call": false }, "glm-4-airx": { "attachment": false, "cost": { "input": 2.006, "output": 2.006 }, "description": "GLM-4 AirX is an AI model provided by nano-gpt.", "id": "glm-4-airx", "last_updated": "2024-06-05", "limit": { "context": 8000, "input": 8000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4 AirX", "open_weights": false, "reasoning": false, "release_date": "2024-06-05", "structured_output": false, "tool_call": false }, "glm-4-flash": { "attachment": false, "cost": { "input": 0.1003, "output": 0.1003 }, "description": "GLM-4 Flash is an AI model provided by nano-gpt.", "id": "glm-4-flash", "last_updated": "2024-08-01", "limit": { "context": 128000, "input": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4 Flash", "open_weights": false, "reasoning": false, "release_date": "2024-08-01", "structured_output": false, "tool_call": false }, "glm-4-long": { "attachment": false, "cost": { "input": 0.2006, "output": 0.2006 }, "description": "GLM-4 Long is an AI model provided by nano-gpt.", "id": "glm-4-long", "last_updated": "2024-08-01", "limit": { "context": 1000000, "input": 1000000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4 Long", "open_weights": false, "reasoning": false, "release_date": "2024-08-01", "structured_output": false, "tool_call": false }, "glm-4-plus": { "attachment": false, "cost": { "input": 7.497, "output": 7.497 }, "description": "GLM-4 Plus is an AI model provided by nano-gpt.", "id": "glm-4-plus", "last_updated": "2024-08-01", "limit": { "context": 128000, "input": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4 Plus", "open_weights": false, "reasoning": false, "release_date": "2024-08-01", "structured_output": false, "tool_call": false }, "glm-4-plus-0111": { "attachment": false, "cost": { "input": 9.996, "output": 9.996 }, "description": "GLM 4 Plus 0111 is an AI model provided by nano-gpt.", "id": "glm-4-plus-0111", "last_updated": "2025-02-19", "limit": { "context": 128000, "input": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4 Plus 0111", "open_weights": false, "reasoning": false, "release_date": "2025-02-19", "structured_output": false, "tool_call": false }, "glm-4.1v-thinking-flash": { "attachment": true, "cost": { "input": 0.3, "output": 0.3 }, "description": "GLM 4.1V Thinking Flash is an AI model provided by nano-gpt.", "id": "glm-4.1v-thinking-flash", "last_updated": "2025-07-09", "limit": { "context": 64000, "input": 64000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GLM 4.1V Thinking Flash", "open_weights": false, "reasoning": false, "release_date": "2025-07-09", "structured_output": false, "tool_call": false }, "glm-4.1v-thinking-flashx": { "attachment": true, "cost": { "input": 0.3, "output": 0.3 }, "description": "GLM 4.1V Thinking FlashX is an AI model provided by nano-gpt.", "id": "glm-4.1v-thinking-flashx", "last_updated": "2025-07-09", "limit": { "context": 64000, "input": 64000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GLM 4.1V Thinking FlashX", "open_weights": false, "reasoning": false, "release_date": "2025-07-09", "structured_output": false, "tool_call": false }, "glm-z1-air": { "attachment": false, "cost": { "input": 0.07, "output": 0.07 }, "description": "GLM Z1 Air is an AI model provided by nano-gpt.", "id": "glm-z1-air", "last_updated": "2025-04-15", "limit": { "context": 32000, "input": 32000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM Z1 Air", "open_weights": false, "reasoning": false, "release_date": "2025-04-15", "structured_output": true, "tool_call": true }, "glm-z1-airx": { "attachment": false, "cost": { "input": 0.7, "output": 0.7 }, "description": "GLM Z1 AirX is an AI model provided by nano-gpt.", "id": "glm-z1-airx", "last_updated": "2025-04-15", "limit": { "context": 32000, "input": 32000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM Z1 AirX", "open_weights": false, "reasoning": false, "release_date": "2025-04-15", "structured_output": true, "tool_call": true }, "glm-zero-preview": { "attachment": false, "cost": { "input": 1.802, "output": 1.802 }, "description": "GLM Zero Preview is an AI model provided by nano-gpt.", "id": "glm-zero-preview", "last_updated": "2024-12-01", "limit": { "context": 8000, "input": 8000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM Zero Preview", "open_weights": false, "reasoning": false, "release_date": "2024-12-01", "structured_output": false, "tool_call": false }, "google/gemini-3-flash-preview": { "attachment": true, "cost": { "input": 0.5, "output": 3 }, "description": "Gemini 3 Flash (Preview) is an AI model provided by nano-gpt.", "family": "gemini-flash", "id": "google/gemini-3-flash-preview", "last_updated": "2025-12-17", "limit": { "context": 1048756, "input": 1048756, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemini 3 Flash (Preview)", "open_weights": false, "reasoning": true, "release_date": "2025-12-17", "structured_output": true, "tool_call": true }, "google/gemini-3-flash-preview-thinking": { "attachment": true, "cost": { "input": 0.5, "output": 3 }, "description": "Gemini 3 Flash Thinking is an AI model provided by nano-gpt.", "family": "gemini-flash", "id": "google/gemini-3-flash-preview-thinking", "last_updated": "2025-12-17", "limit": { "context": 1048756, "input": 1048756, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemini 3 Flash Thinking", "open_weights": false, "reasoning": true, "release_date": "2025-12-17", "structured_output": false, "tool_call": false }, "google/gemini-flash-1.5": { "attachment": false, "cost": { "input": 0.0748, "output": 0.306 }, "description": "Gemini 1.5 Flash is an AI model provided by nano-gpt.", "family": "gemini-flash", "id": "google/gemini-flash-1.5", "last_updated": "2024-05-14", "limit": { "context": 2000000, "input": 2000000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Gemini 1.5 Flash", "open_weights": false, "reasoning": false, "release_date": "2024-05-14", "structured_output": false, "tool_call": false }, "grok-3-beta": { "attachment": false, "cost": { "input": 3, "output": 15 }, "description": "Grok 3 Beta is an AI model provided by nano-gpt.", "id": "grok-3-beta", "last_updated": "2025-09-29", "limit": { "context": 131072, "input": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok 3 Beta", "open_weights": false, "reasoning": false, "release_date": "2025-09-29", "structured_output": false, "tool_call": false }, "grok-3-fast-beta": { "attachment": true, "cost": { "input": 5, "output": 25 }, "description": "Grok 3 Fast Beta is an AI model provided by nano-gpt.", "id": "grok-3-fast-beta", "last_updated": "2025-02-17", "limit": { "context": 131072, "input": 131072, "output": 131072 }, "modalities": { "input": [ "text", "pdf" ], "output": [ "text" ] }, "name": "Grok 3 Fast Beta", "open_weights": false, "reasoning": false, "release_date": "2025-02-17", "structured_output": false, "tool_call": false }, "grok-3-mini-beta": { "attachment": false, "cost": { "input": 0.3, "output": 0.5 }, "description": "Grok 3 Mini Beta is an AI model provided by nano-gpt.", "id": "grok-3-mini-beta", "last_updated": "2025-02-17", "limit": { "context": 131072, "input": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok 3 Mini Beta", "open_weights": false, "reasoning": false, "release_date": "2025-02-17", "structured_output": false, "tool_call": false }, "grok-3-mini-fast-beta": { "attachment": false, "cost": { "input": 0.6, "output": 4 }, "description": "Grok 3 Mini Fast Beta is an AI model provided by nano-gpt.", "id": "grok-3-mini-fast-beta", "last_updated": "2025-02-17", "limit": { "context": 131072, "input": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok 3 Mini Fast Beta", "open_weights": false, "reasoning": false, "release_date": "2025-02-17", "structured_output": false, "tool_call": false }, "hidream": { "attachment": true, "description": "Hidream is an AI model provided by nano-gpt.", "id": "hidream", "last_updated": "2024-01-01", "limit": { "context": 0, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "name": "Hidream", "open_weights": false, "reasoning": false, "release_date": "2024-01-01", "structured_output": false, "temperature": true, "tool_call": false }, "huihui-ai/DeepSeek-R1-Distill-Llama-70B-abliterated": { "attachment": false, "cost": { "input": 0.7, "output": 0.7 }, "description": "DeepSeek R1 Llama 70B Abliterated is an AI model provided by nano-gpt.", "family": "deepseek", "id": "huihui-ai/DeepSeek-R1-Distill-Llama-70B-abliterated", "last_updated": "2025-01-20", "limit": { "context": 16384, "input": 16384, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek R1 Llama 70B Abliterated", "open_weights": false, "reasoning": true, "release_date": "2025-01-20", "structured_output": false, "tool_call": false }, "huihui-ai/DeepSeek-R1-Distill-Qwen-32B-abliterated": { "attachment": false, "cost": { "input": 1.4, "output": 1.4 }, "description": "DeepSeek R1 Qwen Abliterated is an AI model provided by nano-gpt.", "family": "qwen", "id": "huihui-ai/DeepSeek-R1-Distill-Qwen-32B-abliterated", "last_updated": "2025-01-20", "limit": { "context": 16384, "input": 16384, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek R1 Qwen Abliterated", "open_weights": false, "reasoning": true, "release_date": "2025-01-20", "structured_output": false, "tool_call": false }, "huihui-ai/Llama-3.1-Nemotron-70B-Instruct-HF-abliterated": { "attachment": false, "cost": { "input": 0.7, "output": 0.7 }, "description": "Nemotron 3.1 70B abliterated is an AI model provided by nano-gpt.", "family": "nemotron", "id": "huihui-ai/Llama-3.1-Nemotron-70B-Instruct-HF-abliterated", "last_updated": "2024-07-23", "limit": { "context": 16384, "input": 16384, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Nemotron 3.1 70B abliterated", "open_weights": false, "reasoning": false, "release_date": "2024-07-23", "structured_output": false, "tool_call": false }, "huihui-ai/Llama-3.3-70B-Instruct-abliterated": { "attachment": false, "cost": { "input": 0.7, "output": 0.7 }, "description": "Llama 3.3 70B Instruct abliterated is an AI model provided by nano-gpt.", "family": "llama", "id": "huihui-ai/Llama-3.3-70B-Instruct-abliterated", "last_updated": "2025-08-08", "limit": { "context": 16384, "input": 16384, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B Instruct abliterated", "open_weights": false, "reasoning": false, "release_date": "2025-08-08", "structured_output": false, "tool_call": false }, "huihui-ai/Qwen2.5-32B-Instruct-abliterated": { "attachment": false, "cost": { "input": 0.7, "output": 0.7 }, "description": "Qwen 2.5 32B Abliterated is an AI model provided by nano-gpt.", "family": "qwen", "id": "huihui-ai/Qwen2.5-32B-Instruct-abliterated", "last_updated": "2025-01-06", "limit": { "context": 32768, "input": 32768, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen 2.5 32B Abliterated", "open_weights": false, "reasoning": false, "release_date": "2025-01-06", "structured_output": false, "tool_call": false }, "hunyuan-t1-latest": { "attachment": false, "cost": { "input": 0.17, "output": 0.66 }, "description": "Hunyuan T1 is an AI model provided by nano-gpt.", "id": "hunyuan-t1-latest", "last_updated": "2025-03-22", "limit": { "context": 256000, "input": 256000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Hunyuan T1", "open_weights": false, "reasoning": false, "release_date": "2025-03-22", "structured_output": false, "tool_call": false }, "hunyuan-turbos-20250226": { "attachment": false, "cost": { "input": 0.187, "output": 0.374 }, "description": "Hunyuan Turbo S is an AI model provided by nano-gpt.", "id": "hunyuan-turbos-20250226", "last_updated": "2025-02-27", "limit": { "context": 24000, "input": 24000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Hunyuan Turbo S", "open_weights": false, "reasoning": false, "release_date": "2025-02-27", "structured_output": false, "tool_call": false }, "inflatebot/MN-12B-Mag-Mell-R1": { "attachment": false, "cost": { "input": 0.49299999999999994, "output": 0.49299999999999994 }, "description": "Mag Mell R1 is an AI model provided by nano-gpt.", "family": "mistral-nemo", "id": "inflatebot/MN-12B-Mag-Mell-R1", "last_updated": "2024-07-01", "limit": { "context": 16384, "input": 16384, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mag Mell R1", "open_weights": false, "reasoning": false, "release_date": "2024-07-01", "structured_output": false, "tool_call": false }, "inflection/inflection-3-pi": { "attachment": false, "cost": { "input": 2.499, "output": 9.996 }, "description": "Inflection 3 Pi is an AI model provided by nano-gpt.", "family": "gpt", "id": "inflection/inflection-3-pi", "last_updated": "2024-10-11", "limit": { "context": 8000, "input": 8000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Inflection 3 Pi", "open_weights": false, "reasoning": false, "release_date": "2024-10-11", "structured_output": false, "tool_call": false }, "inflection/inflection-3-productivity": { "attachment": false, "cost": { "input": 2.499, "output": 9.996 }, "description": "Inflection 3 Productivity is an AI model provided by nano-gpt.", "family": "gpt", "id": "inflection/inflection-3-productivity", "last_updated": "2024-10-11", "limit": { "context": 8000, "input": 8000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Inflection 3 Productivity", "open_weights": false, "reasoning": false, "release_date": "2024-10-11", "structured_output": false, "tool_call": false }, "jamba-large": { "attachment": false, "cost": { "input": 1.989, "output": 7.99 }, "description": "Jamba Large is an AI model provided by nano-gpt.", "id": "jamba-large", "last_updated": "2025-07-09", "limit": { "context": 256000, "input": 256000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Jamba Large", "open_weights": false, "reasoning": false, "release_date": "2025-07-09", "structured_output": false, "tool_call": false }, "jamba-large-1.6": { "attachment": false, "cost": { "input": 1.989, "output": 7.99 }, "description": "Jamba Large 1.6 is an AI model provided by nano-gpt.", "id": "jamba-large-1.6", "last_updated": "2025-03-12", "limit": { "context": 256000, "input": 256000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Jamba Large 1.6", "open_weights": false, "reasoning": false, "release_date": "2025-03-12", "structured_output": false, "tool_call": false }, "jamba-large-1.7": { "attachment": false, "cost": { "input": 1.989, "output": 7.99 }, "description": "Jamba Large 1.7 is an AI model provided by nano-gpt.", "id": "jamba-large-1.7", "last_updated": "2025-07-09", "limit": { "context": 256000, "input": 256000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Jamba Large 1.7", "open_weights": false, "reasoning": false, "release_date": "2025-07-09", "structured_output": false, "tool_call": false }, "jamba-mini": { "attachment": false, "cost": { "input": 0.1989, "output": 0.408 }, "description": "Jamba Mini is an AI model provided by nano-gpt.", "id": "jamba-mini", "last_updated": "2025-07-09", "limit": { "context": 256000, "input": 256000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Jamba Mini", "open_weights": false, "reasoning": false, "release_date": "2025-07-09", "structured_output": false, "tool_call": false }, "jamba-mini-1.6": { "attachment": false, "cost": { "input": 0.1989, "output": 0.408 }, "description": "Jamba Mini 1.6 is an AI model provided by nano-gpt.", "id": "jamba-mini-1.6", "last_updated": "2025-03-01", "limit": { "context": 256000, "input": 256000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Jamba Mini 1.6", "open_weights": false, "reasoning": false, "release_date": "2025-03-01", "structured_output": false, "tool_call": false }, "jamba-mini-1.7": { "attachment": false, "cost": { "input": 0.1989, "output": 0.408 }, "description": "Jamba Mini 1.7 is an AI model provided by nano-gpt.", "id": "jamba-mini-1.7", "last_updated": "2025-07-09", "limit": { "context": 256000, "input": 256000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Jamba Mini 1.7", "open_weights": false, "reasoning": false, "release_date": "2025-07-09", "structured_output": false, "tool_call": false }, "kimi-k2-instruct-fast": { "attachment": true, "cost": { "input": 0.1, "output": 2 }, "description": "Kimi K2 0711 Fast is an AI model provided by nano-gpt.", "id": "kimi-k2-instruct-fast", "last_updated": "2025-07-15", "limit": { "context": 131072, "input": 131072, "output": 16384 }, "modalities": { "input": [ "text", "pdf" ], "output": [ "text" ] }, "name": "Kimi K2 0711 Fast", "open_weights": false, "reasoning": false, "release_date": "2025-07-15", "structured_output": false, "tool_call": false }, "kimi-thinking-preview": { "attachment": true, "cost": { "input": 31.46, "output": 31.46 }, "description": "Kimi Thinking Preview is an AI model provided by nano-gpt.", "id": "kimi-thinking-preview", "last_updated": "2025-05-07", "limit": { "context": 128000, "input": 128000, "output": 16384 }, "modalities": { "input": [ "text", "pdf" ], "output": [ "text" ] }, "name": "Kimi Thinking Preview", "open_weights": false, "reasoning": false, "release_date": "2025-05-07", "structured_output": false, "tool_call": false }, "learnlm-1.5-pro-experimental": { "attachment": false, "cost": { "input": 3.502, "output": 10.506 }, "description": "Gemini LearnLM Experimental is an AI model provided by nano-gpt.", "id": "learnlm-1.5-pro-experimental", "last_updated": "2024-05-14", "limit": { "context": 32767, "input": 32767, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Gemini LearnLM Experimental", "open_weights": false, "reasoning": false, "release_date": "2024-05-14", "structured_output": false, "tool_call": false }, "meganova-ai/manta-flash-1.0": { "attachment": false, "cost": { "input": 0.02, "output": 0.16 }, "description": "Manta Flash 1.0 is an AI model provided by nano-gpt.", "family": "nova", "id": "meganova-ai/manta-flash-1.0", "last_updated": "2025-12-20", "limit": { "context": 16384, "input": 16384, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Manta Flash 1.0", "open_weights": false, "reasoning": false, "release_date": "2025-12-20", "structured_output": false, "tool_call": false }, "meganova-ai/manta-mini-1.0": { "attachment": false, "cost": { "input": 0.02, "output": 0.16 }, "description": "Manta Mini 1.0 is an AI model provided by nano-gpt.", "family": "nova", "id": "meganova-ai/manta-mini-1.0", "last_updated": "2025-12-20", "limit": { "context": 8192, "input": 8192, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Manta Mini 1.0", "open_weights": false, "reasoning": false, "release_date": "2025-12-20", "structured_output": false, "tool_call": false }, "meganova-ai/manta-pro-1.0": { "attachment": false, "cost": { "input": 0.060000000000000005, "output": 0.5 }, "description": "Manta Pro 1.0 is an AI model provided by nano-gpt.", "family": "nova", "id": "meganova-ai/manta-pro-1.0", "last_updated": "2025-12-20", "limit": { "context": 32768, "input": 32768, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Manta Pro 1.0", "open_weights": false, "reasoning": false, "release_date": "2025-12-20", "structured_output": false, "tool_call": false }, "meituan-longcat/LongCat-Flash-Chat-FP8": { "attachment": false, "cost": { "input": 0.15, "output": 0.7 }, "description": "LongCat Flash is an AI model provided by nano-gpt.", "family": "longcat", "id": "meituan-longcat/LongCat-Flash-Chat-FP8", "last_updated": "2025-08-31", "limit": { "context": 128000, "input": 128000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "LongCat Flash", "open_weights": false, "reasoning": false, "release_date": "2025-08-31", "structured_output": true, "tool_call": true }, "meta-llama/llama-3.1-8b-instruct": { "attachment": false, "cost": { "input": 0.0544, "output": 0.0544 }, "description": "Llama 3.1 8b Instruct is an AI model provided by nano-gpt.", "family": "llama", "id": "meta-llama/llama-3.1-8b-instruct", "last_updated": "2024-07-23", "limit": { "context": 131072, "input": 131072, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.1 8b Instruct", "open_weights": false, "reasoning": false, "release_date": "2024-07-23", "structured_output": false, "tool_call": false }, "meta-llama/llama-3.2-3b-instruct": { "attachment": true, "cost": { "input": 0.0306, "output": 0.0493 }, "description": "Llama 3.2 3b Instruct is an AI model provided by nano-gpt.", "family": "llama", "id": "meta-llama/llama-3.2-3b-instruct", "last_updated": "2024-09-25", "limit": { "context": 131072, "input": 131072, "output": 8192 }, "modalities": { "input": [ "text", "pdf" ], "output": [ "text" ] }, "name": "Llama 3.2 3b Instruct", "open_weights": false, "reasoning": false, "release_date": "2024-09-25", "structured_output": false, "tool_call": false }, "meta-llama/llama-3.2-90b-vision-instruct": { "attachment": false, "cost": { "input": 0.9009999999999999, "output": 0.9009999999999999 }, "description": "Llama 3.2 Medium is an AI model provided by nano-gpt.", "family": "llama", "id": "meta-llama/llama-3.2-90b-vision-instruct", "last_updated": "2025-09-25", "limit": { "context": 131072, "input": 131072, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.2 Medium", "open_weights": false, "reasoning": false, "release_date": "2025-09-25", "structured_output": false, "tool_call": false }, "meta-llama/llama-3.3-70b-instruct": { "attachment": false, "cost": { "input": 0.05, "output": 0.23 }, "description": "Llama 3.3 70b Instruct is an AI model provided by nano-gpt.", "family": "llama", "id": "meta-llama/llama-3.3-70b-instruct", "last_updated": "2025-02-27", "limit": { "context": 131072, "input": 131072, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70b Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-02-27", "structured_output": true, "tool_call": true }, "meta-llama/llama-4-maverick": { "attachment": true, "cost": { "input": 0.18000000000000002, "output": 0.8 }, "description": "Llama 4 Maverick is an AI model provided by nano-gpt.", "family": "llama", "id": "meta-llama/llama-4-maverick", "last_updated": "2025-09-05", "limit": { "context": 1048576, "input": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Llama 4 Maverick", "open_weights": false, "reasoning": false, "release_date": "2025-09-05", "structured_output": true, "tool_call": true }, "meta-llama/llama-4-scout": { "attachment": true, "cost": { "input": 0.085, "output": 0.46 }, "description": "Llama 4 Scout is an AI model provided by nano-gpt.", "family": "llama", "id": "meta-llama/llama-4-scout", "last_updated": "2025-09-05", "limit": { "context": 328000, "input": 328000, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Llama 4 Scout", "open_weights": false, "reasoning": false, "release_date": "2025-09-05", "structured_output": true, "tool_call": true }, "microsoft/MAI-DS-R1-FP8": { "attachment": true, "cost": { "input": 0.3, "output": 0.3 }, "description": "Microsoft DeepSeek R1 is an AI model provided by nano-gpt.", "family": "deepseek", "id": "microsoft/MAI-DS-R1-FP8", "last_updated": "2025-09-25", "limit": { "context": 128000, "input": 128000, "output": 8192 }, "modalities": { "input": [ "text", "pdf" ], "output": [ "text" ] }, "name": "Microsoft DeepSeek R1", "open_weights": false, "reasoning": false, "release_date": "2025-09-25", "structured_output": false, "tool_call": false }, "microsoft/wizardlm-2-8x22b": { "attachment": true, "cost": { "input": 0.49299999999999994, "output": 0.49299999999999994 }, "description": "WizardLM-2 8x22B is an AI model provided by nano-gpt.", "family": "gpt", "id": "microsoft/wizardlm-2-8x22b", "last_updated": "2025-04-15", "limit": { "context": 65536, "input": 65536, "output": 8192 }, "modalities": { "input": [ "text", "pdf" ], "output": [ "text" ] }, "name": "WizardLM-2 8x22B", "open_weights": false, "reasoning": false, "release_date": "2025-04-15", "structured_output": false, "tool_call": false }, "minimax/minimax-01": { "attachment": true, "cost": { "input": 0.1394, "output": 1.1219999999999999 }, "description": "MiniMax 01 is an AI model provided by nano-gpt.", "family": "minimax", "id": "minimax/minimax-01", "last_updated": "2025-01-15", "limit": { "context": 1000192, "input": 1000192, "output": 16384 }, "modalities": { "input": [ "text", "pdf" ], "output": [ "text" ] }, "name": "MiniMax 01", "open_weights": false, "reasoning": false, "release_date": "2025-01-15", "structured_output": false, "tool_call": false }, "minimax/minimax-m2-her": { "attachment": false, "cost": { "input": 0.30200000000000005, "output": 1.2069999999999999 }, "description": "MiniMax M2-her is an AI model provided by nano-gpt.", "family": "minimax", "id": "minimax/minimax-m2-her", "last_updated": "2026-01-24", "limit": { "context": 65532, "input": 65532, "output": 2048 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M2-her", "open_weights": false, "reasoning": false, "release_date": "2026-01-24", "structured_output": false, "tool_call": false }, "minimax/minimax-m2.1": { "attachment": false, "cost": { "input": 0.33, "output": 1.32 }, "description": "MiniMax M2.1 is an AI model provided by nano-gpt.", "family": "minimax", "id": "minimax/minimax-m2.1", "last_updated": "2025-12-19", "limit": { "context": 200000, "input": 200000, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M2.1", "open_weights": false, "reasoning": true, "release_date": "2025-12-19", "structured_output": true, "tool_call": true }, "minimax/minimax-m2.5": { "attachment": false, "cost": { "input": 0.3, "output": 1.2 }, "description": "MiniMax M2.5 is an AI model provided by nano-gpt.", "family": "minimax", "id": "minimax/minimax-m2.5", "last_updated": "2026-02-12", "limit": { "context": 204800, "input": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M2.5", "open_weights": false, "reasoning": true, "release_date": "2026-02-12", "structured_output": true, "tool_call": true }, "minimax/minimax-m2.7": { "attachment": false, "cost": { "input": 0.3, "output": 1.2 }, "description": "MiniMax M2.7 is an AI model provided by nano-gpt.", "family": "minimax", "id": "minimax/minimax-m2.7", "last_updated": "2026-03-18", "limit": { "context": 204800, "input": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M2.7", "open_weights": false, "reasoning": true, "release_date": "2026-03-18", "structured_output": true, "tool_call": true }, "miromind-ai/mirothinker-v1.5-235b": { "attachment": false, "cost": { "input": 0.3, "output": 1.2 }, "description": "MiroThinker v1.5 235B is an AI model provided by nano-gpt.", "family": "gpt", "id": "miromind-ai/mirothinker-v1.5-235b", "last_updated": "2026-01-07", "limit": { "context": 32768, "input": 32768, "output": 4000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiroThinker v1.5 235B", "open_weights": false, "reasoning": false, "release_date": "2026-01-07", "structured_output": false, "tool_call": false }, "mistral-small-31-24b-instruct": { "attachment": true, "cost": { "input": 0.1, "output": 0.3 }, "description": "Mistral Small 31 24b Instruct is an AI model provided by nano-gpt.", "id": "mistral-small-31-24b-instruct", "last_updated": "2025-04-15", "limit": { "context": 128000, "input": 128000, "output": 131072 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Mistral Small 31 24b Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-04-15", "structured_output": false, "tool_call": false }, "mistralai/Devstral-Small-2505": { "attachment": false, "cost": { "input": 0.060000000000000005, "output": 0.060000000000000005 }, "description": "Mistral Devstral Small 2505 is an AI model provided by nano-gpt.", "family": "devstral", "id": "mistralai/Devstral-Small-2505", "last_updated": "2025-08-02", "limit": { "context": 32768, "input": 32768, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral Devstral Small 2505", "open_weights": false, "reasoning": false, "release_date": "2025-08-02", "structured_output": false, "tool_call": false }, "mistralai/Mistral-Nemo-Instruct-2407": { "attachment": false, "cost": { "input": 0.1003, "output": 0.1207 }, "description": "Mistral Nemo is an AI model provided by nano-gpt.", "family": "mistral-nemo", "id": "mistralai/Mistral-Nemo-Instruct-2407", "last_updated": "2024-07-18", "limit": { "context": 16384, "input": 16384, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral Nemo", "open_weights": false, "reasoning": false, "release_date": "2024-07-18", "structured_output": false, "tool_call": false }, "mistralai/codestral-2508": { "attachment": false, "cost": { "input": 0.3, "output": 0.8999999999999999 }, "description": "Codestral 2508 is an AI model provided by nano-gpt.", "family": "codestral", "id": "mistralai/codestral-2508", "last_updated": "2025-08-01", "limit": { "context": 256000, "input": 256000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Codestral 2508", "open_weights": false, "reasoning": false, "release_date": "2025-08-01", "structured_output": false, "tool_call": false }, "mistralai/devstral-2-123b-instruct-2512": { "attachment": false, "cost": { "input": 0.4, "output": 1.4 }, "description": "Devstral 2 123B is an AI model provided by nano-gpt.", "family": "devstral", "id": "mistralai/devstral-2-123b-instruct-2512", "last_updated": "2025-12-09", "limit": { "context": 262144, "input": 262144, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Devstral 2 123B", "open_weights": false, "reasoning": false, "release_date": "2025-12-09", "structured_output": false, "tool_call": false }, "mistralai/ministral-14b-2512": { "attachment": false, "cost": { "input": 0.2, "output": 0.2 }, "description": "Ministral 14B is an AI model provided by nano-gpt.", "family": "ministral", "id": "mistralai/ministral-14b-2512", "last_updated": "2025-12-04", "limit": { "context": 262144, "input": 262144, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Ministral 14B", "open_weights": false, "reasoning": false, "release_date": "2025-12-04", "structured_output": false, "tool_call": false }, "mistralai/ministral-14b-instruct-2512": { "attachment": true, "cost": { "input": 0.1, "output": 0.4 }, "description": "Ministral 3 14B is an AI model provided by nano-gpt.", "family": "ministral", "id": "mistralai/ministral-14b-instruct-2512", "last_updated": "2025-12-02", "limit": { "context": 262144, "input": 262144, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Ministral 3 14B", "open_weights": false, "reasoning": false, "release_date": "2025-12-02", "structured_output": false, "tool_call": false }, "mistralai/ministral-3b-2512": { "attachment": false, "cost": { "input": 0.1, "output": 0.1 }, "description": "Ministral 3B is an AI model provided by nano-gpt.", "family": "ministral", "id": "mistralai/ministral-3b-2512", "last_updated": "2025-12-04", "limit": { "context": 131072, "input": 131072, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Ministral 3B", "open_weights": false, "reasoning": false, "release_date": "2025-12-04", "structured_output": false, "tool_call": false }, "mistralai/ministral-8b-2512": { "attachment": false, "cost": { "input": 0.15, "output": 0.15 }, "description": "Ministral 8B is an AI model provided by nano-gpt.", "family": "ministral", "id": "mistralai/ministral-8b-2512", "last_updated": "2025-12-04", "limit": { "context": 262144, "input": 262144, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Ministral 8B", "open_weights": false, "reasoning": false, "release_date": "2025-12-04", "structured_output": false, "tool_call": false }, "mistralai/mistral-7b-instruct": { "attachment": true, "cost": { "input": 0.0544, "output": 0.0544 }, "description": "Mistral 7B Instruct is an AI model provided by nano-gpt.", "family": "mistral", "id": "mistralai/mistral-7b-instruct", "last_updated": "2024-05-27", "limit": { "context": 32768, "input": 32768, "output": 8192 }, "modalities": { "input": [ "text", "pdf" ], "output": [ "text" ] }, "name": "Mistral 7B Instruct", "open_weights": false, "reasoning": false, "release_date": "2024-05-27", "structured_output": false, "tool_call": false }, "mistralai/mistral-large": { "attachment": false, "cost": { "input": 2.006, "output": 6.001 }, "description": "Mistral Large 2411 is an AI model provided by nano-gpt.", "family": "mistral-large", "id": "mistralai/mistral-large", "last_updated": "2024-02-26", "limit": { "context": 128000, "input": 128000, "output": 256000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral Large 2411", "open_weights": false, "reasoning": false, "release_date": "2024-02-26", "structured_output": false, "tool_call": false }, "mistralai/mistral-large-3-675b-instruct-2512": { "attachment": true, "cost": { "input": 1, "output": 3 }, "description": "Mistral Large 3 675B is an AI model provided by nano-gpt.", "family": "mistral-large", "id": "mistralai/mistral-large-3-675b-instruct-2512", "last_updated": "2025-12-02", "limit": { "context": 262144, "input": 262144, "output": 256000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Mistral Large 3 675B", "open_weights": false, "reasoning": false, "release_date": "2025-12-02", "structured_output": false, "tool_call": false }, "mistralai/mistral-medium-3": { "attachment": true, "cost": { "input": 0.4, "output": 2 }, "description": "Mistral Medium 3 is an AI model provided by nano-gpt.", "family": "mistral-medium", "id": "mistralai/mistral-medium-3", "last_updated": "2025-09-25", "limit": { "context": 131072, "input": 131072, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Mistral Medium 3", "open_weights": false, "reasoning": false, "release_date": "2025-09-25", "structured_output": false, "tool_call": false }, "mistralai/mistral-medium-3.1": { "attachment": false, "cost": { "input": 0.4, "output": 2 }, "description": "Mistral Medium 3.1 is an AI model provided by nano-gpt.", "family": "mistral-medium", "id": "mistralai/mistral-medium-3.1", "last_updated": "2025-09-05", "limit": { "context": 131072, "input": 131072, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral Medium 3.1", "open_weights": false, "reasoning": false, "release_date": "2025-09-05", "structured_output": false, "tool_call": false }, "mistralai/mistral-saba": { "attachment": false, "cost": { "input": 0.1989, "output": 0.595 }, "description": "Mistral Saba is an AI model provided by nano-gpt.", "family": "mistral", "id": "mistralai/mistral-saba", "last_updated": "2025-02-17", "limit": { "context": 32000, "input": 32000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral Saba", "open_weights": false, "reasoning": false, "release_date": "2025-02-17", "structured_output": false, "tool_call": false }, "mistralai/mistral-small-creative": { "attachment": false, "cost": { "input": 0.1, "output": 0.3 }, "description": "Mistral Small Creative is an AI model provided by nano-gpt.", "family": "mistral-small", "id": "mistralai/mistral-small-creative", "last_updated": "2025-12-16", "limit": { "context": 32768, "input": 32768, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral Small Creative", "open_weights": false, "reasoning": false, "release_date": "2025-12-16", "structured_output": true, "tool_call": true }, "mistralai/mistral-tiny": { "attachment": false, "cost": { "input": 0.25499999999999995, "output": 0.25499999999999995 }, "description": "Mistral Tiny is an AI model provided by nano-gpt.", "family": "mistral", "id": "mistralai/mistral-tiny", "last_updated": "2024-01-01", "limit": { "context": 32000, "input": 32000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral Tiny", "open_weights": false, "reasoning": false, "release_date": "2023-12-11", "structured_output": false, "tool_call": false }, "mistralai/mixtral-8x22b-instruct-v0.1": { "attachment": false, "cost": { "input": 0.8999999999999999, "output": 0.8999999999999999 }, "description": "Mixtral 8x22B is an AI model provided by nano-gpt.", "family": "mixtral", "id": "mistralai/mixtral-8x22b-instruct-v0.1", "last_updated": "2025-12-11", "limit": { "context": 65536, "input": 65536, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mixtral 8x22B", "open_weights": false, "reasoning": false, "release_date": "2025-12-11", "structured_output": false, "tool_call": false }, "mistralai/mixtral-8x7b-instruct-v0.1": { "attachment": false, "cost": { "input": 0.27, "output": 0.27 }, "description": "Mixtral 8x7B is an AI model provided by nano-gpt.", "family": "mixtral", "id": "mistralai/mixtral-8x7b-instruct-v0.1", "last_updated": "2025-12-11", "limit": { "context": 32768, "input": 32768, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mixtral 8x7B", "open_weights": false, "reasoning": false, "release_date": "2025-12-11", "structured_output": false, "tool_call": false }, "mlabonne/NeuralDaredevil-8B-abliterated": { "attachment": false, "cost": { "input": 0.44, "output": 0.44 }, "description": "Neural Daredevil 8B abliterated is an AI model provided by nano-gpt.", "family": "llama", "id": "mlabonne/NeuralDaredevil-8B-abliterated", "last_updated": "2024-12-01", "limit": { "context": 8192, "input": 8192, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Neural Daredevil 8B abliterated", "open_weights": false, "reasoning": false, "release_date": "2024-12-01", "structured_output": false, "tool_call": false }, "moonshotai/Kimi-Dev-72B": { "attachment": true, "cost": { "input": 0.4, "output": 0.4 }, "description": "Kimi Dev 72B is an AI model provided by nano-gpt.", "family": "kimi", "id": "moonshotai/Kimi-Dev-72B", "last_updated": "2025-04-15", "limit": { "context": 128000, "input": 128000, "output": 131072 }, "modalities": { "input": [ "text", "pdf" ], "output": [ "text" ] }, "name": "Kimi Dev 72B", "open_weights": false, "reasoning": false, "release_date": "2025-04-15", "structured_output": false, "tool_call": false }, "moonshotai/Kimi-K2-Instruct-0905": { "attachment": false, "cost": { "input": 0.4, "output": 2 }, "description": "Kimi K2 0905 is an AI model provided by nano-gpt.", "family": "kimi", "id": "moonshotai/Kimi-K2-Instruct-0905", "last_updated": "2025-09-25", "limit": { "context": 256000, "input": 256000, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 0905", "open_weights": false, "reasoning": false, "release_date": "2025-09-25", "structured_output": true, "tool_call": true }, "moonshotai/kimi-k2-instruct": { "attachment": false, "cost": { "input": 0.1, "output": 2 }, "description": "Kimi K2 Instruct is an AI model provided by nano-gpt.", "family": "kimi", "id": "moonshotai/kimi-k2-instruct", "last_updated": "2025-07-01", "limit": { "context": 256000, "input": 256000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-07-01", "structured_output": true, "tool_call": true }, "moonshotai/kimi-k2-instruct-0711": { "attachment": false, "cost": { "input": 0.1, "output": 2 }, "description": "Kimi K2 0711 is an AI model provided by nano-gpt.", "family": "kimi", "id": "moonshotai/kimi-k2-instruct-0711", "last_updated": "2025-07-11", "limit": { "context": 128000, "input": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 0711", "open_weights": false, "reasoning": false, "release_date": "2025-07-11", "structured_output": true, "tool_call": true }, "moonshotai/kimi-k2-thinking": { "attachment": false, "cost": { "input": 0.3, "output": 1.2 }, "description": "Kimi K2 Thinking is an AI model provided by nano-gpt.", "family": "kimi-thinking", "id": "moonshotai/kimi-k2-thinking", "last_updated": "2025-11-06", "limit": { "context": 256000, "input": 256000, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 Thinking", "open_weights": false, "reasoning": false, "release_date": "2025-11-06", "structured_output": true, "tool_call": true }, "moonshotai/kimi-k2-thinking-original": { "attachment": false, "cost": { "input": 0.6, "output": 2.5 }, "description": "Kimi K2 Thinking Original is an AI model provided by nano-gpt.", "family": "kimi-thinking", "id": "moonshotai/kimi-k2-thinking-original", "last_updated": "2025-11-06", "limit": { "context": 256000, "input": 256000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 Thinking Original", "open_weights": false, "reasoning": true, "release_date": "2025-11-06", "structured_output": false, "tool_call": false }, "moonshotai/kimi-k2-thinking-turbo-original": { "attachment": false, "cost": { "input": 1.15, "output": 8 }, "description": "Kimi K2 Thinking Turbo Original is an AI model provided by nano-gpt.", "family": "kimi-thinking", "id": "moonshotai/kimi-k2-thinking-turbo-original", "last_updated": "2025-11-06", "limit": { "context": 256000, "input": 256000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 Thinking Turbo Original", "open_weights": false, "reasoning": true, "release_date": "2025-11-06", "structured_output": false, "tool_call": false }, "moonshotai/kimi-k2.5": { "attachment": true, "cost": { "input": 0.3, "output": 1.9 }, "description": "Kimi K2.5 is an AI model provided by nano-gpt.", "family": "kimi", "id": "moonshotai/kimi-k2.5", "last_updated": "2026-01-26", "limit": { "context": 256000, "input": 256000, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Kimi K2.5", "open_weights": false, "reasoning": false, "release_date": "2026-01-26", "structured_output": false, "tool_call": true }, "moonshotai/kimi-k2.5:thinking": { "attachment": true, "cost": { "input": 0.3, "output": 1.9 }, "description": "Kimi K2.5 Thinking is an AI model provided by nano-gpt.", "family": "kimi-thinking", "id": "moonshotai/kimi-k2.5:thinking", "last_updated": "2026-01-26", "limit": { "context": 256000, "input": 256000, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Kimi K2.5 Thinking", "open_weights": false, "reasoning": true, "release_date": "2026-01-26", "structured_output": false, "tool_call": true }, "moonshotai/kimi-k2.6": { "attachment": true, "cost": { "input": 0.53, "output": 2.73 }, "description": "Kimi K2.6 is an AI model provided by nano-gpt.", "family": "kimi-k2.6", "id": "moonshotai/kimi-k2.6", "last_updated": "2026-04-21", "limit": { "context": 256000, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Kimi K2.6", "open_weights": true, "reasoning": false, "release_date": "2026-04-16", "structured_output": false, "tool_call": true }, "moonshotai/kimi-k2.6:thinking": { "attachment": true, "cost": { "input": 0.53, "output": 2.73 }, "description": "Kimi K2.6 Thinking is an AI model provided by nano-gpt.", "family": "kimi-thinking", "id": "moonshotai/kimi-k2.6:thinking", "last_updated": "2026-04-21", "limit": { "context": 256000, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Kimi K2.6 Thinking", "open_weights": true, "reasoning": true, "release_date": "2026-04-16", "structured_output": false, "tool_call": true }, "nex-agi/deepseek-v3.1-nex-n1": { "attachment": false, "cost": { "input": 0.27999999999999997, "output": 0.42000000000000004 }, "description": "DeepSeek V3.1 Nex N1 is an AI model provided by nano-gpt.", "family": "deepseek", "id": "nex-agi/deepseek-v3.1-nex-n1", "last_updated": "2025-12-10", "limit": { "context": 128000, "input": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3.1 Nex N1", "open_weights": false, "reasoning": false, "release_date": "2025-12-10", "structured_output": false, "tool_call": false }, "nothingiisreal/L3.1-70B-Celeste-V0.1-BF16": { "attachment": false, "cost": { "input": 0.49299999999999994, "output": 0.49299999999999994 }, "description": "Llama 3.1 70B Celeste v0.1 is an AI model provided by nano-gpt.", "family": "llama", "id": "nothingiisreal/L3.1-70B-Celeste-V0.1-BF16", "last_updated": "2024-07-23", "limit": { "context": 16384, "input": 16384, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.1 70B Celeste v0.1", "open_weights": false, "reasoning": false, "release_date": "2024-07-23", "structured_output": false, "tool_call": false }, "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF": { "attachment": false, "cost": { "input": 0.357, "output": 0.408 }, "description": "Nvidia Nemotron 70b is an AI model provided by nano-gpt.", "family": "nemotron", "id": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF", "last_updated": "2025-04-15", "limit": { "context": 16384, "input": 16384, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Nvidia Nemotron 70b", "open_weights": false, "reasoning": false, "release_date": "2025-04-15", "structured_output": false, "tool_call": false }, "nvidia/Llama-3.1-Nemotron-Ultra-253B-v1": { "attachment": false, "cost": { "input": 0.4, "output": 0.8 }, "description": "Nvidia Nemotron Ultra 253B is an AI model provided by nano-gpt.", "family": "nemotron", "id": "nvidia/Llama-3.1-Nemotron-Ultra-253B-v1", "last_updated": "2025-07-03", "limit": { "context": 128000, "input": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Nvidia Nemotron Ultra 253B", "open_weights": false, "reasoning": false, "release_date": "2025-07-03", "structured_output": false, "tool_call": false }, "nvidia/Llama-3.3-Nemotron-Super-49B-v1": { "attachment": false, "cost": { "input": 0.15, "output": 0.15 }, "description": "Nvidia Nemotron Super 49B is an AI model provided by nano-gpt.", "family": "nemotron", "id": "nvidia/Llama-3.3-Nemotron-Super-49B-v1", "last_updated": "2025-08-08", "limit": { "context": 128000, "input": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Nvidia Nemotron Super 49B", "open_weights": false, "reasoning": false, "release_date": "2025-08-08", "structured_output": false, "tool_call": false }, "nvidia/Llama-3_3-Nemotron-Super-49B-v1_5": { "attachment": false, "cost": { "input": 0.05, "output": 0.25 }, "description": "Nvidia Nemotron Super 49B v1.5 is an AI model provided by nano-gpt.", "family": "nemotron", "id": "nvidia/Llama-3_3-Nemotron-Super-49B-v1_5", "last_updated": "2025-08-08", "limit": { "context": 128000, "input": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Nvidia Nemotron Super 49B v1.5", "open_weights": false, "reasoning": false, "release_date": "2025-08-08", "structured_output": false, "tool_call": false }, "nvidia/nemotron-3-nano-30b-a3b": { "attachment": false, "cost": { "input": 0.17, "output": 0.68 }, "description": "Nvidia Nemotron 3 Nano 30B is an AI model provided by nano-gpt.", "family": "nemotron", "id": "nvidia/nemotron-3-nano-30b-a3b", "last_updated": "2025-12-15", "limit": { "context": 256000, "input": 256000, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Nvidia Nemotron 3 Nano 30B", "open_weights": false, "reasoning": false, "release_date": "2025-12-15", "structured_output": false, "tool_call": false }, "nvidia/nvidia-nemotron-nano-9b-v2": { "attachment": false, "cost": { "input": 0.17, "output": 0.68 }, "description": "Nvidia Nemotron Nano 9B v2 is an AI model provided by nano-gpt.", "family": "nemotron", "id": "nvidia/nvidia-nemotron-nano-9b-v2", "last_updated": "2025-08-18", "limit": { "context": 128000, "input": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Nvidia Nemotron Nano 9B v2", "open_weights": false, "reasoning": false, "release_date": "2025-08-18", "structured_output": false, "tool_call": false }, "openai/chatgpt-4o-latest": { "attachment": true, "cost": { "input": 4.998, "output": 14.993999999999998 }, "description": "ChatGPT 4o is an AI model provided by nano-gpt.", "family": "gpt", "id": "openai/chatgpt-4o-latest", "last_updated": "2024-05-13", "limit": { "context": 128000, "input": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "ChatGPT 4o", "open_weights": false, "reasoning": false, "release_date": "2024-05-13", "structured_output": true, "tool_call": true }, "openai/gpt-3.5-turbo": { "attachment": false, "cost": { "input": 0.5, "output": 1.5 }, "description": "GPT-3.5 Turbo is an AI model provided by nano-gpt.", "family": "gpt", "id": "openai/gpt-3.5-turbo", "last_updated": "2024-01-01", "limit": { "context": 16385, "input": 16385, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT-3.5 Turbo", "open_weights": false, "reasoning": false, "release_date": "2022-11-30", "structured_output": false, "tool_call": false }, "openai/gpt-4-turbo": { "attachment": true, "cost": { "input": 10, "output": 30 }, "description": "GPT-4 Turbo is an AI model provided by nano-gpt.", "family": "gpt", "id": "openai/gpt-4-turbo", "last_updated": "2024-01-01", "limit": { "context": 128000, "input": 128000, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4 Turbo", "open_weights": false, "reasoning": false, "release_date": "2023-11-06", "structured_output": false, "tool_call": false }, "openai/gpt-4-turbo-preview": { "attachment": false, "cost": { "input": 9.996, "output": 30.004999999999995 }, "description": "GPT-4 Turbo Preview is an AI model provided by nano-gpt.", "family": "gpt", "id": "openai/gpt-4-turbo-preview", "last_updated": "2024-01-01", "limit": { "context": 128000, "input": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT-4 Turbo Preview", "open_weights": false, "reasoning": false, "release_date": "2023-11-06", "structured_output": false, "tool_call": false }, "openai/gpt-4.1": { "attachment": true, "cost": { "input": 2, "output": 8 }, "description": "GPT 4.1 is an AI model provided by nano-gpt.", "family": "gpt", "id": "openai/gpt-4.1", "last_updated": "2025-09-10", "limit": { "context": 1047576, "input": 1047576, "output": 32768 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT 4.1", "open_weights": false, "reasoning": false, "release_date": "2025-09-10", "structured_output": true, "tool_call": true }, "openai/gpt-4.1-mini": { "attachment": true, "cost": { "input": 0.4, "output": 1.6 }, "description": "GPT 4.1 Mini is an AI model provided by nano-gpt.", "family": "gpt-mini", "id": "openai/gpt-4.1-mini", "last_updated": "2025-04-14", "limit": { "context": 1047576, "input": 1047576, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT 4.1 Mini", "open_weights": false, "reasoning": false, "release_date": "2025-04-14", "structured_output": false, "tool_call": false }, "openai/gpt-4.1-nano": { "attachment": true, "cost": { "input": 0.1, "output": 0.4 }, "description": "GPT 4.1 Nano is an AI model provided by nano-gpt.", "family": "gpt-nano", "id": "openai/gpt-4.1-nano", "last_updated": "2025-04-14", "limit": { "context": 1047576, "input": 1047576, "output": 32768 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT 4.1 Nano", "open_weights": false, "reasoning": false, "release_date": "2025-04-14", "structured_output": false, "tool_call": false }, "openai/gpt-4o": { "attachment": true, "cost": { "input": 2.499, "output": 9.996 }, "description": "GPT-4o is an AI model provided by nano-gpt.", "family": "gpt", "id": "openai/gpt-4o", "last_updated": "2024-05-13", "limit": { "context": 128000, "input": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4o", "open_weights": false, "reasoning": false, "release_date": "2024-05-13", "structured_output": false, "tool_call": false }, "openai/gpt-4o-2024-08-06": { "attachment": true, "cost": { "input": 2.499, "output": 9.996 }, "description": "GPT-4o (2024-08-06) is an AI model provided by nano-gpt.", "family": "gpt", "id": "openai/gpt-4o-2024-08-06", "last_updated": "2024-08-06", "limit": { "context": 128000, "input": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4o (2024-08-06)", "open_weights": false, "reasoning": false, "release_date": "2024-08-06", "structured_output": false, "tool_call": false }, "openai/gpt-4o-2024-11-20": { "attachment": true, "cost": { "input": 2.5, "output": 10 }, "description": "GPT-4o (2024-11-20) is an AI model provided by nano-gpt.", "family": "gpt", "id": "openai/gpt-4o-2024-11-20", "last_updated": "2024-11-20", "limit": { "context": 128000, "input": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4o (2024-11-20)", "open_weights": false, "reasoning": false, "release_date": "2024-11-20", "structured_output": false, "tool_call": false }, "openai/gpt-4o-mini": { "attachment": true, "cost": { "input": 0.1496, "output": 0.595 }, "description": "GPT-4o mini is an AI model provided by nano-gpt.", "family": "gpt-mini", "id": "openai/gpt-4o-mini", "last_updated": "2024-07-18", "limit": { "context": 128000, "input": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4o mini", "open_weights": false, "reasoning": false, "release_date": "2024-07-18", "structured_output": false, "tool_call": false }, "openai/gpt-4o-mini-search-preview": { "attachment": false, "cost": { "input": 0.088, "output": 0.35 }, "description": "GPT-4o mini Search Preview is an AI model provided by nano-gpt.", "family": "gpt-mini", "id": "openai/gpt-4o-mini-search-preview", "last_updated": "2024-07-18", "limit": { "context": 128000, "input": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT-4o mini Search Preview", "open_weights": false, "reasoning": false, "release_date": "2024-07-18", "structured_output": false, "tool_call": false }, "openai/gpt-4o-search-preview": { "attachment": true, "cost": { "input": 1.47, "output": 5.88 }, "description": "GPT-4o Search Preview is an AI model provided by nano-gpt.", "family": "gpt", "id": "openai/gpt-4o-search-preview", "last_updated": "2024-05-13", "limit": { "context": 128000, "input": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4o Search Preview", "open_weights": false, "reasoning": false, "release_date": "2024-05-13", "structured_output": false, "tool_call": false }, "openai/gpt-5": { "attachment": true, "cost": { "input": 1.25, "output": 10 }, "description": "GPT 5 is an AI model provided by nano-gpt.", "family": "gpt", "id": "openai/gpt-5", "last_updated": "2025-08-07", "limit": { "context": 400000, "input": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT 5", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "structured_output": true, "tool_call": true }, "openai/gpt-5-chat-latest": { "attachment": true, "cost": { "input": 1.25, "output": 10 }, "description": "GPT 5 Chat is an AI model provided by nano-gpt.", "family": "gpt", "id": "openai/gpt-5-chat-latest", "last_updated": "2025-08-07", "limit": { "context": 400000, "input": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT 5 Chat", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "structured_output": false, "tool_call": false }, "openai/gpt-5-codex": { "attachment": false, "cost": { "input": 9.996, "output": 19.992 }, "description": "GPT-5 Codex is an AI model provided by nano-gpt.", "family": "gpt-codex", "id": "openai/gpt-5-codex", "last_updated": "2025-09-15", "limit": { "context": 256000, "input": 256000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT-5 Codex", "open_weights": false, "reasoning": false, "release_date": "2025-09-15", "structured_output": false, "tool_call": false }, "openai/gpt-5-mini": { "attachment": true, "cost": { "input": 0.25, "output": 2 }, "description": "GPT 5 Mini is an AI model provided by nano-gpt.", "family": "gpt-mini", "id": "openai/gpt-5-mini", "last_updated": "2025-08-07", "limit": { "context": 400000, "input": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT 5 Mini", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "structured_output": false, "tool_call": false }, "openai/gpt-5-nano": { "attachment": true, "cost": { "input": 0.05, "output": 0.4 }, "description": "GPT 5 Nano is an AI model provided by nano-gpt.", "family": "gpt-nano", "id": "openai/gpt-5-nano", "last_updated": "2025-08-07", "limit": { "context": 400000, "input": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT 5 Nano", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "structured_output": false, "tool_call": false }, "openai/gpt-5-pro": { "attachment": true, "cost": { "input": 15, "output": 120 }, "description": "GPT 5 Pro is an AI model provided by nano-gpt.", "family": "gpt-pro", "id": "openai/gpt-5-pro", "last_updated": "2025-08-07", "limit": { "context": 400000, "input": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT 5 Pro", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "structured_output": false, "tool_call": false }, "openai/gpt-5.1": { "attachment": true, "cost": { "input": 1.25, "output": 10 }, "description": "GPT 5.1 is an AI model provided by nano-gpt.", "family": "gpt", "id": "openai/gpt-5.1", "last_updated": "2025-11-13", "limit": { "context": 400000, "input": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT 5.1", "open_weights": false, "reasoning": true, "release_date": "2025-11-13", "structured_output": true, "tool_call": true }, "openai/gpt-5.1-2025-11-13": { "attachment": false, "cost": { "input": 1.25, "output": 10 }, "description": "GPT-5.1 (2025-11-13) is an AI model provided by nano-gpt.", "family": "gpt", "id": "openai/gpt-5.1-2025-11-13", "last_updated": "2025-11-13", "limit": { "context": 1000000, "input": 1000000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT-5.1 (2025-11-13)", "open_weights": false, "reasoning": false, "release_date": "2025-11-13", "structured_output": false, "tool_call": false }, "openai/gpt-5.1-chat": { "attachment": true, "cost": { "input": 1.25, "output": 10 }, "description": "GPT 5.1 Chat is an AI model provided by nano-gpt.", "family": "gpt", "id": "openai/gpt-5.1-chat", "last_updated": "2025-11-13", "limit": { "context": 400000, "input": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT 5.1 Chat", "open_weights": false, "reasoning": true, "release_date": "2025-11-13", "structured_output": false, "tool_call": false }, "openai/gpt-5.1-chat-latest": { "attachment": true, "cost": { "input": 1.25, "output": 10 }, "description": "GPT 5.1 Chat (Latest) is an AI model provided by nano-gpt.", "family": "gpt", "id": "openai/gpt-5.1-chat-latest", "last_updated": "2025-11-13", "limit": { "context": 400000, "input": 400000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT 5.1 Chat (Latest)", "open_weights": false, "reasoning": true, "release_date": "2025-11-13", "structured_output": false, "tool_call": false }, "openai/gpt-5.1-codex": { "attachment": true, "cost": { "input": 1.25, "output": 10 }, "description": "GPT 5.1 Codex is an AI model provided by nano-gpt.", "family": "gpt-codex", "id": "openai/gpt-5.1-codex", "last_updated": "2025-11-13", "limit": { "context": 400000, "input": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT 5.1 Codex", "open_weights": false, "reasoning": true, "release_date": "2025-11-13", "structured_output": false, "tool_call": false }, "openai/gpt-5.1-codex-max": { "attachment": true, "cost": { "input": 2.5, "output": 20 }, "description": "GPT 5.1 Codex Max is an AI model provided by nano-gpt.", "family": "gpt-codex", "id": "openai/gpt-5.1-codex-max", "last_updated": "2025-11-13", "limit": { "context": 400000, "input": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT 5.1 Codex Max", "open_weights": false, "reasoning": true, "release_date": "2025-11-13", "structured_output": true, "tool_call": true }, "openai/gpt-5.1-codex-mini": { "attachment": true, "cost": { "input": 0.25, "output": 2 }, "description": "GPT 5.1 Codex Mini is an AI model provided by nano-gpt.", "family": "gpt-codex-mini", "id": "openai/gpt-5.1-codex-mini", "last_updated": "2025-11-13", "limit": { "context": 400000, "input": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT 5.1 Codex Mini", "open_weights": false, "reasoning": true, "release_date": "2025-11-13", "structured_output": false, "tool_call": false }, "openai/gpt-5.2": { "attachment": true, "cost": { "input": 1.75, "output": 14 }, "description": "GPT 5.2 is an AI model provided by nano-gpt.", "family": "gpt", "id": "openai/gpt-5.2", "last_updated": "2026-01-01", "limit": { "context": 400000, "input": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT 5.2", "open_weights": false, "reasoning": true, "release_date": "2026-01-01", "structured_output": true, "tool_call": true }, "openai/gpt-5.2-chat": { "attachment": true, "cost": { "input": 1.75, "output": 14 }, "description": "GPT 5.2 Chat is an AI model provided by nano-gpt.", "family": "gpt", "id": "openai/gpt-5.2-chat", "last_updated": "2026-01-01", "limit": { "context": 400000, "input": 400000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT 5.2 Chat", "open_weights": false, "reasoning": true, "release_date": "2026-01-01", "structured_output": false, "tool_call": false }, "openai/gpt-5.2-codex": { "attachment": true, "cost": { "input": 1.75, "output": 14 }, "description": "GPT 5.2 Codex is an AI model provided by nano-gpt.", "family": "gpt-codex", "id": "openai/gpt-5.2-codex", "last_updated": "2026-01-14", "limit": { "context": 400000, "input": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT 5.2 Codex", "open_weights": false, "reasoning": true, "release_date": "2026-01-14", "structured_output": true, "tool_call": true }, "openai/gpt-5.2-pro": { "attachment": true, "cost": { "input": 21, "output": 168 }, "description": "GPT 5.2 Pro is an AI model provided by nano-gpt.", "family": "gpt-pro", "id": "openai/gpt-5.2-pro", "last_updated": "2026-01-01", "limit": { "context": 400000, "input": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT 5.2 Pro", "open_weights": false, "reasoning": true, "release_date": "2026-01-01", "structured_output": true, "tool_call": true }, "openai/gpt-oss-120b": { "attachment": false, "cost": { "input": 0.05, "output": 0.25 }, "description": "GPT OSS 120B is an AI model provided by nano-gpt.", "family": "gpt-oss", "id": "openai/gpt-oss-120b", "last_updated": "2025-08-05", "limit": { "context": 128000, "input": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT OSS 120B", "open_weights": false, "reasoning": true, "release_date": "2025-08-05", "structured_output": true, "tool_call": true }, "openai/gpt-oss-20b": { "attachment": false, "cost": { "input": 0.04, "output": 0.15 }, "description": "GPT OSS 20B is an AI model provided by nano-gpt.", "family": "gpt-oss", "id": "openai/gpt-oss-20b", "last_updated": "2025-08-05", "limit": { "context": 128000, "input": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT OSS 20B", "open_weights": false, "reasoning": true, "release_date": "2025-08-05", "structured_output": false, "tool_call": false }, "openai/gpt-oss-safeguard-20b": { "attachment": false, "cost": { "input": 0.075, "output": 0.3 }, "description": "GPT OSS Safeguard 20B is an AI model provided by nano-gpt.", "family": "gpt-oss", "id": "openai/gpt-oss-safeguard-20b", "last_updated": "2025-10-29", "limit": { "context": 128000, "input": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT OSS Safeguard 20B", "open_weights": false, "reasoning": true, "release_date": "2025-10-29", "structured_output": false, "tool_call": false }, "openai/o1": { "attachment": false, "cost": { "input": 14.993999999999998, "output": 59.993 }, "description": "OpenAI o1 is an AI model provided by nano-gpt.", "family": "o", "id": "openai/o1", "last_updated": "2024-12-17", "limit": { "context": 200000, "input": 200000, "output": 100000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "OpenAI o1", "open_weights": false, "reasoning": true, "release_date": "2024-12-17", "structured_output": false, "tool_call": false }, "openai/o1-preview": { "attachment": false, "cost": { "input": 14.993999999999998, "output": 59.993 }, "description": "OpenAI o1-preview is an AI model provided by nano-gpt.", "family": "o", "id": "openai/o1-preview", "last_updated": "2024-09-12", "limit": { "context": 128000, "input": 128000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "OpenAI o1-preview", "open_weights": false, "reasoning": true, "release_date": "2024-09-12", "structured_output": false, "tool_call": false }, "openai/o1-pro": { "attachment": true, "cost": { "input": 150, "output": 600 }, "description": "OpenAI o1 Pro is an AI model provided by nano-gpt.", "family": "o-pro", "id": "openai/o1-pro", "last_updated": "2025-01-25", "limit": { "context": 200000, "input": 200000, "output": 100000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "OpenAI o1 Pro", "open_weights": false, "reasoning": false, "release_date": "2025-01-25", "structured_output": false, "tool_call": false }, "openai/o3": { "attachment": false, "cost": { "input": 2, "output": 8 }, "description": "OpenAI o3 is an AI model provided by nano-gpt.", "family": "o", "id": "openai/o3", "last_updated": "2025-04-16", "limit": { "context": 200000, "input": 200000, "output": 100000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "OpenAI o3", "open_weights": false, "reasoning": false, "release_date": "2025-04-16", "structured_output": false, "tool_call": false }, "openai/o3-deep-research": { "attachment": false, "cost": { "input": 9.996, "output": 19.992 }, "description": "OpenAI o3 Deep Research is an AI model provided by nano-gpt.", "family": "o", "id": "openai/o3-deep-research", "last_updated": "2025-04-16", "limit": { "context": 200000, "input": 200000, "output": 100000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "OpenAI o3 Deep Research", "open_weights": false, "reasoning": true, "release_date": "2025-04-16", "structured_output": false, "tool_call": false }, "openai/o3-mini": { "attachment": false, "cost": { "input": 1.1, "output": 4.4 }, "description": "OpenAI o3-mini is an AI model provided by nano-gpt.", "family": "o-mini", "id": "openai/o3-mini", "last_updated": "2025-01-31", "limit": { "context": 200000, "input": 200000, "output": 100000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "OpenAI o3-mini", "open_weights": false, "reasoning": true, "release_date": "2025-01-31", "structured_output": true, "tool_call": true }, "openai/o3-mini-high": { "attachment": false, "cost": { "input": 0.64, "output": 2.588 }, "description": "OpenAI o3-mini (High) is an AI model provided by nano-gpt.", "family": "o-mini", "id": "openai/o3-mini-high", "last_updated": "2025-01-31", "limit": { "context": 200000, "input": 200000, "output": 100000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "OpenAI o3-mini (High)", "open_weights": false, "reasoning": true, "release_date": "2025-01-31", "structured_output": true, "tool_call": true }, "openai/o3-mini-low": { "attachment": false, "cost": { "input": 9.996, "output": 19.992 }, "description": "OpenAI o3-mini (Low) is an AI model provided by nano-gpt.", "family": "o-mini", "id": "openai/o3-mini-low", "last_updated": "2025-01-31", "limit": { "context": 200000, "input": 200000, "output": 100000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "OpenAI o3-mini (Low)", "open_weights": false, "reasoning": true, "release_date": "2025-01-31", "structured_output": true, "tool_call": true }, "openai/o3-pro-2025-06-10": { "attachment": false, "cost": { "input": 9.996, "output": 19.992 }, "description": "OpenAI o3-pro (2025-06-10) is an AI model provided by nano-gpt.", "family": "o-pro", "id": "openai/o3-pro-2025-06-10", "last_updated": "2025-06-10", "limit": { "context": 200000, "input": 200000, "output": 100000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "OpenAI o3-pro (2025-06-10)", "open_weights": false, "reasoning": true, "release_date": "2025-06-10", "structured_output": true, "tool_call": true }, "openai/o4-mini": { "attachment": false, "cost": { "input": 1.1, "output": 4.4 }, "description": "OpenAI o4-mini is an AI model provided by nano-gpt.", "family": "o-mini", "id": "openai/o4-mini", "last_updated": "2025-04-16", "limit": { "context": 200000, "input": 200000, "output": 100000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "OpenAI o4-mini", "open_weights": false, "reasoning": true, "release_date": "2025-04-16", "structured_output": true, "tool_call": true }, "openai/o4-mini-deep-research": { "attachment": false, "cost": { "input": 9.996, "output": 19.992 }, "description": "OpenAI o4-mini Deep Research is an AI model provided by nano-gpt.", "family": "o-mini", "id": "openai/o4-mini-deep-research", "last_updated": "2025-04-16", "limit": { "context": 200000, "input": 200000, "output": 100000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "OpenAI o4-mini Deep Research", "open_weights": false, "reasoning": true, "release_date": "2025-04-16", "structured_output": false, "tool_call": false }, "openai/o4-mini-high": { "attachment": false, "cost": { "input": 1.1, "output": 4.4 }, "description": "OpenAI o4-mini high is an AI model provided by nano-gpt.", "family": "o-mini", "id": "openai/o4-mini-high", "last_updated": "2025-04-16", "limit": { "context": 200000, "input": 200000, "output": 100000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "OpenAI o4-mini high", "open_weights": false, "reasoning": true, "release_date": "2025-04-16", "structured_output": true, "tool_call": true }, "pamanseau/OpenReasoning-Nemotron-32B": { "attachment": false, "cost": { "input": 0.1, "output": 0.4 }, "description": "OpenReasoning Nemotron 32B is an AI model provided by nano-gpt.", "family": "nemotron", "id": "pamanseau/OpenReasoning-Nemotron-32B", "last_updated": "2025-08-21", "limit": { "context": 32768, "input": 32768, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "OpenReasoning Nemotron 32B", "open_weights": false, "reasoning": true, "release_date": "2025-08-21", "structured_output": false, "tool_call": false }, "phi-4-mini-instruct": { "attachment": false, "cost": { "input": 0.17, "output": 0.68 }, "description": "Phi 4 Mini is an AI model provided by nano-gpt.", "id": "phi-4-mini-instruct", "last_updated": "2025-07-26", "limit": { "context": 128000, "input": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Phi 4 Mini", "open_weights": false, "reasoning": false, "release_date": "2025-07-26", "structured_output": false, "tool_call": false }, "phi-4-multimodal-instruct": { "attachment": false, "cost": { "input": 0.07, "output": 0.11 }, "description": "Phi 4 Multimodal is an AI model provided by nano-gpt.", "id": "phi-4-multimodal-instruct", "last_updated": "2025-07-26", "limit": { "context": 128000, "input": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Phi 4 Multimodal", "open_weights": false, "reasoning": false, "release_date": "2025-07-26", "structured_output": false, "tool_call": false }, "qvq-max": { "attachment": true, "cost": { "input": 1.4, "output": 5.3 }, "description": "Qwen: QvQ Max is an AI model provided by nano-gpt.", "id": "qvq-max", "last_updated": "2025-03-28", "limit": { "context": 128000, "input": 128000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen: QvQ Max", "open_weights": false, "reasoning": false, "release_date": "2025-03-28", "structured_output": false, "tool_call": false }, "qwen-3.6-plus": { "attachment": false, "cost": { "input": 0.45, "output": 2.7 }, "description": "Qwen 3.6 Plus is an AI model provided by nano-gpt.", "family": "qwen3.6", "id": "qwen-3.6-plus", "last_updated": "2026-04-02", "limit": { "context": 991800, "output": 65536 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen 3.6 Plus", "open_weights": false, "reasoning": false, "release_date": "2026-04-02", "structured_output": false, "tool_call": false }, "qwen-image": { "attachment": true, "description": "Qwen Image is an AI model provided by nano-gpt.", "id": "qwen-image", "last_updated": "2025-08-07", "limit": { "context": 0, "output": 0 }, "modalities": { "input": [ "text", "image" ], "output": [ "image" ] }, "name": "Qwen Image", "open_weights": false, "reasoning": false, "release_date": "2025-08-07", "structured_output": false, "temperature": true, "tool_call": false }, "qwen-long": { "attachment": true, "cost": { "input": 0.1003, "output": 0.408 }, "description": "Qwen Long 10M is an AI model provided by nano-gpt.", "id": "qwen-long", "last_updated": "2025-01-25", "limit": { "context": 10000000, "input": 10000000, "output": 8192 }, "modalities": { "input": [ "text", "pdf" ], "output": [ "text" ] }, "name": "Qwen Long 10M", "open_weights": false, "reasoning": false, "release_date": "2025-01-25", "structured_output": false, "tool_call": false }, "qwen-max": { "attachment": false, "cost": { "input": 1.5997, "output": 6.392 }, "description": "Qwen 2.5 Max is an AI model provided by nano-gpt.", "id": "qwen-max", "last_updated": "2024-04-03", "limit": { "context": 32000, "input": 32000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen 2.5 Max", "open_weights": false, "reasoning": false, "release_date": "2024-04-03", "structured_output": false, "tool_call": false }, "qwen-plus": { "attachment": false, "cost": { "input": 0.3995, "output": 1.2002 }, "description": "Qwen Plus is an AI model provided by nano-gpt.", "id": "qwen-plus", "last_updated": "2024-01-25", "limit": { "context": 995904, "input": 995904, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen Plus", "open_weights": false, "reasoning": true, "release_date": "2024-01-25", "structured_output": false, "tool_call": false }, "qwen-turbo": { "attachment": false, "cost": { "input": 0.04998, "output": 0.2006 }, "description": "Qwen Turbo is an AI model provided by nano-gpt.", "id": "qwen-turbo", "last_updated": "2024-11-01", "limit": { "context": 1000000, "input": 1000000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen Turbo", "open_weights": false, "reasoning": false, "release_date": "2024-11-01", "structured_output": false, "tool_call": false }, "qwen/Qwen3.6-35B-A3B": { "attachment": false, "cost": { "input": 0.29, "output": 1.74 }, "description": "Qwen3.6 35B A3B is an AI model provided by nano-gpt.", "family": "qwen3.6", "id": "qwen/Qwen3.6-35B-A3B", "last_updated": "2026-04-21", "limit": { "context": 262144, "output": 16384 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen3.6 35B A3B", "open_weights": true, "reasoning": false, "release_date": "2026-04-17", "structured_output": false, "tool_call": false }, "qwen/Qwen3.6-35B-A3B:thinking": { "attachment": false, "cost": { "input": 0.29, "output": 1.74 }, "description": "Qwen3.6 35B A3B Thinking is an AI model provided by nano-gpt.", "family": "qwen3.6", "id": "qwen/Qwen3.6-35B-A3B:thinking", "last_updated": "2026-04-21", "limit": { "context": 262144, "output": 16384 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen3.6 35B A3B Thinking", "open_weights": true, "reasoning": true, "release_date": "2026-04-19", "structured_output": false, "tool_call": false }, "qwen/qwen3.5-397b-a17b": { "attachment": false, "cost": { "input": 0.6, "output": 3.6 }, "description": "Qwen3.5 397B A17B is an AI model provided by nano-gpt.", "family": "qwen", "id": "qwen/qwen3.5-397b-a17b", "last_updated": "2026-02-16", "limit": { "context": 258048, "input": 258048, "output": 65536 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen3.5 397B A17B", "open_weights": true, "reasoning": false, "release_date": "2026-02-16", "structured_output": false, "tool_call": false }, "qwen25-vl-72b-instruct": { "attachment": true, "cost": { "input": 0.69989, "output": 0.69989 }, "description": "Qwen25 VL 72b is an AI model provided by nano-gpt.", "id": "qwen25-vl-72b-instruct", "last_updated": "2025-05-10", "limit": { "context": 32000, "input": 32000, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen25 VL 72b", "open_weights": false, "reasoning": false, "release_date": "2025-05-10", "structured_output": false, "tool_call": false }, "qwen3-30b-a3b-instruct-2507": { "attachment": false, "cost": { "input": 0.2, "output": 0.5 }, "description": "Qwen3 30B A3B Instruct 2507 is an AI model provided by nano-gpt.", "id": "qwen3-30b-a3b-instruct-2507", "last_updated": "2025-02-20", "limit": { "context": 256000, "input": 256000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 30B A3B Instruct 2507", "open_weights": false, "reasoning": false, "release_date": "2025-02-20", "structured_output": false, "tool_call": false }, "qwen3-coder-30b-a3b-instruct": { "attachment": false, "cost": { "input": 0.1, "output": 0.4 }, "description": "Qwen3 Coder 30B A3B Instruct is an AI model provided by nano-gpt.", "id": "qwen3-coder-30b-a3b-instruct", "last_updated": "2025-08-05", "limit": { "context": 128000, "input": 128000, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Coder 30B A3B Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-08-05", "structured_output": true, "tool_call": true }, "qwen3-max-2026-01-23": { "attachment": false, "cost": { "input": 1.2002, "output": 6.001 }, "description": "Qwen3 Max 2026-01-23 is an AI model provided by nano-gpt.", "id": "qwen3-max-2026-01-23", "last_updated": "2026-01-26", "limit": { "context": 256000, "input": 256000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Max 2026-01-23", "open_weights": false, "reasoning": false, "release_date": "2026-01-26", "structured_output": false, "tool_call": false }, "qwen3-vl-235b-a22b-instruct-original": { "attachment": true, "cost": { "input": 0.5, "output": 1.2 }, "description": "Qwen3 VL 235B A22B Instruct Original is an AI model provided by nano-gpt.", "id": "qwen3-vl-235b-a22b-instruct-original", "last_updated": "2025-09-25", "limit": { "context": 32768, "input": 32768, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen3 VL 235B A22B Instruct Original", "open_weights": false, "reasoning": false, "release_date": "2025-09-25", "structured_output": false, "tool_call": false }, "qwen3-vl-235b-a22b-thinking": { "attachment": true, "cost": { "input": 0.5, "output": 6 }, "description": "Qwen3 VL 235B A22B Thinking is an AI model provided by nano-gpt.", "id": "qwen3-vl-235b-a22b-thinking", "last_updated": "2025-08-26", "limit": { "context": 32768, "input": 32768, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen3 VL 235B A22B Thinking", "open_weights": false, "reasoning": true, "release_date": "2025-08-26", "structured_output": false, "tool_call": false }, "qwen3.6-max-preview": { "attachment": false, "cost": { "input": 1.3, "output": 7.8 }, "description": "Qwen3.6 Max Preview is an AI model provided by nano-gpt.", "family": "qwen3.6", "id": "qwen3.6-max-preview", "last_updated": "2026-04-21", "limit": { "context": 245800, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3.6 Max Preview", "open_weights": false, "reasoning": false, "release_date": "2026-04-20", "structured_output": false, "tool_call": false }, "qwq-32b": { "attachment": false, "cost": { "input": 0.25599999, "output": 0.30499999 }, "description": "Qwen: QwQ 32B is an AI model provided by nano-gpt.", "id": "qwq-32b", "last_updated": "2025-04-15", "limit": { "context": 128000, "input": 128000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen: QwQ 32B", "open_weights": false, "reasoning": false, "release_date": "2025-04-15", "structured_output": false, "tool_call": false }, "raifle/sorcererlm-8x22b": { "attachment": true, "cost": { "input": 4.505, "output": 4.505 }, "description": "SorcererLM 8x22B is an AI model provided by nano-gpt.", "family": "mixtral", "id": "raifle/sorcererlm-8x22b", "last_updated": "2025-01-01", "limit": { "context": 16000, "input": 16000, "output": 8192 }, "modalities": { "input": [ "text", "pdf" ], "output": [ "text" ] }, "name": "SorcererLM 8x22B", "open_weights": false, "reasoning": false, "release_date": "2025-01-01", "structured_output": false, "tool_call": false }, "sarvan-medium": { "attachment": false, "cost": { "input": 0.25, "output": 0.75 }, "description": "Sarvam Medium is an AI model provided by nano-gpt.", "id": "sarvan-medium", "last_updated": "2025-01-01", "limit": { "context": 128000, "input": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Sarvam Medium", "open_weights": false, "reasoning": false, "release_date": "2025-01-01", "structured_output": false, "tool_call": false }, "shisa-ai/shisa-v2-llama3.3-70b": { "attachment": false, "cost": { "input": 0.5, "output": 0.5 }, "description": "Shisa V2 Llama 3.3 70B is an AI model provided by nano-gpt.", "family": "llama", "id": "shisa-ai/shisa-v2-llama3.3-70b", "last_updated": "2025-07-26", "limit": { "context": 128000, "input": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Shisa V2 Llama 3.3 70B", "open_weights": false, "reasoning": false, "release_date": "2025-07-26", "structured_output": false, "tool_call": false }, "shisa-ai/shisa-v2.1-llama3.3-70b": { "attachment": false, "cost": { "input": 0.5, "output": 0.5 }, "description": "Shisa V2.1 Llama 3.3 70B is an AI model provided by nano-gpt.", "family": "llama", "id": "shisa-ai/shisa-v2.1-llama3.3-70b", "last_updated": "2024-12-06", "limit": { "context": 32768, "input": 32768, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Shisa V2.1 Llama 3.3 70B", "open_weights": false, "reasoning": false, "release_date": "2024-12-06", "structured_output": false, "tool_call": false }, "sonar": { "attachment": false, "cost": { "input": 1.003, "output": 1.003 }, "description": "Perplexity Simple is an AI model provided by nano-gpt.", "id": "sonar", "last_updated": "2025-02-19", "limit": { "context": 127000, "input": 127000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Perplexity Simple", "open_weights": false, "reasoning": false, "release_date": "2025-02-19", "structured_output": false, "tool_call": false }, "sonar-deep-research": { "attachment": false, "cost": { "input": 3.4, "output": 13.6 }, "description": "Perplexity Deep Research is an AI model provided by nano-gpt.", "id": "sonar-deep-research", "last_updated": "2025-02-25", "limit": { "context": 60000, "input": 60000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Perplexity Deep Research", "open_weights": false, "reasoning": false, "release_date": "2025-02-25", "structured_output": false, "tool_call": false }, "sonar-pro": { "attachment": false, "cost": { "input": 2.992, "output": 14.994 }, "description": "Perplexity Pro is an AI model provided by nano-gpt.", "id": "sonar-pro", "last_updated": "2025-02-19", "limit": { "context": 200000, "input": 200000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Perplexity Pro", "open_weights": false, "reasoning": false, "release_date": "2025-02-19", "structured_output": false, "tool_call": false }, "sonar-reasoning-pro": { "attachment": false, "cost": { "input": 2.006, "output": 7.9985 }, "description": "Perplexity Reasoning Pro is an AI model provided by nano-gpt.", "id": "sonar-reasoning-pro", "last_updated": "2025-02-19", "limit": { "context": 127000, "input": 127000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Perplexity Reasoning Pro", "open_weights": false, "reasoning": true, "release_date": "2025-02-19", "structured_output": false, "tool_call": false }, "soob3123/GrayLine-Qwen3-8B": { "attachment": false, "cost": { "input": 0.3, "output": 0.3 }, "description": "Grayline Qwen3 8B is an AI model provided by nano-gpt.", "family": "qwen", "id": "soob3123/GrayLine-Qwen3-8B", "last_updated": "2025-09-25", "limit": { "context": 16384, "input": 16384, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grayline Qwen3 8B", "open_weights": false, "reasoning": false, "release_date": "2025-09-25", "structured_output": false, "tool_call": false }, "soob3123/Veiled-Calla-12B": { "attachment": false, "cost": { "input": 0.3, "output": 0.3 }, "description": "Veiled Calla 12B is an AI model provided by nano-gpt.", "family": "llama", "id": "soob3123/Veiled-Calla-12B", "last_updated": "2025-04-13", "limit": { "context": 32768, "input": 32768, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Veiled Calla 12B", "open_weights": false, "reasoning": false, "release_date": "2025-04-13", "structured_output": false, "tool_call": false }, "soob3123/amoral-gemma3-27B-v2": { "attachment": false, "cost": { "input": 0.3, "output": 0.3 }, "description": "Amoral Gemma3 27B v2 is an AI model provided by nano-gpt.", "family": "gemma", "id": "soob3123/amoral-gemma3-27B-v2", "last_updated": "2025-05-23", "limit": { "context": 32768, "input": 32768, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Amoral Gemma3 27B v2", "open_weights": false, "reasoning": false, "release_date": "2025-05-23", "structured_output": false, "tool_call": false }, "step-2-16k-exp": { "attachment": false, "cost": { "input": 7.004, "output": 19.992 }, "description": "Step-2 16k Exp is an AI model provided by nano-gpt.", "id": "step-2-16k-exp", "last_updated": "2024-07-05", "limit": { "context": 16000, "input": 16000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Step-2 16k Exp", "open_weights": false, "reasoning": false, "release_date": "2024-07-05", "structured_output": false, "tool_call": false }, "step-2-mini": { "attachment": false, "cost": { "input": 0.2006, "output": 0.408 }, "description": "Step-2 Mini is an AI model provided by nano-gpt.", "id": "step-2-mini", "last_updated": "2024-07-05", "limit": { "context": 8000, "input": 8000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Step-2 Mini", "open_weights": false, "reasoning": false, "release_date": "2024-07-05", "structured_output": false, "tool_call": false }, "step-3": { "attachment": true, "cost": { "input": 0.2499, "output": 0.6494 }, "description": "Step-3 is an AI model provided by nano-gpt.", "id": "step-3", "last_updated": "2025-07-31", "limit": { "context": 65536, "input": 65536, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Step-3", "open_weights": false, "reasoning": false, "release_date": "2025-07-31", "structured_output": false, "tool_call": false }, "step-r1-v-mini": { "attachment": false, "cost": { "input": 2.5, "output": 11 }, "description": "Step R1 V Mini is an AI model provided by nano-gpt.", "id": "step-r1-v-mini", "last_updated": "2025-04-08", "limit": { "context": 128000, "input": 128000, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Step R1 V Mini", "open_weights": false, "reasoning": false, "release_date": "2025-04-08", "structured_output": false, "tool_call": false }, "stepfun-ai/step-3.5-flash": { "attachment": false, "cost": { "input": 0.2, "output": 0.5 }, "description": "Step 3.5 Flash is an AI model provided by nano-gpt.", "family": "step", "id": "stepfun-ai/step-3.5-flash", "last_updated": "2026-02-02", "limit": { "context": 256000, "input": 256000, "output": 256000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Step 3.5 Flash", "open_weights": false, "reasoning": true, "release_date": "2026-02-02", "structured_output": false, "tool_call": false }, "stepfun-ai/step-3.5-flash:thinking": { "attachment": false, "cost": { "input": 0.2, "output": 0.5 }, "description": "Step 3.5 Flash Thinking is an AI model provided by nano-gpt.", "family": "step", "id": "stepfun-ai/step-3.5-flash:thinking", "last_updated": "2026-02-02", "limit": { "context": 256000, "input": 256000, "output": 256000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Step 3.5 Flash Thinking", "open_weights": false, "reasoning": true, "release_date": "2026-02-02", "structured_output": false, "tool_call": false }, "study_gpt-chatgpt-4o-latest": { "attachment": true, "cost": { "input": 4.998, "output": 14.994 }, "description": "Study Mode is an AI model provided by nano-gpt.", "id": "study_gpt-chatgpt-4o-latest", "last_updated": "2024-05-13", "limit": { "context": 200000, "input": 200000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Study Mode", "open_weights": false, "reasoning": false, "release_date": "2024-05-13", "structured_output": false, "tool_call": false }, "tencent/Hunyuan-MT-7B": { "attachment": false, "cost": { "input": 10, "output": 20 }, "description": "Hunyuan MT 7B is an AI model provided by nano-gpt.", "family": "hunyuan", "id": "tencent/Hunyuan-MT-7B", "last_updated": "2025-09-18", "limit": { "context": 8192, "input": 8192, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Hunyuan MT 7B", "open_weights": false, "reasoning": false, "release_date": "2025-09-18", "structured_output": false, "tool_call": false }, "tngtech/DeepSeek-TNG-R1T2-Chimera": { "attachment": false, "cost": { "input": 0.31, "output": 0.31 }, "description": "DeepSeek TNG R1T2 Chimera is an AI model provided by nano-gpt.", "family": "tngtech", "id": "tngtech/DeepSeek-TNG-R1T2-Chimera", "last_updated": "2025-09-05", "limit": { "context": 128000, "input": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek TNG R1T2 Chimera", "open_weights": false, "reasoning": false, "release_date": "2025-09-05", "structured_output": false, "tool_call": false }, "tngtech/tng-r1t-chimera": { "attachment": false, "cost": { "input": 0.3, "output": 1.2 }, "description": "TNG R1T Chimera is an AI model provided by nano-gpt.", "family": "tngtech", "id": "tngtech/tng-r1t-chimera", "last_updated": "2025-11-26", "limit": { "context": 128000, "input": 128000, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "TNG R1T Chimera", "open_weights": false, "reasoning": false, "release_date": "2025-11-26", "structured_output": false, "tool_call": false }, "undi95/remm-slerp-l2-13b": { "attachment": true, "cost": { "input": 0.7989999999999999, "output": 1.2069999999999999 }, "description": "ReMM SLERP 13B is an AI model provided by nano-gpt.", "family": "llama", "id": "undi95/remm-slerp-l2-13b", "last_updated": "2025-01-01", "limit": { "context": 6144, "input": 6144, "output": 4096 }, "modalities": { "input": [ "text", "pdf" ], "output": [ "text" ] }, "name": "ReMM SLERP 13B", "open_weights": false, "reasoning": false, "release_date": "2025-01-01", "structured_output": false, "tool_call": false }, "universal-summarizer": { "attachment": false, "cost": { "input": 30, "output": 30 }, "description": "Universal Summarizer is an AI model provided by nano-gpt.", "id": "universal-summarizer", "last_updated": "2024-01-01", "limit": { "context": 32768, "input": 32768, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Universal Summarizer", "open_weights": false, "reasoning": false, "release_date": "2023-05-01", "structured_output": false, "tool_call": false }, "unsloth/gemma-3-12b-it": { "attachment": true, "cost": { "input": 0.272, "output": 0.272 }, "description": "Gemma 3 12B IT is an AI model provided by nano-gpt.", "family": "unsloth", "id": "unsloth/gemma-3-12b-it", "last_updated": "2025-03-10", "limit": { "context": 128000, "input": 128000, "output": 131072 }, "modalities": { "input": [ "text", "pdf" ], "output": [ "text" ] }, "name": "Gemma 3 12B IT", "open_weights": false, "reasoning": false, "release_date": "2025-03-10", "structured_output": false, "tool_call": false }, "unsloth/gemma-3-1b-it": { "attachment": false, "cost": { "input": 0.1003, "output": 0.1003 }, "description": "Gemma 3 1B IT is an AI model provided by nano-gpt.", "family": "unsloth", "id": "unsloth/gemma-3-1b-it", "last_updated": "2025-03-10", "limit": { "context": 128000, "input": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Gemma 3 1B IT", "open_weights": false, "reasoning": false, "release_date": "2025-03-10", "structured_output": false, "tool_call": false }, "unsloth/gemma-3-27b-it": { "attachment": true, "cost": { "input": 0.2992, "output": 0.2992 }, "description": "Gemma 3 27B IT is an AI model provided by nano-gpt.", "family": "unsloth", "id": "unsloth/gemma-3-27b-it", "last_updated": "2025-03-10", "limit": { "context": 128000, "input": 128000, "output": 96000 }, "modalities": { "input": [ "text", "pdf" ], "output": [ "text" ] }, "name": "Gemma 3 27B IT", "open_weights": false, "reasoning": false, "release_date": "2025-03-10", "structured_output": false, "tool_call": false }, "unsloth/gemma-3-4b-it": { "attachment": true, "cost": { "input": 0.2006, "output": 0.2006 }, "description": "Gemma 3 4B IT is an AI model provided by nano-gpt.", "family": "unsloth", "id": "unsloth/gemma-3-4b-it", "last_updated": "2025-03-10", "limit": { "context": 128000, "input": 128000, "output": 8192 }, "modalities": { "input": [ "text", "pdf" ], "output": [ "text" ] }, "name": "Gemma 3 4B IT", "open_weights": false, "reasoning": false, "release_date": "2025-03-10", "structured_output": false, "tool_call": false }, "v0-1.0-md": { "attachment": false, "cost": { "input": 3, "output": 15 }, "description": "v0 1.0 MD is an AI model provided by nano-gpt.", "id": "v0-1.0-md", "last_updated": "2025-07-04", "limit": { "context": 200000, "input": 200000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "v0 1.0 MD", "open_weights": false, "reasoning": false, "release_date": "2025-07-04", "structured_output": false, "tool_call": false }, "v0-1.5-lg": { "attachment": false, "cost": { "input": 15, "output": 75 }, "description": "v0 1.5 LG is an AI model provided by nano-gpt.", "id": "v0-1.5-lg", "last_updated": "2025-07-04", "limit": { "context": 1000000, "input": 1000000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "v0 1.5 LG", "open_weights": false, "reasoning": false, "release_date": "2025-07-04", "structured_output": false, "tool_call": false }, "v0-1.5-md": { "attachment": false, "cost": { "input": 3, "output": 15 }, "description": "v0 1.5 MD is an AI model provided by nano-gpt.", "id": "v0-1.5-md", "last_updated": "2025-07-04", "limit": { "context": 200000, "input": 200000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "v0 1.5 MD", "open_weights": false, "reasoning": false, "release_date": "2025-07-04", "structured_output": false, "tool_call": false }, "venice-uncensored": { "attachment": false, "cost": { "input": 0.4, "output": 0.4 }, "description": "Venice Uncensored is an AI model provided by nano-gpt.", "id": "venice-uncensored", "last_updated": "2025-02-24", "limit": { "context": 128000, "input": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Venice Uncensored", "open_weights": false, "reasoning": false, "release_date": "2025-02-24", "structured_output": false, "tool_call": false }, "venice-uncensored:web": { "attachment": false, "cost": { "input": 0.4, "output": 0.4 }, "description": "Venice Uncensored Web is an AI model provided by nano-gpt.", "id": "venice-uncensored:web", "last_updated": "2024-05-01", "limit": { "context": 80000, "input": 80000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Venice Uncensored Web", "open_weights": false, "reasoning": false, "release_date": "2024-05-01", "structured_output": false, "tool_call": false }, "x-ai/grok-4-07-09": { "attachment": true, "cost": { "input": 3, "output": 15 }, "description": "Grok 4 is an AI model provided by nano-gpt.", "family": "grok", "id": "x-ai/grok-4-07-09", "last_updated": "2025-07-09", "limit": { "context": 256000, "input": 256000, "output": 131072 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 4", "open_weights": false, "reasoning": true, "release_date": "2025-07-09", "structured_output": false, "tool_call": false }, "x-ai/grok-4-fast": { "attachment": true, "cost": { "input": 0.2, "output": 0.5 }, "description": "Grok 4 Fast is an AI model provided by nano-gpt.", "family": "grok", "id": "x-ai/grok-4-fast", "last_updated": "2025-09-20", "limit": { "context": 2000000, "input": 2000000, "output": 131072 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 4 Fast", "open_weights": false, "reasoning": true, "release_date": "2025-09-20", "structured_output": true, "tool_call": true }, "x-ai/grok-4-fast:thinking": { "attachment": true, "cost": { "input": 0.2, "output": 0.5 }, "description": "Grok 4 Fast Thinking is an AI model provided by nano-gpt.", "family": "grok", "id": "x-ai/grok-4-fast:thinking", "last_updated": "2025-07-09", "limit": { "context": 2000000, "input": 2000000, "output": 131072 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 4 Fast Thinking", "open_weights": false, "reasoning": true, "release_date": "2025-07-09", "structured_output": true, "tool_call": true }, "x-ai/grok-4.1-fast": { "attachment": true, "cost": { "input": 0.2, "output": 0.5 }, "description": "Grok 4.1 Fast is an AI model provided by nano-gpt.", "family": "grok", "id": "x-ai/grok-4.1-fast", "last_updated": "2025-11-20", "limit": { "context": 2000000, "input": 2000000, "output": 131072 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 4.1 Fast", "open_weights": false, "reasoning": true, "release_date": "2025-11-20", "structured_output": true, "tool_call": true }, "x-ai/grok-4.1-fast-reasoning": { "attachment": true, "cost": { "input": 0.2, "output": 0.5 }, "description": "Grok 4.1 Fast Reasoning is an AI model provided by nano-gpt.", "family": "grok", "id": "x-ai/grok-4.1-fast-reasoning", "last_updated": "2025-11-20", "limit": { "context": 2000000, "input": 2000000, "output": 131072 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 4.1 Fast Reasoning", "open_weights": false, "reasoning": true, "release_date": "2025-11-20", "structured_output": false, "tool_call": false }, "x-ai/grok-code-fast-1": { "attachment": false, "cost": { "input": 0.2, "output": 1.5 }, "description": "Grok Code Fast 1 is an AI model provided by nano-gpt.", "family": "grok", "id": "x-ai/grok-code-fast-1", "last_updated": "2025-08-28", "limit": { "context": 256000, "input": 256000, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok Code Fast 1", "open_weights": false, "reasoning": true, "release_date": "2025-08-28", "structured_output": false, "tool_call": false }, "xiaomi/mimo-v2-flash": { "attachment": false, "cost": { "input": 0.102, "output": 0.306 }, "description": "MiMo V2 Flash is an AI model provided by nano-gpt.", "family": "mimo", "id": "xiaomi/mimo-v2-flash", "last_updated": "2025-12-17", "limit": { "context": 256000, "input": 256000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiMo V2 Flash", "open_weights": false, "reasoning": false, "release_date": "2025-12-17", "structured_output": false, "tool_call": false }, "xiaomi/mimo-v2-flash-original": { "attachment": false, "cost": { "input": 0.102, "output": 0.306 }, "description": "MiMo V2 Flash Original is an AI model provided by nano-gpt.", "family": "mimo", "id": "xiaomi/mimo-v2-flash-original", "last_updated": "2025-12-17", "limit": { "context": 256000, "input": 256000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiMo V2 Flash Original", "open_weights": false, "reasoning": false, "release_date": "2025-12-17", "structured_output": false, "tool_call": false }, "xiaomi/mimo-v2-flash-thinking": { "attachment": false, "cost": { "input": 0.102, "output": 0.306 }, "description": "MiMo V2 Flash (Thinking) is an AI model provided by nano-gpt.", "family": "mimo", "id": "xiaomi/mimo-v2-flash-thinking", "last_updated": "2025-12-17", "limit": { "context": 256000, "input": 256000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiMo V2 Flash (Thinking)", "open_weights": false, "reasoning": false, "release_date": "2025-12-17", "structured_output": false, "tool_call": false }, "xiaomi/mimo-v2-flash-thinking-original": { "attachment": false, "cost": { "input": 0.102, "output": 0.306 }, "description": "MiMo V2 Flash (Thinking) Original is an AI model provided by nano-gpt.", "family": "mimo", "id": "xiaomi/mimo-v2-flash-thinking-original", "last_updated": "2025-12-17", "limit": { "context": 256000, "input": 256000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiMo V2 Flash (Thinking) Original", "open_weights": false, "reasoning": false, "release_date": "2025-12-17", "structured_output": false, "tool_call": false }, "yi-large": { "attachment": false, "cost": { "input": 3.196, "output": 3.196 }, "description": "Yi Large is an AI model provided by nano-gpt.", "id": "yi-large", "last_updated": "2024-05-13", "limit": { "context": 32000, "input": 32000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Yi Large", "open_weights": false, "reasoning": false, "release_date": "2024-05-13", "structured_output": false, "tool_call": false }, "yi-lightning": { "attachment": false, "cost": { "input": 0.2006, "output": 0.2006 }, "description": "Yi Lightning is an AI model provided by nano-gpt.", "id": "yi-lightning", "last_updated": "2024-10-16", "limit": { "context": 12000, "input": 12000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Yi Lightning", "open_weights": false, "reasoning": false, "release_date": "2024-10-16", "structured_output": false, "tool_call": false }, "yi-medium-200k": { "attachment": false, "cost": { "input": 2.499, "output": 2.499 }, "description": "Yi Medium 200k is an AI model provided by nano-gpt.", "id": "yi-medium-200k", "last_updated": "2024-03-01", "limit": { "context": 200000, "input": 200000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Yi Medium 200k", "open_weights": false, "reasoning": false, "release_date": "2024-03-01", "structured_output": false, "tool_call": false }, "z-ai/glm-4.5v": { "attachment": true, "cost": { "input": 0.6, "output": 1.7999999999999998 }, "description": "GLM 4.5V is an AI model provided by nano-gpt.", "family": "glmv", "id": "z-ai/glm-4.5v", "last_updated": "2025-11-22", "limit": { "context": 64000, "input": 64000, "output": 96000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GLM 4.5V", "open_weights": false, "reasoning": true, "release_date": "2025-11-22", "structured_output": false, "tool_call": false }, "z-ai/glm-4.5v:thinking": { "attachment": true, "cost": { "input": 0.6, "output": 1.7999999999999998 }, "description": "GLM 4.5V Thinking is an AI model provided by nano-gpt.", "family": "glmv", "id": "z-ai/glm-4.5v:thinking", "last_updated": "2025-11-22", "limit": { "context": 64000, "input": 64000, "output": 96000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GLM 4.5V Thinking", "open_weights": false, "reasoning": true, "release_date": "2025-11-22", "structured_output": false, "tool_call": false }, "z-ai/glm-4.6": { "attachment": false, "cost": { "input": 0.4, "output": 1.5 }, "description": "GLM 4.6 is an AI model provided by nano-gpt.", "family": "glm", "id": "z-ai/glm-4.6", "last_updated": "2025-09-30", "limit": { "context": 200000, "input": 200000, "output": 65535 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.6", "open_weights": false, "reasoning": true, "release_date": "2025-09-30", "structured_output": true, "tool_call": true }, "z-ai/glm-4.6:thinking": { "attachment": false, "cost": { "input": 0.4, "output": 1.5 }, "description": "GLM 4.6 Thinking is an AI model provided by nano-gpt.", "family": "glm", "id": "z-ai/glm-4.6:thinking", "last_updated": "2025-09-29", "limit": { "context": 200000, "input": 200000, "output": 65535 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.6 Thinking", "open_weights": false, "reasoning": true, "release_date": "2025-09-29", "structured_output": true, "tool_call": true }, "z-image-turbo": { "attachment": true, "description": "Z Image Turbo is an AI model provided by nano-gpt.", "id": "z-image-turbo", "last_updated": "2025-11-27", "limit": { "context": 0, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "name": "Z Image Turbo", "open_weights": false, "reasoning": false, "release_date": "2025-11-27", "structured_output": false, "temperature": true, "tool_call": false }, "zai-org/glm-4.7": { "attachment": false, "cost": { "input": 0.15, "output": 0.8 }, "description": "GLM 4.7 is an AI model provided by nano-gpt.", "family": "glm", "id": "zai-org/glm-4.7", "last_updated": "2026-01-29", "limit": { "context": 200000, "input": 200000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.7", "open_weights": true, "reasoning": true, "release_date": "2026-01-29", "structured_output": true, "tool_call": true }, "zai-org/glm-4.7-flash": { "attachment": false, "cost": { "input": 0.07, "output": 0.4 }, "description": "GLM 4.7 Flash is an AI model provided by nano-gpt.", "family": "glm-flash", "id": "zai-org/glm-4.7-flash", "last_updated": "2026-01-19", "limit": { "context": 200000, "input": 200000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.7 Flash", "open_weights": true, "reasoning": true, "release_date": "2026-01-19", "structured_output": true, "tool_call": true }, "zai-org/glm-5": { "attachment": false, "cost": { "input": 0.3, "output": 2.55 }, "description": "GLM 5 is an AI model provided by nano-gpt.", "family": "glm", "id": "zai-org/glm-5", "last_updated": "2026-02-11", "limit": { "context": 200000, "input": 200000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 5", "open_weights": true, "reasoning": true, "release_date": "2026-02-11", "structured_output": true, "tool_call": true }, "zai-org/glm-5.1": { "attachment": false, "cost": { "input": 0.3, "output": 2.55 }, "description": "GLM 5.1 is an AI model provided by nano-gpt.", "family": "glm", "id": "zai-org/glm-5.1", "last_updated": "2026-03-27", "limit": { "context": 200000, "input": 200000, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 5.1", "open_weights": true, "reasoning": true, "release_date": "2026-03-27", "structured_output": true, "tool_call": true }, "zai-org/glm-5.1:thinking": { "attachment": false, "cost": { "input": 0.3, "output": 2.55 }, "description": "GLM 5.1 Thinking is an AI model provided by nano-gpt.", "family": "glm", "id": "zai-org/glm-5.1:thinking", "last_updated": "2026-03-27", "limit": { "context": 200000, "input": 200000, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 5.1 Thinking", "open_weights": true, "reasoning": true, "release_date": "2026-03-27", "structured_output": true, "tool_call": true }, "zai-org/glm-5:thinking": { "attachment": false, "cost": { "input": 0.3, "output": 2.55 }, "description": "GLM 5 Thinking is an AI model provided by nano-gpt.", "family": "glm", "id": "zai-org/glm-5:thinking", "last_updated": "2026-02-11", "limit": { "context": 200000, "input": 200000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 5 Thinking", "open_weights": true, "reasoning": true, "release_date": "2026-02-11", "structured_output": true, "tool_call": true } }, "name": "NanoGPT", "npm": "@ai-sdk/openai-compatible" }, "nebius": { "api": "https://api.tokenfactory.nebius.com/v1", "doc": "https://docs.tokenfactory.nebius.com/", "env": [ "NEBIUS_API_KEY" ], "iconURL": "https://models.dev/logos/nebius.svg", "id": "nebius", "models": { "MiniMaxAI/MiniMax-M2.5": { "attachment": false, "cost": { "cache_read": 0.03, "cache_write": 0.375, "input": 0.3, "output": 1.2 }, "description": "MiniMax-M2.5 is an AI model provided by nebius.", "id": "MiniMaxAI/MiniMax-M2.5", "knowledge": "2025-01", "last_updated": "2026-05-07", "limit": { "context": 196608, "input": 190000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.5", "open_weights": true, "reasoning": true, "release_date": "2025-01-20", "structured_output": true, "temperature": true, "tool_call": true }, "MiniMaxAI/MiniMax-M2.5-fast": { "attachment": false, "cost": { "cache_read": 0.03, "cache_write": 0.375, "input": 0.3, "output": 1.2 }, "description": "MiniMax-M2.5-fast is an AI model provided by nebius.", "id": "MiniMaxAI/MiniMax-M2.5-fast", "knowledge": "2025-01", "last_updated": "2026-05-07", "limit": { "context": 8000, "input": 7000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.5-fast", "open_weights": true, "reasoning": true, "release_date": "2025-01-20", "structured_output": true, "temperature": true, "tool_call": true }, "NousResearch/Hermes-4-405B": { "attachment": false, "cost": { "cache_read": 0.1, "cache_write": 1.25, "input": 1, "output": 3, "reasoning": 3 }, "description": "Hermes-4-405B is an AI model provided by nebius.", "id": "NousResearch/Hermes-4-405B", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-11", "last_updated": "2026-02-04", "limit": { "context": 128000, "input": 120000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Hermes-4-405B", "open_weights": true, "reasoning": true, "release_date": "2026-01-30", "structured_output": true, "temperature": true, "tool_call": true }, "NousResearch/Hermes-4-70B": { "attachment": false, "cost": { "cache_read": 0.013, "cache_write": 0.16, "input": 0.13, "output": 0.4, "reasoning": 0.4 }, "description": "Hermes-4-70B is an AI model provided by nebius.", "id": "NousResearch/Hermes-4-70B", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-11", "last_updated": "2026-02-04", "limit": { "context": 128000, "input": 120000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Hermes-4-70B", "open_weights": true, "reasoning": true, "release_date": "2026-01-30", "structured_output": true, "temperature": true, "tool_call": true }, "PrimeIntellect/INTELLECT-3": { "attachment": false, "cost": { "cache_read": 0.02, "cache_write": 0.25, "input": 0.2, "output": 1.1 }, "description": "INTELLECT-3 is an AI model provided by nebius.", "id": "PrimeIntellect/INTELLECT-3", "knowledge": "2025-10", "last_updated": "2026-02-04", "limit": { "context": 128000, "input": 120000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "INTELLECT-3", "open_weights": true, "reasoning": false, "release_date": "2026-01-25", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen2.5-VL-72B-Instruct": { "attachment": true, "cost": { "cache_read": 0.025, "cache_write": 0.31, "input": 0.25, "output": 0.75 }, "description": "Qwen2.5-VL-72B-Instruct is an AI model provided by nebius.", "id": "Qwen/Qwen2.5-VL-72B-Instruct", "knowledge": "2024-12", "last_updated": "2026-02-04", "limit": { "context": 128000, "input": 120000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen2.5-VL-72B-Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-01-20", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-235B-A22B-Instruct-2507": { "attachment": false, "cost": { "input": 0.2, "output": 0.6 }, "description": "Qwen3 235B A22B Instruct 2507 is an AI model provided by nebius.", "family": "qwen", "id": "Qwen/Qwen3-235B-A22B-Instruct-2507", "knowledge": "2025-07", "last_updated": "2025-10-04", "limit": { "context": 262144, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 235B A22B Instruct 2507", "open_weights": false, "reasoning": true, "release_date": "2025-07-25", "temperature": true, "tool_call": true }, "Qwen/Qwen3-235B-A22B-Thinking-2507-fast": { "attachment": false, "cost": { "cache_read": 0.05, "cache_write": 0.625, "input": 0.5, "output": 2 }, "description": "Qwen3-235B-A22B-Thinking-2507-fast is an AI model provided by nebius.", "id": "Qwen/Qwen3-235B-A22B-Thinking-2507-fast", "knowledge": "2025-07", "last_updated": "2026-05-07", "limit": { "context": 8000, "input": 7000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3-235B-A22B-Thinking-2507-fast", "open_weights": true, "reasoning": true, "release_date": "2025-07-25", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-30B-A3B-Instruct-2507": { "attachment": false, "cost": { "cache_read": 0.01, "cache_write": 0.125, "input": 0.1, "output": 0.3 }, "description": "Qwen3-30B-A3B-Instruct-2507 is an AI model provided by nebius.", "id": "Qwen/Qwen3-30B-A3B-Instruct-2507", "knowledge": "2025-12", "last_updated": "2026-02-04", "limit": { "context": 128000, "input": 120000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3-30B-A3B-Instruct-2507", "open_weights": true, "reasoning": false, "release_date": "2026-01-28", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-32B": { "attachment": false, "cost": { "cache_read": 0.01, "cache_write": 0.125, "input": 0.1, "output": 0.3 }, "description": "Qwen3-32B is an AI model provided by nebius.", "id": "Qwen/Qwen3-32B", "knowledge": "2025-12", "last_updated": "2026-02-04", "limit": { "context": 128000, "input": 120000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3-32B", "open_weights": true, "reasoning": false, "release_date": "2026-01-28", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-Embedding-8B": { "attachment": false, "cost": { "input": 0.01, "output": 0 }, "description": "Qwen3-Embedding-8B is an AI model provided by nebius.", "family": "text-embedding", "id": "Qwen/Qwen3-Embedding-8B", "knowledge": "2025-10", "last_updated": "2026-02-04", "limit": { "context": 32768, "input": 32768, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3-Embedding-8B", "open_weights": true, "reasoning": false, "release_date": "2026-01-10", "structured_output": false, "temperature": false, "tool_call": false }, "Qwen/Qwen3-Next-80B-A3B-Thinking": { "attachment": false, "cost": { "cache_read": 0.015, "cache_write": 0.18, "input": 0.15, "output": 1.2, "reasoning": 1.2 }, "description": "Qwen3-Next-80B-A3B-Thinking is an AI model provided by nebius.", "id": "Qwen/Qwen3-Next-80B-A3B-Thinking", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-12", "last_updated": "2026-02-04", "limit": { "context": 128000, "input": 120000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3-Next-80B-A3B-Thinking", "open_weights": true, "reasoning": true, "release_date": "2026-01-28", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-Next-80B-A3B-Thinking-fast": { "attachment": false, "cost": { "cache_read": 0.015, "cache_write": 0.1875, "input": 0.15, "output": 1.2 }, "description": "Qwen3-Next-80B-A3B-Thinking-fast is an AI model provided by nebius.", "id": "Qwen/Qwen3-Next-80B-A3B-Thinking-fast", "knowledge": "2025-07", "last_updated": "2026-05-07", "limit": { "context": 8000, "input": 7000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3-Next-80B-A3B-Thinking-fast", "open_weights": true, "reasoning": true, "release_date": "2025-07-25", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3.5-397B-A17B": { "attachment": false, "cost": { "cache_read": 0.06, "cache_write": 0.75, "input": 0.6, "output": 3.6 }, "description": "Qwen3.5-397B-A17B is an AI model provided by nebius.", "id": "Qwen/Qwen3.5-397B-A17B", "knowledge": "2025-07", "last_updated": "2026-05-07", "limit": { "context": 262144, "input": 250000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3.5-397B-A17B", "open_weights": true, "reasoning": true, "release_date": "2025-07-15", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3.5-397B-A17B-fast": { "attachment": false, "cost": { "cache_read": 0.06, "cache_write": 0.75, "input": 0.6, "output": 3.6 }, "description": "Qwen3.5-397B-A17B-fast is an AI model provided by nebius.", "id": "Qwen/Qwen3.5-397B-A17B-fast", "knowledge": "2025-07", "last_updated": "2026-05-07", "limit": { "context": 8000, "input": 7000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3.5-397B-A17B-fast", "open_weights": true, "reasoning": true, "release_date": "2025-07-15", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek-ai/DeepSeek-V3.2": { "attachment": false, "cost": { "cache_read": 0.03, "cache_write": 0.375, "input": 0.3, "output": 0.45, "reasoning": 0.45 }, "description": "DeepSeek-V3.2 is an AI model provided by nebius.", "id": "deepseek-ai/DeepSeek-V3.2", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-11", "last_updated": "2026-02-04", "limit": { "context": 163000, "input": 160000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek-V3.2", "open_weights": true, "reasoning": true, "release_date": "2026-01-20", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek-ai/DeepSeek-V3.2-fast": { "attachment": false, "cost": { "cache_read": 0.04, "cache_write": 0.5, "input": 0.4, "output": 2 }, "description": "DeepSeek-V3.2-fast is an AI model provided by nebius.", "id": "deepseek-ai/DeepSeek-V3.2-fast", "knowledge": "2025-01", "last_updated": "2026-05-07", "limit": { "context": 8000, "input": 7000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek-V3.2-fast", "open_weights": true, "reasoning": true, "release_date": "2025-01-27", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek-ai/DeepSeek-V4-Pro": { "attachment": false, "cost": { "cache_read": 0.15, "input": 1.75, "output": 3.5 }, "description": "DeepSeek V4 Pro is an AI model provided by nebius.", "family": "deepseek-thinking", "id": "deepseek-ai/DeepSeek-V4-Pro", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-05", "last_updated": "2026-04-24", "limit": { "context": 1000000, "output": 384000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V4 Pro", "open_weights": true, "reasoning": true, "release_date": "2026-04-24", "structured_output": true, "temperature": true, "tool_call": true }, "google/gemma-2-2b-it": { "attachment": false, "cost": { "cache_read": 0.002, "cache_write": 0.025, "input": 0.02, "output": 0.06 }, "description": "Gemma-2-2b-it is an AI model provided by nebius.", "id": "google/gemma-2-2b-it", "knowledge": "2024-06", "last_updated": "2026-02-04", "limit": { "context": 8192, "input": 8000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Gemma-2-2b-it", "open_weights": true, "reasoning": false, "release_date": "2024-07-31", "structured_output": false, "temperature": true, "tool_call": false }, "google/gemma-3-27b-it": { "attachment": true, "cost": { "cache_read": 0.01, "cache_write": 0.125, "input": 0.1, "output": 0.3 }, "description": "Gemma-3-27b-it is an AI model provided by nebius.", "id": "google/gemma-3-27b-it", "knowledge": "2025-10", "last_updated": "2026-02-04", "limit": { "context": 110000, "input": 100000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemma-3-27b-it", "open_weights": true, "reasoning": false, "release_date": "2026-01-20", "structured_output": true, "temperature": true, "tool_call": true }, "meta-llama/Llama-3.3-70B-Instruct": { "attachment": false, "cost": { "cache_read": 0.013, "cache_write": 0.16, "input": 0.13, "output": 0.4 }, "description": "Llama-3.3-70B-Instruct is an AI model provided by nebius.", "id": "meta-llama/Llama-3.3-70B-Instruct", "knowledge": "2025-08", "last_updated": "2026-02-04", "limit": { "context": 128000, "input": 120000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama-3.3-70B-Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-12-05", "structured_output": true, "temperature": true, "tool_call": true }, "meta-llama/Meta-Llama-3.1-8B-Instruct": { "attachment": false, "cost": { "cache_read": 0.002, "cache_write": 0.025, "input": 0.02, "output": 0.06 }, "description": "Meta-Llama-3.1-8B-Instruct is an AI model provided by nebius.", "id": "meta-llama/Meta-Llama-3.1-8B-Instruct", "knowledge": "2024-12", "last_updated": "2026-02-04", "limit": { "context": 128000, "input": 120000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Meta-Llama-3.1-8B-Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-07-23", "structured_output": true, "temperature": true, "tool_call": true }, "moonshotai/Kimi-K2.5": { "attachment": true, "cost": { "cache_read": 0.05, "cache_write": 0.625, "input": 0.5, "output": 2.5, "reasoning": 2.5 }, "description": "Kimi-K2.5 is an AI model provided by nebius.", "family": "kimi", "id": "moonshotai/Kimi-K2.5", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-06", "last_updated": "2026-02-04", "limit": { "context": 256000, "input": 256000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Kimi-K2.5", "open_weights": true, "reasoning": true, "release_date": "2025-12-15", "structured_output": true, "temperature": true, "tool_call": true }, "moonshotai/Kimi-K2.5-fast": { "attachment": true, "cost": { "cache_read": 0.05, "cache_write": 0.625, "input": 0.5, "output": 2.5 }, "description": "Kimi-K2.5-fast is an AI model provided by nebius.", "family": "kimi", "id": "moonshotai/Kimi-K2.5-fast", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-06", "last_updated": "2026-02-04", "limit": { "context": 256000, "input": 256000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Kimi-K2.5-fast", "open_weights": true, "reasoning": true, "release_date": "2025-12-15", "structured_output": true, "temperature": true, "tool_call": true }, "nvidia/Llama-3_1-Nemotron-Ultra-253B-v1": { "attachment": false, "cost": { "cache_read": 0.06, "cache_write": 0.75, "input": 0.6, "output": 1.8 }, "description": "Llama-3.1-Nemotron-Ultra-253B-v1 is an AI model provided by nebius.", "id": "nvidia/Llama-3_1-Nemotron-Ultra-253B-v1", "knowledge": "2024-12", "last_updated": "2026-02-04", "limit": { "context": 128000, "input": 120000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama-3.1-Nemotron-Ultra-253B-v1", "open_weights": true, "reasoning": false, "release_date": "2025-01-15", "structured_output": true, "temperature": true, "tool_call": true }, "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B": { "attachment": false, "cost": { "cache_read": 0.006, "cache_write": 0.075, "input": 0.06, "output": 0.24 }, "description": "Nemotron-3-Nano-30B-A3B is an AI model provided by nebius.", "id": "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B", "knowledge": "2025-05", "last_updated": "2026-02-04", "limit": { "context": 32000, "input": 30000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Nemotron-3-Nano-30B-A3B", "open_weights": true, "reasoning": false, "release_date": "2025-08-10", "structured_output": true, "temperature": true, "tool_call": true }, "nvidia/Nemotron-3-Nano-Omni": { "attachment": false, "cost": { "cache_read": 0.006, "cache_write": 0.075, "input": 0.06, "output": 0.24 }, "description": "Nemotron-3-Nano-Omni is an AI model provided by nebius.", "id": "nvidia/Nemotron-3-Nano-Omni", "knowledge": "2025-01", "last_updated": "2026-05-07", "limit": { "context": 65536, "input": 60000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Nemotron-3-Nano-Omni", "open_weights": true, "reasoning": true, "release_date": "2025-01-20", "structured_output": true, "temperature": true, "tool_call": true }, "nvidia/nemotron-3-super-120b-a12b": { "attachment": false, "cost": { "input": 0.3, "output": 0.9 }, "description": "Nemotron-3-Super-120B-A12B is an AI model provided by nebius.", "id": "nvidia/nemotron-3-super-120b-a12b", "knowledge": "2026-02", "last_updated": "2026-03-12", "limit": { "context": 256000, "input": 256000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Nemotron-3-Super-120B-A12B", "open_weights": true, "reasoning": true, "release_date": "2026-03-11", "structured_output": true, "temperature": true, "tool_call": true }, "openai/gpt-oss-120b": { "attachment": false, "cost": { "cache_read": 0.015, "cache_write": 0.18, "input": 0.15, "output": 0.6, "reasoning": 0.6 }, "description": "gpt-oss-120b is an AI model provided by nebius.", "id": "openai/gpt-oss-120b", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-09", "last_updated": "2026-02-04", "limit": { "context": 128000, "input": 124000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "gpt-oss-120b", "open_weights": true, "reasoning": true, "release_date": "2026-01-10", "structured_output": true, "temperature": true, "tool_call": true }, "openai/gpt-oss-120b-fast": { "attachment": false, "cost": { "cache_read": 0.01, "cache_write": 0.125, "input": 0.1, "output": 0.5 }, "description": "gpt-oss-120b-fast is an AI model provided by nebius.", "id": "openai/gpt-oss-120b-fast", "knowledge": "2025-06", "last_updated": "2026-05-07", "limit": { "context": 8000, "input": 7000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "gpt-oss-120b-fast", "open_weights": true, "reasoning": true, "release_date": "2025-06-10", "structured_output": true, "temperature": true, "tool_call": true }, "zai-org/GLM-5": { "attachment": false, "cost": { "cache_read": 0.1, "cache_write": 1, "input": 1, "output": 3.2 }, "description": "GLM-5 is an AI model provided by nebius.", "id": "zai-org/GLM-5", "interleaved": { "field": "reasoning_content" }, "knowledge": "2026-01", "last_updated": "2026-03-10", "limit": { "context": 200000, "input": 200000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5", "open_weights": false, "reasoning": true, "release_date": "2026-03-01", "structured_output": true, "temperature": true, "tool_call": true } }, "name": "Nebius Token Factory", "npm": "@ai-sdk/openai-compatible" }, "neuralwatt": { "api": "https://api.neuralwatt.com/v1", "doc": "https://portal.neuralwatt.com/docs", "env": [ "NEURALWATT_API_KEY" ], "iconURL": "https://models.dev/logos/neuralwatt.svg", "id": "neuralwatt", "models": { "MiniMaxAI/MiniMax-M2.5": { "attachment": false, "cost": { "input": 0.35, "output": 1.38 }, "description": "MiniMax M2.5 is an AI model provided by neuralwatt.", "family": "minimax", "id": "MiniMaxAI/MiniMax-M2.5", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-02-12", "limit": { "context": 196608, "output": 196608 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M2.5", "open_weights": true, "reasoning": true, "release_date": "2026-02-12", "temperature": true, "tool_call": true }, "Qwen/Qwen3.5-397B-A17B-FP8": { "attachment": false, "cost": { "input": 0.69, "output": 4.14 }, "description": "Qwen3.5 397B A17B FP8 is an AI model provided by neuralwatt.", "family": "qwen", "id": "Qwen/Qwen3.5-397B-A17B-FP8", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-02-01", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3.5 397B A17B FP8", "open_weights": true, "reasoning": true, "release_date": "2026-02-01", "temperature": true, "tool_call": true }, "Qwen/Qwen3.6-35B-A3B": { "attachment": true, "cost": { "input": 0.05, "output": 0.1 }, "description": "Qwen3.6 35B A3B is an AI model provided by neuralwatt.", "family": "qwen3.6", "id": "Qwen/Qwen3.6-35B-A3B", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-01", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen3.6 35B A3B", "open_weights": true, "reasoning": true, "release_date": "2026-04-01", "temperature": true, "tool_call": true }, "glm-5-fast": { "attachment": false, "cost": { "input": 1.1, "output": 3.6 }, "description": "GLM 5 Fast is an AI model provided by neuralwatt.", "family": "glm", "id": "glm-5-fast", "last_updated": "2026-04-07", "limit": { "context": 200000, "output": 200000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 5 Fast", "open_weights": true, "reasoning": false, "release_date": "2026-04-07", "temperature": true, "tool_call": true }, "glm-5.1-fast": { "attachment": false, "cost": { "input": 1.1, "output": 3.6 }, "description": "GLM 5.1 Fast is an AI model provided by neuralwatt.", "family": "glm", "id": "glm-5.1-fast", "last_updated": "2026-04-07", "limit": { "context": 200000, "output": 200000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 5.1 Fast", "open_weights": true, "reasoning": false, "release_date": "2026-04-07", "temperature": true, "tool_call": true }, "kimi-k2.5-fast": { "attachment": true, "cost": { "input": 0.52, "output": 2.59 }, "description": "Kimi K2.5 Fast is an AI model provided by neuralwatt.", "family": "kimi", "id": "kimi-k2.5-fast", "last_updated": "2026-01-27", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Kimi K2.5 Fast", "open_weights": true, "reasoning": false, "release_date": "2026-01-27", "temperature": true, "tool_call": true }, "kimi-k2.6-fast": { "attachment": true, "cost": { "input": 0.69, "output": 3.22 }, "description": "Kimi K2.6 Fast is an AI model provided by neuralwatt.", "family": "kimi", "id": "kimi-k2.6-fast", "last_updated": "2026-04-21", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Kimi K2.6 Fast", "open_weights": true, "reasoning": false, "release_date": "2026-04-21", "temperature": true, "tool_call": true }, "mistralai/Devstral-Small-2-24B-Instruct-2512": { "attachment": true, "cost": { "input": 0.12, "output": 0.35 }, "description": "Devstral Small 2 24B Instruct 2512 is an AI model provided by neuralwatt.", "family": "devstral", "id": "mistralai/Devstral-Small-2-24B-Instruct-2512", "last_updated": "2025-12-09", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Devstral Small 2 24B Instruct 2512", "open_weights": true, "reasoning": false, "release_date": "2025-12-09", "temperature": true, "tool_call": true }, "moonshotai/Kimi-K2.5": { "attachment": true, "cost": { "input": 0.52, "output": 2.59 }, "description": "Kimi K2.5 is an AI model provided by neuralwatt.", "family": "kimi", "id": "moonshotai/Kimi-K2.5", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-01-27", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Kimi K2.5", "open_weights": true, "reasoning": true, "release_date": "2026-01-27", "temperature": true, "tool_call": true }, "moonshotai/Kimi-K2.6": { "attachment": true, "cost": { "input": 0.69, "output": 3.22 }, "description": "Kimi K2.6 is an AI model provided by neuralwatt.", "family": "kimi", "id": "moonshotai/Kimi-K2.6", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-21", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Kimi K2.6", "open_weights": true, "reasoning": true, "release_date": "2026-04-21", "temperature": true, "tool_call": true }, "openai/gpt-oss-20b": { "attachment": false, "cost": { "input": 0.03, "output": 0.16 }, "description": "GPT OSS 20B is an AI model provided by neuralwatt.", "family": "gpt-oss", "id": "openai/gpt-oss-20b", "last_updated": "2025-08-05", "limit": { "context": 16384, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT OSS 20B", "open_weights": true, "reasoning": true, "release_date": "2025-08-05", "temperature": true, "tool_call": true }, "qwen3.5-397b-fast": { "attachment": false, "cost": { "input": 0.69, "output": 4.14 }, "description": "Qwen3.5 397B Fast is an AI model provided by neuralwatt.", "family": "qwen", "id": "qwen3.5-397b-fast", "last_updated": "2026-02-01", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3.5 397B Fast", "open_weights": true, "reasoning": false, "release_date": "2026-02-01", "temperature": true, "tool_call": true }, "qwen3.6-35b-fast": { "attachment": true, "cost": { "input": 0.05, "output": 0.1 }, "description": "Qwen3.6 35B Fast is an AI model provided by neuralwatt.", "family": "qwen3.6", "id": "qwen3.6-35b-fast", "last_updated": "2026-04-01", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen3.6 35B Fast", "open_weights": true, "reasoning": false, "release_date": "2026-04-01", "temperature": true, "tool_call": true }, "zai-org/GLM-5.1-FP8": { "attachment": false, "cost": { "input": 1.1, "output": 3.6 }, "description": "GLM 5.1 FP8 is an AI model provided by neuralwatt.", "family": "glm", "id": "zai-org/GLM-5.1-FP8", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-07", "limit": { "context": 200000, "output": 200000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 5.1 FP8", "open_weights": true, "reasoning": true, "release_date": "2026-04-07", "temperature": true, "tool_call": true } }, "name": "Neuralwatt", "npm": "@ai-sdk/openai-compatible" }, "nova": { "api": "https://api.nova.amazon.com/v1", "doc": "https://nova.amazon.com/dev/documentation", "env": [ "NOVA_API_KEY" ], "iconURL": "https://models.dev/logos/nova.svg", "id": "nova", "models": { "nova-2-lite-v1": { "attachment": true, "cost": { "input": 0, "output": 0, "reasoning": 0 }, "description": "Nova 2 Lite is an AI model provided by nova.", "family": "nova-lite", "id": "nova-2-lite-v1", "last_updated": "2025-12-01", "limit": { "context": 1000000, "output": 64000 }, "modalities": { "input": [ "text", "image", "video", "pdf" ], "output": [ "text" ] }, "name": "Nova 2 Lite", "open_weights": false, "reasoning": true, "release_date": "2025-12-01", "temperature": true, "tool_call": true }, "nova-2-pro-v1": { "attachment": true, "cost": { "input": 0, "output": 0, "reasoning": 0 }, "description": "Nova 2 Pro is an AI model provided by nova.", "family": "nova-pro", "id": "nova-2-pro-v1", "last_updated": "2026-01-03", "limit": { "context": 1000000, "output": 64000 }, "modalities": { "input": [ "text", "image", "video", "pdf" ], "output": [ "text" ] }, "name": "Nova 2 Pro", "open_weights": false, "reasoning": true, "release_date": "2025-12-03", "temperature": true, "tool_call": true } }, "name": "Nova", "npm": "@ai-sdk/openai-compatible" }, "novita-ai": { "api": "https://api.novita.ai/openai", "doc": "https://novita.ai/docs/guides/introduction", "env": [ "NOVITA_API_KEY" ], "iconURL": "https://models.dev/logos/novita-ai.svg", "id": "novita-ai", "models": { "Sao10K/L3-8B-Stheno-v3.2": { "attachment": false, "cost": { "input": 0.05, "output": 0.05 }, "description": "L3 8B Stheno V3.2 is an AI model provided by novita-ai.", "family": "llama", "id": "Sao10K/L3-8B-Stheno-v3.2", "last_updated": "2024-11-29", "limit": { "context": 8192, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "L3 8B Stheno V3.2", "open_weights": true, "reasoning": false, "release_date": "2024-11-29", "temperature": true, "tool_call": true }, "baichuan/baichuan-m2-32b": { "attachment": false, "cost": { "input": 0.07, "output": 0.07 }, "description": "baichuan-m2-32b is an AI model provided by novita-ai.", "family": "baichuan", "id": "baichuan/baichuan-m2-32b", "knowledge": "2024-12", "last_updated": "2025-08-13", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "baichuan-m2-32b", "open_weights": true, "reasoning": false, "release_date": "2025-08-13", "structured_output": false, "temperature": true, "tool_call": false }, "baidu/ernie-4.5-21B-a3b": { "attachment": false, "cost": { "input": 0.07, "output": 0.28 }, "description": "ERNIE 4.5 21B A3B is an AI model provided by novita-ai.", "family": "ernie", "id": "baidu/ernie-4.5-21B-a3b", "knowledge": "2025-03", "last_updated": "2025-06-30", "limit": { "context": 120000, "output": 8000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "ERNIE 4.5 21B A3B", "open_weights": true, "reasoning": false, "release_date": "2025-06-30", "temperature": true, "tool_call": true }, "baidu/ernie-4.5-21B-a3b-thinking": { "attachment": false, "cost": { "input": 0.07, "output": 0.28 }, "description": "ERNIE-4.5-21B-A3B-Thinking is an AI model provided by novita-ai.", "family": "ernie", "id": "baidu/ernie-4.5-21B-a3b-thinking", "knowledge": "2025-03", "last_updated": "2025-09-19", "limit": { "context": 131072, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "ERNIE-4.5-21B-A3B-Thinking", "open_weights": true, "reasoning": true, "release_date": "2025-09-19", "temperature": true, "tool_call": false }, "baidu/ernie-4.5-300b-a47b-paddle": { "attachment": false, "cost": { "input": 0.28, "output": 1.1 }, "description": "ERNIE 4.5 300B A47B is an AI model provided by novita-ai.", "id": "baidu/ernie-4.5-300b-a47b-paddle", "last_updated": "2025-06-30", "limit": { "context": 123000, "output": 12000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "ERNIE 4.5 300B A47B", "open_weights": true, "reasoning": false, "release_date": "2025-06-30", "structured_output": true, "temperature": true, "tool_call": false }, "baidu/ernie-4.5-vl-28b-a3b": { "attachment": true, "cost": { "input": 1.4, "output": 5.6 }, "description": "ERNIE 4.5 VL 28B A3B is an AI model provided by novita-ai.", "id": "baidu/ernie-4.5-vl-28b-a3b", "last_updated": "2025-06-30", "limit": { "context": 30000, "output": 8000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "ERNIE 4.5 VL 28B A3B", "open_weights": true, "reasoning": true, "release_date": "2025-06-30", "temperature": true, "tool_call": true }, "baidu/ernie-4.5-vl-28b-a3b-thinking": { "attachment": true, "cost": { "input": 0.39, "output": 0.39 }, "description": "ERNIE-4.5-VL-28B-A3B-Thinking is an AI model provided by novita-ai.", "id": "baidu/ernie-4.5-vl-28b-a3b-thinking", "last_updated": "2025-11-26", "limit": { "context": 131072, "output": 65536 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "ERNIE-4.5-VL-28B-A3B-Thinking", "open_weights": true, "reasoning": true, "release_date": "2025-11-26", "structured_output": true, "temperature": true, "tool_call": true }, "baidu/ernie-4.5-vl-424b-a47b": { "attachment": true, "cost": { "input": 0.42, "output": 1.25 }, "description": "ERNIE 4.5 VL 424B A47B is an AI model provided by novita-ai.", "id": "baidu/ernie-4.5-vl-424b-a47b", "last_updated": "2025-06-30", "limit": { "context": 123000, "output": 16000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "ERNIE 4.5 VL 424B A47B", "open_weights": true, "reasoning": true, "release_date": "2025-06-30", "temperature": true, "tool_call": false }, "deepseek/deepseek-ocr": { "attachment": true, "cost": { "input": 0.03, "output": 0.03 }, "description": "DeepSeek-OCR is an AI model provided by novita-ai.", "id": "deepseek/deepseek-ocr", "last_updated": "2025-10-24", "limit": { "context": 8192, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "DeepSeek-OCR", "open_weights": true, "reasoning": false, "release_date": "2025-10-24", "structured_output": true, "temperature": true, "tool_call": false }, "deepseek/deepseek-ocr-2": { "attachment": true, "cost": { "input": 0.03, "output": 0.03 }, "description": "deepseek/deepseek-ocr-2 is an AI model provided by novita-ai.", "id": "deepseek/deepseek-ocr-2", "last_updated": "2026-01-27", "limit": { "context": 8192, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "deepseek/deepseek-ocr-2", "open_weights": true, "reasoning": false, "release_date": "2026-01-27", "tool_call": false }, "deepseek/deepseek-prover-v2-671b": { "attachment": false, "cost": { "input": 0.7, "output": 2.5 }, "description": "Deepseek Prover V2 671B is an AI model provided by novita-ai.", "id": "deepseek/deepseek-prover-v2-671b", "last_updated": "2025-04-30", "limit": { "context": 160000, "output": 160000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Deepseek Prover V2 671B", "open_weights": true, "reasoning": false, "release_date": "2025-04-30", "temperature": true, "tool_call": false }, "deepseek/deepseek-r1-0528": { "attachment": false, "cost": { "cache_read": 0.35, "input": 0.7, "output": 2.5 }, "description": "DeepSeek R1 0528 is an AI model provided by novita-ai.", "family": "deepseek-thinking", "id": "deepseek/deepseek-r1-0528", "knowledge": "2024-07", "last_updated": "2025-05-28", "limit": { "context": 163840, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek R1 0528", "open_weights": true, "reasoning": true, "release_date": "2025-05-28", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek/deepseek-r1-0528-qwen3-8b": { "attachment": false, "cost": { "input": 0.06, "output": 0.09 }, "description": "DeepSeek R1 0528 Qwen3 8B is an AI model provided by novita-ai.", "id": "deepseek/deepseek-r1-0528-qwen3-8b", "last_updated": "2025-05-29", "limit": { "context": 128000, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek R1 0528 Qwen3 8B", "open_weights": true, "reasoning": true, "release_date": "2025-05-29", "temperature": true, "tool_call": false }, "deepseek/deepseek-r1-distill-llama-70b": { "attachment": false, "cost": { "input": 0.8, "output": 0.8 }, "description": "DeepSeek R1 Distill LLama 70B is an AI model provided by novita-ai.", "family": "deepseek-thinking", "id": "deepseek/deepseek-r1-distill-llama-70b", "last_updated": "2025-01-27", "limit": { "context": 8192, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek R1 Distill LLama 70B", "open_weights": true, "reasoning": true, "release_date": "2025-01-27", "structured_output": true, "temperature": true, "tool_call": false }, "deepseek/deepseek-r1-distill-qwen-14b": { "attachment": false, "cost": { "input": 0.15, "output": 0.15 }, "description": "DeepSeek R1 Distill Qwen 14B is an AI model provided by novita-ai.", "family": "deepseek-thinking", "id": "deepseek/deepseek-r1-distill-qwen-14b", "last_updated": "2025-01-20", "limit": { "context": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek R1 Distill Qwen 14B", "open_weights": true, "reasoning": false, "release_date": "2025-01-20", "temperature": true, "tool_call": false }, "deepseek/deepseek-r1-distill-qwen-32b": { "attachment": false, "cost": { "input": 0.3, "output": 0.3 }, "description": "DeepSeek R1 Distill Qwen 32B is an AI model provided by novita-ai.", "family": "deepseek-thinking", "id": "deepseek/deepseek-r1-distill-qwen-32b", "last_updated": "2025-01-20", "limit": { "context": 64000, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek R1 Distill Qwen 32B", "open_weights": true, "reasoning": false, "release_date": "2025-01-20", "temperature": true, "tool_call": false }, "deepseek/deepseek-r1-turbo": { "attachment": false, "cost": { "input": 0.7, "output": 2.5 }, "description": "DeepSeek R1 (Turbo)\t is an AI model provided by novita-ai.", "id": "deepseek/deepseek-r1-turbo", "last_updated": "2025-03-05", "limit": { "context": 64000, "output": 16000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek R1 (Turbo)\t", "open_weights": true, "reasoning": true, "release_date": "2025-03-05", "temperature": true, "tool_call": true }, "deepseek/deepseek-v3-0324": { "attachment": false, "cost": { "cache_read": 0.135, "input": 0.27, "output": 1.12 }, "description": "DeepSeek V3 0324 is an AI model provided by novita-ai.", "family": "deepseek", "id": "deepseek/deepseek-v3-0324", "knowledge": "2024-07", "last_updated": "2025-03-25", "limit": { "context": 163840, "output": 163840 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3 0324", "open_weights": true, "reasoning": false, "release_date": "2025-03-25", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek/deepseek-v3-turbo": { "attachment": false, "cost": { "input": 0.4, "output": 1.3 }, "description": "DeepSeek V3 (Turbo)\t is an AI model provided by novita-ai.", "id": "deepseek/deepseek-v3-turbo", "last_updated": "2025-03-05", "limit": { "context": 64000, "output": 16000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3 (Turbo)\t", "open_weights": true, "reasoning": false, "release_date": "2025-03-05", "temperature": true, "tool_call": true }, "deepseek/deepseek-v3.1": { "attachment": false, "cost": { "cache_read": 0.135, "input": 0.27, "output": 1 }, "description": "DeepSeek V3.1 is an AI model provided by novita-ai.", "family": "deepseek", "id": "deepseek/deepseek-v3.1", "last_updated": "2025-08-21", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3.1", "open_weights": true, "reasoning": true, "release_date": "2025-08-21", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek/deepseek-v3.1-terminus": { "attachment": false, "cost": { "cache_read": 0.135, "input": 0.27, "output": 1 }, "description": "Deepseek V3.1 Terminus is an AI model provided by novita-ai.", "family": "deepseek", "id": "deepseek/deepseek-v3.1-terminus", "last_updated": "2025-09-22", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Deepseek V3.1 Terminus", "open_weights": true, "reasoning": true, "release_date": "2025-09-22", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek/deepseek-v3.2": { "attachment": false, "cost": { "cache_read": 0.1345, "input": 0.269, "output": 0.4 }, "description": "Deepseek V3.2 is an AI model provided by novita-ai.", "family": "deepseek", "id": "deepseek/deepseek-v3.2", "interleaved": { "field": "reasoning_content" }, "last_updated": "2025-12-01", "limit": { "context": 163840, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Deepseek V3.2", "open_weights": true, "reasoning": true, "release_date": "2025-12-01", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek/deepseek-v3.2-exp": { "attachment": false, "cost": { "input": 0.27, "output": 0.41 }, "description": "Deepseek V3.2 Exp is an AI model provided by novita-ai.", "id": "deepseek/deepseek-v3.2-exp", "last_updated": "2025-09-29", "limit": { "context": 163840, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Deepseek V3.2 Exp", "open_weights": true, "reasoning": true, "release_date": "2025-09-29", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek/deepseek-v4-flash": { "attachment": false, "cost": { "cache_read": 0.028, "input": 0.14, "output": 0.28 }, "description": "DeepSeek V4 Flash is an AI model provided by novita-ai.", "family": "deepseek-flash", "id": "deepseek/deepseek-v4-flash", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-05", "last_updated": "2026-04-24", "limit": { "context": 1048576, "output": 393216 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V4 Flash", "open_weights": true, "reasoning": true, "release_date": "2026-04-24", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek/deepseek-v4-pro": { "attachment": false, "cost": { "cache_read": 0.13, "input": 1.69, "output": 3.38 }, "description": "DeepSeek V4 Pro is an AI model provided by novita-ai.", "family": "deepseek-thinking", "id": "deepseek/deepseek-v4-pro", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-05", "last_updated": "2026-04-24", "limit": { "context": 1048576, "output": 393216 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V4 Pro", "open_weights": true, "reasoning": true, "release_date": "2026-04-24", "structured_output": true, "temperature": true, "tool_call": true }, "google/gemma-3-12b-it": { "attachment": true, "cost": { "input": 0.05, "output": 0.1 }, "description": "Gemma 3 12B is an AI model provided by novita-ai.", "family": "gemma", "id": "google/gemma-3-12b-it", "last_updated": "2025-03-13", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemma 3 12B", "open_weights": true, "reasoning": false, "release_date": "2025-03-13", "temperature": true, "tool_call": false }, "google/gemma-3-27b-it": { "attachment": true, "cost": { "input": 0.119, "output": 0.2 }, "description": "Gemma 3 27B is an AI model provided by novita-ai.", "family": "gemma", "id": "google/gemma-3-27b-it", "last_updated": "2025-03-25", "limit": { "context": 98304, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemma 3 27B", "open_weights": true, "reasoning": false, "release_date": "2025-03-25", "temperature": true, "tool_call": false }, "google/gemma-4-26b-a4b-it": { "attachment": true, "cost": { "input": 0.13, "output": 0.4 }, "description": "Gemma 4 26B A4B is an AI model provided by novita-ai.", "family": "gemma", "id": "google/gemma-4-26b-a4b-it", "last_updated": "2026-04-02", "limit": { "context": 262144, "output": 131072 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemma 4 26B A4B", "open_weights": true, "reasoning": true, "release_date": "2026-04-02", "structured_output": true, "temperature": true, "tool_call": true }, "google/gemma-4-31b-it": { "attachment": true, "cost": { "input": 0.14, "output": 0.4 }, "description": "Gemma 4 31B is an AI model provided by novita-ai.", "family": "gemma", "id": "google/gemma-4-31b-it", "last_updated": "2026-04-02", "limit": { "context": 262144, "output": 131072 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemma 4 31B", "open_weights": true, "reasoning": true, "release_date": "2026-04-02", "structured_output": true, "temperature": true, "tool_call": true }, "gryphe/mythomax-l2-13b": { "attachment": false, "cost": { "input": 0.09, "output": 0.09 }, "description": "Mythomax L2 13B is an AI model provided by novita-ai.", "id": "gryphe/mythomax-l2-13b", "last_updated": "2024-04-25", "limit": { "context": 4096, "output": 3200 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mythomax L2 13B", "open_weights": true, "reasoning": false, "release_date": "2024-04-25", "temperature": true, "tool_call": false }, "inclusionai/ling-2.6-1t": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Ling-2.6-1T is an AI model provided by novita-ai.", "family": "ling", "id": "inclusionai/ling-2.6-1t", "last_updated": "2026-04-23", "limit": { "context": 262144, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Ling-2.6-1T", "open_weights": true, "reasoning": false, "release_date": "2026-04-23", "structured_output": true, "temperature": true, "tool_call": true }, "inclusionai/ling-2.6-flash": { "attachment": false, "cost": { "cache_read": 0.02, "input": 0.1, "output": 0.3 }, "description": "Ling-2.6-flash is an AI model provided by novita-ai.", "family": "ling", "id": "inclusionai/ling-2.6-flash", "last_updated": "2026-04-24", "limit": { "context": 262144, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Ling-2.6-flash", "open_weights": true, "reasoning": false, "release_date": "2026-04-24", "structured_output": true, "temperature": true, "tool_call": true }, "kwaipilot/kat-coder-pro": { "attachment": false, "cost": { "cache_read": 0.06, "input": 0.3, "output": 1.2 }, "description": "Kat Coder Pro is an AI model provided by novita-ai.", "id": "kwaipilot/kat-coder-pro", "last_updated": "2026-01-05", "limit": { "context": 256000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kat Coder Pro", "open_weights": true, "reasoning": false, "release_date": "2026-01-05", "structured_output": true, "temperature": true, "tool_call": true }, "meta-llama/llama-3-70b-instruct": { "attachment": false, "cost": { "input": 0.51, "output": 0.74 }, "description": "Llama3 70B Instruct is an AI model provided by novita-ai.", "family": "llama", "id": "meta-llama/llama-3-70b-instruct", "last_updated": "2024-04-25", "limit": { "context": 8192, "output": 8000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama3 70B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-04-25", "structured_output": true, "temperature": true, "tool_call": false }, "meta-llama/llama-3-8b-instruct": { "attachment": false, "cost": { "input": 0.04, "output": 0.04 }, "description": "Llama 3 8B Instruct is an AI model provided by novita-ai.", "family": "llama", "id": "meta-llama/llama-3-8b-instruct", "last_updated": "2024-04-25", "limit": { "context": 8192, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3 8B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-04-25", "temperature": true, "tool_call": false }, "meta-llama/llama-3.1-8b-instruct": { "attachment": false, "cost": { "input": 0.02, "output": 0.05 }, "description": "Llama 3.1 8B Instruct is an AI model provided by novita-ai.", "family": "llama", "id": "meta-llama/llama-3.1-8b-instruct", "last_updated": "2024-07-24", "limit": { "context": 16384, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.1 8B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-07-24", "temperature": true, "tool_call": false }, "meta-llama/llama-3.2-3b-instruct": { "attachment": false, "cost": { "input": 0.03, "output": 0.05 }, "description": "Llama 3.2 3B Instruct is an AI model provided by novita-ai.", "family": "llama", "id": "meta-llama/llama-3.2-3b-instruct", "last_updated": "2024-09-18", "limit": { "context": 32768, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.2 3B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-09-18", "temperature": true, "tool_call": false }, "meta-llama/llama-3.3-70b-instruct": { "attachment": false, "cost": { "input": 0.135, "output": 0.4 }, "description": "Llama 3.3 70B Instruct is an AI model provided by novita-ai.", "family": "llama", "id": "meta-llama/llama-3.3-70b-instruct", "knowledge": "2023-12", "last_updated": "2024-12-07", "limit": { "context": 131072, "output": 120000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-12-07", "temperature": true, "tool_call": true }, "meta-llama/llama-4-maverick-17b-128e-instruct-fp8": { "attachment": true, "cost": { "input": 0.27, "output": 0.85 }, "description": "Llama 4 Maverick Instruct is an AI model provided by novita-ai.", "id": "meta-llama/llama-4-maverick-17b-128e-instruct-fp8", "last_updated": "2025-04-06", "limit": { "context": 1048576, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Llama 4 Maverick Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-04-06", "temperature": true, "tool_call": false }, "meta-llama/llama-4-scout-17b-16e-instruct": { "attachment": true, "cost": { "input": 0.18, "output": 0.59 }, "description": "Llama 4 Scout Instruct is an AI model provided by novita-ai.", "id": "meta-llama/llama-4-scout-17b-16e-instruct", "last_updated": "2025-04-06", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Llama 4 Scout Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-04-06", "temperature": true, "tool_call": false }, "microsoft/wizardlm-2-8x22b": { "attachment": false, "cost": { "input": 0.62, "output": 0.62 }, "description": "Wizardlm 2 8x22B is an AI model provided by novita-ai.", "id": "microsoft/wizardlm-2-8x22b", "last_updated": "2024-04-24", "limit": { "context": 65535, "output": 8000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Wizardlm 2 8x22B", "open_weights": true, "reasoning": false, "release_date": "2024-04-24", "temperature": true, "tool_call": false }, "minimax/minimax-m2": { "attachment": false, "cost": { "cache_read": 0.03, "input": 0.3, "output": 1.2 }, "description": "MiniMax-M2 is an AI model provided by novita-ai.", "family": "minimax", "id": "minimax/minimax-m2", "interleaved": { "field": "reasoning_content" }, "last_updated": "2025-10-27", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2", "open_weights": true, "reasoning": true, "release_date": "2025-10-27", "temperature": true, "tool_call": true }, "minimax/minimax-m2.1": { "attachment": false, "cost": { "cache_read": 0.03, "input": 0.3, "output": 1.2 }, "description": "Minimax M2.1 is an AI model provided by novita-ai.", "family": "minimax", "id": "minimax/minimax-m2.1", "interleaved": { "field": "reasoning_content" }, "last_updated": "2025-12-23", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Minimax M2.1", "open_weights": true, "reasoning": false, "release_date": "2025-12-23", "structured_output": true, "temperature": true, "tool_call": true }, "minimax/minimax-m2.5": { "attachment": false, "cost": { "cache_read": 0.03, "input": 0.3, "output": 1.2 }, "description": "MiniMax M2.5 is an AI model provided by novita-ai.", "family": "minimax", "id": "minimax/minimax-m2.5", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-02-12", "limit": { "context": 204800, "output": 131100 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M2.5", "open_weights": false, "reasoning": true, "release_date": "2026-02-12", "structured_output": true, "temperature": true, "tool_call": true }, "minimax/minimax-m2.5-highspeed": { "attachment": false, "cost": { "cache_read": 0.03, "input": 0.6, "output": 2.4 }, "description": "MiniMax M2.5 Highspeed is an AI model provided by novita-ai.", "family": "minimax-m2.5", "id": "minimax/minimax-m2.5-highspeed", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-02-12", "limit": { "context": 204800, "output": 131100 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M2.5 Highspeed", "open_weights": false, "reasoning": true, "release_date": "2026-02-12", "structured_output": true, "temperature": true, "tool_call": true }, "minimax/minimax-m2.7": { "attachment": false, "cost": { "cache_read": 0.06, "input": 0.3, "output": 1.2 }, "description": "MiniMax M2.7 is an AI model provided by novita-ai.", "family": "minimax-m2.7", "id": "minimax/minimax-m2.7", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-03-18", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M2.7", "open_weights": true, "reasoning": true, "release_date": "2026-03-18", "structured_output": true, "temperature": true, "tool_call": true }, "minimaxai/minimax-m1-80k": { "attachment": false, "cost": { "input": 0.55, "output": 2.2 }, "description": "MiniMax M1 is an AI model provided by novita-ai.", "family": "minimax", "id": "minimaxai/minimax-m1-80k", "last_updated": "2025-06-17", "limit": { "context": 1000000, "output": 40000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M1", "open_weights": true, "reasoning": true, "release_date": "2025-06-17", "temperature": true, "tool_call": true }, "mistralai/mistral-nemo": { "attachment": false, "cost": { "input": 0.04, "output": 0.17 }, "description": "Mistral Nemo is an AI model provided by novita-ai.", "family": "mistral-nemo", "id": "mistralai/mistral-nemo", "last_updated": "2024-07-30", "limit": { "context": 60288, "output": 16000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral Nemo", "open_weights": true, "reasoning": false, "release_date": "2024-07-30", "structured_output": true, "temperature": true, "tool_call": false }, "moonshotai/kimi-k2-0905": { "attachment": false, "cost": { "input": 0.6, "output": 2.5 }, "description": "Kimi K2 0905 is an AI model provided by novita-ai.", "family": "kimi", "id": "moonshotai/kimi-k2-0905", "knowledge": "2024-10", "last_updated": "2025-09-05", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 0905", "open_weights": true, "reasoning": false, "release_date": "2025-09-05", "structured_output": true, "temperature": true, "tool_call": true }, "moonshotai/kimi-k2-instruct": { "attachment": false, "cost": { "input": 0.57, "output": 2.3 }, "description": "Kimi K2 Instruct is an AI model provided by novita-ai.", "id": "moonshotai/kimi-k2-instruct", "last_updated": "2025-07-11", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-07-11", "structured_output": true, "temperature": true, "tool_call": true }, "moonshotai/kimi-k2-thinking": { "attachment": false, "cost": { "input": 0.6, "output": 2.5 }, "description": "Kimi K2 Thinking is an AI model provided by novita-ai.", "family": "kimi", "id": "moonshotai/kimi-k2-thinking", "interleaved": { "field": "reasoning_content" }, "last_updated": "2025-11-07", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 Thinking", "open_weights": true, "reasoning": true, "release_date": "2025-11-07", "structured_output": true, "temperature": true, "tool_call": true }, "moonshotai/kimi-k2.5": { "attachment": true, "cost": { "cache_read": 0.1, "input": 0.6, "output": 3 }, "description": "Kimi K2.5 is an AI model provided by novita-ai.", "family": "kimi", "id": "moonshotai/kimi-k2.5", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-01", "last_updated": "2026-01-27", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Kimi K2.5", "open_weights": true, "reasoning": true, "release_date": "2026-01-27", "structured_output": true, "temperature": true, "tool_call": true }, "moonshotai/kimi-k2.6": { "attachment": true, "cost": { "cache_read": 0.16, "input": 0.95, "output": 4 }, "description": "Kimi K2.6 is an AI model provided by novita-ai.", "family": "kimi-k2.6", "id": "moonshotai/kimi-k2.6", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-01", "last_updated": "2026-04-21", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Kimi K2.6", "open_weights": true, "reasoning": true, "release_date": "2026-04-21", "structured_output": true, "temperature": true, "tool_call": true }, "nousresearch/hermes-2-pro-llama-3-8b": { "attachment": false, "cost": { "input": 0.14, "output": 0.14 }, "description": "Hermes 2 Pro Llama 3 8B is an AI model provided by novita-ai.", "id": "nousresearch/hermes-2-pro-llama-3-8b", "last_updated": "2024-06-27", "limit": { "context": 8192, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Hermes 2 Pro Llama 3 8B", "open_weights": true, "reasoning": false, "release_date": "2024-06-27", "structured_output": true, "temperature": true, "tool_call": false }, "openai/gpt-oss-120b": { "attachment": true, "cost": { "input": 0.05, "output": 0.25 }, "description": "OpenAI GPT OSS 120B is an AI model provided by novita-ai.", "id": "openai/gpt-oss-120b", "last_updated": "2025-08-06", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "OpenAI GPT OSS 120B", "open_weights": true, "reasoning": true, "release_date": "2025-08-06", "structured_output": true, "temperature": true, "tool_call": true }, "openai/gpt-oss-20b": { "attachment": true, "cost": { "input": 0.04, "output": 0.15 }, "description": "OpenAI: GPT OSS 20B is an AI model provided by novita-ai.", "id": "openai/gpt-oss-20b", "last_updated": "2025-08-06", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "OpenAI: GPT OSS 20B", "open_weights": true, "reasoning": true, "release_date": "2025-08-06", "structured_output": true, "temperature": true, "tool_call": false }, "paddlepaddle/paddleocr-vl": { "attachment": true, "cost": { "input": 0.02, "output": 0.02 }, "description": "PaddleOCR-VL is an AI model provided by novita-ai.", "id": "paddlepaddle/paddleocr-vl", "last_updated": "2025-10-22", "limit": { "context": 16384, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "PaddleOCR-VL", "open_weights": true, "reasoning": false, "release_date": "2025-10-22", "temperature": true, "tool_call": false }, "qwen/qwen-2.5-72b-instruct": { "attachment": false, "cost": { "input": 0.38, "output": 0.4 }, "description": "Qwen 2.5 72B Instruct is an AI model provided by novita-ai.", "family": "qwen", "id": "qwen/qwen-2.5-72b-instruct", "knowledge": "2024-04", "last_updated": "2024-10-15", "limit": { "context": 32000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen 2.5 72B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-10-15", "structured_output": true, "temperature": true, "tool_call": true }, "qwen/qwen-mt-plus": { "attachment": false, "cost": { "input": 0.25, "output": 0.75 }, "description": "Qwen MT Plus is an AI model provided by novita-ai.", "id": "qwen/qwen-mt-plus", "last_updated": "2025-09-03", "limit": { "context": 16384, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen MT Plus", "open_weights": true, "reasoning": false, "release_date": "2025-09-03", "temperature": true, "tool_call": false }, "qwen/qwen2.5-7b-instruct": { "attachment": false, "cost": { "input": 0.07, "output": 0.07 }, "description": "Qwen2.5 7B Instruct is an AI model provided by novita-ai.", "id": "qwen/qwen2.5-7b-instruct", "last_updated": "2025-04-16", "limit": { "context": 32000, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen2.5 7B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-04-16", "structured_output": true, "temperature": true, "tool_call": true }, "qwen/qwen2.5-vl-72b-instruct": { "attachment": true, "cost": { "input": 0.8, "output": 0.8 }, "description": "Qwen2.5 VL 72B Instruct is an AI model provided by novita-ai.", "family": "qwen", "id": "qwen/qwen2.5-vl-72b-instruct", "last_updated": "2025-03-25", "limit": { "context": 32768, "output": 32768 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen2.5 VL 72B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-03-25", "temperature": true, "tool_call": false }, "qwen/qwen3-235b-a22b-fp8": { "attachment": false, "cost": { "input": 0.2, "output": 0.8 }, "description": "Qwen3 235B A22B is an AI model provided by novita-ai.", "id": "qwen/qwen3-235b-a22b-fp8", "last_updated": "2025-04-29", "limit": { "context": 40960, "output": 20000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 235B A22B", "open_weights": true, "reasoning": true, "release_date": "2025-04-29", "temperature": true, "tool_call": false }, "qwen/qwen3-235b-a22b-instruct-2507": { "attachment": false, "cost": { "input": 0.09, "output": 0.58 }, "description": "Qwen3 235B A22B Instruct 2507 is an AI model provided by novita-ai.", "family": "qwen", "id": "qwen/qwen3-235b-a22b-instruct-2507", "knowledge": "2025-04", "last_updated": "2025-07-22", "limit": { "context": 131072, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 235B A22B Instruct 2507", "open_weights": true, "reasoning": false, "release_date": "2025-07-22", "structured_output": true, "temperature": true, "tool_call": true }, "qwen/qwen3-235b-a22b-thinking-2507": { "attachment": false, "cost": { "input": 0.3, "output": 3 }, "description": "Qwen3 235B A22b Thinking 2507 is an AI model provided by novita-ai.", "family": "qwen", "id": "qwen/qwen3-235b-a22b-thinking-2507", "knowledge": "2025-04", "last_updated": "2025-07-25", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 235B A22b Thinking 2507", "open_weights": true, "reasoning": true, "release_date": "2025-07-25", "temperature": true, "tool_call": true }, "qwen/qwen3-30b-a3b-fp8": { "attachment": false, "cost": { "input": 0.09, "output": 0.45 }, "description": "Qwen3 30B A3B is an AI model provided by novita-ai.", "id": "qwen/qwen3-30b-a3b-fp8", "last_updated": "2025-04-29", "limit": { "context": 40960, "output": 20000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 30B A3B", "open_weights": true, "reasoning": true, "release_date": "2025-04-29", "temperature": true, "tool_call": false }, "qwen/qwen3-32b-fp8": { "attachment": false, "cost": { "input": 0.1, "output": 0.45 }, "description": "Qwen3 32B is an AI model provided by novita-ai.", "id": "qwen/qwen3-32b-fp8", "last_updated": "2025-04-29", "limit": { "context": 40960, "output": 20000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 32B", "open_weights": true, "reasoning": true, "release_date": "2025-04-29", "temperature": true, "tool_call": false }, "qwen/qwen3-4b-fp8": { "attachment": false, "cost": { "input": 0.03, "output": 0.03 }, "description": "Qwen3 4B is an AI model provided by novita-ai.", "id": "qwen/qwen3-4b-fp8", "last_updated": "2025-04-29", "limit": { "context": 128000, "output": 20000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 4B", "open_weights": true, "reasoning": true, "release_date": "2025-04-29", "temperature": true, "tool_call": false }, "qwen/qwen3-8b-fp8": { "attachment": false, "cost": { "input": 0.035, "output": 0.138 }, "description": "Qwen3 8B is an AI model provided by novita-ai.", "id": "qwen/qwen3-8b-fp8", "last_updated": "2025-04-29", "limit": { "context": 128000, "output": 20000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 8B", "open_weights": true, "reasoning": true, "release_date": "2025-04-29", "temperature": true, "tool_call": false }, "qwen/qwen3-coder-30b-a3b-instruct": { "attachment": false, "cost": { "input": 0.07, "output": 0.27 }, "description": "Qwen3 Coder 30b A3B Instruct is an AI model provided by novita-ai.", "id": "qwen/qwen3-coder-30b-a3b-instruct", "last_updated": "2025-10-09", "limit": { "context": 160000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Coder 30b A3B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-10-09", "structured_output": true, "temperature": true, "tool_call": true }, "qwen/qwen3-coder-480b-a35b-instruct": { "attachment": false, "cost": { "input": 0.3, "output": 1.3 }, "description": "Qwen3 Coder 480B A35B Instruct is an AI model provided by novita-ai.", "family": "qwen", "id": "qwen/qwen3-coder-480b-a35b-instruct", "knowledge": "2025-04", "last_updated": "2025-07-23", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Coder 480B A35B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-07-23", "structured_output": true, "temperature": true, "tool_call": true }, "qwen/qwen3-coder-next": { "attachment": false, "cost": { "input": 0.2, "output": 1.5 }, "description": "Qwen3 Coder Next is an AI model provided by novita-ai.", "family": "qwen", "id": "qwen/qwen3-coder-next", "last_updated": "2026-02-03", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Coder Next", "open_weights": true, "reasoning": false, "release_date": "2026-02-03", "structured_output": true, "temperature": true, "tool_call": true }, "qwen/qwen3-max": { "attachment": false, "cost": { "input": 2.11, "output": 8.45 }, "description": "Qwen3 Max is an AI model provided by novita-ai.", "family": "qwen", "id": "qwen/qwen3-max", "knowledge": "2025-04", "last_updated": "2025-09-24", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Max", "open_weights": false, "reasoning": false, "release_date": "2025-09-24", "structured_output": true, "temperature": true, "tool_call": true }, "qwen/qwen3-next-80b-a3b-instruct": { "attachment": false, "cost": { "input": 0.15, "output": 1.5 }, "description": "Qwen3 Next 80B A3B Instruct is an AI model provided by novita-ai.", "id": "qwen/qwen3-next-80b-a3b-instruct", "last_updated": "2025-09-10", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Next 80B A3B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-09-10", "structured_output": true, "temperature": true, "tool_call": true }, "qwen/qwen3-next-80b-a3b-thinking": { "attachment": false, "cost": { "input": 0.15, "output": 1.5 }, "description": "Qwen3 Next 80B A3B Thinking is an AI model provided by novita-ai.", "id": "qwen/qwen3-next-80b-a3b-thinking", "last_updated": "2025-09-10", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Next 80B A3B Thinking", "open_weights": true, "reasoning": true, "release_date": "2025-09-10", "structured_output": true, "temperature": true, "tool_call": true }, "qwen/qwen3-omni-30b-a3b-instruct": { "attachment": true, "cost": { "input": 0.25, "input_audio": 2.2, "output": 0.97, "output_audio": 1.788 }, "description": "Qwen3 Omni 30B A3B Instruct is an AI model provided by novita-ai.", "family": "qwen", "id": "qwen/qwen3-omni-30b-a3b-instruct", "knowledge": "2024-04", "last_updated": "2025-09-24", "limit": { "context": 65536, "output": 16384 }, "modalities": { "input": [ "text", "video", "audio", "image" ], "output": [ "text", "audio" ] }, "name": "Qwen3 Omni 30B A3B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-09-24", "structured_output": true, "temperature": true, "tool_call": true }, "qwen/qwen3-omni-30b-a3b-thinking": { "attachment": true, "cost": { "input": 0.25, "input_audio": 2.2, "output": 0.97, "output_audio": 1.788 }, "description": "Qwen3 Omni 30B A3B Thinking is an AI model provided by novita-ai.", "id": "qwen/qwen3-omni-30b-a3b-thinking", "last_updated": "2025-09-24", "limit": { "context": 65536, "output": 16384 }, "modalities": { "input": [ "text", "audio", "video", "image" ], "output": [ "text" ] }, "name": "Qwen3 Omni 30B A3B Thinking", "open_weights": true, "reasoning": true, "release_date": "2025-09-24", "structured_output": true, "temperature": true, "tool_call": true }, "qwen/qwen3-vl-235b-a22b-instruct": { "attachment": true, "cost": { "input": 0.3, "output": 1.5 }, "description": "Qwen3 VL 235B A22B Instruct is an AI model provided by novita-ai.", "id": "qwen/qwen3-vl-235b-a22b-instruct", "last_updated": "2025-09-24", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen3 VL 235B A22B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-09-24", "structured_output": true, "temperature": true, "tool_call": true }, "qwen/qwen3-vl-235b-a22b-thinking": { "attachment": true, "cost": { "input": 0.98, "output": 3.95 }, "description": "Qwen3 VL 235B A22B Thinking is an AI model provided by novita-ai.", "id": "qwen/qwen3-vl-235b-a22b-thinking", "last_updated": "2025-09-24", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen3 VL 235B A22B Thinking", "open_weights": true, "reasoning": true, "release_date": "2025-09-24", "temperature": true, "tool_call": false }, "qwen/qwen3-vl-30b-a3b-instruct": { "attachment": true, "cost": { "input": 0.2, "output": 0.7 }, "description": "qwen/qwen3-vl-30b-a3b-instruct is an AI model provided by novita-ai.", "id": "qwen/qwen3-vl-30b-a3b-instruct", "last_updated": "2025-10-11", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text", "video", "image" ], "output": [ "text" ] }, "name": "qwen/qwen3-vl-30b-a3b-instruct", "open_weights": true, "reasoning": false, "release_date": "2025-10-11", "structured_output": true, "temperature": true, "tool_call": true }, "qwen/qwen3-vl-30b-a3b-thinking": { "attachment": true, "cost": { "input": 0.2, "output": 1 }, "description": "qwen/qwen3-vl-30b-a3b-thinking is an AI model provided by novita-ai.", "id": "qwen/qwen3-vl-30b-a3b-thinking", "last_updated": "2025-10-11", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "qwen/qwen3-vl-30b-a3b-thinking", "open_weights": true, "reasoning": false, "release_date": "2025-10-11", "structured_output": true, "temperature": true, "tool_call": true }, "qwen/qwen3-vl-8b-instruct": { "attachment": true, "cost": { "input": 0.08, "output": 0.5 }, "description": "qwen/qwen3-vl-8b-instruct is an AI model provided by novita-ai.", "id": "qwen/qwen3-vl-8b-instruct", "last_updated": "2025-10-17", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "qwen/qwen3-vl-8b-instruct", "open_weights": true, "reasoning": false, "release_date": "2025-10-17", "structured_output": true, "temperature": true, "tool_call": true }, "qwen/qwen3.5-122b-a10b": { "attachment": true, "cost": { "input": 0.4, "output": 3.2 }, "description": "Qwen3.5-122B-A10B is an AI model provided by novita-ai.", "family": "qwen", "id": "qwen/qwen3.5-122b-a10b", "last_updated": "2026-02-26", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen3.5-122B-A10B", "open_weights": true, "reasoning": true, "release_date": "2026-02-26", "structured_output": true, "temperature": true, "tool_call": true }, "qwen/qwen3.5-27b": { "attachment": true, "cost": { "input": 0.3, "output": 2.4 }, "description": "Qwen3.5-27B is an AI model provided by novita-ai.", "family": "qwen", "id": "qwen/qwen3.5-27b", "last_updated": "2026-02-26", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen3.5-27B", "open_weights": true, "reasoning": true, "release_date": "2026-02-26", "structured_output": true, "temperature": true, "tool_call": true }, "qwen/qwen3.5-35b-a3b": { "attachment": true, "cost": { "input": 0.25, "output": 2 }, "description": "Qwen3.5-35B-A3B is an AI model provided by novita-ai.", "family": "qwen", "id": "qwen/qwen3.5-35b-a3b", "last_updated": "2026-02-26", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen3.5-35B-A3B", "open_weights": true, "reasoning": true, "release_date": "2026-02-26", "structured_output": true, "temperature": true, "tool_call": true }, "qwen/qwen3.5-397b-a17b": { "attachment": true, "cost": { "input": 0.6, "output": 3.6 }, "description": "Qwen3.5-397B-A17B is an AI model provided by novita-ai.", "family": "qwen", "id": "qwen/qwen3.5-397b-a17b", "last_updated": "2026-02-17", "limit": { "context": 262144, "output": 64000 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen3.5-397B-A17B", "open_weights": true, "reasoning": true, "release_date": "2026-02-17", "structured_output": true, "temperature": true, "tool_call": true }, "sao10k/l3-70b-euryale-v2.1": { "attachment": false, "cost": { "input": 1.48, "output": 1.48 }, "description": "L3 70B Euryale V2.1\t is an AI model provided by novita-ai.", "id": "sao10k/l3-70b-euryale-v2.1", "last_updated": "2024-06-18", "limit": { "context": 8192, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "L3 70B Euryale V2.1\t", "open_weights": true, "reasoning": false, "release_date": "2024-06-18", "temperature": true, "tool_call": true }, "sao10k/l3-8b-lunaris": { "attachment": false, "cost": { "input": 0.05, "output": 0.05 }, "description": "Sao10k L3 8B Lunaris\t is an AI model provided by novita-ai.", "id": "sao10k/l3-8b-lunaris", "last_updated": "2024-11-28", "limit": { "context": 8192, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Sao10k L3 8B Lunaris\t", "open_weights": true, "reasoning": false, "release_date": "2024-11-28", "structured_output": true, "temperature": true, "tool_call": false }, "sao10k/l31-70b-euryale-v2.2": { "attachment": false, "cost": { "input": 1.48, "output": 1.48 }, "description": "L31 70B Euryale V2.2 is an AI model provided by novita-ai.", "id": "sao10k/l31-70b-euryale-v2.2", "last_updated": "2024-09-19", "limit": { "context": 8192, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "L31 70B Euryale V2.2", "open_weights": true, "reasoning": false, "release_date": "2024-09-19", "temperature": true, "tool_call": true }, "xiaomimimo/mimo-v2-flash": { "attachment": false, "cost": { "cache_read": 0.3, "input": 0.1, "output": 0.3 }, "description": "XiaomiMiMo/MiMo-V2-Flash is an AI model provided by novita-ai.", "family": "mimo", "id": "xiaomimimo/mimo-v2-flash", "knowledge": "2024-12", "last_updated": "2025-12-19", "limit": { "context": 262144, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "XiaomiMiMo/MiMo-V2-Flash", "open_weights": true, "reasoning": true, "release_date": "2025-12-19", "structured_output": true, "temperature": true, "tool_call": true }, "zai-org/autoglm-phone-9b-multilingual": { "attachment": true, "cost": { "input": 0.035, "output": 0.138 }, "description": "AutoGLM-Phone-9B-Multilingual is an AI model provided by novita-ai.", "id": "zai-org/autoglm-phone-9b-multilingual", "last_updated": "2025-12-10", "limit": { "context": 65536, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "AutoGLM-Phone-9B-Multilingual", "open_weights": true, "reasoning": false, "release_date": "2025-12-10", "temperature": true, "tool_call": false }, "zai-org/glm-4.5": { "attachment": false, "cost": { "cache_read": 0.11, "input": 0.6, "output": 2.2 }, "description": "GLM-4.5 is an AI model provided by novita-ai.", "family": "glm", "id": "zai-org/glm-4.5", "interleaved": { "field": "reasoning_content" }, "last_updated": "2025-07-28", "limit": { "context": 131072, "output": 98304 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.5", "open_weights": true, "reasoning": true, "release_date": "2025-07-28", "temperature": true, "tool_call": true }, "zai-org/glm-4.5-air": { "attachment": false, "cost": { "input": 0.13, "output": 0.85 }, "description": "GLM 4.5 Air is an AI model provided by novita-ai.", "family": "glm-air", "id": "zai-org/glm-4.5-air", "knowledge": "2025-04", "last_updated": "2025-10-13", "limit": { "context": 131072, "output": 98304 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.5 Air", "open_weights": true, "reasoning": true, "release_date": "2025-10-13", "temperature": true, "tool_call": true }, "zai-org/glm-4.5v": { "attachment": true, "cost": { "cache_read": 0.11, "input": 0.6, "output": 1.8 }, "description": "GLM 4.5V is an AI model provided by novita-ai.", "family": "glmv", "id": "zai-org/glm-4.5v", "knowledge": "2025-04", "last_updated": "2025-08-11", "limit": { "context": 65536, "output": 16384 }, "modalities": { "input": [ "text", "video", "image" ], "output": [ "text" ] }, "name": "GLM 4.5V", "open_weights": true, "reasoning": true, "release_date": "2025-08-11", "structured_output": true, "temperature": true, "tool_call": true }, "zai-org/glm-4.6": { "attachment": false, "cost": { "cache_read": 0.11, "input": 0.55, "output": 2.2 }, "description": "GLM 4.6 is an AI model provided by novita-ai.", "family": "glm", "id": "zai-org/glm-4.6", "interleaved": { "field": "reasoning_content" }, "last_updated": "2025-09-30", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.6", "open_weights": true, "reasoning": true, "release_date": "2025-09-30", "structured_output": true, "temperature": true, "tool_call": true }, "zai-org/glm-4.6v": { "attachment": true, "cost": { "cache_read": 0.055, "input": 0.3, "output": 0.9 }, "description": "GLM 4.6V is an AI model provided by novita-ai.", "family": "glmv", "id": "zai-org/glm-4.6v", "knowledge": "2025-04", "last_updated": "2025-12-08", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text", "video", "image" ], "output": [ "text" ] }, "name": "GLM 4.6V", "open_weights": true, "reasoning": true, "release_date": "2025-12-08", "structured_output": true, "temperature": true, "tool_call": true }, "zai-org/glm-4.7": { "attachment": false, "cost": { "cache_read": 0.11, "input": 0.6, "output": 2.2 }, "description": "GLM-4.7 is an AI model provided by novita-ai.", "family": "glm", "id": "zai-org/glm-4.7", "interleaved": { "field": "reasoning_content" }, "last_updated": "2025-12-22", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.7", "open_weights": true, "reasoning": true, "release_date": "2025-12-22", "structured_output": true, "temperature": true, "tool_call": true }, "zai-org/glm-4.7-flash": { "attachment": false, "cost": { "cache_read": 0.01, "input": 0.07, "output": 0.4 }, "description": "GLM-4.7-Flash is an AI model provided by novita-ai.", "family": "glm", "id": "zai-org/glm-4.7-flash", "knowledge": "2025-04", "last_updated": "2026-01-19", "limit": { "context": 200000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.7-Flash", "open_weights": true, "reasoning": true, "release_date": "2026-01-19", "structured_output": true, "temperature": true, "tool_call": true }, "zai-org/glm-5": { "attachment": false, "cost": { "cache_read": 0.2, "input": 1, "output": 3.2 }, "description": "GLM-5 is an AI model provided by novita-ai.", "family": "glm", "id": "zai-org/glm-5", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-02-12", "limit": { "context": 202800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5", "open_weights": true, "reasoning": true, "release_date": "2026-02-11", "structured_output": true, "temperature": true, "tool_call": true }, "zai-org/glm-5.1": { "attachment": false, "cost": { "cache_read": 0.26, "input": 1.4, "output": 4.4 }, "description": "GLM-5.1 is an AI model provided by novita-ai.", "family": "glm", "id": "zai-org/glm-5.1", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-03-27", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5.1", "open_weights": true, "reasoning": true, "release_date": "2026-03-27", "structured_output": true, "temperature": true, "tool_call": true } }, "name": "NovitaAI", "npm": "@ai-sdk/openai-compatible" }, "nvidia": { "api": "https://integrate.api.nvidia.com/v1", "doc": "https://docs.api.nvidia.com/nim/", "env": [ "NVIDIA_API_KEY" ], "iconURL": "https://models.dev/logos/nvidia.svg", "id": "nvidia", "models": { "abacusai/dracarys-llama-3_1-70b-instruct": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "dracarys-llama-3.1-70b-instruct is an AI model provided by nvidia.", "id": "abacusai/dracarys-llama-3_1-70b-instruct", "last_updated": "2025-05-22", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "dracarys-llama-3.1-70b-instruct", "open_weights": true, "reasoning": false, "release_date": "2024-09-11", "temperature": true, "tool_call": true }, "baai/bge-m3": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "BGE M3 is an AI model provided by nvidia.", "family": "bge", "id": "baai/bge-m3", "last_updated": "2026-04-30", "limit": { "context": 8192, "output": 1024 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "BGE M3", "open_weights": true, "reasoning": false, "release_date": "2024-01-30", "temperature": false, "tool_call": false }, "black-forest-labs/flux.1-dev": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "FLUX.1-dev is an AI model provided by nvidia.", "family": "flux", "id": "black-forest-labs/flux.1-dev", "knowledge": "2024-08", "last_updated": "2025-09-05", "limit": { "context": 4096, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "name": "FLUX.1-dev", "open_weights": false, "reasoning": false, "release_date": "2024-08-01", "temperature": true, "tool_call": false }, "black-forest-labs/flux_1-kontext-dev": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "FLUX.1-Kontext-dev is an AI model provided by nvidia.", "id": "black-forest-labs/flux_1-kontext-dev", "last_updated": "2025-08-12", "limit": { "context": 40960, "output": 40960 }, "modalities": { "input": [ "text", "image" ], "output": [ "image" ] }, "name": "FLUX.1-Kontext-dev", "open_weights": true, "reasoning": false, "release_date": "2025-08-12", "temperature": false, "tool_call": false }, "black-forest-labs/flux_1-schnell": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "FLUX.1-schnell is an AI model provided by nvidia.", "id": "black-forest-labs/flux_1-schnell", "knowledge": "2024-07", "last_updated": "2026-02-04", "limit": { "context": 77, "input": 77, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "name": "FLUX.1-schnell", "open_weights": true, "reasoning": false, "release_date": "2024-08-01", "structured_output": false, "temperature": false, "tool_call": false }, "black-forest-labs/flux_2-klein-4b": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "FLUX.2 Klein 4B is an AI model provided by nvidia.", "family": "flux", "id": "black-forest-labs/flux_2-klein-4b", "knowledge": "2025-06", "last_updated": "2026-01-31", "limit": { "context": 40960, "output": 40960 }, "modalities": { "input": [ "image", "text" ], "output": [ "image" ] }, "name": "FLUX.2 Klein 4B", "open_weights": true, "reasoning": false, "release_date": "2026-01-14", "temperature": true, "tool_call": false }, "bytedance/seed-oss-36b-instruct": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "ByteDance-Seed/Seed-OSS-36B-Instruct is an AI model provided by nvidia.", "family": "seed", "id": "bytedance/seed-oss-36b-instruct", "last_updated": "2025-11-25", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "ByteDance-Seed/Seed-OSS-36B-Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-09-04", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek-ai/deepseek-v3.1-terminus": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "DeepSeek V3.1 Terminus is an AI model provided by nvidia.", "family": "deepseek", "id": "deepseek-ai/deepseek-v3.1-terminus", "knowledge": "2025-01", "last_updated": "2025-09-22", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3.1 Terminus", "open_weights": false, "reasoning": true, "release_date": "2025-09-22", "temperature": true, "tool_call": true }, "deepseek-ai/deepseek-v3.2": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "DeepSeek V3.2 is an AI model provided by nvidia.", "family": "deepseek", "id": "deepseek-ai/deepseek-v3.2", "knowledge": "2024-07", "last_updated": "2025-12-01", "limit": { "context": 163840, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3.2", "open_weights": false, "reasoning": true, "release_date": "2025-12-01", "temperature": true, "tool_call": true }, "deepseek-ai/deepseek-v4-flash": { "attachment": false, "cost": { "cache_read": 0.028, "input": 0.14, "output": 0.28 }, "description": "DeepSeek V4 Flash is an AI model provided by nvidia.", "family": "deepseek-flash", "id": "deepseek-ai/deepseek-v4-flash", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-05", "last_updated": "2026-04-24", "limit": { "context": 1048576, "output": 393216 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V4 Flash", "open_weights": true, "reasoning": true, "release_date": "2026-04-24", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek-ai/deepseek-v4-pro": { "attachment": false, "cost": { "cache_read": 0.145, "input": 1.74, "output": 3.48 }, "description": "DeepSeek V4 Pro is an AI model provided by nvidia.", "family": "deepseek-thinking", "id": "deepseek-ai/deepseek-v4-pro", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-05", "last_updated": "2026-04-24", "limit": { "context": 1048576, "output": 393216 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V4 Pro", "open_weights": true, "reasoning": true, "release_date": "2026-04-24", "structured_output": true, "temperature": true, "tool_call": true }, "google/gemma-2-2b-it": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Gemma 2 2b It is an AI model provided by nvidia.", "id": "google/gemma-2-2b-it", "last_updated": "2024-07-16", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Gemma 2 2b It", "open_weights": true, "reasoning": false, "release_date": "2024-07-16", "structured_output": true, "temperature": true, "tool_call": true }, "google/gemma-3-27b-it": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Gemma-3-27B-IT is an AI model provided by nvidia.", "family": "gemma", "id": "google/gemma-3-27b-it", "knowledge": "2024-12", "last_updated": "2025-09-05", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemma-3-27B-IT", "open_weights": false, "reasoning": true, "release_date": "2024-12-01", "temperature": true, "tool_call": true }, "google/gemma-3n-e2b-it": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Gemma 3n E2b It is an AI model provided by nvidia.", "id": "google/gemma-3n-e2b-it", "knowledge": "2024-06", "last_updated": "2025-06-12", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemma 3n E2b It", "open_weights": true, "reasoning": false, "release_date": "2025-06-12", "structured_output": true, "temperature": true, "tool_call": true }, "google/gemma-3n-e4b-it": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Gemma 3n E4b It is an AI model provided by nvidia.", "id": "google/gemma-3n-e4b-it", "knowledge": "2024-06", "last_updated": "2025-06-03", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemma 3n E4b It", "open_weights": true, "reasoning": false, "release_date": "2025-06-03", "structured_output": true, "temperature": true, "tool_call": true }, "google/gemma-4-31b-it": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Gemma-4-31B-IT is an AI model provided by nvidia.", "family": "gemma", "id": "google/gemma-4-31b-it", "knowledge": "2025-01", "last_updated": "2026-04-02", "limit": { "context": 256000, "output": 16384 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Gemma-4-31B-IT", "open_weights": true, "reasoning": true, "release_date": "2026-04-02", "temperature": true, "tool_call": true }, "google/google-paligemma": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "paligemma is an AI model provided by nvidia.", "id": "google/google-paligemma", "last_updated": "2024-08-26", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "paligemma", "open_weights": true, "reasoning": false, "release_date": "2024-05-14", "temperature": true, "tool_call": false }, "meta/esm2-650m": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "esm2-650m is an AI model provided by nvidia.", "id": "meta/esm2-650m", "last_updated": "2025-03-10", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "esm2-650m", "open_weights": true, "reasoning": false, "release_date": "2024-08-29", "temperature": true, "tool_call": false }, "meta/esmfold": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "esmfold is an AI model provided by nvidia.", "id": "meta/esmfold", "last_updated": "2025-06-12", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "esmfold", "open_weights": true, "reasoning": false, "release_date": "2024-03-15", "temperature": true, "tool_call": false }, "meta/llama-3.1-70b-instruct": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Llama 3.1 70b Instruct is an AI model provided by nvidia.", "id": "meta/llama-3.1-70b-instruct", "last_updated": "2024-07-16", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.1 70b Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-07-16", "structured_output": true, "temperature": true, "tool_call": true }, "meta/llama-3.1-8b-instruct": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Llama 3.1 8B Instruct is an AI model provided by nvidia.", "family": "llama", "id": "meta/llama-3.1-8b-instruct", "knowledge": "2023-12", "last_updated": "2025-01-01", "limit": { "context": 16000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.1 8B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-01-01", "temperature": true, "tool_call": true }, "meta/llama-3.2-11b-vision-instruct": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Llama 3.2 11b Vision Instruct is an AI model provided by nvidia.", "id": "meta/llama-3.2-11b-vision-instruct", "knowledge": "2023-12", "last_updated": "2024-09-18", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Llama 3.2 11b Vision Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-09-18", "structured_output": true, "temperature": true, "tool_call": true }, "meta/llama-3.2-1b-instruct": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Llama 3.2 1b Instruct is an AI model provided by nvidia.", "id": "meta/llama-3.2-1b-instruct", "knowledge": "2023-12", "last_updated": "2024-09-18", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.2 1b Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-09-18", "structured_output": true, "temperature": true, "tool_call": true }, "meta/llama-3.2-3b-instruct": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Llama 3.2 3B Instruct is an AI model provided by nvidia.", "family": "llama", "id": "meta/llama-3.2-3b-instruct", "last_updated": "2024-09-18", "limit": { "context": 32768, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.2 3B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-09-18", "structured_output": true, "temperature": true, "tool_call": false }, "meta/llama-3.2-90b-vision-instruct": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Llama-3.2-90B-Vision-Instruct is an AI model provided by nvidia.", "family": "llama", "id": "meta/llama-3.2-90b-vision-instruct", "knowledge": "2023-12", "last_updated": "2024-09-25", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Llama-3.2-90B-Vision-Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-09-25", "temperature": true, "tool_call": true }, "meta/llama-3.3-70b-instruct": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Llama 3.3 70b Instruct is an AI model provided by nvidia.", "id": "meta/llama-3.3-70b-instruct", "last_updated": "2024-11-26", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70b Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-11-26", "structured_output": true, "temperature": true, "tool_call": true }, "meta/llama-4-maverick-17b-128e-instruct": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Llama 4 Maverick 17b 128e Instruct is an AI model provided by nvidia.", "id": "meta/llama-4-maverick-17b-128e-instruct", "knowledge": "2024-02", "last_updated": "2025-04-01", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Llama 4 Maverick 17b 128e Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-04-01", "structured_output": true, "temperature": true, "tool_call": true }, "meta/llama-guard-4-12b": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Llama Guard 4 12B is an AI model provided by nvidia.", "family": "llama", "id": "meta/llama-guard-4-12b", "last_updated": "2026-04-30", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Llama Guard 4 12B", "open_weights": true, "reasoning": false, "release_date": "2025-04-05", "temperature": true, "tool_call": false }, "microsoft/phi-4-mini-instruct": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Phi-4-Mini is an AI model provided by nvidia.", "family": "phi", "id": "microsoft/phi-4-mini-instruct", "knowledge": "2024-12", "last_updated": "2025-09-05", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text", "image", "audio" ], "output": [ "text" ] }, "name": "Phi-4-Mini", "open_weights": false, "reasoning": true, "release_date": "2024-12-01", "temperature": true, "tool_call": true }, "microsoft/phi-4-multimodal-instruct": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Phi 4 Multimodal is an AI model provided by nvidia.", "id": "microsoft/phi-4-multimodal-instruct", "last_updated": "2025-07-26", "limit": { "context": 128000, "input": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Phi 4 Multimodal", "open_weights": false, "reasoning": false, "release_date": "2025-07-26", "structured_output": false, "tool_call": false }, "minimaxai/minimax-m2.5": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "MiniMax-M2.5 is an AI model provided by nvidia.", "family": "minimax", "id": "minimaxai/minimax-m2.5", "knowledge": "2025-08", "last_updated": "2026-02-12", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.5", "open_weights": true, "reasoning": true, "release_date": "2026-02-12", "temperature": true, "tool_call": true }, "minimaxai/minimax-m2.7": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "MiniMax-M2.7 is an AI model provided by nvidia.", "family": "minimax", "id": "minimaxai/minimax-m2.7", "last_updated": "2026-04-11", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.7", "open_weights": true, "reasoning": true, "release_date": "2026-03-18", "temperature": true, "tool_call": true }, "mistralai/devstral-2-123b-instruct-2512": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Devstral-2-123B-Instruct-2512 is an AI model provided by nvidia.", "family": "devstral", "id": "mistralai/devstral-2-123b-instruct-2512", "knowledge": "2025-12", "last_updated": "2025-12-09", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Devstral-2-123B-Instruct-2512", "open_weights": true, "reasoning": true, "release_date": "2025-12-08", "structured_output": true, "temperature": true, "tool_call": true }, "mistralai/magistral-small-2506": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Magistral Small 2506 is an AI model provided by nvidia.", "id": "mistralai/magistral-small-2506", "last_updated": "2025-09-25", "limit": { "context": 32768, "input": 32768, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Magistral Small 2506", "open_weights": false, "reasoning": false, "release_date": "2025-09-25", "structured_output": false, "tool_call": false }, "mistralai/mistral-7b-instruct-v03": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Mistral-7B-Instruct-v0.3 is an AI model provided by nvidia.", "id": "mistralai/mistral-7b-instruct-v03", "last_updated": "2025-04-01", "limit": { "context": 65536, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral-7B-Instruct-v0.3", "open_weights": true, "reasoning": false, "release_date": "2025-04-01", "structured_output": true, "temperature": true, "tool_call": true }, "mistralai/mistral-large-3-675b-instruct-2512": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Mistral Large 3 675B Instruct 2512 is an AI model provided by nvidia.", "family": "mistral-large", "id": "mistralai/mistral-large-3-675b-instruct-2512", "knowledge": "2025-01", "last_updated": "2025-12-02", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Mistral Large 3 675B Instruct 2512", "open_weights": true, "reasoning": false, "release_date": "2025-12-02", "structured_output": true, "temperature": true, "tool_call": true }, "mistralai/mistral-medium-3-instruct": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Mistral Medium 3 is an AI model provided by nvidia.", "family": "mistral-medium", "id": "mistralai/mistral-medium-3-instruct", "last_updated": "2025-09-25", "limit": { "context": 131072, "input": 131072, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Mistral Medium 3", "open_weights": false, "reasoning": false, "release_date": "2025-09-25", "structured_output": false, "tool_call": false }, "mistralai/mistral-nemotron": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "mistral-nemotron is an AI model provided by nvidia.", "id": "mistralai/mistral-nemotron", "last_updated": "2025-06-12", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "mistral-nemotron", "open_weights": true, "reasoning": false, "release_date": "2025-06-11", "temperature": true, "tool_call": true }, "mistralai/mistral-small-4-119b-2603": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "mistral-small-4-119b-2603 is an AI model provided by nvidia.", "id": "mistralai/mistral-small-4-119b-2603", "last_updated": "2026-03-16", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "mistral-small-4-119b-2603", "open_weights": true, "reasoning": false, "release_date": "2026-03-16", "temperature": true, "tool_call": true }, "mistralai/mixtral-8x22b-instruct": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Mistral: Mixtral 8x22B Instruct is an AI model provided by nvidia.", "id": "mistralai/mixtral-8x22b-instruct", "last_updated": "2024-04-17", "limit": { "context": 65536, "output": 13108 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral: Mixtral 8x22B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-04-17", "temperature": true, "tool_call": true }, "mistralai/mixtral-8x7b-instruct": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Mistral: Mixtral 8x7B Instruct is an AI model provided by nvidia.", "id": "mistralai/mixtral-8x7b-instruct", "last_updated": "2026-03-15", "limit": { "context": 32768, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral: Mixtral 8x7B Instruct", "open_weights": true, "reasoning": false, "release_date": "2023-12-10", "temperature": true, "tool_call": true }, "moonshotai/kimi-k2-instruct": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Kimi K2 Instruct is an AI model provided by nvidia.", "family": "kimi", "id": "moonshotai/kimi-k2-instruct", "knowledge": "2024-01", "last_updated": "2025-09-05", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 Instruct", "open_weights": false, "reasoning": true, "release_date": "2025-01-01", "temperature": true, "tool_call": true }, "moonshotai/kimi-k2-instruct-0905": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Kimi K2 0905 is an AI model provided by nvidia.", "family": "kimi", "id": "moonshotai/kimi-k2-instruct-0905", "knowledge": "2024-10", "last_updated": "2025-09-05", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 0905", "open_weights": true, "reasoning": false, "release_date": "2025-09-05", "temperature": true, "tool_call": true }, "moonshotai/kimi-k2-thinking": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "Kimi K2 Thinking is an AI model provided by nvidia.", "family": "kimi-thinking", "id": "moonshotai/kimi-k2-thinking", "interleaved": true, "knowledge": "2025-07", "last_updated": "2025-12", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 Thinking", "open_weights": true, "reasoning": true, "release_date": "2025-11", "structured_output": true, "temperature": true, "tool_call": true }, "moonshotai/kimi-k2.6": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Kimi K2.6 is an AI model provided by nvidia.", "family": "kimi-k2.6", "id": "moonshotai/kimi-k2.6", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-01", "last_updated": "2026-04-21", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Kimi K2.6", "open_weights": true, "reasoning": true, "release_date": "2026-04-21", "structured_output": true, "temperature": true, "tool_call": true }, "nvidia/active-speaker-detection": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Active Speaker Detection is an AI model provided by nvidia.", "id": "nvidia/active-speaker-detection", "last_updated": "2026-04-16", "limit": { "context": 0, "output": 4096 }, "modalities": { "input": [ "video" ], "output": [ "text" ] }, "name": "Active Speaker Detection", "open_weights": true, "reasoning": false, "release_date": "2026-04-16", "temperature": false, "tool_call": false }, "nvidia/bevformer": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "bevformer is an AI model provided by nvidia.", "id": "nvidia/bevformer", "last_updated": "2025-07-20", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "video" ], "output": [ "text" ] }, "name": "bevformer", "open_weights": true, "reasoning": false, "release_date": "2025-03-18", "temperature": true, "tool_call": false }, "nvidia/cosmos-predict1-5b": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "cosmos-predict1-5b is an AI model provided by nvidia.", "id": "nvidia/cosmos-predict1-5b", "last_updated": "2025-03-18", "limit": { "context": 0, "output": 4096 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "video" ] }, "name": "cosmos-predict1-5b", "open_weights": true, "reasoning": false, "release_date": "2025-03-18", "temperature": false, "tool_call": false }, "nvidia/cosmos-transfer1-7b": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "cosmos-transfer1-7b is an AI model provided by nvidia.", "id": "nvidia/cosmos-transfer1-7b", "last_updated": "2025-06-30", "limit": { "context": 0, "output": 4096 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "video" ] }, "name": "cosmos-transfer1-7b", "open_weights": true, "reasoning": false, "release_date": "2025-06-13", "temperature": false, "tool_call": false }, "nvidia/cosmos-transfer2_5-2b": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "cosmos-transfer2.5-2b is an AI model provided by nvidia.", "id": "nvidia/cosmos-transfer2_5-2b", "last_updated": "2026-02-26", "limit": { "context": 0, "output": 4096 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "video" ] }, "name": "cosmos-transfer2.5-2b", "open_weights": true, "reasoning": false, "release_date": "2026-02-26", "temperature": false, "tool_call": false }, "nvidia/gliner-pii": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "gliner-pii is an AI model provided by nvidia.", "id": "nvidia/gliner-pii", "last_updated": "2026-03-03", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "gliner-pii", "open_weights": true, "reasoning": false, "release_date": "2026-03-03", "temperature": true, "tool_call": false }, "nvidia/llama-3_1-nemotron-safety-guard-8b-v3": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "llama-3.1-nemotron-safety-guard-8b-v3 is an AI model provided by nvidia.", "id": "nvidia/llama-3_1-nemotron-safety-guard-8b-v3", "last_updated": "2025-10-28", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "llama-3.1-nemotron-safety-guard-8b-v3", "open_weights": true, "reasoning": false, "release_date": "2025-10-28", "temperature": false, "tool_call": false }, "nvidia/llama-3_2-nemoretriever-300m-embed-v1": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "llama-3_2-nemoretriever-300m-embed-v1 is an AI model provided by nvidia.", "id": "nvidia/llama-3_2-nemoretriever-300m-embed-v1", "last_updated": "2025-07-24", "limit": { "context": 32768, "output": 2048 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "llama-3_2-nemoretriever-300m-embed-v1", "open_weights": true, "reasoning": false, "release_date": "2025-07-24", "temperature": false, "tool_call": false }, "nvidia/llama-3_3-nemotron-super-49b-v1": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Llama 3.3 Nemotron Super 49B v1 is an AI model provided by nvidia.", "family": "nemotron", "id": "nvidia/llama-3_3-nemotron-super-49b-v1", "knowledge": "2023-12", "last_updated": "2025-04-07", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 Nemotron Super 49B v1", "open_weights": true, "reasoning": true, "release_date": "2025-04-07", "temperature": true, "tool_call": true }, "nvidia/llama-3_3-nemotron-super-49b-v1_5": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Llama 3.3 Nemotron Super 49B v1.5 is an AI model provided by nvidia.", "family": "nemotron", "id": "nvidia/llama-3_3-nemotron-super-49b-v1_5", "knowledge": "2023-12", "last_updated": "2025-07-25", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 Nemotron Super 49B v1.5", "open_weights": true, "reasoning": true, "release_date": "2025-07-25", "temperature": true, "tool_call": true }, "nvidia/llama-nemotron-embed-vl-1b-v2": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "llama-nemotron-embed-vl-1b-v2 is an AI model provided by nvidia.", "id": "nvidia/llama-nemotron-embed-vl-1b-v2", "last_updated": "2026-02-10", "limit": { "context": 32768, "output": 2048 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "llama-nemotron-embed-vl-1b-v2", "open_weights": true, "reasoning": false, "release_date": "2026-02-10", "temperature": false, "tool_call": false }, "nvidia/llama-nemotron-rerank-vl-1b-v2": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "llama-nemotron-rerank-vl-1b-v2 is an AI model provided by nvidia.", "id": "nvidia/llama-nemotron-rerank-vl-1b-v2", "last_updated": "2026-03-31", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "llama-nemotron-rerank-vl-1b-v2", "open_weights": true, "reasoning": false, "release_date": "2026-03-31", "temperature": false, "tool_call": false }, "nvidia/magpie-tts-zeroshot": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "magpie-tts-zeroshot is an AI model provided by nvidia.", "id": "nvidia/magpie-tts-zeroshot", "last_updated": "2025-06-12", "limit": { "context": 0, "output": 4096 }, "modalities": { "input": [ "text", "audio" ], "output": [ "audio" ] }, "name": "magpie-tts-zeroshot", "open_weights": true, "reasoning": false, "release_date": "2025-05-22", "temperature": false, "tool_call": false }, "nvidia/nemotron-3-content-safety": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "nemotron-3-content-safety is an AI model provided by nvidia.", "id": "nvidia/nemotron-3-content-safety", "last_updated": "2026-04-16", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "nemotron-3-content-safety", "open_weights": true, "reasoning": false, "release_date": "2026-04-16", "temperature": false, "tool_call": false }, "nvidia/nemotron-3-nano-30b-a3b": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "nemotron-3-nano-30b-a3b is an AI model provided by nvidia.", "family": "nemotron", "id": "nvidia/nemotron-3-nano-30b-a3b", "knowledge": "2024-09", "last_updated": "2024-12", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "nemotron-3-nano-30b-a3b", "open_weights": true, "reasoning": true, "release_date": "2024-12", "temperature": true, "tool_call": true }, "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Nemotron 3 Nano Omni is an AI model provided by nvidia.", "family": "nemotron", "id": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning", "last_updated": "2026-04-28", "limit": { "context": 256000, "output": 65536 }, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text" ] }, "name": "Nemotron 3 Nano Omni", "open_weights": true, "reasoning": true, "release_date": "2026-04-28", "structured_output": true, "temperature": true, "tool_call": true }, "nvidia/nemotron-3-super-120b-a12b": { "attachment": false, "cost": { "input": 0.2, "output": 0.8 }, "description": "Nemotron 3 Super is an AI model provided by nvidia.", "family": "nemotron", "id": "nvidia/nemotron-3-super-120b-a12b", "knowledge": "2024-04", "last_updated": "2026-03-11", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Nemotron 3 Super", "open_weights": true, "reasoning": true, "release_date": "2026-03-11", "temperature": true, "tool_call": true }, "nvidia/nemotron-content-safety-reasoning-4b": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "nemotron-content-safety-reasoning-4b is an AI model provided by nvidia.", "id": "nvidia/nemotron-content-safety-reasoning-4b", "last_updated": "2026-01-22", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "nemotron-content-safety-reasoning-4b", "open_weights": true, "reasoning": true, "release_date": "2026-01-22", "temperature": false, "tool_call": false }, "nvidia/nemotron-mini-4b-instruct": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "nemotron-mini-4b-instruct is an AI model provided by nvidia.", "id": "nvidia/nemotron-mini-4b-instruct", "last_updated": "2024-08-26", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "nemotron-mini-4b-instruct", "open_weights": true, "reasoning": false, "release_date": "2024-08-21", "temperature": true, "tool_call": true }, "nvidia/nemotron-voicechat": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "nemotron-voicechat is an AI model provided by nvidia.", "id": "nvidia/nemotron-voicechat", "last_updated": "2026-03-16", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text", "audio" ], "output": [ "text" ] }, "name": "nemotron-voicechat", "open_weights": true, "reasoning": false, "release_date": "2026-03-16", "temperature": true, "tool_call": true }, "nvidia/nv-embed-v1": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "nv-embed-v1 is an AI model provided by nvidia.", "id": "nvidia/nv-embed-v1", "last_updated": "2025-07-22", "limit": { "context": 32768, "output": 2048 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "nv-embed-v1", "open_weights": true, "reasoning": false, "release_date": "2024-06-07", "temperature": false, "tool_call": false }, "nvidia/nv-embedcode-7b-v1": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "nv-embedcode-7b-v1 is an AI model provided by nvidia.", "id": "nvidia/nv-embedcode-7b-v1", "last_updated": "2025-05-29", "limit": { "context": 32768, "output": 2048 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "nv-embedcode-7b-v1", "open_weights": true, "reasoning": false, "release_date": "2025-03-17", "temperature": false, "tool_call": false }, "nvidia/nvidia-nemotron-nano-9b-v2": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "nvidia-nemotron-nano-9b-v2 is an AI model provided by nvidia.", "family": "nemotron", "id": "nvidia/nvidia-nemotron-nano-9b-v2", "knowledge": "2024-09", "last_updated": "2025-08-18", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "nvidia-nemotron-nano-9b-v2", "open_weights": true, "reasoning": true, "release_date": "2025-08-18", "temperature": true, "tool_call": true }, "nvidia/rerank-qa-mistral-4b": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "rerank-qa-mistral-4b is an AI model provided by nvidia.", "id": "nvidia/rerank-qa-mistral-4b", "last_updated": "2025-01-17", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "rerank-qa-mistral-4b", "open_weights": true, "reasoning": false, "release_date": "2024-03-17", "temperature": false, "tool_call": false }, "nvidia/riva-translate-4b-instruct-v1_1": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "riva-translate-4b-instruct-v1_1 is an AI model provided by nvidia.", "id": "nvidia/riva-translate-4b-instruct-v1_1", "last_updated": "2025-12-12", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "riva-translate-4b-instruct-v1_1", "open_weights": true, "reasoning": false, "release_date": "2025-12-12", "temperature": false, "tool_call": false }, "nvidia/sparsedrive": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "sparsedrive is an AI model provided by nvidia.", "id": "nvidia/sparsedrive", "last_updated": "2025-07-20", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "video" ], "output": [ "text" ] }, "name": "sparsedrive", "open_weights": true, "reasoning": false, "release_date": "2025-03-18", "temperature": true, "tool_call": false }, "nvidia/streampetr": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "streampetr is an AI model provided by nvidia.", "id": "nvidia/streampetr", "last_updated": "2025-11-13", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "video" ], "output": [ "text" ] }, "name": "streampetr", "open_weights": true, "reasoning": false, "release_date": "2025-11-13", "temperature": true, "tool_call": false }, "nvidia/studiovoice": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "studiovoice is an AI model provided by nvidia.", "id": "nvidia/studiovoice", "last_updated": "2025-06-13", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "studiovoice", "open_weights": true, "reasoning": false, "release_date": "2024-10-03", "temperature": true, "tool_call": false }, "nvidia/synthetic-video-detector": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "synthetic-video-detector is an AI model provided by nvidia.", "id": "nvidia/synthetic-video-detector", "last_updated": "2026-04-16", "limit": { "context": 0, "output": 4096 }, "modalities": { "input": [ "video" ], "output": [ "text" ] }, "name": "synthetic-video-detector", "open_weights": true, "reasoning": false, "release_date": "2026-04-16", "temperature": true, "tool_call": false }, "nvidia/usdcode": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "usdcode is an AI model provided by nvidia.", "id": "nvidia/usdcode", "last_updated": "2026-01-01", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "usdcode", "open_weights": false, "reasoning": false, "release_date": "2026-01-01", "temperature": true, "tool_call": false }, "nvidia/usdvalidate": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "usdvalidate is an AI model provided by nvidia.", "id": "nvidia/usdvalidate", "last_updated": "2025-01-08", "limit": { "context": 0, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "usdvalidate", "open_weights": true, "reasoning": false, "release_date": "2024-07-24", "temperature": false, "tool_call": false }, "openai/gpt-oss-120b": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "GPT-OSS-120B is an AI model provided by nvidia.", "family": "gpt-oss", "id": "openai/gpt-oss-120b", "knowledge": "2025-08", "last_updated": "2025-08-14", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT-OSS-120B", "open_weights": false, "reasoning": true, "release_date": "2025-08-04", "temperature": true, "tool_call": false }, "openai/gpt-oss-20b": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "GPT OSS 20B is an AI model provided by nvidia.", "family": "gpt-oss", "id": "openai/gpt-oss-20b", "last_updated": "2025-08-05", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT OSS 20B", "open_weights": true, "reasoning": true, "release_date": "2025-08-05", "structured_output": true, "temperature": true, "tool_call": true }, "openai/whisper-large-v3": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Whisper Large v3 is an AI model provided by nvidia.", "family": "whisper", "id": "openai/whisper-large-v3", "knowledge": "2023-09", "last_updated": "2025-09-05", "limit": { "context": 0, "output": 4096 }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "name": "Whisper Large v3", "open_weights": true, "reasoning": false, "release_date": "2023-09-01", "temperature": false, "tool_call": false }, "qwen/qwen-image": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Qwen Image is an AI model provided by nvidia.", "family": "qwen", "id": "qwen/qwen-image", "last_updated": "2025-08-07", "limit": { "context": 0, "output": 0 }, "modalities": { "input": [ "text", "image" ], "output": [ "image" ] }, "name": "Qwen Image", "open_weights": false, "reasoning": false, "release_date": "2025-08-07", "structured_output": false, "temperature": true, "tool_call": false }, "qwen/qwen-image-edit": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Qwen Image Edit is an AI model provided by nvidia.", "family": "qwen", "id": "qwen/qwen-image-edit", "last_updated": "2025-08-19", "limit": { "context": 0, "output": 0 }, "modalities": { "input": [ "text", "image" ], "output": [ "image" ] }, "name": "Qwen Image Edit", "open_weights": false, "reasoning": false, "release_date": "2025-08-19", "structured_output": false, "temperature": true, "tool_call": false }, "qwen/qwen2.5-coder-32b-instruct": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Qwen2.5 Coder 32b Instruct is an AI model provided by nvidia.", "id": "qwen/qwen2.5-coder-32b-instruct", "last_updated": "2024-11-06", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen2.5 Coder 32b Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-11-06", "structured_output": true, "temperature": true, "tool_call": true }, "qwen/qwen3-coder-480b-a35b-instruct": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Qwen3 Coder 480B A35B Instruct is an AI model provided by nvidia.", "family": "qwen", "id": "qwen/qwen3-coder-480b-a35b-instruct", "knowledge": "2025-04", "last_updated": "2025-07-23", "limit": { "context": 262144, "output": 66536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Coder 480B A35B Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-07-23", "temperature": true, "tool_call": true }, "qwen/qwen3-next-80b-a3b-instruct": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Qwen3-Next-80B-A3B-Instruct is an AI model provided by nvidia.", "family": "qwen", "id": "qwen/qwen3-next-80b-a3b-instruct", "knowledge": "2024-12", "last_updated": "2025-09-05", "limit": { "context": 262144, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3-Next-80B-A3B-Instruct", "open_weights": false, "reasoning": false, "release_date": "2024-12-01", "temperature": true, "tool_call": true }, "qwen/qwen3-next-80b-a3b-thinking": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Qwen3-Next-80B-A3B-Thinking is an AI model provided by nvidia.", "family": "qwen", "id": "qwen/qwen3-next-80b-a3b-thinking", "knowledge": "2024-12", "last_updated": "2025-09-05", "limit": { "context": 262144, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3-Next-80B-A3B-Thinking", "open_weights": true, "reasoning": true, "release_date": "2024-12-01", "temperature": true, "tool_call": true }, "qwen/qwen3.5-122b-a10b": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Qwen3.5 122B-A10B is an AI model provided by nvidia.", "family": "qwen", "id": "qwen/qwen3.5-122b-a10b", "last_updated": "2026-02-23", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text" ] }, "name": "Qwen3.5 122B-A10B", "open_weights": true, "reasoning": true, "release_date": "2026-02-23", "structured_output": true, "temperature": true, "tool_call": true }, "qwen/qwen3.5-397b-a17b": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Qwen3.5-397B-A17B is an AI model provided by nvidia.", "family": "qwen", "id": "qwen/qwen3.5-397b-a17b", "knowledge": "2026-01", "last_updated": "2026-02-16", "limit": { "context": 262144, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen3.5-397B-A17B", "open_weights": true, "reasoning": true, "release_date": "2026-02-16", "structured_output": true, "temperature": true, "tool_call": true }, "sarvamai/sarvam-m": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "sarvam-m is an AI model provided by nvidia.", "id": "sarvamai/sarvam-m", "last_updated": "2025-07-25", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "sarvam-m", "open_weights": true, "reasoning": false, "release_date": "2025-07-25", "temperature": true, "tool_call": true }, "stepfun-ai/step-3.5-flash": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Step 3.5 Flash is an AI model provided by nvidia.", "id": "stepfun-ai/step-3.5-flash", "last_updated": "2026-02-02", "limit": { "context": 256000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Step 3.5 Flash", "open_weights": true, "reasoning": true, "release_date": "2026-02-02", "temperature": true, "tool_call": true }, "upstage/solar-10_7b-instruct": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "solar-10.7b-instruct is an AI model provided by nvidia.", "id": "upstage/solar-10_7b-instruct", "last_updated": "2025-04-10", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "solar-10.7b-instruct", "open_weights": true, "reasoning": false, "release_date": "2024-06-05", "temperature": true, "tool_call": true }, "z-ai/glm-5.1": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "GLM-5.1 is an AI model provided by nvidia.", "family": "glm", "id": "z-ai/glm-5.1", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-03-27", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5.1", "open_weights": true, "reasoning": true, "release_date": "2026-03-27", "structured_output": true, "temperature": true, "tool_call": true }, "z-ai/glm4.7": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "GLM-4.7 is an AI model provided by nvidia.", "family": "glm", "id": "z-ai/glm4.7", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-04", "last_updated": "2025-12-22", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.7", "open_weights": true, "reasoning": true, "release_date": "2025-12-22", "temperature": true, "tool_call": true } }, "name": "Nvidia", "npm": "@ai-sdk/openai-compatible" }, "ollama-cloud": { "api": "https://ollama.com/v1", "doc": "https://docs.ollama.com/cloud", "env": [ "OLLAMA_API_KEY" ], "iconURL": "https://models.dev/logos/ollama-cloud.svg", "id": "ollama-cloud", "models": { "cogito-2.1:671b": { "attachment": false, "description": "cogito-2.1:671b is an AI model provided by ollama-cloud.", "family": "cogito", "id": "cogito-2.1:671b", "last_updated": "2026-01-19", "limit": { "context": 163840, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "cogito-2.1:671b", "open_weights": true, "reasoning": true, "release_date": "2025-11-19", "tool_call": true }, "deepseek-v3.1:671b": { "attachment": false, "description": "deepseek-v3.1:671b is an AI model provided by ollama-cloud.", "family": "deepseek", "id": "deepseek-v3.1:671b", "last_updated": "2026-01-19", "limit": { "context": 163840, "output": 163840 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "deepseek-v3.1:671b", "open_weights": true, "reasoning": true, "release_date": "2025-08-21", "tool_call": true }, "deepseek-v3.2": { "attachment": false, "description": "deepseek-v3.2 is an AI model provided by ollama-cloud.", "family": "deepseek", "id": "deepseek-v3.2", "last_updated": "2026-01-19", "limit": { "context": 163840, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "deepseek-v3.2", "open_weights": true, "reasoning": true, "release_date": "2025-06-15", "tool_call": true }, "deepseek-v4-flash": { "attachment": false, "description": "deepseek-v4-flash is an AI model provided by ollama-cloud.", "family": "deepseek-flash", "id": "deepseek-v4-flash", "last_updated": "2026-04-24", "limit": { "context": 1048576, "output": 1048576 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "deepseek-v4-flash", "open_weights": true, "reasoning": true, "release_date": "2026-04-24", "tool_call": true }, "deepseek-v4-pro": { "attachment": false, "description": "deepseek-v4-pro is an AI model provided by ollama-cloud.", "family": "deepseek-thinking", "id": "deepseek-v4-pro", "last_updated": "2026-04-24", "limit": { "context": 1048576, "output": 1048576 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "deepseek-v4-pro", "open_weights": true, "reasoning": true, "release_date": "2026-04-24", "tool_call": true }, "devstral-2:123b": { "attachment": false, "description": "devstral-2:123b is an AI model provided by ollama-cloud.", "family": "devstral", "id": "devstral-2:123b", "last_updated": "2026-01-19", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "devstral-2:123b", "open_weights": true, "reasoning": false, "release_date": "2025-12-09", "tool_call": true }, "devstral-small-2:24b": { "attachment": true, "description": "devstral-small-2:24b is an AI model provided by ollama-cloud.", "family": "devstral", "id": "devstral-small-2:24b", "last_updated": "2026-01-19", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "devstral-small-2:24b", "open_weights": true, "reasoning": false, "release_date": "2025-12-09", "tool_call": true }, "gemini-3-flash-preview": { "attachment": true, "description": "gemini-3-flash-preview is an AI model provided by ollama-cloud.", "family": "gemini-flash", "id": "gemini-3-flash-preview", "knowledge": "2025-01", "last_updated": "2026-04-08", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "gemini-3-flash-preview", "open_weights": true, "reasoning": true, "release_date": "2025-12-17", "tool_call": true }, "gemma3:12b": { "attachment": true, "description": "gemma3:12b is an AI model provided by ollama-cloud.", "family": "gemma", "id": "gemma3:12b", "last_updated": "2026-01-19", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "gemma3:12b", "open_weights": true, "reasoning": false, "release_date": "2024-12-01", "tool_call": false }, "gemma3:27b": { "attachment": true, "description": "gemma3:27b is an AI model provided by ollama-cloud.", "family": "gemma", "id": "gemma3:27b", "last_updated": "2026-01-19", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "gemma3:27b", "open_weights": true, "reasoning": false, "release_date": "2025-07-27", "tool_call": false }, "gemma3:4b": { "attachment": true, "description": "gemma3:4b is an AI model provided by ollama-cloud.", "family": "gemma", "id": "gemma3:4b", "last_updated": "2026-01-19", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "gemma3:4b", "open_weights": true, "reasoning": false, "release_date": "2024-12-01", "tool_call": false }, "gemma4:31b": { "attachment": true, "description": "gemma4:31b is an AI model provided by ollama-cloud.", "family": "gemma", "id": "gemma4:31b", "knowledge": "2025-01", "last_updated": "2026-04-08", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "gemma4:31b", "open_weights": true, "reasoning": true, "release_date": "2026-04-02", "tool_call": true }, "glm-4.6": { "attachment": false, "description": "glm-4.6 is an AI model provided by ollama-cloud.", "family": "glm", "id": "glm-4.6", "last_updated": "2026-01-19", "limit": { "context": 202752, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "glm-4.6", "open_weights": true, "reasoning": true, "release_date": "2025-09-29", "tool_call": true }, "glm-4.7": { "attachment": false, "description": "glm-4.7 is an AI model provided by ollama-cloud.", "family": "glm", "id": "glm-4.7", "last_updated": "2026-01-19", "limit": { "context": 202752, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "glm-4.7", "open_weights": true, "reasoning": true, "release_date": "2025-12-22", "tool_call": true }, "glm-5": { "attachment": false, "description": "glm-5 is an AI model provided by ollama-cloud.", "family": "glm", "id": "glm-5", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-02-11", "limit": { "context": 202752, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "glm-5", "open_weights": true, "reasoning": true, "release_date": "2026-02-11", "tool_call": true }, "glm-5.1": { "attachment": false, "description": "glm-5.1 is an AI model provided by ollama-cloud.", "family": "glm", "id": "glm-5.1", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-07", "limit": { "context": 202752, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "glm-5.1", "open_weights": true, "reasoning": true, "release_date": "2026-03-27", "tool_call": true }, "gpt-oss:120b": { "attachment": false, "description": "gpt-oss:120b is an AI model provided by ollama-cloud.", "family": "gpt-oss", "id": "gpt-oss:120b", "last_updated": "2026-01-19", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "gpt-oss:120b", "open_weights": true, "reasoning": true, "release_date": "2025-08-05", "tool_call": true }, "gpt-oss:20b": { "attachment": false, "description": "gpt-oss:20b is an AI model provided by ollama-cloud.", "family": "gpt-oss", "id": "gpt-oss:20b", "last_updated": "2026-01-19", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "gpt-oss:20b", "open_weights": true, "reasoning": true, "release_date": "2025-08-05", "tool_call": true }, "kimi-k2-thinking": { "attachment": false, "description": "kimi-k2-thinking is an AI model provided by ollama-cloud.", "family": "kimi-thinking", "id": "kimi-k2-thinking", "knowledge": "2024-08", "last_updated": "2026-01-19", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "kimi-k2-thinking", "open_weights": true, "reasoning": true, "release_date": "2025-11-06", "tool_call": true }, "kimi-k2.5": { "attachment": true, "description": "kimi-k2.5 is an AI model provided by ollama-cloud.", "family": "kimi", "id": "kimi-k2.5", "last_updated": "2026-01-27", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "kimi-k2.5", "open_weights": true, "reasoning": true, "release_date": "2026-01-27", "tool_call": true }, "kimi-k2.6": { "attachment": true, "description": "kimi-k2.6 is an AI model provided by ollama-cloud.", "family": "kimi", "id": "kimi-k2.6", "last_updated": "2026-04-20", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "kimi-k2.6", "open_weights": true, "reasoning": true, "release_date": "2026-04-20", "tool_call": true }, "kimi-k2:1t": { "attachment": false, "description": "kimi-k2:1t is an AI model provided by ollama-cloud.", "family": "kimi", "id": "kimi-k2:1t", "knowledge": "2024-10", "last_updated": "2026-01-19", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "kimi-k2:1t", "open_weights": true, "reasoning": false, "release_date": "2025-07-11", "tool_call": true }, "minimax-m2": { "attachment": false, "description": "minimax-m2 is an AI model provided by ollama-cloud.", "family": "minimax", "id": "minimax-m2", "last_updated": "2026-01-19", "limit": { "context": 204800, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "minimax-m2", "open_weights": true, "reasoning": false, "release_date": "2025-10-23", "tool_call": true }, "minimax-m2.1": { "attachment": false, "description": "minimax-m2.1 is an AI model provided by ollama-cloud.", "family": "minimax", "id": "minimax-m2.1", "last_updated": "2026-01-19", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "minimax-m2.1", "open_weights": true, "reasoning": true, "release_date": "2025-12-23", "tool_call": true }, "minimax-m2.5": { "attachment": false, "description": "minimax-m2.5 is an AI model provided by ollama-cloud.", "family": "minimax", "id": "minimax-m2.5", "knowledge": "2025-01", "last_updated": "2026-02-12", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "minimax-m2.5", "open_weights": true, "reasoning": true, "release_date": "2026-02-12", "tool_call": true }, "minimax-m2.7": { "attachment": false, "description": "minimax-m2.7 is an AI model provided by ollama-cloud.", "family": "minimax", "id": "minimax-m2.7", "last_updated": "2026-03-18", "limit": { "context": 196608, "output": 196608 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "minimax-m2.7", "open_weights": true, "reasoning": true, "release_date": "2026-03-18", "tool_call": true }, "ministral-3:14b": { "attachment": true, "description": "ministral-3:14b is an AI model provided by ollama-cloud.", "family": "ministral", "id": "ministral-3:14b", "last_updated": "2026-01-19", "limit": { "context": 262144, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "ministral-3:14b", "open_weights": true, "reasoning": false, "release_date": "2024-12-01", "tool_call": true }, "ministral-3:3b": { "attachment": true, "description": "ministral-3:3b is an AI model provided by ollama-cloud.", "family": "ministral", "id": "ministral-3:3b", "last_updated": "2026-01-19", "limit": { "context": 262144, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "ministral-3:3b", "open_weights": true, "reasoning": false, "release_date": "2024-10-22", "tool_call": true }, "ministral-3:8b": { "attachment": true, "description": "ministral-3:8b is an AI model provided by ollama-cloud.", "family": "ministral", "id": "ministral-3:8b", "last_updated": "2026-01-19", "limit": { "context": 262144, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "ministral-3:8b", "open_weights": true, "reasoning": false, "release_date": "2024-12-01", "tool_call": true }, "mistral-large-3:675b": { "attachment": true, "description": "mistral-large-3:675b is an AI model provided by ollama-cloud.", "family": "mistral-large", "id": "mistral-large-3:675b", "last_updated": "2026-01-19", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "mistral-large-3:675b", "open_weights": true, "reasoning": false, "release_date": "2025-12-02", "tool_call": true }, "nemotron-3-nano:30b": { "attachment": false, "description": "nemotron-3-nano:30b is an AI model provided by ollama-cloud.", "family": "nemotron", "id": "nemotron-3-nano:30b", "last_updated": "2026-01-19", "limit": { "context": 1048576, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "nemotron-3-nano:30b", "open_weights": true, "reasoning": true, "release_date": "2025-12-15", "tool_call": true }, "nemotron-3-super": { "attachment": false, "description": "nemotron-3-super is an AI model provided by ollama-cloud.", "family": "nemotron", "id": "nemotron-3-super", "last_updated": "2026-03-12", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "nemotron-3-super", "open_weights": true, "reasoning": true, "release_date": "2026-03-11", "tool_call": true }, "qwen3-coder-next": { "attachment": false, "description": "qwen3-coder-next is an AI model provided by ollama-cloud.", "family": "qwen", "id": "qwen3-coder-next", "last_updated": "2026-02-08", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "qwen3-coder-next", "open_weights": true, "reasoning": false, "release_date": "2026-02-02", "tool_call": true }, "qwen3-coder:480b": { "attachment": false, "description": "qwen3-coder:480b is an AI model provided by ollama-cloud.", "family": "qwen", "id": "qwen3-coder:480b", "last_updated": "2026-01-19", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "qwen3-coder:480b", "open_weights": true, "reasoning": false, "release_date": "2025-07-22", "tool_call": true }, "qwen3-next:80b": { "attachment": false, "description": "qwen3-next:80b is an AI model provided by ollama-cloud.", "family": "qwen", "id": "qwen3-next:80b", "last_updated": "2026-01-19", "limit": { "context": 262144, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "qwen3-next:80b", "open_weights": true, "reasoning": true, "release_date": "2025-09-15", "tool_call": true }, "qwen3-vl:235b": { "attachment": true, "description": "qwen3-vl:235b is an AI model provided by ollama-cloud.", "family": "qwen", "id": "qwen3-vl:235b", "last_updated": "2026-01-19", "limit": { "context": 262144, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "qwen3-vl:235b", "open_weights": true, "reasoning": true, "release_date": "2025-09-22", "tool_call": true }, "qwen3-vl:235b-instruct": { "attachment": true, "description": "qwen3-vl:235b-instruct is an AI model provided by ollama-cloud.", "family": "qwen", "id": "qwen3-vl:235b-instruct", "last_updated": "2026-01-19", "limit": { "context": 262144, "output": 131072 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "qwen3-vl:235b-instruct", "open_weights": true, "reasoning": false, "release_date": "2025-09-22", "tool_call": true }, "qwen3.5:397b": { "attachment": true, "description": "qwen3.5:397b is an AI model provided by ollama-cloud.", "family": "qwen", "id": "qwen3.5:397b", "interleaved": { "field": "reasoning_details" }, "last_updated": "2026-02-17", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "qwen3.5:397b", "open_weights": true, "reasoning": true, "release_date": "2026-02-15", "tool_call": true }, "rnj-1:8b": { "attachment": false, "description": "rnj-1:8b is an AI model provided by ollama-cloud.", "family": "rnj", "id": "rnj-1:8b", "last_updated": "2026-01-19", "limit": { "context": 32768, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "rnj-1:8b", "open_weights": true, "reasoning": false, "release_date": "2025-12-06", "tool_call": true } }, "name": "Ollama Cloud", "npm": "@ai-sdk/openai-compatible" }, "openai": { "doc": "https://platform.openai.com/docs/models", "env": [ "OPENAI_API_KEY" ], "iconURL": "https://models.dev/logos/openai.svg", "id": "openai", "lobeIcon": "OpenAI.Color", "models": { "chatgpt-image-latest": { "attachment": true, "description": "chatgpt-image-latest is an AI model provided by openai.", "family": "gpt-image", "id": "chatgpt-image-latest", "last_updated": "2025-12-16", "limit": { "context": 0, "input": 0, "output": 0 }, "modalities": { "input": [ "text", "image" ], "output": [ "text", "image" ] }, "name": "chatgpt-image-latest", "open_weights": false, "reasoning": false, "release_date": "2025-12-16", "temperature": false, "tool_call": false }, "dall-e-2": { "attachment": true, "cost": { "cache_read": 0.01, "cache_write": 0.05, "input": 0.02, "output": 0.1 }, "description": "An AI model that generates images from textual descriptions.", "id": "dall-e-2", "knowledge": "2021-04", "last_updated": "2022-06-15", "limit": { "context": 1024, "output": 1 }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "name": "DALL-E 2", "open_weights": false, "reasoning": false, "release_date": "2022-04-06", "temperature": false, "tool_call": true }, "dall-e-3": { "attachment": true, "cost": { "cache_read": 0.01, "cache_write": 0.05, "input": 0.03, "output": 0.15 }, "description": "The latest version of DALL-E for generating images from text.", "id": "dall-e-3", "knowledge": "2024-04", "last_updated": "2024-08-15", "limit": { "context": 2048, "output": 1 }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "name": "DALL-E 3", "open_weights": false, "reasoning": false, "release_date": "2024-03-01", "temperature": false, "tool_call": true }, "gpt-3.5-turbo": { "attachment": false, "cost": { "cache_read": 1.25, "input": 0.5, "output": 1.5 }, "description": "GPT-3.5-turbo is an AI model provided by openai.", "family": "gpt", "id": "gpt-3.5-turbo", "knowledge": "2021-09-01", "last_updated": "2023-11-06", "limit": { "context": 16385, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT-3.5-turbo", "open_weights": false, "reasoning": false, "release_date": "2023-03-01", "structured_output": false, "temperature": true, "tool_call": false }, "gpt-4": { "attachment": true, "cost": { "input": 30, "output": 60 }, "description": "GPT-4 is an AI model provided by openai.", "family": "gpt", "id": "gpt-4", "knowledge": "2023-11", "last_updated": "2024-04-09", "limit": { "context": 8192, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT-4", "open_weights": false, "reasoning": false, "release_date": "2023-11-06", "structured_output": false, "temperature": true, "tool_call": true }, "gpt-4-turbo": { "attachment": true, "cost": { "input": 10, "output": 30 }, "description": "GPT-4 Turbo is an AI model provided by openai.", "family": "gpt", "id": "gpt-4-turbo", "knowledge": "2023-12", "last_updated": "2024-04-09", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4 Turbo", "open_weights": false, "reasoning": false, "release_date": "2023-11-06", "structured_output": false, "temperature": true, "tool_call": true }, "gpt-4.1": { "attachment": true, "cost": { "cache_read": 0.5, "input": 2, "output": 8 }, "description": "GPT-4.1 is an AI model provided by openai.", "family": "gpt", "id": "gpt-4.1", "knowledge": "2024-04", "last_updated": "2025-04-14", "limit": { "context": 1047576, "output": 32768 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-4.1", "open_weights": false, "reasoning": false, "release_date": "2025-04-14", "structured_output": true, "temperature": true, "tool_call": true }, "gpt-4.1-mini": { "attachment": true, "cost": { "cache_read": 0.1, "input": 0.4, "output": 1.6 }, "description": "GPT-4.1 mini is an AI model provided by openai.", "family": "gpt-mini", "id": "gpt-4.1-mini", "knowledge": "2024-04", "last_updated": "2025-04-14", "limit": { "context": 1047576, "output": 32768 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-4.1 mini", "open_weights": false, "reasoning": false, "release_date": "2025-04-14", "structured_output": true, "temperature": true, "tool_call": true }, "gpt-4.1-nano": { "attachment": true, "cost": { "cache_read": 0.03, "input": 0.1, "output": 0.4 }, "description": "GPT-4.1 nano is an AI model provided by openai.", "family": "gpt-nano", "id": "gpt-4.1-nano", "knowledge": "2024-04", "last_updated": "2025-04-14", "limit": { "context": 1047576, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4.1 nano", "open_weights": false, "reasoning": false, "release_date": "2025-04-14", "structured_output": true, "temperature": true, "tool_call": true }, "gpt-4o": { "attachment": true, "cost": { "cache_read": 1.25, "input": 2.5, "output": 10 }, "description": "GPT-4o is an AI model provided by openai.", "family": "gpt", "id": "gpt-4o", "knowledge": "2023-09", "last_updated": "2024-08-06", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-4o", "open_weights": false, "reasoning": false, "release_date": "2024-05-13", "structured_output": true, "temperature": true, "tool_call": true }, "gpt-4o-2024-05-13": { "attachment": true, "cost": { "input": 5, "output": 15 }, "description": "GPT-4o (2024-05-13) is an AI model provided by openai.", "family": "gpt", "id": "gpt-4o-2024-05-13", "knowledge": "2023-09", "last_updated": "2024-05-13", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4o (2024-05-13)", "open_weights": false, "reasoning": false, "release_date": "2024-05-13", "structured_output": true, "temperature": true, "tool_call": true }, "gpt-4o-2024-08-06": { "attachment": true, "cost": { "cache_read": 1.25, "input": 2.5, "output": 10 }, "description": "GPT-4o (2024-08-06) is an AI model provided by openai.", "family": "gpt", "id": "gpt-4o-2024-08-06", "knowledge": "2023-09", "last_updated": "2024-08-06", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4o (2024-08-06)", "open_weights": false, "reasoning": false, "release_date": "2024-08-06", "structured_output": true, "temperature": true, "tool_call": true }, "gpt-4o-2024-11-20": { "attachment": true, "cost": { "cache_read": 1.25, "input": 2.5, "output": 10 }, "description": "GPT-4o (2024-11-20) is an AI model provided by openai.", "family": "gpt", "id": "gpt-4o-2024-11-20", "knowledge": "2023-09", "last_updated": "2024-11-20", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4o (2024-11-20)", "open_weights": false, "reasoning": false, "release_date": "2024-11-20", "structured_output": true, "temperature": true, "tool_call": true }, "gpt-4o-mini": { "attachment": true, "cost": { "cache_read": 0.08, "input": 0.15, "output": 0.6 }, "description": "GPT-4o mini is an AI model provided by openai.", "family": "gpt-mini", "id": "gpt-4o-mini", "knowledge": "2023-09", "last_updated": "2024-07-18", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-4o mini", "open_weights": false, "reasoning": false, "release_date": "2024-07-18", "structured_output": true, "temperature": true, "tool_call": true }, "gpt-5": { "attachment": true, "cost": { "cache_read": 0.125, "input": 1.25, "output": 10 }, "description": "GPT-5 is an AI model provided by openai.", "family": "gpt", "id": "gpt-5", "knowledge": "2024-09-30", "last_updated": "2025-08-07", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5-chat-latest": { "attachment": true, "cost": { "input": 1.25, "output": 10 }, "description": "GPT-5 Chat (latest) is an AI model provided by openai.", "family": "gpt-codex", "id": "gpt-5-chat-latest", "knowledge": "2024-09-30", "last_updated": "2025-08-07", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5 Chat (latest)", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "structured_output": true, "temperature": true, "tool_call": false }, "gpt-5-codex": { "attachment": false, "cost": { "cache_read": 0.125, "input": 1.25, "output": 10 }, "description": "GPT-5-Codex is an AI model provided by openai.", "family": "gpt-codex", "id": "gpt-5-codex", "knowledge": "2024-09-30", "last_updated": "2025-09-15", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5-Codex", "open_weights": false, "reasoning": true, "release_date": "2025-09-15", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5-mini": { "attachment": true, "cost": { "cache_read": 0.025, "input": 0.25, "output": 2 }, "description": "GPT-5 Mini is an AI model provided by openai.", "family": "gpt-mini", "id": "gpt-5-mini", "knowledge": "2024-05-30", "last_updated": "2025-08-07", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5 Mini", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5-nano": { "attachment": true, "cost": { "cache_read": 0.005, "input": 0.05, "output": 0.4 }, "description": "GPT-5 Nano is an AI model provided by openai.", "family": "gpt-nano", "id": "gpt-5-nano", "knowledge": "2024-05-30", "last_updated": "2025-08-07", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5 Nano", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5-pro": { "attachment": true, "cost": { "input": 15, "output": 120 }, "description": "GPT-5 Pro is an AI model provided by openai.", "family": "gpt-pro", "id": "gpt-5-pro", "knowledge": "2024-09-30", "last_updated": "2025-10-06", "limit": { "context": 400000, "input": 272000, "output": 272000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5 Pro", "open_weights": false, "reasoning": true, "release_date": "2025-10-06", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.1": { "attachment": true, "cost": { "cache_read": 0.13, "input": 1.25, "output": 10 }, "description": "GPT-5.1 is an AI model provided by openai.", "family": "gpt", "id": "gpt-5.1", "knowledge": "2024-09-30", "last_updated": "2025-11-13", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.1", "open_weights": false, "reasoning": true, "release_date": "2025-11-13", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.1-chat-latest": { "attachment": true, "cost": { "cache_read": 0.125, "input": 1.25, "output": 10 }, "description": "GPT-5.1 Chat is an AI model provided by openai.", "family": "gpt-codex", "id": "gpt-5.1-chat-latest", "knowledge": "2024-09-30", "last_updated": "2025-11-13", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.1 Chat", "open_weights": false, "reasoning": true, "release_date": "2025-11-13", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.1-codex": { "attachment": true, "cost": { "cache_read": 0.125, "input": 1.25, "output": 10 }, "description": "GPT-5.1 Codex is an AI model provided by openai.", "family": "gpt-codex", "id": "gpt-5.1-codex", "knowledge": "2024-09-30", "last_updated": "2025-11-13", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.1 Codex", "open_weights": false, "reasoning": true, "release_date": "2025-11-13", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.1-codex-max": { "attachment": true, "cost": { "cache_read": 0.125, "input": 1.25, "output": 10 }, "description": "GPT-5.1 Codex Max is an AI model provided by openai.", "family": "gpt-codex", "id": "gpt-5.1-codex-max", "knowledge": "2024-09-30", "last_updated": "2025-11-13", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.1 Codex Max", "open_weights": false, "reasoning": true, "release_date": "2025-11-13", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.1-codex-mini": { "attachment": true, "cost": { "cache_read": 0.025, "input": 0.25, "output": 2 }, "description": "GPT-5.1 Codex mini is an AI model provided by openai.", "family": "gpt-codex", "id": "gpt-5.1-codex-mini", "knowledge": "2024-09-30", "last_updated": "2025-11-13", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.1 Codex mini", "open_weights": false, "reasoning": true, "release_date": "2025-11-13", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.2": { "attachment": true, "cost": { "cache_read": 0.175, "input": 1.75, "output": 14 }, "description": "GPT-5.2 is an AI model provided by openai.", "family": "gpt", "id": "gpt-5.2", "knowledge": "2025-08-31", "last_updated": "2025-12-11", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.2", "open_weights": false, "reasoning": true, "release_date": "2025-12-11", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.2-chat-latest": { "attachment": true, "cost": { "cache_read": 0.175, "input": 1.75, "output": 14 }, "description": "GPT-5.2 Chat is an AI model provided by openai.", "family": "gpt-codex", "id": "gpt-5.2-chat-latest", "knowledge": "2025-08-31", "last_updated": "2025-12-11", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.2 Chat", "open_weights": false, "reasoning": true, "release_date": "2025-12-11", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.2-codex": { "attachment": true, "cost": { "cache_read": 0.175, "input": 1.75, "output": 14 }, "description": "GPT-5.2 Codex is an AI model provided by openai.", "family": "gpt-codex", "id": "gpt-5.2-codex", "knowledge": "2025-08-31", "last_updated": "2025-12-11", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.2 Codex", "open_weights": false, "reasoning": true, "release_date": "2025-12-11", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.2-pro": { "attachment": true, "cost": { "input": 21, "output": 168 }, "description": "GPT-5.2 Pro is an AI model provided by openai.", "family": "gpt-pro", "id": "gpt-5.2-pro", "knowledge": "2025-08-31", "last_updated": "2025-12-11", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.2 Pro", "open_weights": false, "reasoning": true, "release_date": "2025-12-11", "structured_output": false, "temperature": false, "tool_call": true }, "gpt-5.3-chat-latest": { "attachment": true, "cost": { "cache_read": 0.175, "input": 1.75, "output": 14 }, "description": "GPT-5.3 Chat (latest) is an AI model provided by openai.", "family": "gpt", "id": "gpt-5.3-chat-latest", "knowledge": "2025-08-31", "last_updated": "2026-03-03", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.3 Chat (latest)", "open_weights": false, "reasoning": false, "release_date": "2026-03-03", "structured_output": true, "temperature": true, "tool_call": true }, "gpt-5.3-codex": { "attachment": true, "cost": { "cache_read": 0.175, "input": 1.75, "output": 14 }, "description": "GPT-5.3 Codex is an AI model provided by openai.", "family": "gpt-codex", "id": "gpt-5.3-codex", "knowledge": "2025-08-31", "last_updated": "2026-02-05", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.3 Codex", "open_weights": false, "reasoning": true, "release_date": "2026-02-05", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.3-codex-spark": { "attachment": true, "cost": { "cache_read": 0.175, "input": 1.75, "output": 14 }, "description": "GPT-5.3 Codex Spark is an AI model provided by openai.", "family": "gpt-codex-spark", "id": "gpt-5.3-codex-spark", "knowledge": "2025-08-31", "last_updated": "2026-02-05", "limit": { "context": 128000, "input": 100000, "output": 32000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.3 Codex Spark", "open_weights": false, "reasoning": true, "release_date": "2026-02-05", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.4": { "attachment": true, "cost": { "cache_read": 0.25, "context_over_200k": { "cache_read": 0.5, "input": 5, "output": 22.5 }, "input": 2.5, "output": 15, "tiers": [ { "cache_read": 0.5, "input": 5, "output": 22.5, "tier": { "size": 272000, "type": "context" } } ] }, "description": "GPT-5.4 is an AI model provided by openai.", "experimental": { "modes": { "fast": { "cost": { "cache_read": 0.5, "input": 5, "output": 30 }, "provider": { "body": { "service_tier": "priority" } } } } }, "family": "gpt", "id": "gpt-5.4", "knowledge": "2025-08-31", "last_updated": "2026-03-05", "limit": { "context": 1050000, "input": 922000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.4", "open_weights": false, "reasoning": true, "release_date": "2026-03-05", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.4-mini": { "attachment": true, "cost": { "cache_read": 0.075, "input": 0.75, "output": 4.5 }, "description": "GPT-5.4 mini is an AI model provided by openai.", "experimental": { "modes": { "fast": { "cost": { "cache_read": 0.15, "input": 1.5, "output": 9 }, "provider": { "body": { "service_tier": "priority" } } } } }, "family": "gpt-mini", "id": "gpt-5.4-mini", "knowledge": "2025-08-31", "last_updated": "2026-03-17", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.4 mini", "open_weights": false, "reasoning": true, "release_date": "2026-03-17", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.4-nano": { "attachment": true, "cost": { "cache_read": 0.02, "input": 0.2, "output": 1.25 }, "description": "GPT-5.4 nano is an AI model provided by openai.", "family": "gpt-nano", "id": "gpt-5.4-nano", "knowledge": "2025-08-31", "last_updated": "2026-03-17", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.4 nano", "open_weights": false, "reasoning": true, "release_date": "2026-03-17", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.4-pro": { "attachment": true, "cost": { "context_over_200k": { "input": 60, "output": 270 }, "input": 30, "output": 180, "tiers": [ { "input": 60, "output": 270, "tier": { "size": 272000, "type": "context" } } ] }, "description": "GPT-5.4 Pro is an AI model provided by openai.", "family": "gpt-pro", "id": "gpt-5.4-pro", "knowledge": "2025-08-31", "last_updated": "2026-03-05", "limit": { "context": 1050000, "input": 922000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.4 Pro", "open_weights": false, "reasoning": true, "release_date": "2026-03-05", "structured_output": false, "temperature": false, "tool_call": true }, "gpt-5.5": { "attachment": true, "cost": { "cache_read": 0.5, "context_over_200k": { "cache_read": 1, "input": 10, "output": 45 }, "input": 5, "output": 30, "tiers": [ { "cache_read": 1, "input": 10, "output": 45, "tier": { "size": 272000, "type": "context" } } ] }, "description": "GPT-5.5 is an AI model provided by openai.", "experimental": { "modes": { "fast": { "cost": { "cache_read": 1.25, "input": 12.5, "output": 75 }, "provider": { "body": { "service_tier": "priority" } } } } }, "family": "gpt", "id": "gpt-5.5", "knowledge": "2025-12-01", "last_updated": "2026-04-23", "limit": { "context": 1050000, "input": 922000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.5", "open_weights": false, "reasoning": true, "release_date": "2026-04-23", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.5-pro": { "attachment": true, "cost": { "context_over_200k": { "input": 60, "output": 270 }, "input": 30, "output": 180, "tiers": [ { "input": 60, "output": 270, "tier": { "size": 272000, "type": "context" } } ] }, "description": "GPT-5.5 Pro is an AI model provided by openai.", "family": "gpt-pro", "id": "gpt-5.5-pro", "knowledge": "2025-12-01", "last_updated": "2026-04-23", "limit": { "context": 1050000, "input": 922000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.5 Pro", "open_weights": false, "reasoning": true, "release_date": "2026-04-23", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-image-1": { "attachment": true, "cost": { "cache_read": 0.1, "cache_write": 0.6, "input": 10, "output": 20 }, "description": "An advanced AI model for generating images from textual descriptions.", "family": "gpt-image", "id": "gpt-image-1", "knowledge": "2023-10", "last_updated": "2024-10-01", "limit": { "context": 1000, "input": 0, "output": 512 }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "name": "GPT-IMAGE-1", "open_weights": true, "reasoning": true, "release_date": "2024-01-15", "temperature": true, "tool_call": true }, "gpt-image-1-mini": { "attachment": true, "description": "gpt-image-1-mini is an AI model provided by openai.", "family": "gpt-image", "id": "gpt-image-1-mini", "last_updated": "2025-09-26", "limit": { "context": 0, "input": 0, "output": 0 }, "modalities": { "input": [ "text", "image" ], "output": [ "text", "image" ] }, "name": "gpt-image-1-mini", "open_weights": false, "reasoning": false, "release_date": "2025-09-26", "temperature": false, "tool_call": false }, "gpt-image-1.5": { "attachment": true, "description": "gpt-image-1.5 is an AI model provided by openai.", "family": "gpt-image", "id": "gpt-image-1.5", "last_updated": "2025-11-25", "limit": { "context": 0, "input": 0, "output": 0 }, "modalities": { "input": [ "text", "image" ], "output": [ "text", "image" ] }, "name": "gpt-image-1.5", "open_weights": false, "reasoning": false, "release_date": "2025-11-25", "temperature": false, "tool_call": false }, "o1": { "attachment": true, "cost": { "cache_read": 7.5, "input": 15, "output": 60 }, "description": "o1 is an AI model provided by openai.", "family": "o", "id": "o1", "knowledge": "2023-09", "last_updated": "2024-12-05", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "o1", "open_weights": false, "reasoning": true, "release_date": "2024-12-05", "structured_output": true, "temperature": false, "tool_call": true }, "o1-mini": { "attachment": false, "cost": { "cache_read": 0.55, "input": 1.1, "output": 4.4 }, "description": "o1-mini is an AI model provided by openai.", "family": "o-mini", "id": "o1-mini", "knowledge": "2023-09", "last_updated": "2024-09-12", "limit": { "context": 128000, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "o1-mini", "open_weights": false, "reasoning": true, "release_date": "2024-09-12", "structured_output": true, "temperature": false, "tool_call": false }, "o1-preview": { "attachment": false, "cost": { "cache_read": 7.5, "input": 15, "output": 60 }, "description": "o1-preview is an AI model provided by openai.", "family": "o", "id": "o1-preview", "knowledge": "2023-09", "last_updated": "2024-09-12", "limit": { "context": 128000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "o1-preview", "open_weights": false, "reasoning": true, "release_date": "2024-09-12", "temperature": true, "tool_call": false }, "o1-pro": { "attachment": true, "cost": { "input": 150, "output": 600 }, "description": "o1-pro is an AI model provided by openai.", "family": "o-pro", "id": "o1-pro", "knowledge": "2023-09", "last_updated": "2025-03-19", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "o1-pro", "open_weights": false, "reasoning": true, "release_date": "2025-03-19", "structured_output": true, "temperature": false, "tool_call": true }, "o3": { "attachment": true, "cost": { "cache_read": 0.5, "input": 2, "output": 8 }, "description": "o3 is an AI model provided by openai.", "family": "o", "id": "o3", "knowledge": "2024-05", "last_updated": "2025-04-16", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "o3", "open_weights": false, "reasoning": true, "release_date": "2025-04-16", "structured_output": true, "temperature": false, "tool_call": true }, "o3-deep-research": { "attachment": true, "cost": { "cache_read": 2.5, "input": 10, "output": 40 }, "description": "o3-deep-research is an AI model provided by openai.", "family": "o", "id": "o3-deep-research", "knowledge": "2024-05", "last_updated": "2024-06-26", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "o3-deep-research", "open_weights": false, "reasoning": true, "release_date": "2024-06-26", "temperature": false, "tool_call": true }, "o3-mini": { "attachment": false, "cost": { "cache_read": 0.55, "input": 1.1, "output": 4.4 }, "description": "o3-mini is an AI model provided by openai.", "family": "o-mini", "id": "o3-mini", "knowledge": "2024-05", "last_updated": "2025-01-29", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "o3-mini", "open_weights": false, "reasoning": true, "release_date": "2024-12-20", "structured_output": true, "temperature": false, "tool_call": true }, "o3-pro": { "attachment": true, "cost": { "input": 20, "output": 80 }, "description": "o3-pro is an AI model provided by openai.", "family": "o-pro", "id": "o3-pro", "knowledge": "2024-05", "last_updated": "2025-06-10", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "o3-pro", "open_weights": false, "reasoning": true, "release_date": "2025-06-10", "structured_output": true, "temperature": false, "tool_call": true }, "o4-mini": { "attachment": true, "cost": { "cache_read": 0.28, "input": 1.1, "output": 4.4 }, "description": "o4-mini is an AI model provided by openai.", "family": "o-mini", "id": "o4-mini", "knowledge": "2024-05", "last_updated": "2025-04-16", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "o4-mini", "open_weights": false, "reasoning": true, "release_date": "2025-04-16", "structured_output": true, "temperature": false, "tool_call": true }, "o4-mini-deep-research": { "attachment": true, "cost": { "cache_read": 0.5, "input": 2, "output": 8 }, "description": "o4-mini-deep-research is an AI model provided by openai.", "family": "o-mini", "id": "o4-mini-deep-research", "knowledge": "2024-05", "last_updated": "2024-06-26", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "o4-mini-deep-research", "open_weights": false, "reasoning": true, "release_date": "2024-06-26", "temperature": false, "tool_call": true }, "text-embedding-3-large": { "attachment": true, "cost": { "cache_read": 0.05, "cache_write": 0.4, "input": 7, "output": 10 }, "description": "Large size text embedding model for extensive natural language processing tasks.", "family": "text-embedding", "id": "text-embedding-3-large", "knowledge": "2023-10", "last_updated": "2023-10-01", "limit": { "context": 64000, "output": 2048 }, "modalities": { "input": [ "text" ], "output": [ "vector" ] }, "name": "TEXT-EMBEDDING-3-LARGE", "open_weights": false, "reasoning": true, "release_date": "2023-12-15", "temperature": true, "tool_call": true }, "text-embedding-3-small": { "attachment": true, "cost": { "cache_read": 0.04, "cache_write": 0.3, "input": 4, "output": 8 }, "description": "Small size text embedding model for efficient processing.", "family": "text-embedding", "id": "text-embedding-3-small", "knowledge": "2023-10", "last_updated": "2023-10-01", "limit": { "context": 32000, "output": 1024 }, "modalities": { "input": [ "text" ], "output": [ "vector" ] }, "name": "TEXT-EMBEDDING-3-SMALL", "open_weights": false, "reasoning": true, "release_date": "2023-11-10", "temperature": true, "tool_call": true }, "text-embedding-ada-002": { "attachment": true, "cost": { "cache_read": 0.06, "cache_write": 0.45, "input": 6, "output": 12 }, "description": "Ada-based text embedding model optimized for various NLP tasks.", "family": "text-embedding", "id": "text-embedding-ada-002", "knowledge": "2023-10", "last_updated": "2023-10-01", "limit": { "context": 60000, "output": 1500 }, "modalities": { "input": [ "text" ], "output": [ "vector" ] }, "name": "TEXT-EMBEDDING-ADA-002", "open_weights": false, "reasoning": true, "release_date": "2023-11-20", "temperature": true, "tool_call": true } }, "name": "OpenAI", "npm": "@ai-sdk/openai" }, "opencode": { "api": "https://opencode.ai/zen/v1", "doc": "https://opencode.ai/docs/zen", "env": [ "OPENCODE_API_KEY" ], "iconURL": "https://models.dev/logos/opencode.svg", "id": "opencode", "lobeIcon": "OpenCode", "models": { "big-pickle": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "Big Pickle is an AI model provided by opencode.", "family": "big-pickle", "id": "big-pickle", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-01", "last_updated": "2025-10-17", "limit": { "context": 200000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Big Pickle", "open_weights": false, "reasoning": true, "release_date": "2025-10-17", "structured_output": true, "temperature": true, "tool_call": true }, "claude-3-5-haiku": { "attachment": true, "cost": { "cache_read": 0.08, "cache_write": 1, "input": 0.8, "output": 4 }, "description": "Claude Haiku 3.5 is an AI model provided by opencode.", "family": "claude-haiku", "id": "claude-3-5-haiku", "knowledge": "2024-07-31", "last_updated": "2024-10-22", "limit": { "context": 200000, "output": 8192 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Haiku 3.5", "open_weights": false, "provider": { "npm": "@ai-sdk/anthropic" }, "reasoning": false, "release_date": "2024-10-22", "status": "deprecated", "temperature": true, "tool_call": true }, "claude-haiku-4-5": { "attachment": true, "cost": { "cache_read": 0.1, "cache_write": 1.25, "input": 1, "output": 5 }, "description": "Claude Haiku 4.5 is an AI model provided by opencode.", "family": "claude-haiku", "id": "claude-haiku-4-5", "knowledge": "2025-02-28", "last_updated": "2025-10-15", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Haiku 4.5", "open_weights": false, "provider": { "npm": "@ai-sdk/anthropic" }, "reasoning": true, "release_date": "2025-10-15", "temperature": true, "tool_call": true }, "claude-opus-4-1": { "attachment": true, "cost": { "cache_read": 1.5, "cache_write": 18.75, "input": 15, "output": 75 }, "description": "Claude Opus 4.1 is an AI model provided by opencode.", "family": "claude-opus", "id": "claude-opus-4-1", "knowledge": "2025-03-31", "last_updated": "2025-08-05", "limit": { "context": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.1", "open_weights": false, "provider": { "npm": "@ai-sdk/anthropic" }, "reasoning": true, "release_date": "2025-08-05", "temperature": true, "tool_call": true }, "claude-opus-4-5": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "input": 5, "output": 25 }, "description": "Claude Opus 4.5 is an AI model provided by opencode.", "family": "claude-opus", "id": "claude-opus-4-5", "knowledge": "2025-03-31", "last_updated": "2025-11-24", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.5", "open_weights": false, "provider": { "npm": "@ai-sdk/anthropic" }, "reasoning": true, "release_date": "2025-11-24", "temperature": true, "tool_call": true }, "claude-opus-4-6": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "input": 5, "output": 25 }, "description": "Claude Opus 4.6 is an AI model provided by opencode.", "family": "claude-opus", "id": "claude-opus-4-6", "knowledge": "2025-05-31", "last_updated": "2026-03-13", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.6", "open_weights": false, "provider": { "npm": "@ai-sdk/anthropic" }, "reasoning": true, "release_date": "2026-02-05", "temperature": true, "tool_call": true }, "claude-opus-4-7": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "input": 5, "output": 25 }, "description": "Claude Opus 4.7 is an AI model provided by opencode.", "family": "claude-opus", "id": "claude-opus-4-7", "knowledge": "2026-01-31", "last_updated": "2026-04-16", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.7", "open_weights": false, "provider": { "npm": "@ai-sdk/anthropic" }, "reasoning": true, "release_date": "2026-04-16", "temperature": false, "tool_call": true }, "claude-sonnet-4": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "context_over_200k": { "cache_read": 0.6, "cache_write": 7.5, "input": 6, "output": 22.5 }, "input": 3, "output": 15, "tiers": [ { "cache_read": 0.6, "cache_write": 7.5, "input": 6, "output": 22.5, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Claude Sonnet 4 is an AI model provided by opencode.", "family": "claude-sonnet", "id": "claude-sonnet-4", "knowledge": "2025-03-31", "last_updated": "2025-05-22", "limit": { "context": 1000000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4", "open_weights": false, "provider": { "npm": "@ai-sdk/anthropic" }, "reasoning": true, "release_date": "2025-05-22", "temperature": true, "tool_call": true }, "claude-sonnet-4-5": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "context_over_200k": { "cache_read": 0.6, "cache_write": 7.5, "input": 6, "output": 22.5 }, "input": 3, "output": 15, "tiers": [ { "cache_read": 0.6, "cache_write": 7.5, "input": 6, "output": 22.5, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Claude Sonnet 4.5 is an AI model provided by opencode.", "family": "claude-sonnet", "id": "claude-sonnet-4-5", "interleaved": true, "knowledge": "2025-07-31", "last_updated": "2025-09-29", "limit": { "context": 1000000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.5", "open_weights": false, "provider": { "npm": "@ai-sdk/anthropic" }, "reasoning": true, "release_date": "2025-09-29", "temperature": true, "tool_call": true }, "claude-sonnet-4-6": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 4.6 is an AI model provided by opencode.", "family": "claude-sonnet", "id": "claude-sonnet-4-6", "interleaved": true, "knowledge": "2025-08-31", "last_updated": "2026-02-17", "limit": { "context": 1000000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.6", "open_weights": false, "provider": { "npm": "@ai-sdk/anthropic" }, "reasoning": true, "release_date": "2026-02-17", "temperature": true, "tool_call": true }, "deepseek-v4-flash-free": { "attachment": false, "cost": { "cache_read": 0, "input": 0, "output": 0 }, "description": "DeepSeek V4 Flash Free is an AI model provided by opencode.", "family": "deepseek-flash-free", "id": "deepseek-v4-flash-free", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-05", "last_updated": "2026-04-24", "limit": { "context": 1000000, "output": 384000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V4 Flash Free", "open_weights": true, "reasoning": true, "release_date": "2026-04-24", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-3-flash": { "attachment": true, "cost": { "cache_read": 0.05, "input": 0.5, "output": 3 }, "description": "Gemini 3 Flash is an AI model provided by opencode.", "family": "gemini-flash", "id": "gemini-3-flash", "knowledge": "2025-01", "last_updated": "2025-12-17", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "name": "Gemini 3 Flash", "open_weights": false, "provider": { "npm": "@ai-sdk/google" }, "reasoning": true, "release_date": "2025-12-17", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-3-pro": { "attachment": true, "cost": { "cache_read": 0.2, "context_over_200k": { "cache_read": 0.4, "input": 4, "output": 18 }, "input": 2, "output": 12, "tiers": [ { "cache_read": 0.4, "input": 4, "output": 18, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Gemini 3 Pro is an AI model provided by opencode.", "family": "gemini-pro", "id": "gemini-3-pro", "knowledge": "2025-01", "last_updated": "2025-11-18", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "name": "Gemini 3 Pro", "open_weights": false, "provider": { "npm": "@ai-sdk/google" }, "reasoning": true, "release_date": "2025-11-18", "status": "deprecated", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-3.1-pro": { "attachment": true, "cost": { "cache_read": 0.2, "context_over_200k": { "cache_read": 0.4, "input": 4, "output": 18 }, "input": 2, "output": 12, "tiers": [ { "cache_read": 0.4, "input": 4, "output": 18, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Gemini 3.1 Pro Preview is an AI model provided by opencode.", "family": "gemini-pro", "id": "gemini-3.1-pro", "knowledge": "2025-01", "last_updated": "2026-02-19", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "name": "Gemini 3.1 Pro Preview", "open_weights": false, "provider": { "npm": "@ai-sdk/google" }, "reasoning": true, "release_date": "2026-02-19", "structured_output": true, "temperature": true, "tool_call": true }, "glm-4.6": { "attachment": false, "cost": { "cache_read": 0.1, "input": 0.6, "output": 2.2 }, "description": "GLM-4.6 is an AI model provided by opencode.", "family": "glm", "id": "glm-4.6", "knowledge": "2025-04", "last_updated": "2025-09-30", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.6", "open_weights": true, "reasoning": true, "release_date": "2025-09-30", "status": "deprecated", "temperature": true, "tool_call": true }, "glm-4.7": { "attachment": false, "cost": { "cache_read": 0.1, "input": 0.6, "output": 2.2 }, "description": "GLM-4.7 is an AI model provided by opencode.", "family": "glm", "id": "glm-4.7", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-04", "last_updated": "2025-12-22", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.7", "open_weights": true, "reasoning": true, "release_date": "2025-12-22", "status": "deprecated", "temperature": true, "tool_call": true }, "glm-4.7-free": { "attachment": false, "cost": { "cache_read": 0, "input": 0, "output": 0 }, "description": "GLM-4.7 Free is an AI model provided by opencode.", "family": "glm-free", "id": "glm-4.7-free", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-04", "last_updated": "2025-12-22", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.7 Free", "open_weights": true, "reasoning": true, "release_date": "2025-12-22", "status": "deprecated", "temperature": true, "tool_call": true }, "glm-5": { "attachment": false, "cost": { "cache_read": 0.2, "input": 1, "output": 3.2 }, "description": "GLM-5 is an AI model provided by opencode.", "family": "glm", "id": "glm-5", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-04", "last_updated": "2026-02-11", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5", "open_weights": true, "reasoning": true, "release_date": "2026-02-11", "temperature": true, "tool_call": true }, "glm-5-free": { "attachment": false, "cost": { "cache_read": 0, "input": 0, "output": 0 }, "description": "GLM-5 Free is an AI model provided by opencode.", "family": "glm-free", "id": "glm-5-free", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-04", "last_updated": "2026-02-11", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5 Free", "open_weights": true, "reasoning": true, "release_date": "2026-02-11", "status": "deprecated", "temperature": true, "tool_call": true }, "glm-5.1": { "attachment": false, "cost": { "cache_read": 0.26, "input": 1.4, "output": 4.4 }, "description": "GLM-5.1 is an AI model provided by opencode.", "family": "glm", "id": "glm-5.1", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-04", "last_updated": "2026-04-07", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5.1", "open_weights": true, "reasoning": true, "release_date": "2026-04-07", "temperature": true, "tool_call": true }, "gpt-5": { "attachment": true, "cost": { "cache_read": 0.107, "input": 1.07, "output": 8.5 }, "description": "GPT-5 is an AI model provided by opencode.", "family": "gpt", "id": "gpt-5", "knowledge": "2024-09-30", "last_updated": "2025-08-07", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5", "open_weights": false, "provider": { "npm": "@ai-sdk/openai" }, "reasoning": true, "release_date": "2025-08-07", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5-codex": { "attachment": true, "cost": { "cache_read": 0.107, "input": 1.07, "output": 8.5 }, "description": "GPT-5 Codex is an AI model provided by opencode.", "family": "gpt-codex", "id": "gpt-5-codex", "knowledge": "2024-09-30", "last_updated": "2025-09-15", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5 Codex", "open_weights": false, "provider": { "npm": "@ai-sdk/openai" }, "reasoning": true, "release_date": "2025-09-15", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5-nano": { "attachment": true, "cost": { "cache_read": 0.005, "input": 0.05, "output": 0.4 }, "description": "GPT-5 Nano is an AI model provided by opencode.", "family": "gpt-nano", "id": "gpt-5-nano", "knowledge": "2024-05-30", "last_updated": "2025-08-07", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5 Nano", "open_weights": false, "provider": { "npm": "@ai-sdk/openai" }, "reasoning": true, "release_date": "2025-08-07", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.1": { "attachment": true, "cost": { "cache_read": 0.107, "input": 1.07, "output": 8.5 }, "description": "GPT-5.1 is an AI model provided by opencode.", "family": "gpt", "id": "gpt-5.1", "knowledge": "2024-09-30", "last_updated": "2025-11-13", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.1", "open_weights": false, "provider": { "npm": "@ai-sdk/openai" }, "reasoning": true, "release_date": "2025-11-13", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.1-codex": { "attachment": true, "cost": { "cache_read": 0.107, "input": 1.07, "output": 8.5 }, "description": "GPT-5.1 Codex is an AI model provided by opencode.", "family": "gpt-codex", "id": "gpt-5.1-codex", "knowledge": "2024-09-30", "last_updated": "2025-11-13", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.1 Codex", "open_weights": false, "provider": { "npm": "@ai-sdk/openai" }, "reasoning": true, "release_date": "2025-11-13", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.1-codex-max": { "attachment": true, "cost": { "cache_read": 0.125, "input": 1.25, "output": 10 }, "description": "GPT-5.1 Codex Max is an AI model provided by opencode.", "family": "gpt-codex", "id": "gpt-5.1-codex-max", "knowledge": "2024-09-30", "last_updated": "2025-11-13", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.1 Codex Max", "open_weights": false, "provider": { "npm": "@ai-sdk/openai" }, "reasoning": true, "release_date": "2025-11-13", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.1-codex-mini": { "attachment": true, "cost": { "cache_read": 0.025, "input": 0.25, "output": 2 }, "description": "GPT-5.1 Codex Mini is an AI model provided by opencode.", "family": "gpt-codex", "id": "gpt-5.1-codex-mini", "knowledge": "2024-09-30", "last_updated": "2025-11-13", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.1 Codex Mini", "open_weights": false, "provider": { "npm": "@ai-sdk/openai" }, "reasoning": true, "release_date": "2025-11-13", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.2": { "attachment": true, "cost": { "cache_read": 0.175, "input": 1.75, "output": 14 }, "description": "GPT-5.2 is an AI model provided by opencode.", "family": "gpt", "id": "gpt-5.2", "knowledge": "2025-08-31", "last_updated": "2025-12-11", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.2", "open_weights": false, "provider": { "npm": "@ai-sdk/openai" }, "reasoning": true, "release_date": "2025-12-11", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.2-codex": { "attachment": true, "cost": { "cache_read": 0.175, "input": 1.75, "output": 14 }, "description": "GPT-5.2 Codex is an AI model provided by opencode.", "family": "gpt-codex", "id": "gpt-5.2-codex", "knowledge": "2025-08-31", "last_updated": "2026-01-14", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.2 Codex", "open_weights": false, "provider": { "npm": "@ai-sdk/openai" }, "reasoning": true, "release_date": "2026-01-14", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.3-codex": { "attachment": true, "cost": { "cache_read": 0.175, "input": 1.75, "output": 14 }, "description": "GPT-5.3 Codex is an AI model provided by opencode.", "family": "gpt-codex", "id": "gpt-5.3-codex", "knowledge": "2025-08-31", "last_updated": "2026-02-24", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.3 Codex", "open_weights": false, "provider": { "npm": "@ai-sdk/openai" }, "reasoning": true, "release_date": "2026-02-24", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.3-codex-spark": { "attachment": false, "cost": { "cache_read": 0.175, "input": 1.75, "output": 14 }, "description": "GPT-5.3 Codex Spark is an AI model provided by opencode.", "family": "gpt-codex-spark", "id": "gpt-5.3-codex-spark", "knowledge": "2025-08-31", "last_updated": "2026-02-12", "limit": { "context": 128000, "input": 128000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT-5.3 Codex Spark", "open_weights": false, "provider": { "npm": "@ai-sdk/openai" }, "reasoning": true, "release_date": "2026-02-12", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.4": { "attachment": true, "cost": { "cache_read": 0.25, "context_over_200k": { "cache_read": 0.5, "input": 5, "output": 22.5 }, "input": 2.5, "output": 15, "tiers": [ { "cache_read": 0.5, "input": 5, "output": 22.5, "tier": { "size": 272000, "type": "context" } } ] }, "description": "GPT-5.4 is an AI model provided by opencode.", "family": "gpt", "id": "gpt-5.4", "knowledge": "2025-08-31", "last_updated": "2026-03-05", "limit": { "context": 1050000, "input": 922000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.4", "open_weights": false, "provider": { "npm": "@ai-sdk/openai" }, "reasoning": true, "release_date": "2026-03-05", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.4-mini": { "attachment": true, "cost": { "cache_read": 0.075, "input": 0.75, "output": 4.5 }, "description": "GPT-5.4 Mini is an AI model provided by opencode.", "family": "gpt-mini", "id": "gpt-5.4-mini", "knowledge": "2025-08-31", "last_updated": "2026-03-17", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.4 Mini", "open_weights": false, "provider": { "npm": "@ai-sdk/openai" }, "reasoning": true, "release_date": "2026-03-17", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.4-nano": { "attachment": true, "cost": { "cache_read": 0.02, "input": 0.2, "output": 1.25 }, "description": "GPT-5.4 Nano is an AI model provided by opencode.", "family": "gpt-nano", "id": "gpt-5.4-nano", "knowledge": "2025-08-31", "last_updated": "2026-03-17", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.4 Nano", "open_weights": false, "provider": { "npm": "@ai-sdk/openai" }, "reasoning": true, "release_date": "2026-03-17", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.4-pro": { "attachment": true, "cost": { "cache_read": 30, "input": 30, "output": 180 }, "description": "GPT-5.4 Pro is an AI model provided by opencode.", "family": "gpt-pro", "id": "gpt-5.4-pro", "knowledge": "2025-08-31", "last_updated": "2026-03-05", "limit": { "context": 1050000, "input": 922000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.4 Pro", "open_weights": false, "provider": { "npm": "@ai-sdk/openai" }, "reasoning": true, "release_date": "2026-03-05", "structured_output": false, "temperature": false, "tool_call": true }, "gpt-5.5": { "attachment": true, "cost": { "cache_read": 0.5, "context_over_200k": { "cache_read": 1, "input": 10, "output": 45 }, "input": 5, "output": 30, "tiers": [ { "cache_read": 1, "input": 10, "output": 45, "tier": { "size": 272000, "type": "context" } } ] }, "description": "GPT-5.5 is an AI model provided by opencode.", "family": "gpt", "id": "gpt-5.5", "knowledge": "2025-12-01", "last_updated": "2026-04-23", "limit": { "context": 1050000, "input": 922000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.5", "open_weights": false, "provider": { "npm": "@ai-sdk/openai" }, "reasoning": true, "release_date": "2026-04-23", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.5-pro": { "attachment": true, "cost": { "cache_read": 30, "input": 30, "output": 180 }, "description": "GPT-5.5 Pro is an AI model provided by opencode.", "family": "gpt-pro", "id": "gpt-5.5-pro", "knowledge": "2025-12-01", "last_updated": "2026-04-24", "limit": { "context": 1050000, "input": 922000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.5 Pro", "open_weights": false, "provider": { "npm": "@ai-sdk/openai" }, "reasoning": true, "release_date": "2026-04-24", "structured_output": false, "temperature": false, "tool_call": true }, "grok-code": { "attachment": true, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "Grok Code Fast 1 is an AI model provided by opencode.", "family": "grok", "id": "grok-code", "last_updated": "2025-08-20", "limit": { "context": 256000, "output": 256000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok Code Fast 1", "open_weights": false, "reasoning": true, "release_date": "2025-08-20", "status": "deprecated", "temperature": true, "tool_call": true }, "hy3-preview-free": { "attachment": false, "cost": { "cache_read": 0, "input": 0, "output": 0 }, "description": "Hy3 preview Free is an AI model provided by opencode.", "family": "hy3-free", "id": "hy3-preview-free", "knowledge": "2025-06", "last_updated": "2026-04-20", "limit": { "context": 256000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Hy3 preview Free", "open_weights": true, "reasoning": true, "release_date": "2026-04-20", "status": "deprecated", "temperature": true, "tool_call": true }, "kimi-k2": { "attachment": false, "cost": { "cache_read": 0.4, "input": 0.4, "output": 2.5 }, "description": "Kimi K2 is an AI model provided by opencode.", "family": "kimi", "id": "kimi-k2", "knowledge": "2024-10", "last_updated": "2025-09-05", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2", "open_weights": true, "reasoning": false, "release_date": "2025-09-05", "status": "deprecated", "temperature": true, "tool_call": true }, "kimi-k2-thinking": { "attachment": false, "cost": { "cache_read": 0.4, "input": 0.4, "output": 2.5 }, "description": "Kimi K2 Thinking is an AI model provided by opencode.", "family": "kimi-thinking", "id": "kimi-k2-thinking", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-10", "last_updated": "2025-09-05", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 Thinking", "open_weights": true, "reasoning": true, "release_date": "2025-09-05", "status": "deprecated", "temperature": true, "tool_call": true }, "kimi-k2.5": { "attachment": true, "cost": { "cache_read": 0.08, "input": 0.6, "output": 3 }, "description": "Kimi K2.5 is an AI model provided by opencode.", "family": "kimi", "id": "kimi-k2.5", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-10", "last_updated": "2026-01-27", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Kimi K2.5", "open_weights": true, "reasoning": true, "release_date": "2026-01-27", "temperature": true, "tool_call": true }, "kimi-k2.5-free": { "attachment": true, "cost": { "cache_read": 0, "input": 0, "output": 0 }, "description": "Kimi K2.5 Free is an AI model provided by opencode.", "family": "kimi-free", "id": "kimi-k2.5-free", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-10", "last_updated": "2026-01-27", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Kimi K2.5 Free", "open_weights": true, "reasoning": true, "release_date": "2026-01-27", "status": "deprecated", "temperature": true, "tool_call": true }, "kimi-k2.6": { "attachment": true, "cost": { "cache_read": 0.16, "input": 0.95, "output": 4 }, "description": "Kimi K2.6 is an AI model provided by opencode.", "family": "kimi", "id": "kimi-k2.6", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-10", "last_updated": "2026-04-21", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Kimi K2.6", "open_weights": true, "reasoning": true, "release_date": "2026-04-21", "temperature": true, "tool_call": true }, "ling-2.6-flash-free": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Ling 2.6 Flash Free is an AI model provided by opencode.", "family": "ling-flash-free", "id": "ling-2.6-flash-free", "knowledge": "2025-06", "last_updated": "2026-04-21", "limit": { "context": 262100, "output": 32800 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Ling 2.6 Flash Free", "open_weights": true, "reasoning": false, "release_date": "2026-04-21", "status": "deprecated", "temperature": true, "tool_call": true }, "mimo-v2-flash-free": { "attachment": false, "cost": { "cache_read": 0, "input": 0, "output": 0 }, "description": "MiMo V2 Flash Free is an AI model provided by opencode.", "family": "mimo-flash-free", "id": "mimo-v2-flash-free", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-12", "last_updated": "2025-12-16", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiMo V2 Flash Free", "open_weights": true, "reasoning": true, "release_date": "2025-12-16", "status": "deprecated", "temperature": true, "tool_call": true }, "mimo-v2-omni-free": { "attachment": true, "cost": { "cache_read": 0, "input": 0, "output": 0 }, "description": "MiMo V2 Omni Free is an AI model provided by opencode.", "family": "mimo-omni-free", "id": "mimo-v2-omni-free", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-12", "last_updated": "2026-03-18", "limit": { "context": 262144, "output": 64000 }, "modalities": { "input": [ "text", "image", "audio", "pdf" ], "output": [ "text" ] }, "name": "MiMo V2 Omni Free", "open_weights": true, "reasoning": true, "release_date": "2026-03-18", "status": "deprecated", "temperature": true, "tool_call": true }, "mimo-v2-pro-free": { "attachment": true, "cost": { "cache_read": 0, "input": 0, "output": 0 }, "description": "MiMo V2 Pro Free is an AI model provided by opencode.", "family": "mimo-pro-free", "id": "mimo-v2-pro-free", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-12", "last_updated": "2026-03-18", "limit": { "context": 1048576, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiMo V2 Pro Free", "open_weights": true, "reasoning": true, "release_date": "2026-03-18", "status": "deprecated", "temperature": true, "tool_call": true }, "minimax-m2.1": { "attachment": false, "cost": { "cache_read": 0.1, "input": 0.3, "output": 1.2 }, "description": "MiniMax M2.1 is an AI model provided by opencode.", "family": "minimax", "id": "minimax-m2.1", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-01", "last_updated": "2025-12-23", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M2.1", "open_weights": true, "reasoning": true, "release_date": "2025-12-23", "status": "deprecated", "temperature": true, "tool_call": true }, "minimax-m2.1-free": { "attachment": false, "cost": { "cache_read": 0, "input": 0, "output": 0 }, "description": "MiniMax M2.1 Free is an AI model provided by opencode.", "family": "minimax-free", "id": "minimax-m2.1-free", "knowledge": "2025-01", "last_updated": "2025-12-23", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M2.1 Free", "open_weights": true, "provider": { "npm": "@ai-sdk/anthropic" }, "reasoning": true, "release_date": "2025-12-23", "status": "deprecated", "temperature": true, "tool_call": true }, "minimax-m2.5": { "attachment": false, "cost": { "cache_read": 0.06, "input": 0.3, "output": 1.2 }, "description": "MiniMax M2.5 is an AI model provided by opencode.", "family": "minimax", "id": "minimax-m2.5", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-01", "last_updated": "2026-02-12", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M2.5", "open_weights": true, "reasoning": true, "release_date": "2026-02-12", "temperature": true, "tool_call": true }, "minimax-m2.5-free": { "attachment": false, "cost": { "cache_read": 0, "input": 0, "output": 0 }, "description": "MiniMax M2.5 Free is an AI model provided by opencode.", "family": "minimax-free", "id": "minimax-m2.5-free", "knowledge": "2025-01", "last_updated": "2026-02-12", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M2.5 Free", "open_weights": true, "provider": { "npm": "@ai-sdk/anthropic" }, "reasoning": true, "release_date": "2026-02-12", "temperature": true, "tool_call": true }, "minimax-m2.7": { "attachment": false, "cost": { "cache_read": 0.06, "input": 0.3, "output": 1.2 }, "description": "MiniMax M2.7 is an AI model provided by opencode.", "family": "minimax", "id": "minimax-m2.7", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-01", "last_updated": "2026-03-18", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M2.7", "open_weights": true, "reasoning": true, "release_date": "2026-03-18", "temperature": true, "tool_call": true }, "nemotron-3-super-free": { "attachment": false, "cost": { "cache_read": 0, "input": 0, "output": 0 }, "description": "Nemotron 3 Super Free is an AI model provided by opencode.", "family": "nemotron-free", "id": "nemotron-3-super-free", "interleaved": { "field": "reasoning_content" }, "knowledge": "2026-02", "last_updated": "2026-03-11", "limit": { "context": 204800, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Nemotron 3 Super Free", "open_weights": true, "reasoning": true, "release_date": "2026-03-11", "temperature": true, "tool_call": true }, "qwen3-coder": { "attachment": false, "cost": { "input": 0.45, "output": 1.8 }, "description": "Qwen3 Coder is an AI model provided by opencode.", "family": "qwen", "id": "qwen3-coder", "knowledge": "2025-04", "last_updated": "2025-07-23", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Coder", "open_weights": true, "reasoning": false, "release_date": "2025-07-23", "status": "deprecated", "temperature": true, "tool_call": true }, "qwen3.5-plus": { "attachment": true, "cost": { "cache_read": 0.02, "cache_write": 0.25, "input": 0.2, "output": 1.2 }, "description": "Qwen3.5 Plus is an AI model provided by opencode.", "family": "qwen3.5", "id": "qwen3.5-plus", "knowledge": "2025-04", "last_updated": "2026-02-16", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen3.5 Plus", "open_weights": false, "provider": { "npm": "@ai-sdk/anthropic" }, "reasoning": true, "release_date": "2026-02-16", "temperature": true, "tool_call": true }, "qwen3.6-plus": { "attachment": true, "cost": { "cache_read": 0.05, "cache_write": 0.625, "input": 0.5, "output": 3 }, "description": "Qwen3.6 Plus is an AI model provided by opencode.", "family": "qwen3.6", "id": "qwen3.6-plus", "knowledge": "2025-04", "last_updated": "2026-04-02", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen3.6 Plus", "open_weights": false, "provider": { "npm": "@ai-sdk/anthropic" }, "reasoning": true, "release_date": "2026-04-02", "temperature": true, "tool_call": true }, "qwen3.6-plus-free": { "attachment": false, "cost": { "cache_read": 0, "input": 0, "output": 0 }, "description": "Qwen3.6 Plus Free is an AI model provided by opencode.", "family": "qwen-free", "id": "qwen3.6-plus-free", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-12", "last_updated": "2026-03-30", "limit": { "context": 1048576, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3.6 Plus Free", "open_weights": false, "reasoning": true, "release_date": "2026-03-30", "status": "deprecated", "temperature": true, "tool_call": true }, "ring-2.6-1t-free": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Ring 2.6 1T Free is an AI model provided by opencode.", "family": "ring-1t-free", "id": "ring-2.6-1t-free", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-06", "last_updated": "2026-05-08", "limit": { "context": 262000, "output": 66000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Ring 2.6 1T Free", "open_weights": true, "reasoning": true, "release_date": "2026-05-08", "temperature": true, "tool_call": true }, "trinity-large-preview-free": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Trinity Large Preview is an AI model provided by opencode.", "family": "trinity", "id": "trinity-large-preview-free", "knowledge": "2025-06", "last_updated": "2026-01-28", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Trinity Large Preview", "open_weights": true, "reasoning": false, "release_date": "2026-01-28", "status": "deprecated", "temperature": true, "tool_call": true } }, "name": "OpenCode Zen", "npm": "@ai-sdk/openai-compatible" }, "opencode-go": { "api": "https://opencode.ai/zen/go/v1", "doc": "https://opencode.ai/docs/zen", "env": [ "OPENCODE_API_KEY" ], "iconURL": "https://models.dev/logos/opencode-go.svg", "id": "opencode-go", "models": { "deepseek-v4-flash": { "attachment": false, "cost": { "cache_read": 0.0028, "input": 0.14, "output": 0.28 }, "description": "DeepSeek V4 Flash is an AI model provided by opencode-go.", "family": "deepseek-flash", "id": "deepseek-v4-flash", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-05", "last_updated": "2026-04-24", "limit": { "context": 1000000, "output": 384000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V4 Flash", "open_weights": true, "reasoning": true, "release_date": "2026-04-24", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek-v4-pro": { "attachment": false, "cost": { "cache_read": 0.0145, "input": 1.74, "output": 3.48 }, "description": "DeepSeek V4 Pro is an AI model provided by opencode-go.", "family": "deepseek-thinking", "id": "deepseek-v4-pro", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-05", "last_updated": "2026-04-24", "limit": { "context": 1000000, "output": 384000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V4 Pro", "open_weights": true, "reasoning": true, "release_date": "2026-04-24", "structured_output": true, "temperature": true, "tool_call": true }, "glm-5": { "attachment": false, "cost": { "cache_read": 0.2, "input": 1, "output": 3.2 }, "description": "GLM-5 is an AI model provided by opencode-go.", "family": "glm", "id": "glm-5", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-04", "last_updated": "2026-02-11", "limit": { "context": 202752, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5", "open_weights": true, "reasoning": true, "release_date": "2026-02-11", "temperature": true, "tool_call": true }, "glm-5.1": { "attachment": false, "cost": { "cache_read": 0.26, "input": 1.4, "output": 4.4 }, "description": "GLM-5.1 is an AI model provided by opencode-go.", "family": "glm", "id": "glm-5.1", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-04", "last_updated": "2026-04-07", "limit": { "context": 202752, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5.1", "open_weights": true, "reasoning": true, "release_date": "2026-04-07", "temperature": true, "tool_call": true }, "kimi-k2.5": { "attachment": true, "cost": { "cache_read": 0.1, "input": 0.6, "output": 3 }, "description": "Kimi K2.5 is an AI model provided by opencode-go.", "family": "kimi-k2.5", "id": "kimi-k2.5", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-10", "last_updated": "2026-01-27", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Kimi K2.5", "open_weights": true, "reasoning": true, "release_date": "2026-01-27", "temperature": true, "tool_call": true }, "kimi-k2.6": { "attachment": true, "cost": { "cache_read": 0.16, "input": 0.95, "output": 4 }, "description": "Kimi K2.6 is an AI model provided by opencode-go.", "family": "kimi-k2.6", "id": "kimi-k2.6", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-10", "last_updated": "2026-04-21", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Kimi K2.6", "open_weights": true, "reasoning": true, "release_date": "2026-04-21", "temperature": true, "tool_call": true }, "mimo-v2-omni": { "attachment": true, "cost": { "cache_read": 0.08, "input": 0.4, "output": 2 }, "description": "MiMo V2 Omni is an AI model provided by opencode-go.", "family": "mimo-v2-omni", "id": "mimo-v2-omni", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-12", "last_updated": "2026-03-18", "limit": { "context": 262144, "output": 128000 }, "modalities": { "input": [ "text", "image", "audio", "pdf" ], "output": [ "text" ] }, "name": "MiMo V2 Omni", "open_weights": true, "reasoning": true, "release_date": "2026-03-18", "status": "deprecated", "temperature": true, "tool_call": true }, "mimo-v2-pro": { "attachment": true, "cost": { "cache_read": 0.2, "context_over_200k": { "cache_read": 0.4, "input": 2, "output": 6 }, "input": 1, "output": 3, "tiers": [ { "cache_read": 0.4, "input": 2, "output": 6, "tier": { "size": 256000, "type": "context" } } ] }, "description": "MiMo V2 Pro is an AI model provided by opencode-go.", "family": "mimo-v2-pro", "id": "mimo-v2-pro", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-12", "last_updated": "2026-03-18", "limit": { "context": 1048576, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiMo V2 Pro", "open_weights": true, "reasoning": true, "release_date": "2026-03-18", "status": "deprecated", "temperature": true, "tool_call": true }, "mimo-v2.5": { "attachment": true, "cost": { "cache_read": 0.08, "context_over_200k": { "cache_read": 0.16, "input": 0.8, "output": 4 }, "input": 0.4, "output": 2, "tiers": [ { "cache_read": 0.16, "input": 0.8, "output": 4, "tier": { "size": 256000, "type": "context" } } ] }, "description": "MiMo V2.5 is an AI model provided by opencode-go.", "family": "mimo-v2.5", "id": "mimo-v2.5", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-12", "last_updated": "2026-04-22", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "name": "MiMo V2.5", "open_weights": true, "reasoning": true, "release_date": "2026-04-22", "temperature": true, "tool_call": true }, "mimo-v2.5-pro": { "attachment": true, "cost": { "cache_read": 0.2, "context_over_200k": { "cache_read": 0.4, "input": 2, "output": 6 }, "input": 1, "output": 3, "tiers": [ { "cache_read": 0.4, "input": 2, "output": 6, "tier": { "size": 256000, "type": "context" } } ] }, "description": "MiMo V2.5 Pro is an AI model provided by opencode-go.", "family": "mimo-v2.5-pro", "id": "mimo-v2.5-pro", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-12", "last_updated": "2026-04-22", "limit": { "context": 1048576, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiMo V2.5 Pro", "open_weights": true, "reasoning": true, "release_date": "2026-04-22", "temperature": true, "tool_call": true }, "minimax-m2.5": { "attachment": false, "cost": { "cache_read": 0.03, "input": 0.3, "output": 1.2 }, "description": "MiniMax M2.5 is an AI model provided by opencode-go.", "family": "minimax-m2.5", "id": "minimax-m2.5", "knowledge": "2025-01", "last_updated": "2026-02-12", "limit": { "context": 204800, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M2.5", "open_weights": true, "provider": { "npm": "@ai-sdk/anthropic" }, "reasoning": true, "release_date": "2026-02-12", "temperature": true, "tool_call": true }, "minimax-m2.7": { "attachment": false, "cost": { "cache_read": 0.06, "input": 0.3, "output": 1.2 }, "description": "MiniMax M2.7 is an AI model provided by opencode-go.", "family": "minimax-m2.7", "id": "minimax-m2.7", "knowledge": "2025-01", "last_updated": "2026-03-18", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M2.7", "open_weights": true, "provider": { "npm": "@ai-sdk/anthropic" }, "reasoning": true, "release_date": "2026-03-18", "temperature": true, "tool_call": true }, "qwen3.5-plus": { "attachment": true, "cost": { "cache_read": 0.02, "cache_write": 0.25, "input": 0.2, "output": 1.2 }, "description": "Qwen3.5 Plus is an AI model provided by opencode-go.", "family": "qwen3.5", "id": "qwen3.5-plus", "knowledge": "2025-04", "last_updated": "2026-02-16", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen3.5 Plus", "open_weights": false, "provider": { "npm": "@ai-sdk/anthropic" }, "reasoning": true, "release_date": "2026-02-16", "temperature": true, "tool_call": true }, "qwen3.6-plus": { "attachment": true, "cost": { "cache_read": 0.05, "cache_write": 0.625, "input": 0.5, "output": 3 }, "description": "Qwen3.6 Plus is an AI model provided by opencode-go.", "family": "qwen3.6", "id": "qwen3.6-plus", "knowledge": "2025-04", "last_updated": "2026-04-02", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen3.6 Plus", "open_weights": false, "provider": { "npm": "@ai-sdk/anthropic" }, "reasoning": true, "release_date": "2026-04-02", "temperature": true, "tool_call": true } }, "name": "OpenCode Go", "npm": "@ai-sdk/openai-compatible" }, "openrouter": { "api": "https://openrouter.ai/api/v1", "doc": "https://openrouter.ai/models", "env": [ "OPENROUTER_API_KEY" ], "iconURL": "https://models.dev/logos/openrouter.svg", "id": "openrouter", "lobeIcon": "OpenRouter.Color", "models": { "anthropic/claude-3.5-haiku": { "attachment": true, "cost": { "cache_read": 0.08, "cache_write": 1, "input": 0.8, "output": 4 }, "description": "Claude Haiku 3.5 is an AI model provided by openrouter.", "family": "claude-haiku", "id": "anthropic/claude-3.5-haiku", "knowledge": "2024-07-31", "last_updated": "2024-10-22", "limit": { "context": 200000, "output": 8192 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Haiku 3.5", "open_weights": false, "reasoning": false, "release_date": "2024-10-22", "temperature": true, "tool_call": true }, "anthropic/claude-3.7-sonnet": { "attachment": true, "cost": { "cache_read": 1.5, "cache_write": 18.75, "input": 15, "output": 75 }, "description": "Claude Sonnet 3.7 is an AI model provided by openrouter.", "family": "claude-sonnet", "id": "anthropic/claude-3.7-sonnet", "knowledge": "2024-01", "last_updated": "2025-02-19", "limit": { "context": 200000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 3.7", "open_weights": false, "reasoning": true, "release_date": "2025-02-19", "temperature": true, "tool_call": true }, "anthropic/claude-haiku-4.5": { "attachment": true, "cost": { "cache_read": 0.1, "cache_write": 1.25, "input": 1, "output": 5 }, "description": "Claude Haiku 4.5 is an AI model provided by openrouter.", "family": "claude-haiku", "id": "anthropic/claude-haiku-4.5", "knowledge": "2025-02-28", "last_updated": "2025-10-15", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Haiku 4.5", "open_weights": false, "reasoning": true, "release_date": "2025-10-15", "structured_output": true, "temperature": true, "tool_call": true }, "anthropic/claude-opus-4": { "attachment": true, "cost": { "cache_read": 1.5, "cache_write": 18.75, "input": 15, "output": 75 }, "description": "Claude Opus 4 is an AI model provided by openrouter.", "family": "claude-opus", "id": "anthropic/claude-opus-4", "knowledge": "2025-03-31", "last_updated": "2025-05-22", "limit": { "context": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4", "open_weights": false, "reasoning": true, "release_date": "2025-05-22", "temperature": true, "tool_call": true }, "anthropic/claude-opus-4.1": { "attachment": true, "cost": { "cache_read": 1.5, "cache_write": 18.75, "input": 15, "output": 75 }, "description": "Claude Opus 4.1 is an AI model provided by openrouter.", "family": "claude-opus", "id": "anthropic/claude-opus-4.1", "knowledge": "2025-03-31", "last_updated": "2025-08-05", "limit": { "context": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.1", "open_weights": false, "reasoning": true, "release_date": "2025-08-05", "structured_output": true, "temperature": true, "tool_call": true }, "anthropic/claude-opus-4.5": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "input": 5, "output": 25 }, "description": "Claude Opus 4.5 is an AI model provided by openrouter.", "family": "claude-opus", "id": "anthropic/claude-opus-4.5", "knowledge": "2025-05-30", "last_updated": "2025-11-24", "limit": { "context": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.5", "open_weights": false, "reasoning": true, "release_date": "2025-11-24", "structured_output": true, "temperature": true, "tool_call": true }, "anthropic/claude-opus-4.6": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "context_over_200k": { "cache_read": 1, "cache_write": 12.5, "input": 10, "output": 37.5 }, "input": 5, "output": 25, "tiers": [ { "cache_read": 1, "cache_write": 12.5, "input": 10, "output": 37.5, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Claude Opus 4.6 is an AI model provided by openrouter.", "family": "claude-opus", "id": "anthropic/claude-opus-4.6", "knowledge": "2025-05-31", "last_updated": "2026-02-05", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.6", "open_weights": false, "reasoning": true, "release_date": "2026-02-05", "structured_output": true, "temperature": true, "tool_call": true }, "anthropic/claude-opus-4.7": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "context_over_200k": { "cache_read": 1, "cache_write": 12.5, "input": 10, "output": 37.5 }, "input": 5, "output": 25, "tiers": [ { "cache_read": 1, "cache_write": 12.5, "input": 10, "output": 37.5, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Claude Opus 4.7 is an AI model provided by openrouter.", "family": "claude-opus", "id": "anthropic/claude-opus-4.7", "knowledge": "2026-01-31", "last_updated": "2026-04-16", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.7", "open_weights": false, "reasoning": true, "release_date": "2026-04-16", "structured_output": true, "temperature": false, "tool_call": true }, "anthropic/claude-sonnet-4": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "context_over_200k": { "cache_read": 0.6, "cache_write": 7.5, "input": 6, "output": 22.5 }, "input": 3, "output": 15, "tiers": [ { "cache_read": 0.6, "cache_write": 7.5, "input": 6, "output": 22.5, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Claude Sonnet 4 is an AI model provided by openrouter.", "family": "claude-sonnet", "id": "anthropic/claude-sonnet-4", "knowledge": "2025-03-31", "last_updated": "2025-05-22", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4", "open_weights": false, "reasoning": true, "release_date": "2025-05-22", "temperature": true, "tool_call": true }, "anthropic/claude-sonnet-4.5": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "context_over_200k": { "cache_read": 0.6, "cache_write": 7.5, "input": 6, "output": 22.5 }, "input": 3, "output": 15, "tiers": [ { "cache_read": 0.6, "cache_write": 7.5, "input": 6, "output": 22.5, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Claude Sonnet 4.5 is an AI model provided by openrouter.", "family": "claude-sonnet", "id": "anthropic/claude-sonnet-4.5", "knowledge": "2025-07-31", "last_updated": "2025-09-29", "limit": { "context": 1000000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.5", "open_weights": false, "reasoning": true, "release_date": "2025-09-29", "structured_output": true, "temperature": true, "tool_call": true }, "anthropic/claude-sonnet-4.6": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "context_over_200k": { "cache_read": 0.6, "cache_write": 7.5, "input": 6, "output": 22.5 }, "input": 3, "output": 15, "tiers": [ { "cache_read": 0.6, "cache_write": 7.5, "input": 6, "output": 22.5, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Claude Sonnet 4.6 is an AI model provided by openrouter.", "family": "claude-sonnet", "id": "anthropic/claude-sonnet-4.6", "knowledge": "2025-08-31", "last_updated": "2026-02-17", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.6", "open_weights": false, "reasoning": true, "release_date": "2026-02-17", "structured_output": true, "temperature": true, "tool_call": true }, "arcee-ai/trinity-large-preview:free": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Trinity Large Preview is an AI model provided by openrouter.", "family": "trinity", "id": "arcee-ai/trinity-large-preview:free", "knowledge": "2025-06", "last_updated": "2026-01-28", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Trinity Large Preview", "open_weights": true, "reasoning": false, "release_date": "2026-01-28", "structured_output": true, "temperature": true, "tool_call": true }, "arcee-ai/trinity-large-thinking": { "attachment": false, "cost": { "input": 0.22, "output": 0.85 }, "description": "Trinity Large Thinking is an AI model provided by openrouter.", "family": "trinity", "id": "arcee-ai/trinity-large-thinking", "last_updated": "2026-04-03", "limit": { "context": 262144, "output": 80000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Trinity Large Thinking", "open_weights": true, "reasoning": true, "release_date": "2026-04-01", "temperature": true, "tool_call": true }, "black-forest-labs/flux.2-flex": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "FLUX.2 Flex is an AI model provided by openrouter.", "family": "flux", "id": "black-forest-labs/flux.2-flex", "knowledge": "2025-06", "last_updated": "2026-01-31", "limit": { "context": 67344, "output": 67344 }, "modalities": { "input": [ "image", "text" ], "output": [ "image" ] }, "name": "FLUX.2 Flex", "open_weights": false, "reasoning": false, "release_date": "2025-11-25", "temperature": true, "tool_call": false }, "black-forest-labs/flux.2-klein-4b": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "FLUX.2 Klein 4B is an AI model provided by openrouter.", "family": "flux", "id": "black-forest-labs/flux.2-klein-4b", "knowledge": "2025-06", "last_updated": "2026-01-31", "limit": { "context": 40960, "output": 40960 }, "modalities": { "input": [ "image", "text" ], "output": [ "image" ] }, "name": "FLUX.2 Klein 4B", "open_weights": true, "reasoning": false, "release_date": "2026-01-14", "temperature": true, "tool_call": false }, "black-forest-labs/flux.2-max": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "FLUX.2 Max is an AI model provided by openrouter.", "family": "flux", "id": "black-forest-labs/flux.2-max", "knowledge": "2025-06", "last_updated": "2026-01-31", "limit": { "context": 46864, "output": 46864 }, "modalities": { "input": [ "image", "text" ], "output": [ "image" ] }, "name": "FLUX.2 Max", "open_weights": false, "reasoning": false, "release_date": "2025-12-16", "temperature": true, "tool_call": false }, "black-forest-labs/flux.2-pro": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "FLUX.2 Pro is an AI model provided by openrouter.", "family": "flux", "id": "black-forest-labs/flux.2-pro", "knowledge": "2025-06", "last_updated": "2026-01-31", "limit": { "context": 46864, "output": 46864 }, "modalities": { "input": [ "image", "text" ], "output": [ "image" ] }, "name": "FLUX.2 Pro", "open_weights": false, "reasoning": false, "release_date": "2025-11-25", "temperature": true, "tool_call": false }, "bytedance-seed/seedream-4.5": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Seedream 4.5 is an AI model provided by openrouter.", "family": "seed", "id": "bytedance-seed/seedream-4.5", "knowledge": "2025-06", "last_updated": "2026-01-31", "limit": { "context": 4096, "output": 4096 }, "modalities": { "input": [ "image", "text" ], "output": [ "image" ] }, "name": "Seedream 4.5", "open_weights": true, "reasoning": false, "release_date": "2025-12-23", "temperature": true, "tool_call": false }, "cognitivecomputations/dolphin-mistral-24b-venice-edition:free": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Uncensored (free) is an AI model provided by openrouter.", "family": "mistral", "id": "cognitivecomputations/dolphin-mistral-24b-venice-edition:free", "knowledge": "2025-06", "last_updated": "2026-01-31", "limit": { "context": 32768, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Uncensored (free)", "open_weights": true, "reasoning": false, "release_date": "2025-07-09", "structured_output": true, "temperature": true, "tool_call": false }, "deepseek/deepseek-chat-v3-0324": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "DeepSeek V3 0324 is an AI model provided by openrouter.", "family": "deepseek", "id": "deepseek/deepseek-chat-v3-0324", "knowledge": "2024-10", "last_updated": "2025-03-24", "limit": { "context": 16384, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3 0324", "open_weights": true, "reasoning": false, "release_date": "2025-03-24", "structured_output": true, "temperature": true, "tool_call": false }, "deepseek/deepseek-chat-v3.1": { "attachment": false, "cost": { "input": 0.2, "output": 0.8 }, "description": "DeepSeek-V3.1 is an AI model provided by openrouter.", "family": "deepseek", "id": "deepseek/deepseek-chat-v3.1", "knowledge": "2025-07", "last_updated": "2025-08-21", "limit": { "context": 163840, "output": 163840 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek-V3.1", "open_weights": true, "reasoning": true, "release_date": "2025-08-21", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek/deepseek-r1": { "attachment": false, "cost": { "input": 0.7, "output": 2.5 }, "description": "DeepSeek: R1 is an AI model provided by openrouter.", "family": "deepseek-thinking", "id": "deepseek/deepseek-r1", "knowledge": "2024-07", "last_updated": "2025-01-20", "limit": { "context": 64000, "output": 16000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek: R1", "open_weights": true, "reasoning": true, "release_date": "2025-01-20", "structured_output": false, "temperature": true, "tool_call": true }, "deepseek/deepseek-r1-distill-llama-70b": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "DeepSeek R1 Distill Llama 70B is an AI model provided by openrouter.", "family": "deepseek-thinking", "id": "deepseek/deepseek-r1-distill-llama-70b", "knowledge": "2024-10", "last_updated": "2025-01-23", "limit": { "context": 8192, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek R1 Distill Llama 70B", "open_weights": true, "reasoning": true, "release_date": "2025-01-23", "structured_output": true, "temperature": true, "tool_call": false }, "deepseek/deepseek-v3.1-terminus": { "attachment": false, "cost": { "input": 0.27, "output": 1 }, "description": "DeepSeek V3.1 Terminus is an AI model provided by openrouter.", "family": "deepseek", "id": "deepseek/deepseek-v3.1-terminus", "knowledge": "2025-07", "last_updated": "2025-09-22", "limit": { "context": 131072, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3.1 Terminus", "open_weights": true, "reasoning": true, "release_date": "2025-09-22", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek/deepseek-v3.1-terminus:exacto": { "attachment": false, "cost": { "input": 0.27, "output": 1 }, "description": "DeepSeek V3.1 Terminus (exacto) is an AI model provided by openrouter.", "family": "deepseek", "id": "deepseek/deepseek-v3.1-terminus:exacto", "knowledge": "2025-07", "last_updated": "2025-09-22", "limit": { "context": 131072, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3.1 Terminus (exacto)", "open_weights": true, "reasoning": true, "release_date": "2025-09-22", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek/deepseek-v3.2": { "attachment": false, "cost": { "input": 0.28, "output": 0.4 }, "description": "DeepSeek V3.2 is an AI model provided by openrouter.", "family": "deepseek", "id": "deepseek/deepseek-v3.2", "knowledge": "2024-07", "last_updated": "2025-12-01", "limit": { "context": 163840, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3.2", "open_weights": true, "reasoning": true, "release_date": "2025-12-01", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek/deepseek-v3.2-speciale": { "attachment": false, "cost": { "input": 0.27, "output": 0.41 }, "description": "DeepSeek V3.2 Speciale is an AI model provided by openrouter.", "family": "deepseek", "id": "deepseek/deepseek-v3.2-speciale", "knowledge": "2024-07", "last_updated": "2025-12-01", "limit": { "context": 163840, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3.2 Speciale", "open_weights": true, "reasoning": true, "release_date": "2025-12-01", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek/deepseek-v4-flash": { "attachment": false, "cost": { "cache_read": 0.028, "input": 0.14, "output": 0.28 }, "description": "DeepSeek V4 Flash is an AI model provided by openrouter.", "family": "deepseek-flash", "id": "deepseek/deepseek-v4-flash", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-05", "last_updated": "2026-04-24", "limit": { "context": 1048576, "output": 393216 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V4 Flash", "open_weights": true, "reasoning": true, "release_date": "2026-04-24", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek/deepseek-v4-pro": { "attachment": false, "cost": { "cache_read": 0.145, "input": 1.74, "output": 3.48 }, "description": "DeepSeek V4 Pro is an AI model provided by openrouter.", "family": "deepseek-thinking", "id": "deepseek/deepseek-v4-pro", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-05", "last_updated": "2026-04-24", "limit": { "context": 1048576, "output": 393216 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V4 Pro", "open_weights": true, "reasoning": true, "release_date": "2026-04-24", "structured_output": true, "temperature": true, "tool_call": true }, "google/gemini-2.0-flash-001": { "attachment": true, "cost": { "cache_read": 0.025, "input": 0.1, "output": 0.4 }, "description": "Gemini 2.0 Flash is an AI model provided by openrouter.", "family": "gemini-flash", "id": "google/gemini-2.0-flash-001", "knowledge": "2024-06", "last_updated": "2024-12-11", "limit": { "context": 1048576, "output": 8192 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.0 Flash", "open_weights": false, "reasoning": false, "release_date": "2024-12-11", "structured_output": true, "temperature": true, "tool_call": true }, "google/gemini-2.5-flash": { "attachment": true, "cost": { "cache_read": 0.0375, "input": 0.3, "output": 2.5 }, "description": "Gemini 2.5 Flash is an AI model provided by openrouter.", "family": "gemini-flash", "id": "google/gemini-2.5-flash", "knowledge": "2025-01", "last_updated": "2025-07-17", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Flash", "open_weights": false, "reasoning": true, "release_date": "2025-07-17", "structured_output": true, "temperature": true, "tool_call": true }, "google/gemini-2.5-flash-lite": { "attachment": true, "cost": { "cache_read": 0.025, "input": 0.1, "output": 0.4 }, "description": "Gemini 2.5 Flash Lite is an AI model provided by openrouter.", "family": "gemini-flash-lite", "id": "google/gemini-2.5-flash-lite", "knowledge": "2025-01", "last_updated": "2025-06-17", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Flash Lite", "open_weights": false, "reasoning": true, "release_date": "2025-06-17", "structured_output": true, "temperature": true, "tool_call": true }, "google/gemini-2.5-flash-lite-preview-09-2025": { "attachment": true, "cost": { "cache_read": 0.025, "input": 0.1, "output": 0.4 }, "description": "Gemini 2.5 Flash Lite Preview 09-25 is an AI model provided by openrouter.", "family": "gemini-flash-lite", "id": "google/gemini-2.5-flash-lite-preview-09-2025", "knowledge": "2025-01", "last_updated": "2025-09-25", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Flash Lite Preview 09-25", "open_weights": false, "reasoning": true, "release_date": "2025-09-25", "structured_output": true, "temperature": true, "tool_call": true }, "google/gemini-2.5-flash-preview-09-2025": { "attachment": true, "cost": { "cache_read": 0.031, "input": 0.3, "output": 2.5 }, "description": "Gemini 2.5 Flash Preview 09-25 is an AI model provided by openrouter.", "family": "gemini-flash", "id": "google/gemini-2.5-flash-preview-09-2025", "knowledge": "2025-01", "last_updated": "2025-09-25", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Flash Preview 09-25", "open_weights": false, "reasoning": true, "release_date": "2025-09-25", "structured_output": true, "temperature": true, "tool_call": true }, "google/gemini-2.5-pro": { "attachment": true, "cost": { "cache_read": 0.125, "context_over_200k": { "cache_read": 0.25, "input": 2.5, "output": 15 }, "input": 1.25, "output": 10, "tiers": [ { "cache_read": 0.25, "input": 2.5, "output": 15, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Gemini 2.5 Pro is an AI model provided by openrouter.", "family": "gemini-pro", "id": "google/gemini-2.5-pro", "knowledge": "2025-01", "last_updated": "2025-06-05", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Pro", "open_weights": false, "reasoning": true, "release_date": "2025-03-20", "structured_output": true, "temperature": true, "tool_call": true }, "google/gemini-2.5-pro-preview-05-06": { "attachment": true, "cost": { "cache_read": 0.31, "input": 1.25, "output": 10 }, "description": "Gemini 2.5 Pro Preview 05-06 is an AI model provided by openrouter.", "family": "gemini-pro", "id": "google/gemini-2.5-pro-preview-05-06", "knowledge": "2025-01", "last_updated": "2025-05-06", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Pro Preview 05-06", "open_weights": false, "reasoning": true, "release_date": "2025-05-06", "structured_output": true, "temperature": true, "tool_call": true }, "google/gemini-2.5-pro-preview-06-05": { "attachment": true, "cost": { "cache_read": 0.31, "input": 1.25, "output": 10 }, "description": "Gemini 2.5 Pro Preview 06-05 is an AI model provided by openrouter.", "family": "gemini-pro", "id": "google/gemini-2.5-pro-preview-06-05", "knowledge": "2025-01", "last_updated": "2025-06-05", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Pro Preview 06-05", "open_weights": false, "reasoning": true, "release_date": "2025-06-05", "structured_output": true, "temperature": true, "tool_call": true }, "google/gemini-3-flash-preview": { "attachment": true, "cost": { "cache_read": 0.05, "input": 0.5, "output": 3 }, "description": "Gemini 3 Flash Preview is an AI model provided by openrouter.", "family": "gemini-flash", "id": "google/gemini-3-flash-preview", "interleaved": { "field": "reasoning_details" }, "knowledge": "2025-01", "last_updated": "2025-12-17", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 3 Flash Preview", "open_weights": false, "reasoning": true, "release_date": "2025-12-17", "structured_output": true, "temperature": true, "tool_call": true }, "google/gemini-3-pro-preview": { "attachment": true, "cost": { "input": 2, "output": 12 }, "description": "Gemini 3 Pro Preview is an AI model provided by openrouter.", "family": "gemini-pro", "id": "google/gemini-3-pro-preview", "interleaved": { "field": "reasoning_details" }, "knowledge": "2025-01", "last_updated": "2025-11", "limit": { "context": 1050000, "output": 66000 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 3 Pro Preview", "open_weights": false, "reasoning": true, "release_date": "2025-11-18", "structured_output": true, "temperature": true, "tool_call": true }, "google/gemini-3.1-flash-image-preview": { "attachment": true, "cost": { "input": 0.5, "output": 3 }, "description": "Gemini 3.1 Flash Image Preview (Nano Banana 2) is an AI model provided by openrouter.", "family": "gemini-flash", "id": "google/gemini-3.1-flash-image-preview", "knowledge": "2025-01", "last_updated": "2026-02-26", "limit": { "context": 65536, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text", "image" ] }, "name": "Gemini 3.1 Flash Image Preview (Nano Banana 2)", "open_weights": false, "reasoning": true, "release_date": "2026-02-26", "structured_output": true, "temperature": true, "tool_call": false }, "google/gemini-3.1-flash-lite-preview": { "attachment": true, "cost": { "cache_read": 0.025, "cache_write": 0.083, "input": 0.25, "input_audio": 0.5, "output": 1.5, "output_audio": 0.5, "reasoning": 1.5 }, "description": "Gemini 3.1 Flash Lite Preview is an AI model provided by openrouter.", "family": "gemini-flash-lite", "id": "google/gemini-3.1-flash-lite-preview", "last_updated": "2026-03-03", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "video", "pdf", "audio" ], "output": [ "text" ] }, "name": "Gemini 3.1 Flash Lite Preview", "open_weights": false, "reasoning": true, "release_date": "2026-03-03", "structured_output": true, "temperature": true, "tool_call": true }, "google/gemini-3.1-pro-preview": { "attachment": true, "cost": { "context_over_200k": { "cache_read": 0.4, "input": 4, "output": 18 }, "input": 2, "output": 12, "reasoning": 12, "tiers": [ { "cache_read": 0.4, "input": 4, "output": 18, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Gemini 3.1 Pro Preview is an AI model provided by openrouter.", "family": "gemini-pro", "id": "google/gemini-3.1-pro-preview", "interleaved": { "field": "reasoning_details" }, "knowledge": "2025-01", "last_updated": "2026-02-19", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 3.1 Pro Preview", "open_weights": false, "reasoning": true, "release_date": "2026-02-19", "structured_output": true, "temperature": true, "tool_call": true }, "google/gemini-3.1-pro-preview-customtools": { "attachment": true, "cost": { "context_over_200k": { "cache_read": 0.4, "input": 4, "output": 18 }, "input": 2, "output": 12, "reasoning": 12, "tiers": [ { "cache_read": 0.4, "input": 4, "output": 18, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Gemini 3.1 Pro Preview Custom Tools is an AI model provided by openrouter.", "family": "gemini-pro", "id": "google/gemini-3.1-pro-preview-customtools", "interleaved": { "field": "reasoning_details" }, "knowledge": "2025-01", "last_updated": "2026-02-19", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 3.1 Pro Preview Custom Tools", "open_weights": false, "reasoning": true, "release_date": "2026-02-19", "structured_output": true, "temperature": true, "tool_call": true }, "google/gemma-2-9b-it": { "attachment": false, "cost": { "input": 0.03, "output": 0.09 }, "description": "Gemma 2 9B is an AI model provided by openrouter.", "family": "gemma", "id": "google/gemma-2-9b-it", "knowledge": "2024-06", "last_updated": "2024-06-28", "limit": { "context": 8192, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Gemma 2 9B", "open_weights": true, "reasoning": false, "release_date": "2024-06-28", "temperature": true, "tool_call": false }, "google/gemma-3-12b-it": { "attachment": true, "cost": { "input": 0.03, "output": 0.1 }, "description": "Gemma 3 12B is an AI model provided by openrouter.", "family": "gemma", "id": "google/gemma-3-12b-it", "knowledge": "2024-10", "last_updated": "2025-03-13", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemma 3 12B", "open_weights": true, "reasoning": false, "release_date": "2025-03-13", "structured_output": true, "temperature": true, "tool_call": false }, "google/gemma-3-12b-it:free": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Gemma 3 12B (free) is an AI model provided by openrouter.", "family": "gemma", "id": "google/gemma-3-12b-it:free", "knowledge": "2024-10", "last_updated": "2025-03-13", "limit": { "context": 32768, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemma 3 12B (free)", "open_weights": true, "reasoning": false, "release_date": "2025-03-13", "temperature": true, "tool_call": false }, "google/gemma-3-27b-it": { "attachment": true, "cost": { "input": 0.04, "output": 0.15 }, "description": "Gemma 3 27B is an AI model provided by openrouter.", "family": "gemma", "id": "google/gemma-3-27b-it", "knowledge": "2024-10", "last_updated": "2025-03-12", "limit": { "context": 96000, "output": 96000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemma 3 27B", "open_weights": true, "reasoning": false, "release_date": "2025-03-12", "structured_output": true, "temperature": true, "tool_call": true }, "google/gemma-3-27b-it:free": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Gemma 3 27B (free) is an AI model provided by openrouter.", "family": "gemma", "id": "google/gemma-3-27b-it:free", "knowledge": "2024-10", "last_updated": "2025-03-12", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemma 3 27B (free)", "open_weights": true, "reasoning": false, "release_date": "2025-03-12", "temperature": true, "tool_call": true }, "google/gemma-3-4b-it": { "attachment": true, "cost": { "input": 0.01703, "output": 0.06815 }, "description": "Gemma 3 4B is an AI model provided by openrouter.", "family": "gemma", "id": "google/gemma-3-4b-it", "knowledge": "2024-10", "last_updated": "2025-03-13", "limit": { "context": 96000, "output": 96000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemma 3 4B", "open_weights": true, "reasoning": false, "release_date": "2025-03-13", "temperature": true, "tool_call": false }, "google/gemma-3-4b-it:free": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Gemma 3 4B (free) is an AI model provided by openrouter.", "family": "gemma", "id": "google/gemma-3-4b-it:free", "knowledge": "2024-10", "last_updated": "2025-03-13", "limit": { "context": 32768, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemma 3 4B (free)", "open_weights": true, "reasoning": false, "release_date": "2025-03-13", "temperature": true, "tool_call": false }, "google/gemma-3n-e2b-it:free": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Gemma 3n 2B (free) is an AI model provided by openrouter.", "family": "gemma", "id": "google/gemma-3n-e2b-it:free", "knowledge": "2024-06", "last_updated": "2025-07-09", "limit": { "context": 8192, "output": 2000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Gemma 3n 2B (free)", "open_weights": true, "reasoning": false, "release_date": "2025-07-09", "temperature": true, "tool_call": false }, "google/gemma-3n-e4b-it": { "attachment": true, "cost": { "input": 0.02, "output": 0.04 }, "description": "Gemma 3n 4B is an AI model provided by openrouter.", "family": "gemma", "id": "google/gemma-3n-e4b-it", "knowledge": "2024-06", "last_updated": "2025-05-20", "limit": { "context": 32768, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Gemma 3n 4B", "open_weights": true, "reasoning": false, "release_date": "2025-05-20", "temperature": true, "tool_call": false }, "google/gemma-3n-e4b-it:free": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Gemma 3n 4B (free) is an AI model provided by openrouter.", "family": "gemma", "id": "google/gemma-3n-e4b-it:free", "knowledge": "2024-06", "last_updated": "2025-05-20", "limit": { "context": 8192, "output": 2000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Gemma 3n 4B (free)", "open_weights": true, "reasoning": false, "release_date": "2025-05-20", "temperature": true, "tool_call": false }, "google/gemma-4-26b-a4b-it": { "attachment": true, "cost": { "input": 0.13, "output": 0.4 }, "description": "Gemma 4 26B A4B is an AI model provided by openrouter.", "family": "gemma", "id": "google/gemma-4-26b-a4b-it", "knowledge": "2025-01", "last_updated": "2026-04-03", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Gemma 4 26B A4B", "open_weights": true, "reasoning": true, "release_date": "2026-04-03", "structured_output": true, "temperature": true, "tool_call": true }, "google/gemma-4-26b-a4b-it:free": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Gemma 4 26B A4B (free) is an AI model provided by openrouter.", "family": "gemma", "id": "google/gemma-4-26b-a4b-it:free", "knowledge": "2025-01", "last_updated": "2026-04-03", "limit": { "context": 262144, "output": 32768 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Gemma 4 26B A4B (free)", "open_weights": true, "reasoning": true, "release_date": "2026-04-03", "structured_output": true, "temperature": true, "tool_call": true }, "google/gemma-4-31b-it": { "attachment": true, "cost": { "input": 0.14, "output": 0.4 }, "description": "Gemma 4 31B is an AI model provided by openrouter.", "family": "gemma", "id": "google/gemma-4-31b-it", "knowledge": "2025-01", "last_updated": "2026-04-02", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Gemma 4 31B", "open_weights": true, "reasoning": true, "release_date": "2026-04-02", "structured_output": true, "temperature": true, "tool_call": true }, "google/gemma-4-31b-it:free": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Gemma 4 31B (free) is an AI model provided by openrouter.", "family": "gemma", "id": "google/gemma-4-31b-it:free", "knowledge": "2025-01", "last_updated": "2026-04-02", "limit": { "context": 262144, "output": 32768 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Gemma 4 31B (free)", "open_weights": true, "reasoning": true, "release_date": "2026-04-02", "structured_output": true, "temperature": true, "tool_call": true }, "inception/mercury-2": { "attachment": false, "cost": { "cache_read": 0.025, "input": 0.25, "output": 0.75 }, "description": "Mercury 2 is an AI model provided by openrouter.", "family": "mercury", "id": "inception/mercury-2", "last_updated": "2026-03-04", "limit": { "context": 128000, "output": 50000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mercury 2", "open_weights": false, "reasoning": true, "release_date": "2026-03-04", "structured_output": true, "temperature": true, "tool_call": true }, "inception/mercury-edit-2": { "attachment": false, "cost": { "cache_read": 0.025, "input": 0.25, "output": 0.75 }, "description": "Mercury Edit 2 is an AI model provided by openrouter.", "id": "inception/mercury-edit-2", "last_updated": "2026-03-30", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mercury Edit 2", "open_weights": false, "reasoning": true, "release_date": "2026-03-30", "temperature": true, "tool_call": false }, "liquid/lfm-2.5-1.2b-instruct:free": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "LFM2.5-1.2B-Instruct (free) is an AI model provided by openrouter.", "family": "liquid", "id": "liquid/lfm-2.5-1.2b-instruct:free", "knowledge": "2025-06", "last_updated": "2026-01-28", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "LFM2.5-1.2B-Instruct (free)", "open_weights": true, "reasoning": false, "release_date": "2026-01-20", "temperature": true, "tool_call": false }, "liquid/lfm-2.5-1.2b-thinking:free": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "LFM2.5-1.2B-Thinking (free) is an AI model provided by openrouter.", "family": "liquid", "id": "liquid/lfm-2.5-1.2b-thinking:free", "knowledge": "2025-06", "last_updated": "2026-01-28", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "LFM2.5-1.2B-Thinking (free)", "open_weights": true, "reasoning": true, "release_date": "2026-01-20", "temperature": true, "tool_call": false }, "meta-llama/llama-3.2-11b-vision-instruct": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Llama 3.2 11B Vision Instruct is an AI model provided by openrouter.", "family": "llama", "id": "meta-llama/llama-3.2-11b-vision-instruct", "knowledge": "2023-12", "last_updated": "2024-09-25", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Llama 3.2 11B Vision Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-09-25", "temperature": true, "tool_call": false }, "meta-llama/llama-3.2-3b-instruct:free": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Llama 3.2 3B Instruct (free) is an AI model provided by openrouter.", "family": "llama", "id": "meta-llama/llama-3.2-3b-instruct:free", "knowledge": "2023-12", "last_updated": "2024-09-25", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Llama 3.2 3B Instruct (free)", "open_weights": true, "reasoning": false, "release_date": "2024-09-25", "temperature": true, "tool_call": false }, "meta-llama/llama-3.3-70b-instruct:free": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Llama 3.3 70B Instruct (free) is an AI model provided by openrouter.", "family": "llama", "id": "meta-llama/llama-3.3-70b-instruct:free", "knowledge": "2024-12", "last_updated": "2024-12-06", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B Instruct (free)", "open_weights": true, "reasoning": false, "release_date": "2024-12-06", "structured_output": true, "temperature": true, "tool_call": true }, "minimax/minimax-01": { "attachment": true, "cost": { "input": 0.2, "output": 1.1 }, "description": "MiniMax-01 is an AI model provided by openrouter.", "family": "minimax", "id": "minimax/minimax-01", "last_updated": "2025-01-15", "limit": { "context": 1000000, "output": 1000000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "MiniMax-01", "open_weights": true, "reasoning": true, "release_date": "2025-01-15", "temperature": true, "tool_call": true }, "minimax/minimax-m1": { "attachment": false, "cost": { "input": 0.4, "output": 2.2 }, "description": "MiniMax M1 is an AI model provided by openrouter.", "family": "minimax", "id": "minimax/minimax-m1", "last_updated": "2025-06-17", "limit": { "context": 1000000, "output": 40000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M1", "open_weights": true, "reasoning": true, "release_date": "2025-06-17", "temperature": true, "tool_call": true }, "minimax/minimax-m2": { "attachment": false, "cost": { "cache_read": 0.28, "cache_write": 1.15, "input": 0.28, "output": 1.15 }, "description": "MiniMax M2 is an AI model provided by openrouter.", "family": "minimax", "id": "minimax/minimax-m2", "interleaved": { "field": "reasoning_details" }, "last_updated": "2025-10-23", "limit": { "context": 196600, "output": 118000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M2", "open_weights": true, "reasoning": true, "release_date": "2025-10-23", "structured_output": true, "temperature": true, "tool_call": true }, "minimax/minimax-m2.1": { "attachment": false, "cost": { "input": 0.3, "output": 1.2 }, "description": "MiniMax M2.1 is an AI model provided by openrouter.", "family": "minimax", "id": "minimax/minimax-m2.1", "interleaved": { "field": "reasoning_details" }, "last_updated": "2025-12-23", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M2.1", "open_weights": true, "reasoning": true, "release_date": "2025-12-23", "structured_output": true, "temperature": true, "tool_call": true }, "minimax/minimax-m2.5": { "attachment": false, "cost": { "cache_read": 0.03, "input": 0.3, "output": 1.2 }, "description": "MiniMax M2.5 is an AI model provided by openrouter.", "family": "minimax", "id": "minimax/minimax-m2.5", "interleaved": { "field": "reasoning_details" }, "last_updated": "2026-02-12", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M2.5", "open_weights": true, "reasoning": true, "release_date": "2026-02-12", "structured_output": true, "temperature": true, "tool_call": true }, "minimax/minimax-m2.5:free": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "MiniMax M2.5 (free) is an AI model provided by openrouter.", "family": "minimax", "id": "minimax/minimax-m2.5:free", "interleaved": { "field": "reasoning_details" }, "last_updated": "2026-02-12", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M2.5 (free)", "open_weights": true, "reasoning": true, "release_date": "2026-02-12", "structured_output": true, "temperature": true, "tool_call": true }, "minimax/minimax-m2.7": { "attachment": false, "cost": { "cache_read": 0.06, "cache_write": 0.375, "input": 0.3, "output": 1.2 }, "description": "MiniMax M2.7 is an AI model provided by openrouter.", "family": "minimax", "id": "minimax/minimax-m2.7", "last_updated": "2026-03-18", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M2.7", "open_weights": true, "reasoning": true, "release_date": "2026-03-18", "temperature": true, "tool_call": true }, "mistralai/codestral-2508": { "attachment": false, "cost": { "input": 0.3, "output": 0.9 }, "description": "Codestral 2508 is an AI model provided by openrouter.", "family": "codestral", "id": "mistralai/codestral-2508", "knowledge": "2025-05", "last_updated": "2025-08-01", "limit": { "context": 256000, "output": 256000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Codestral 2508", "open_weights": true, "reasoning": false, "release_date": "2025-08-01", "structured_output": true, "temperature": true, "tool_call": true }, "mistralai/devstral-2512": { "attachment": false, "cost": { "input": 0.15, "output": 0.6 }, "description": "Devstral 2 2512 is an AI model provided by openrouter.", "family": "devstral", "id": "mistralai/devstral-2512", "knowledge": "2025-12", "last_updated": "2025-09-12", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Devstral 2 2512", "open_weights": true, "reasoning": false, "release_date": "2025-09-12", "structured_output": true, "temperature": true, "tool_call": true }, "mistralai/devstral-medium-2507": { "attachment": false, "cost": { "input": 0.4, "output": 2 }, "description": "Devstral Medium is an AI model provided by openrouter.", "family": "devstral", "id": "mistralai/devstral-medium-2507", "knowledge": "2025-05", "last_updated": "2025-07-10", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Devstral Medium", "open_weights": true, "reasoning": false, "release_date": "2025-07-10", "structured_output": true, "temperature": true, "tool_call": true }, "mistralai/devstral-small-2505": { "attachment": false, "cost": { "input": 0.06, "output": 0.12 }, "description": "Devstral Small is an AI model provided by openrouter.", "family": "devstral", "id": "mistralai/devstral-small-2505", "knowledge": "2025-05", "last_updated": "2025-05-07", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Devstral Small", "open_weights": true, "reasoning": false, "release_date": "2025-05-07", "temperature": true, "tool_call": true }, "mistralai/devstral-small-2507": { "attachment": false, "cost": { "input": 0.1, "output": 0.3 }, "description": "Devstral Small 1.1 is an AI model provided by openrouter.", "family": "devstral", "id": "mistralai/devstral-small-2507", "knowledge": "2025-05", "last_updated": "2025-07-10", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Devstral Small 1.1", "open_weights": true, "reasoning": false, "release_date": "2025-07-10", "structured_output": true, "temperature": true, "tool_call": true }, "mistralai/mistral-medium-3": { "attachment": true, "cost": { "input": 0.4, "output": 2 }, "description": "Mistral Medium 3 is an AI model provided by openrouter.", "family": "mistral-medium", "id": "mistralai/mistral-medium-3", "knowledge": "2025-05", "last_updated": "2025-05-07", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Mistral Medium 3", "open_weights": false, "reasoning": false, "release_date": "2025-05-07", "structured_output": true, "temperature": true, "tool_call": true }, "mistralai/mistral-medium-3.1": { "attachment": true, "cost": { "input": 0.4, "output": 2 }, "description": "Mistral Medium 3.1 is an AI model provided by openrouter.", "family": "mistral-medium", "id": "mistralai/mistral-medium-3.1", "knowledge": "2025-05", "last_updated": "2025-08-12", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Mistral Medium 3.1", "open_weights": false, "reasoning": false, "release_date": "2025-08-12", "structured_output": true, "temperature": true, "tool_call": true }, "mistralai/mistral-small-2603": { "attachment": true, "cost": { "input": 0.15, "output": 0.6 }, "description": "Mistral Small 4 is an AI model provided by openrouter.", "family": "mistral-small", "id": "mistralai/mistral-small-2603", "knowledge": "2025-06", "last_updated": "2026-03-16", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Mistral Small 4", "open_weights": true, "reasoning": true, "release_date": "2026-03-16", "temperature": true, "tool_call": true }, "mistralai/mistral-small-3.1-24b-instruct": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Mistral Small 3.1 24B Instruct is an AI model provided by openrouter.", "family": "mistral-small", "id": "mistralai/mistral-small-3.1-24b-instruct", "knowledge": "2024-10", "last_updated": "2025-03-17", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Mistral Small 3.1 24B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-03-17", "structured_output": true, "temperature": true, "tool_call": true }, "mistralai/mistral-small-3.2-24b-instruct": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Mistral Small 3.2 24B Instruct is an AI model provided by openrouter.", "family": "mistral-small", "id": "mistralai/mistral-small-3.2-24b-instruct", "knowledge": "2024-10", "last_updated": "2025-06-20", "limit": { "context": 96000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Mistral Small 3.2 24B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-06-20", "structured_output": true, "temperature": true, "tool_call": true }, "moonshotai/kimi-k2": { "attachment": false, "cost": { "input": 0.55, "output": 2.2 }, "description": "Kimi K2 is an AI model provided by openrouter.", "family": "kimi", "id": "moonshotai/kimi-k2", "knowledge": "2024-10", "last_updated": "2025-07-11", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2", "open_weights": true, "reasoning": false, "release_date": "2025-07-11", "temperature": true, "tool_call": true }, "moonshotai/kimi-k2-0905": { "attachment": false, "cost": { "input": 0.6, "output": 2.5 }, "description": "Kimi K2 Instruct 0905 is an AI model provided by openrouter.", "family": "kimi", "id": "moonshotai/kimi-k2-0905", "knowledge": "2024-10", "last_updated": "2025-09-05", "limit": { "context": 262144, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 Instruct 0905", "open_weights": true, "reasoning": false, "release_date": "2025-09-05", "structured_output": true, "temperature": true, "tool_call": true }, "moonshotai/kimi-k2-0905:exacto": { "attachment": false, "cost": { "input": 0.6, "output": 2.5 }, "description": "Kimi K2 Instruct 0905 (exacto) is an AI model provided by openrouter.", "family": "kimi", "id": "moonshotai/kimi-k2-0905:exacto", "knowledge": "2024-10", "last_updated": "2025-09-05", "limit": { "context": 262144, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 Instruct 0905 (exacto)", "open_weights": true, "reasoning": false, "release_date": "2025-09-05", "structured_output": true, "temperature": true, "tool_call": true }, "moonshotai/kimi-k2-thinking": { "attachment": false, "cost": { "cache_read": 0.15, "input": 0.6, "output": 2.5 }, "description": "Kimi K2 Thinking is an AI model provided by openrouter.", "family": "kimi-thinking", "id": "moonshotai/kimi-k2-thinking", "interleaved": { "field": "reasoning_details" }, "knowledge": "2024-08", "last_updated": "2025-11-06", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 Thinking", "open_weights": true, "reasoning": true, "release_date": "2025-11-06", "structured_output": true, "temperature": true, "tool_call": true }, "moonshotai/kimi-k2.5": { "attachment": true, "cost": { "cache_read": 0.1, "input": 0.6, "output": 3 }, "description": "Kimi K2.5 is an AI model provided by openrouter.", "family": "kimi", "id": "moonshotai/kimi-k2.5", "interleaved": { "field": "reasoning_details" }, "knowledge": "2025-01", "last_updated": "2026-01-27", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Kimi K2.5", "open_weights": true, "reasoning": true, "release_date": "2026-01-27", "structured_output": true, "temperature": true, "tool_call": true }, "moonshotai/kimi-k2.6": { "attachment": true, "cost": { "cache_read": 0.16, "input": 0.95, "output": 4 }, "description": "Kimi K2.6 is an AI model provided by openrouter.", "family": "kimi", "id": "moonshotai/kimi-k2.6", "interleaved": { "field": "reasoning_details" }, "last_updated": "2026-04-20", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Kimi K2.6", "open_weights": true, "reasoning": true, "release_date": "2026-04-20", "structured_output": true, "temperature": true, "tool_call": true }, "nousresearch/hermes-3-llama-3.1-405b:free": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Hermes 3 405B Instruct (free) is an AI model provided by openrouter.", "family": "hermes", "id": "nousresearch/hermes-3-llama-3.1-405b:free", "knowledge": "2023-12", "last_updated": "2024-08-16", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Hermes 3 405B Instruct (free)", "open_weights": true, "reasoning": true, "release_date": "2024-08-16", "temperature": true, "tool_call": false }, "nousresearch/hermes-4-405b": { "attachment": false, "cost": { "input": 1, "output": 3 }, "description": "Hermes 4 405B is an AI model provided by openrouter.", "family": "hermes", "id": "nousresearch/hermes-4-405b", "knowledge": "2023-12", "last_updated": "2025-08-25", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Hermes 4 405B", "open_weights": true, "reasoning": true, "release_date": "2025-08-25", "temperature": true, "tool_call": true }, "nousresearch/hermes-4-70b": { "attachment": false, "cost": { "input": 0.13, "output": 0.4 }, "description": "Hermes 4 70B is an AI model provided by openrouter.", "family": "hermes", "id": "nousresearch/hermes-4-70b", "knowledge": "2023-12", "last_updated": "2025-08-25", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Hermes 4 70B", "open_weights": true, "reasoning": true, "release_date": "2025-08-25", "structured_output": true, "temperature": true, "tool_call": true }, "nvidia/nemotron-3-nano-30b-a3b:free": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Nemotron 3 Nano 30B A3B (free) is an AI model provided by openrouter.", "family": "nemotron", "id": "nvidia/nemotron-3-nano-30b-a3b:free", "knowledge": "2025-11", "last_updated": "2026-01-31", "limit": { "context": 256000, "output": 256000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Nemotron 3 Nano 30B A3B (free)", "open_weights": true, "reasoning": true, "release_date": "2025-12-14", "structured_output": true, "temperature": true, "tool_call": true }, "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Nemotron 3 Nano Omni (free) is an AI model provided by openrouter.", "family": "nemotron", "id": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free", "last_updated": "2026-04-28", "limit": { "context": 256000, "output": 65536 }, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text" ] }, "name": "Nemotron 3 Nano Omni (free)", "open_weights": true, "reasoning": true, "release_date": "2026-04-28", "structured_output": true, "temperature": true, "tool_call": true }, "nvidia/nemotron-3-super-120b-a12b": { "attachment": false, "cost": { "input": 0.1, "output": 0.5 }, "description": "Nemotron 3 Super is an AI model provided by openrouter.", "family": "nemotron", "id": "nvidia/nemotron-3-super-120b-a12b", "knowledge": "2024-04", "last_updated": "2026-03-11", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Nemotron 3 Super", "open_weights": true, "reasoning": true, "release_date": "2026-03-11", "temperature": true, "tool_call": true }, "nvidia/nemotron-3-super-120b-a12b:free": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Nemotron 3 Super (free) is an AI model provided by openrouter.", "family": "nemotron", "id": "nvidia/nemotron-3-super-120b-a12b:free", "knowledge": "2024-04", "last_updated": "2026-03-11", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Nemotron 3 Super (free)", "open_weights": true, "reasoning": true, "release_date": "2026-03-11", "temperature": true, "tool_call": true }, "nvidia/nemotron-nano-12b-v2-vl:free": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Nemotron Nano 12B 2 VL (free) is an AI model provided by openrouter.", "family": "nemotron", "id": "nvidia/nemotron-nano-12b-v2-vl:free", "knowledge": "2025-11", "last_updated": "2026-01-31", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Nemotron Nano 12B 2 VL (free)", "open_weights": true, "reasoning": true, "release_date": "2025-10-28", "temperature": true, "tool_call": true }, "nvidia/nemotron-nano-9b-v2": { "attachment": false, "cost": { "input": 0.04, "output": 0.16 }, "description": "nvidia-nemotron-nano-9b-v2 is an AI model provided by openrouter.", "family": "nemotron", "id": "nvidia/nemotron-nano-9b-v2", "knowledge": "2024-09", "last_updated": "2025-08-18", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "nvidia-nemotron-nano-9b-v2", "open_weights": true, "reasoning": true, "release_date": "2025-08-18", "temperature": true, "tool_call": true }, "nvidia/nemotron-nano-9b-v2:free": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Nemotron Nano 9B V2 (free) is an AI model provided by openrouter.", "family": "nemotron", "id": "nvidia/nemotron-nano-9b-v2:free", "knowledge": "2024-09", "last_updated": "2025-08-18", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Nemotron Nano 9B V2 (free)", "open_weights": true, "reasoning": true, "release_date": "2025-09-05", "structured_output": true, "temperature": true, "tool_call": true }, "openai/gpt-4.1": { "attachment": true, "cost": { "cache_read": 0.5, "input": 2, "output": 8 }, "description": "GPT-4.1 is an AI model provided by openrouter.", "family": "gpt", "id": "openai/gpt-4.1", "knowledge": "2024-04", "last_updated": "2025-04-14", "limit": { "context": 1047576, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4.1", "open_weights": false, "reasoning": false, "release_date": "2025-04-14", "structured_output": true, "temperature": true, "tool_call": true }, "openai/gpt-4.1-mini": { "attachment": true, "cost": { "cache_read": 0.1, "input": 0.4, "output": 1.6 }, "description": "GPT-4.1 Mini is an AI model provided by openrouter.", "family": "gpt-mini", "id": "openai/gpt-4.1-mini", "knowledge": "2024-04", "last_updated": "2025-04-14", "limit": { "context": 1047576, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4.1 Mini", "open_weights": false, "reasoning": false, "release_date": "2025-04-14", "structured_output": true, "temperature": true, "tool_call": true }, "openai/gpt-4o-mini": { "attachment": true, "cost": { "cache_read": 0.08, "input": 0.15, "output": 0.6 }, "description": "GPT-4o-mini is an AI model provided by openrouter.", "family": "gpt-mini", "id": "openai/gpt-4o-mini", "knowledge": "2024-10", "last_updated": "2024-07-18", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4o-mini", "open_weights": false, "reasoning": false, "release_date": "2024-07-18", "structured_output": true, "temperature": true, "tool_call": true }, "openai/gpt-5": { "attachment": true, "cost": { "input": 1.25, "output": 10 }, "description": "GPT-5 is an AI model provided by openrouter.", "family": "gpt", "id": "openai/gpt-5", "knowledge": "2024-10-01", "last_updated": "2025-08-07", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "structured_output": true, "temperature": true, "tool_call": true }, "openai/gpt-5-chat": { "attachment": true, "cost": { "input": 1.25, "output": 10 }, "description": "GPT-5 Chat (latest) is an AI model provided by openrouter.", "family": "gpt-codex", "id": "openai/gpt-5-chat", "knowledge": "2024-09-30", "last_updated": "2025-08-07", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5 Chat (latest)", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "structured_output": true, "temperature": true, "tool_call": false }, "openai/gpt-5-codex": { "attachment": true, "cost": { "cache_read": 0.125, "input": 1.25, "output": 10 }, "description": "GPT-5 Codex is an AI model provided by openrouter.", "family": "gpt-codex", "id": "openai/gpt-5-codex", "knowledge": "2024-10-01", "last_updated": "2025-09-15", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5 Codex", "open_weights": false, "reasoning": true, "release_date": "2025-09-15", "structured_output": true, "temperature": true, "tool_call": true }, "openai/gpt-5-image": { "attachment": true, "cost": { "cache_read": 1.25, "input": 5, "output": 10 }, "description": "GPT-5 Image is an AI model provided by openrouter.", "family": "gpt", "id": "openai/gpt-5-image", "knowledge": "2024-10-01", "last_updated": "2025-10-14", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text", "image" ] }, "name": "GPT-5 Image", "open_weights": false, "reasoning": true, "release_date": "2025-10-14", "structured_output": true, "temperature": true, "tool_call": true }, "openai/gpt-5-mini": { "attachment": true, "cost": { "input": 0.25, "output": 2 }, "description": "GPT-5 Mini is an AI model provided by openrouter.", "family": "gpt-mini", "id": "openai/gpt-5-mini", "knowledge": "2024-10-01", "last_updated": "2025-08-07", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5 Mini", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "structured_output": true, "temperature": true, "tool_call": true }, "openai/gpt-5-nano": { "attachment": true, "cost": { "input": 0.05, "output": 0.4 }, "description": "GPT-5 Nano is an AI model provided by openrouter.", "family": "gpt-nano", "id": "openai/gpt-5-nano", "knowledge": "2024-10-01", "last_updated": "2025-08-07", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5 Nano", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "structured_output": true, "temperature": true, "tool_call": true }, "openai/gpt-5-pro": { "attachment": true, "cost": { "input": 15, "output": 120 }, "description": "GPT-5 Pro is an AI model provided by openrouter.", "family": "gpt-pro", "id": "openai/gpt-5-pro", "knowledge": "2024-09-30", "last_updated": "2025-10-06", "limit": { "context": 400000, "output": 272000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5 Pro", "open_weights": false, "reasoning": true, "release_date": "2025-10-06", "structured_output": true, "temperature": false, "tool_call": true }, "openai/gpt-5.1": { "attachment": true, "cost": { "cache_read": 0.125, "input": 1.25, "output": 10 }, "description": "GPT-5.1 is an AI model provided by openrouter.", "family": "gpt", "id": "openai/gpt-5.1", "knowledge": "2024-09-30", "last_updated": "2025-11-13", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.1", "open_weights": false, "reasoning": true, "release_date": "2025-11-13", "structured_output": true, "temperature": true, "tool_call": true }, "openai/gpt-5.1-chat": { "attachment": true, "cost": { "cache_read": 0.125, "input": 1.25, "output": 10 }, "description": "GPT-5.1 Chat is an AI model provided by openrouter.", "family": "gpt-codex", "id": "openai/gpt-5.1-chat", "knowledge": "2024-09-30", "last_updated": "2025-11-13", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.1 Chat", "open_weights": false, "reasoning": true, "release_date": "2025-11-13", "structured_output": true, "temperature": true, "tool_call": true }, "openai/gpt-5.1-codex": { "attachment": true, "cost": { "cache_read": 0.125, "input": 1.25, "output": 10 }, "description": "GPT-5.1-Codex is an AI model provided by openrouter.", "family": "gpt-codex", "id": "openai/gpt-5.1-codex", "knowledge": "2024-09-30", "last_updated": "2025-11-13", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.1-Codex", "open_weights": false, "reasoning": true, "release_date": "2025-11-13", "structured_output": true, "temperature": true, "tool_call": true }, "openai/gpt-5.1-codex-max": { "attachment": true, "cost": { "cache_read": 0.11, "input": 1.1, "output": 9 }, "description": "GPT-5.1-Codex-Max is an AI model provided by openrouter.", "family": "gpt-codex", "id": "openai/gpt-5.1-codex-max", "knowledge": "2024-09-30", "last_updated": "2025-11-13", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.1-Codex-Max", "open_weights": false, "reasoning": true, "release_date": "2025-11-13", "structured_output": true, "temperature": true, "tool_call": true }, "openai/gpt-5.1-codex-mini": { "attachment": true, "cost": { "cache_read": 0.025, "input": 0.25, "output": 2 }, "description": "GPT-5.1-Codex-Mini is an AI model provided by openrouter.", "family": "gpt-codex", "id": "openai/gpt-5.1-codex-mini", "knowledge": "2024-09-30", "last_updated": "2025-11-13", "limit": { "context": 400000, "output": 100000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.1-Codex-Mini", "open_weights": false, "reasoning": true, "release_date": "2025-11-13", "structured_output": true, "temperature": true, "tool_call": true }, "openai/gpt-5.2": { "attachment": true, "cost": { "cache_read": 0.175, "input": 1.75, "output": 14 }, "description": "GPT-5.2 is an AI model provided by openrouter.", "family": "gpt", "id": "openai/gpt-5.2", "knowledge": "2025-08-31", "last_updated": "2025-12-11", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.2", "open_weights": false, "reasoning": true, "release_date": "2025-12-11", "structured_output": true, "temperature": false, "tool_call": true }, "openai/gpt-5.2-chat": { "attachment": true, "cost": { "cache_read": 0.175, "input": 1.75, "output": 14 }, "description": "GPT-5.2 Chat is an AI model provided by openrouter.", "family": "gpt-codex", "id": "openai/gpt-5.2-chat", "knowledge": "2025-08-31", "last_updated": "2025-12-11", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.2 Chat", "open_weights": false, "reasoning": true, "release_date": "2025-12-11", "structured_output": true, "temperature": false, "tool_call": true }, "openai/gpt-5.2-codex": { "attachment": true, "cost": { "cache_read": 0.175, "input": 1.75, "output": 14 }, "description": "GPT-5.2-Codex is an AI model provided by openrouter.", "family": "gpt-codex", "id": "openai/gpt-5.2-codex", "knowledge": "2025-08-31", "last_updated": "2026-01-14", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.2-Codex", "open_weights": false, "reasoning": true, "release_date": "2026-01-14", "structured_output": true, "temperature": true, "tool_call": true }, "openai/gpt-5.2-pro": { "attachment": true, "cost": { "input": 21, "output": 168 }, "description": "GPT-5.2 Pro is an AI model provided by openrouter.", "family": "gpt-pro", "id": "openai/gpt-5.2-pro", "knowledge": "2025-08-31", "last_updated": "2025-12-11", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.2 Pro", "open_weights": false, "reasoning": true, "release_date": "2025-12-11", "structured_output": true, "temperature": false, "tool_call": true }, "openai/gpt-5.3-codex": { "attachment": true, "cost": { "cache_read": 0.175, "input": 1.75, "output": 14 }, "description": "GPT-5.3-Codex is an AI model provided by openrouter.", "family": "gpt-codex", "id": "openai/gpt-5.3-codex", "knowledge": "2025-08-31", "last_updated": "2026-02-24", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.3-Codex", "open_weights": false, "reasoning": true, "release_date": "2026-02-24", "structured_output": true, "temperature": false, "tool_call": true }, "openai/gpt-5.4": { "attachment": true, "cost": { "cache_read": 0.25, "context_over_200k": { "cache_read": 0.5, "input": 5, "output": 22.5 }, "input": 2.5, "output": 15, "tiers": [ { "cache_read": 0.5, "input": 5, "output": 22.5, "tier": { "size": 272000, "type": "context" } } ] }, "description": "GPT-5.4 is an AI model provided by openrouter.", "family": "gpt", "id": "openai/gpt-5.4", "knowledge": "2025-08-31", "last_updated": "2026-03-05", "limit": { "context": 1050000, "input": 922000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.4", "open_weights": false, "reasoning": true, "release_date": "2026-03-05", "structured_output": true, "temperature": false, "tool_call": true }, "openai/gpt-5.4-mini": { "attachment": true, "cost": { "cache_read": 0.075, "input": 0.75, "output": 4.5 }, "description": "GPT-5.4 Mini is an AI model provided by openrouter.", "family": "gpt-mini", "id": "openai/gpt-5.4-mini", "knowledge": "2025-08-31", "last_updated": "2026-03-17", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.4 Mini", "open_weights": false, "reasoning": true, "release_date": "2026-03-17", "structured_output": true, "temperature": true, "tool_call": true }, "openai/gpt-5.4-nano": { "attachment": true, "cost": { "cache_read": 0.02, "input": 0.2, "output": 1.25 }, "description": "GPT-5.4 Nano is an AI model provided by openrouter.", "family": "gpt-nano", "id": "openai/gpt-5.4-nano", "knowledge": "2025-08-31", "last_updated": "2026-03-17", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.4 Nano", "open_weights": false, "reasoning": false, "release_date": "2026-03-17", "structured_output": true, "temperature": true, "tool_call": true }, "openai/gpt-5.4-pro": { "attachment": true, "cost": { "cache_read": 30, "input": 30, "output": 180 }, "description": "GPT-5.4 Pro is an AI model provided by openrouter.", "family": "gpt-pro", "id": "openai/gpt-5.4-pro", "knowledge": "2025-08-31", "last_updated": "2026-03-05", "limit": { "context": 1050000, "input": 922000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.4 Pro", "open_weights": false, "reasoning": true, "release_date": "2026-03-05", "structured_output": false, "temperature": false, "tool_call": true }, "openai/gpt-5.5": { "attachment": true, "cost": { "cache_read": 0.5, "context_over_200k": { "cache_read": 1, "input": 10, "output": 45 }, "input": 5, "output": 30, "tiers": [ { "cache_read": 1, "input": 10, "output": 45, "tier": { "size": 272000, "type": "context" } } ] }, "description": "GPT-5.5 is an AI model provided by openrouter.", "family": "gpt", "id": "openai/gpt-5.5", "knowledge": "2025-12-01", "last_updated": "2026-04-23", "limit": { "context": 1050000, "input": 922000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.5", "open_weights": false, "reasoning": true, "release_date": "2026-04-23", "structured_output": true, "temperature": false, "tool_call": true }, "openai/gpt-5.5-pro": { "attachment": true, "cost": { "context_over_200k": { "input": 60, "output": 270 }, "input": 30, "output": 180, "tiers": [ { "input": 60, "output": 270, "tier": { "size": 272000, "type": "context" } } ] }, "description": "GPT-5.5 Pro is an AI model provided by openrouter.", "family": "gpt-pro", "id": "openai/gpt-5.5-pro", "knowledge": "2025-12-01", "last_updated": "2026-04-23", "limit": { "context": 1050000, "input": 922000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.5 Pro", "open_weights": false, "reasoning": true, "release_date": "2026-04-23", "structured_output": true, "temperature": false, "tool_call": true }, "openai/gpt-oss-120b": { "attachment": false, "cost": { "input": 0.072, "output": 0.28 }, "description": "GPT OSS 120B is an AI model provided by openrouter.", "family": "gpt-oss", "id": "openai/gpt-oss-120b", "last_updated": "2025-08-05", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT OSS 120B", "open_weights": true, "reasoning": true, "release_date": "2025-08-05", "structured_output": true, "temperature": true, "tool_call": true }, "openai/gpt-oss-120b:exacto": { "attachment": false, "cost": { "input": 0.05, "output": 0.24 }, "description": "GPT OSS 120B (exacto) is an AI model provided by openrouter.", "family": "gpt-oss", "id": "openai/gpt-oss-120b:exacto", "last_updated": "2025-08-05", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT OSS 120B (exacto)", "open_weights": true, "reasoning": true, "release_date": "2025-08-05", "structured_output": true, "temperature": true, "tool_call": true }, "openai/gpt-oss-120b:free": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "gpt-oss-120b (free) is an AI model provided by openrouter.", "family": "gpt-oss", "id": "openai/gpt-oss-120b:free", "last_updated": "2025-08-05", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "gpt-oss-120b (free)", "open_weights": true, "reasoning": true, "release_date": "2025-08-05", "temperature": true, "tool_call": true }, "openai/gpt-oss-20b": { "attachment": false, "cost": { "input": 0.05, "output": 0.2 }, "description": "GPT OSS 20B is an AI model provided by openrouter.", "family": "gpt-oss", "id": "openai/gpt-oss-20b", "last_updated": "2025-08-05", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT OSS 20B", "open_weights": true, "reasoning": true, "release_date": "2025-08-05", "structured_output": true, "temperature": true, "tool_call": true }, "openai/gpt-oss-20b:free": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "gpt-oss-20b (free) is an AI model provided by openrouter.", "family": "gpt-oss", "id": "openai/gpt-oss-20b:free", "last_updated": "2026-01-31", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "gpt-oss-20b (free)", "open_weights": true, "reasoning": true, "release_date": "2025-08-05", "temperature": true, "tool_call": true }, "openai/gpt-oss-safeguard-20b": { "attachment": false, "cost": { "input": 0.075, "output": 0.3 }, "description": "GPT OSS Safeguard 20B is an AI model provided by openrouter.", "family": "gpt-oss", "id": "openai/gpt-oss-safeguard-20b", "last_updated": "2025-10-29", "limit": { "context": 131072, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT OSS Safeguard 20B", "open_weights": false, "reasoning": true, "release_date": "2025-10-29", "temperature": true, "tool_call": true }, "openai/o4-mini": { "attachment": true, "cost": { "cache_read": 0.28, "input": 1.1, "output": 4.4 }, "description": "o4 Mini is an AI model provided by openrouter.", "family": "o-mini", "id": "openai/o4-mini", "knowledge": "2024-06", "last_updated": "2025-04-16", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "o4 Mini", "open_weights": false, "reasoning": true, "release_date": "2025-04-16", "structured_output": true, "temperature": true, "tool_call": true }, "openrouter/elephant-alpha": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Elephant (free) is an AI model provided by openrouter.", "family": "elephant", "id": "openrouter/elephant-alpha", "last_updated": "2026-04-13", "limit": { "context": 262144, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Elephant (free)", "open_weights": false, "reasoning": true, "release_date": "2026-04-13", "structured_output": true, "temperature": true, "tool_call": true }, "openrouter/free": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Free Models Router is an AI model provided by openrouter.", "id": "openrouter/free", "last_updated": "2026-02-01", "limit": { "context": 200000, "input": 200000, "output": 8000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Free Models Router", "open_weights": false, "reasoning": true, "release_date": "2026-02-01", "structured_output": true, "temperature": true, "tool_call": true }, "openrouter/owl-alpha": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Owl Alpha is an AI model provided by openrouter.", "id": "openrouter/owl-alpha", "last_updated": "2026-04-30", "limit": { "context": 1048756, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Owl Alpha", "open_weights": false, "reasoning": true, "release_date": "2026-04-28", "status": "alpha", "structured_output": true, "temperature": true, "tool_call": true }, "openrouter/pareto-code": { "attachment": true, "description": "Pareto Code Router is an AI model provided by openrouter.", "id": "openrouter/pareto-code", "last_updated": "2026-04-21", "limit": { "context": 200000, "output": 200000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Pareto Code Router", "open_weights": false, "reasoning": true, "release_date": "2026-04-21", "structured_output": true, "temperature": true, "tool_call": true }, "poolside/laguna-m.1:free": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "Laguna M.1 is an AI model provided by openrouter.", "id": "poolside/laguna-m.1:free", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-28", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Laguna M.1", "open_weights": false, "reasoning": true, "release_date": "2026-04-28", "temperature": true, "tool_call": true }, "poolside/laguna-xs.2:free": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "Laguna XS.2 is an AI model provided by openrouter.", "id": "poolside/laguna-xs.2:free", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-28", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Laguna XS.2", "open_weights": true, "reasoning": true, "release_date": "2026-04-28", "temperature": true, "tool_call": true }, "prime-intellect/intellect-3": { "attachment": false, "cost": { "input": 0.2, "output": 1.1 }, "description": "Intellect 3 is an AI model provided by openrouter.", "family": "glm", "id": "prime-intellect/intellect-3", "knowledge": "2024-10", "last_updated": "2025-01-15", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Intellect 3", "open_weights": true, "reasoning": true, "release_date": "2025-01-15", "structured_output": true, "temperature": true, "tool_call": true }, "qwen/qwen-2.5-coder-32b-instruct": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Qwen2.5 Coder 32B Instruct is an AI model provided by openrouter.", "family": "qwen", "id": "qwen/qwen-2.5-coder-32b-instruct", "knowledge": "2024-10", "last_updated": "2024-11-11", "limit": { "context": 32768, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen2.5 Coder 32B Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-11-11", "structured_output": true, "temperature": true, "tool_call": false }, "qwen/qwen-3.6-27b": { "attachment": true, "cost": { "input": 0.195, "output": 1.56 }, "description": "Qwen3.6 27B is an AI model provided by openrouter.", "family": "qwen", "id": "qwen/qwen-3.6-27b", "knowledge": "2025-04", "last_updated": "2026-04-22", "limit": { "context": 262144, "output": 81920 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen3.6 27B", "open_weights": true, "reasoning": false, "release_date": "2026-04-22", "structured_output": true, "temperature": true, "tool_call": true }, "qwen/qwen-plus": { "attachment": false, "cost": { "cache_read": 0.052, "cache_write": 0.325, "input": 0.26, "output": 0.78 }, "description": "Qwen: Qwen-Plus is an AI model provided by openrouter.", "family": "qwen", "id": "qwen/qwen-plus", "knowledge": "2024-04", "last_updated": "2025-01-25", "limit": { "context": 1000000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen: Qwen-Plus", "open_weights": false, "reasoning": false, "release_date": "2025-01-25", "structured_output": false, "temperature": true, "tool_call": true }, "qwen/qwen2.5-vl-72b-instruct": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Qwen2.5 VL 72B Instruct is an AI model provided by openrouter.", "family": "qwen", "id": "qwen/qwen2.5-vl-72b-instruct", "knowledge": "2024-10", "last_updated": "2025-02-01", "limit": { "context": 32768, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen2.5 VL 72B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-02-01", "structured_output": true, "temperature": true, "tool_call": false }, "qwen/qwen3-235b-a22b-07-25": { "attachment": false, "cost": { "input": 0.15, "output": 0.85 }, "description": "Qwen3 235B A22B Instruct 2507 is an AI model provided by openrouter.", "family": "qwen", "id": "qwen/qwen3-235b-a22b-07-25", "knowledge": "2025-04", "last_updated": "2025-07-21", "limit": { "context": 262144, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 235B A22B Instruct 2507", "open_weights": true, "reasoning": false, "release_date": "2025-04-28", "structured_output": true, "temperature": true, "tool_call": true }, "qwen/qwen3-235b-a22b-thinking-2507": { "attachment": false, "cost": { "input": 0.078, "output": 0.312 }, "description": "Qwen3 235B A22B Thinking 2507 is an AI model provided by openrouter.", "family": "qwen", "id": "qwen/qwen3-235b-a22b-thinking-2507", "knowledge": "2025-04", "last_updated": "2025-07-25", "limit": { "context": 262144, "output": 81920 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 235B A22B Thinking 2507", "open_weights": true, "reasoning": true, "release_date": "2025-07-25", "structured_output": true, "temperature": true, "tool_call": true }, "qwen/qwen3-30b-a3b-instruct-2507": { "attachment": false, "cost": { "input": 0.2, "output": 0.8 }, "description": "Qwen3 30B A3B Instruct 2507 is an AI model provided by openrouter.", "family": "qwen", "id": "qwen/qwen3-30b-a3b-instruct-2507", "knowledge": "2025-04", "last_updated": "2025-07-29", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 30B A3B Instruct 2507", "open_weights": true, "reasoning": false, "release_date": "2025-07-29", "structured_output": true, "temperature": true, "tool_call": true }, "qwen/qwen3-30b-a3b-thinking-2507": { "attachment": false, "cost": { "input": 0.2, "output": 0.8 }, "description": "Qwen3 30B A3B Thinking 2507 is an AI model provided by openrouter.", "family": "qwen", "id": "qwen/qwen3-30b-a3b-thinking-2507", "knowledge": "2025-04", "last_updated": "2025-07-29", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 30B A3B Thinking 2507", "open_weights": true, "reasoning": true, "release_date": "2025-07-29", "structured_output": true, "temperature": true, "tool_call": true }, "qwen/qwen3-coder": { "attachment": false, "cost": { "input": 0.3, "output": 1.2 }, "description": "Qwen3 Coder is an AI model provided by openrouter.", "family": "qwen", "id": "qwen/qwen3-coder", "knowledge": "2025-04", "last_updated": "2025-07-23", "limit": { "context": 262144, "output": 66536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Coder", "open_weights": true, "reasoning": false, "release_date": "2025-07-23", "structured_output": true, "temperature": true, "tool_call": true }, "qwen/qwen3-coder-30b-a3b-instruct": { "attachment": false, "cost": { "input": 0.07, "output": 0.27 }, "description": "Qwen3 Coder 30B A3B Instruct is an AI model provided by openrouter.", "family": "qwen", "id": "qwen/qwen3-coder-30b-a3b-instruct", "knowledge": "2025-04", "last_updated": "2025-07-31", "limit": { "context": 160000, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Coder 30B A3B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-07-31", "structured_output": true, "temperature": true, "tool_call": true }, "qwen/qwen3-coder-flash": { "attachment": false, "cost": { "cache_read": 0.039, "cache_write": 0.24375, "input": 0.3, "output": 1.5 }, "description": "Qwen3 Coder Flash is an AI model provided by openrouter.", "family": "qwen", "id": "qwen/qwen3-coder-flash", "knowledge": "2025-04", "last_updated": "2025-07-23", "limit": { "context": 128000, "output": 66536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Coder Flash", "open_weights": false, "reasoning": false, "release_date": "2025-07-23", "structured_output": false, "temperature": true, "tool_call": true }, "qwen/qwen3-coder-plus": { "attachment": false, "cost": { "cache_read": 0.13, "cache_write": 0.8125, "input": 0.65, "output": 3.25 }, "description": "Qwen3 Coder Plus is an AI model provided by openrouter.", "family": "qwen", "id": "qwen/qwen3-coder-plus", "knowledge": "2025-04", "last_updated": "2025-09-23", "limit": { "context": 1000000, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Coder Plus", "open_weights": true, "reasoning": false, "release_date": "2025-09-23", "structured_output": true, "temperature": true, "tool_call": true }, "qwen/qwen3-coder:exacto": { "attachment": false, "cost": { "input": 0.38, "output": 1.53 }, "description": "Qwen3 Coder (exacto) is an AI model provided by openrouter.", "family": "qwen", "id": "qwen/qwen3-coder:exacto", "knowledge": "2025-04", "last_updated": "2025-07-23", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Coder (exacto)", "open_weights": true, "reasoning": false, "release_date": "2025-07-23", "structured_output": true, "temperature": true, "tool_call": true }, "qwen/qwen3-max": { "attachment": false, "cost": { "cache_read": 0.156, "cache_write": 0.975, "input": 1.2, "output": 6 }, "description": "Qwen3 Max is an AI model provided by openrouter.", "family": "qwen", "id": "qwen/qwen3-max", "last_updated": "2025-09-05", "limit": { "context": 262144, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Max", "open_weights": false, "reasoning": true, "release_date": "2025-09-05", "temperature": true, "tool_call": true }, "qwen/qwen3-next-80b-a3b-instruct": { "attachment": false, "cost": { "input": 0.14, "output": 1.4 }, "description": "Qwen3 Next 80B A3B Instruct is an AI model provided by openrouter.", "family": "qwen", "id": "qwen/qwen3-next-80b-a3b-instruct", "knowledge": "2025-04", "last_updated": "2025-09-11", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Next 80B A3B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-09-11", "structured_output": true, "temperature": true, "tool_call": true }, "qwen/qwen3-next-80b-a3b-thinking": { "attachment": false, "cost": { "input": 0.14, "output": 1.4 }, "description": "Qwen3 Next 80B A3B Thinking is an AI model provided by openrouter.", "family": "qwen", "id": "qwen/qwen3-next-80b-a3b-thinking", "knowledge": "2025-04", "last_updated": "2025-09-11", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Next 80B A3B Thinking", "open_weights": true, "reasoning": true, "release_date": "2025-09-11", "structured_output": true, "temperature": true, "tool_call": true }, "qwen/qwen3.5-397b-a17b": { "attachment": true, "cost": { "input": 0.6, "output": 3.6 }, "description": "Qwen3.5 397B A17B is an AI model provided by openrouter.", "family": "qwen", "id": "qwen/qwen3.5-397b-a17b", "knowledge": "2025-04", "last_updated": "2026-02-16", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen3.5 397B A17B", "open_weights": true, "reasoning": true, "release_date": "2026-02-16", "structured_output": true, "temperature": true, "tool_call": true }, "qwen/qwen3.5-flash-02-23": { "attachment": true, "cost": { "input": 0.065, "output": 0.26 }, "description": "Qwen: Qwen3.5-Flash is an AI model provided by openrouter.", "family": "qwen", "id": "qwen/qwen3.5-flash-02-23", "last_updated": "2026-02-25", "limit": { "context": 1000000, "output": 65536 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen: Qwen3.5-Flash", "open_weights": false, "reasoning": true, "release_date": "2026-02-25", "structured_output": true, "temperature": true, "tool_call": true }, "qwen/qwen3.5-plus-02-15": { "attachment": true, "cost": { "input": 0.4, "output": 2.4 }, "description": "Qwen3.5 Plus 2026-02-15 is an AI model provided by openrouter.", "family": "qwen", "id": "qwen/qwen3.5-plus-02-15", "knowledge": "2025-04", "last_updated": "2026-02-16", "limit": { "context": 1000000, "output": 65536 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen3.5 Plus 2026-02-15", "open_weights": false, "reasoning": true, "release_date": "2026-02-16", "structured_output": true, "temperature": true, "tool_call": true }, "qwen/qwen3.6-plus": { "attachment": true, "cost": { "cache_read": 0.0325, "cache_write": 0.40625, "input": 0.325, "output": 1.95 }, "description": "Qwen3.6 Plus is an AI model provided by openrouter.", "family": "qwen", "id": "qwen/qwen3.6-plus", "knowledge": "2025-04", "last_updated": "2026-04-02", "limit": { "context": 1000000, "output": 65536 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen3.6 Plus", "open_weights": false, "reasoning": true, "release_date": "2026-04-02", "structured_output": true, "temperature": true, "tool_call": true }, "sourceful/riverflow-v2-fast-preview": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Riverflow V2 Fast Preview is an AI model provided by openrouter.", "family": "sourceful", "id": "sourceful/riverflow-v2-fast-preview", "knowledge": "2025-06", "last_updated": "2026-01-28", "limit": { "context": 8192, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "image" ] }, "name": "Riverflow V2 Fast Preview", "open_weights": true, "reasoning": false, "release_date": "2025-12-08", "temperature": true, "tool_call": false }, "sourceful/riverflow-v2-max-preview": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Riverflow V2 Max Preview is an AI model provided by openrouter.", "family": "sourceful", "id": "sourceful/riverflow-v2-max-preview", "knowledge": "2025-06", "last_updated": "2026-01-28", "limit": { "context": 8192, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "image" ] }, "name": "Riverflow V2 Max Preview", "open_weights": true, "reasoning": false, "release_date": "2025-12-08", "temperature": true, "tool_call": false }, "sourceful/riverflow-v2-standard-preview": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Riverflow V2 Standard Preview is an AI model provided by openrouter.", "family": "sourceful", "id": "sourceful/riverflow-v2-standard-preview", "knowledge": "2025-06", "last_updated": "2026-01-28", "limit": { "context": 8192, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "image" ] }, "name": "Riverflow V2 Standard Preview", "open_weights": true, "reasoning": false, "release_date": "2025-12-08", "temperature": true, "tool_call": false }, "stepfun/step-3.5-flash": { "attachment": false, "cost": { "cache_read": 0.02, "input": 0.1, "output": 0.3 }, "description": "Step 3.5 Flash is an AI model provided by openrouter.", "family": "step", "id": "stepfun/step-3.5-flash", "knowledge": "2025-01", "last_updated": "2026-01-29", "limit": { "context": 256000, "output": 256000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Step 3.5 Flash", "open_weights": true, "reasoning": true, "release_date": "2026-01-29", "temperature": true, "tool_call": true }, "tencent/hy3-preview": { "attachment": false, "cost": { "cache_read": 0.029, "cache_write": 0.029, "input": 0.066, "output": 0.26 }, "description": "Hy3 preview is an AI model provided by openrouter.", "family": "Hy", "id": "tencent/hy3-preview", "last_updated": "2026-04-20", "limit": { "context": 256000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Hy3 preview", "open_weights": true, "reasoning": true, "release_date": "2026-04-20", "temperature": true, "tool_call": true }, "x-ai/grok-3": { "attachment": false, "cost": { "cache_read": 0.75, "cache_write": 15, "input": 3, "output": 15 }, "description": "Grok 3 is an AI model provided by openrouter.", "family": "grok", "id": "x-ai/grok-3", "knowledge": "2024-11", "last_updated": "2025-02-17", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok 3", "open_weights": false, "reasoning": false, "release_date": "2025-02-17", "structured_output": true, "temperature": true, "tool_call": true }, "x-ai/grok-3-beta": { "attachment": false, "cost": { "cache_read": 0.75, "cache_write": 15, "input": 3, "output": 15 }, "description": "Grok 3 Beta is an AI model provided by openrouter.", "family": "grok", "id": "x-ai/grok-3-beta", "knowledge": "2024-11", "last_updated": "2025-02-17", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok 3 Beta", "open_weights": false, "reasoning": false, "release_date": "2025-02-17", "temperature": true, "tool_call": true }, "x-ai/grok-3-mini": { "attachment": false, "cost": { "cache_read": 0.075, "cache_write": 0.5, "input": 0.3, "output": 0.5 }, "description": "Grok 3 Mini is an AI model provided by openrouter.", "family": "grok", "id": "x-ai/grok-3-mini", "knowledge": "2024-11", "last_updated": "2025-02-17", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok 3 Mini", "open_weights": false, "reasoning": true, "release_date": "2025-02-17", "structured_output": true, "temperature": true, "tool_call": true }, "x-ai/grok-3-mini-beta": { "attachment": false, "cost": { "cache_read": 0.075, "cache_write": 0.5, "input": 0.3, "output": 0.5 }, "description": "Grok 3 Mini Beta is an AI model provided by openrouter.", "family": "grok", "id": "x-ai/grok-3-mini-beta", "knowledge": "2024-11", "last_updated": "2025-02-17", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok 3 Mini Beta", "open_weights": false, "reasoning": true, "release_date": "2025-02-17", "temperature": true, "tool_call": true }, "x-ai/grok-4": { "attachment": false, "cost": { "cache_read": 0.75, "cache_write": 15, "input": 3, "output": 15, "tiers": [ { "input": 6, "output": 30, "tier": { "size": 128000, "type": "context" } } ] }, "description": "Grok 4 is an AI model provided by openrouter.", "family": "grok", "id": "x-ai/grok-4", "knowledge": "2025-07", "last_updated": "2025-07-09", "limit": { "context": 256000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok 4", "open_weights": false, "reasoning": true, "release_date": "2025-07-09", "structured_output": true, "temperature": true, "tool_call": true }, "x-ai/grok-4-fast": { "attachment": false, "cost": { "cache_read": 0.05, "cache_write": 0.05, "input": 0.2, "output": 0.5 }, "description": "Grok 4 Fast is an AI model provided by openrouter.", "family": "grok", "id": "x-ai/grok-4-fast", "knowledge": "2024-11", "last_updated": "2025-08-19", "limit": { "context": 2000000, "output": 30000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 4 Fast", "open_weights": false, "reasoning": true, "release_date": "2025-08-19", "structured_output": true, "temperature": true, "tool_call": true }, "x-ai/grok-4.1-fast": { "attachment": false, "cost": { "cache_read": 0.05, "cache_write": 0.05, "input": 0.2, "output": 0.5 }, "description": "Grok 4.1 Fast is an AI model provided by openrouter.", "family": "grok", "id": "x-ai/grok-4.1-fast", "knowledge": "2024-11", "last_updated": "2025-11-19", "limit": { "context": 2000000, "output": 30000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 4.1 Fast", "open_weights": false, "reasoning": true, "release_date": "2025-11-19", "structured_output": true, "temperature": true, "tool_call": true }, "x-ai/grok-4.20-beta": { "attachment": true, "cost": { "cache_read": 0.2, "context_over_200k": { "cache_read": 0.4, "input": 4, "output": 12 }, "input": 2, "output": 6, "tiers": [ { "cache_read": 0.4, "input": 4, "output": 12, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Grok 4.20 Beta is an AI model provided by openrouter.", "family": "grok", "id": "x-ai/grok-4.20-beta", "last_updated": "2026-03-12", "limit": { "context": 2000000, "output": 30000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 4.20 Beta", "open_weights": false, "reasoning": true, "release_date": "2026-03-12", "status": "beta", "temperature": true, "tool_call": true }, "x-ai/grok-4.20-multi-agent-beta": { "attachment": true, "cost": { "cache_read": 0.2, "context_over_200k": { "cache_read": 0.4, "input": 4, "output": 12 }, "input": 2, "output": 6, "tiers": [ { "cache_read": 0.4, "input": 4, "output": 12, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Grok 4.20 Multi - Agent Beta is an AI model provided by openrouter.", "family": "grok", "id": "x-ai/grok-4.20-multi-agent-beta", "last_updated": "2026-03-12", "limit": { "context": 2000000, "output": 30000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 4.20 Multi - Agent Beta", "open_weights": false, "reasoning": true, "release_date": "2026-03-12", "status": "beta", "temperature": true, "tool_call": false }, "x-ai/grok-4.3": { "attachment": true, "cost": { "cache_read": 0.2, "context_over_200k": { "cache_read": 0.4, "input": 2.5, "output": 5 }, "input": 1.25, "output": 2.5, "tiers": [ { "cache_read": 0.4, "input": 2.5, "output": 5, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Grok 4.3 is an AI model provided by openrouter.", "family": "grok", "id": "x-ai/grok-4.3", "last_updated": "2026-05-01", "limit": { "context": 1000000, "output": 1000000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 4.3", "open_weights": false, "reasoning": true, "release_date": "2026-05-01", "structured_output": true, "temperature": true, "tool_call": true }, "x-ai/grok-code-fast-1": { "attachment": false, "cost": { "cache_read": 0.02, "input": 0.2, "output": 1.5 }, "description": "Grok Code Fast 1 is an AI model provided by openrouter.", "family": "grok", "id": "x-ai/grok-code-fast-1", "knowledge": "2025-08", "last_updated": "2025-08-26", "limit": { "context": 256000, "output": 10000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok Code Fast 1", "open_weights": false, "reasoning": true, "release_date": "2025-08-26", "structured_output": true, "temperature": true, "tool_call": true }, "xiaomi/mimo-v2-flash": { "attachment": false, "cost": { "cache_read": 0.01, "input": 0.1, "output": 0.3 }, "description": "Xiaomi: MiMo-V2-Flash is an AI model provided by openrouter.", "family": "mimo", "id": "xiaomi/mimo-v2-flash", "interleaved": { "field": "reasoning_details" }, "knowledge": "2024-12-01", "last_updated": "2026-02-04", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Xiaomi: MiMo-V2-Flash", "open_weights": true, "reasoning": true, "release_date": "2025-12-16", "temperature": true, "tool_call": true }, "xiaomi/mimo-v2-omni": { "attachment": true, "cost": { "cache_read": 0.08, "input": 0.4, "output": 2 }, "description": "Xiaomi: MiMo-V2-Omni is an AI model provided by openrouter.", "family": "mimo", "id": "xiaomi/mimo-v2-omni", "interleaved": { "field": "reasoning_details" }, "knowledge": "2024-12", "last_updated": "2026-03-18", "limit": { "context": 262144, "output": 131072 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Xiaomi: MiMo-V2-Omni", "open_weights": false, "reasoning": true, "release_date": "2026-03-18", "temperature": true, "tool_call": true }, "xiaomi/mimo-v2-pro": { "attachment": false, "cost": { "cache_read": 0.2, "context_over_200k": { "cache_read": 0.4, "input": 2, "output": 6 }, "input": 1, "output": 3, "tiers": [ { "cache_read": 0.4, "input": 2, "output": 6, "tier": { "size": 256000, "type": "context" } } ] }, "description": "Xiaomi: MiMo-V2-Pro is an AI model provided by openrouter.", "family": "mimo", "id": "xiaomi/mimo-v2-pro", "interleaved": { "field": "reasoning_details" }, "knowledge": "2024-12", "last_updated": "2026-03-18", "limit": { "context": 1048576, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Xiaomi: MiMo-V2-Pro", "open_weights": false, "reasoning": true, "release_date": "2026-03-18", "temperature": true, "tool_call": true }, "xiaomi/mimo-v2.5": { "attachment": true, "cost": { "cache_read": 0.08, "context_over_200k": { "cache_read": 0.16, "input": 0.8, "output": 4 }, "input": 0.4, "output": 2, "tiers": [ { "cache_read": 0.16, "input": 0.8, "output": 4, "tier": { "size": 256000, "type": "context" } } ] }, "description": "Xiaomi: MiMo-V2.5 is an AI model provided by openrouter.", "family": "mimo", "id": "xiaomi/mimo-v2.5", "interleaved": { "field": "reasoning_details" }, "knowledge": "2024-12", "last_updated": "2026-04-22", "limit": { "context": 1048576, "output": 131072 }, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "name": "Xiaomi: MiMo-V2.5", "open_weights": true, "reasoning": true, "release_date": "2026-04-22", "temperature": true, "tool_call": true }, "xiaomi/mimo-v2.5-pro": { "attachment": false, "cost": { "cache_read": 0.2, "context_over_200k": { "cache_read": 0.4, "input": 2, "output": 6 }, "input": 1, "output": 3, "tiers": [ { "cache_read": 0.4, "input": 2, "output": 6, "tier": { "size": 256000, "type": "context" } } ] }, "description": "Xiaomi: MiMo-V2.5-Pro is an AI model provided by openrouter.", "family": "mimo", "id": "xiaomi/mimo-v2.5-pro", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-12", "last_updated": "2026-04-22", "limit": { "context": 1048576, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Xiaomi: MiMo-V2.5-Pro", "open_weights": true, "reasoning": true, "release_date": "2026-04-22", "temperature": true, "tool_call": true }, "z-ai/glm-4.5": { "attachment": false, "cost": { "input": 0.6, "output": 2.2 }, "description": "GLM 4.5 is an AI model provided by openrouter.", "family": "glm", "id": "z-ai/glm-4.5", "knowledge": "2025-04", "last_updated": "2025-07-28", "limit": { "context": 128000, "output": 96000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.5", "open_weights": true, "reasoning": true, "release_date": "2025-07-28", "structured_output": true, "temperature": true, "tool_call": true }, "z-ai/glm-4.5-air": { "attachment": false, "cost": { "input": 0.2, "output": 1.1 }, "description": "GLM 4.5 Air is an AI model provided by openrouter.", "family": "glm-air", "id": "z-ai/glm-4.5-air", "knowledge": "2025-04", "last_updated": "2025-07-28", "limit": { "context": 128000, "output": 96000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.5 Air", "open_weights": true, "reasoning": true, "release_date": "2025-07-28", "structured_output": true, "temperature": true, "tool_call": true }, "z-ai/glm-4.5-air:free": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "GLM 4.5 Air (free) is an AI model provided by openrouter.", "family": "glm-air", "id": "z-ai/glm-4.5-air:free", "knowledge": "2025-04", "last_updated": "2025-07-28", "limit": { "context": 128000, "output": 96000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.5 Air (free)", "open_weights": true, "reasoning": true, "release_date": "2025-07-28", "temperature": true, "tool_call": false }, "z-ai/glm-4.5v": { "attachment": true, "cost": { "input": 0.6, "output": 1.8 }, "description": "GLM 4.5V is an AI model provided by openrouter.", "family": "glm", "id": "z-ai/glm-4.5v", "knowledge": "2025-04", "last_updated": "2025-08-11", "limit": { "context": 64000, "output": 16384 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "GLM 4.5V", "open_weights": true, "reasoning": true, "release_date": "2025-08-11", "structured_output": true, "temperature": true, "tool_call": true }, "z-ai/glm-4.6": { "attachment": false, "cost": { "cache_read": 0.11, "input": 0.6, "output": 2.2 }, "description": "GLM 4.6 is an AI model provided by openrouter.", "family": "glm", "id": "z-ai/glm-4.6", "knowledge": "2025-09", "last_updated": "2025-09-30", "limit": { "context": 200000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.6", "open_weights": true, "reasoning": true, "release_date": "2025-09-30", "structured_output": true, "temperature": true, "tool_call": true }, "z-ai/glm-4.6:exacto": { "attachment": false, "cost": { "cache_read": 0.11, "input": 0.6, "output": 1.9 }, "description": "GLM 4.6 (exacto) is an AI model provided by openrouter.", "family": "glm", "id": "z-ai/glm-4.6:exacto", "knowledge": "2025-09", "last_updated": "2025-09-30", "limit": { "context": 200000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.6 (exacto)", "open_weights": true, "reasoning": true, "release_date": "2025-09-30", "structured_output": true, "temperature": true, "tool_call": true }, "z-ai/glm-4.7": { "attachment": false, "cost": { "cache_read": 0.11, "input": 0.6, "output": 2.2 }, "description": "GLM-4.7 is an AI model provided by openrouter.", "family": "glm", "id": "z-ai/glm-4.7", "interleaved": { "field": "reasoning_details" }, "knowledge": "2025-04", "last_updated": "2025-12-22", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.7", "open_weights": true, "reasoning": true, "release_date": "2025-12-22", "structured_output": true, "temperature": true, "tool_call": true }, "z-ai/glm-4.7-flash": { "attachment": false, "cost": { "input": 0.07, "output": 0.4 }, "description": "GLM-4.7-Flash is an AI model provided by openrouter.", "family": "glm", "id": "z-ai/glm-4.7-flash", "interleaved": { "field": "reasoning_details" }, "last_updated": "2026-01-19", "limit": { "context": 200000, "output": 65535 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.7-Flash", "open_weights": true, "reasoning": true, "release_date": "2026-01-19", "structured_output": true, "temperature": true, "tool_call": true }, "z-ai/glm-5": { "attachment": false, "cost": { "cache_read": 0.2, "input": 1, "output": 3.2 }, "description": "GLM-5 is an AI model provided by openrouter.", "family": "glm", "id": "z-ai/glm-5", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-02-12", "limit": { "context": 202752, "output": 131000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5", "open_weights": true, "reasoning": true, "release_date": "2026-02-12", "structured_output": true, "temperature": true, "tool_call": true }, "z-ai/glm-5-turbo": { "attachment": false, "cost": { "cache_read": 0.192, "cache_write": 0, "input": 0.96, "output": 3.2 }, "description": "GLM-5-Turbo is an AI model provided by openrouter.", "family": "glm", "id": "z-ai/glm-5-turbo", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-03-16", "limit": { "context": 202752, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5-Turbo", "open_weights": false, "reasoning": true, "release_date": "2026-03-16", "structured_output": true, "temperature": true, "tool_call": true }, "z-ai/glm-5.1": { "attachment": false, "cost": { "cache_read": 0.26, "input": 1.4, "output": 4.4 }, "description": "GLM-5.1 is an AI model provided by openrouter.", "family": "glm", "id": "z-ai/glm-5.1", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-07", "limit": { "context": 202752, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5.1", "open_weights": true, "reasoning": true, "release_date": "2026-04-07", "structured_output": true, "temperature": true, "tool_call": true } }, "name": "OpenRouter", "npm": "@openrouter/ai-sdk-provider" }, "ovhcloud": { "api": "https://oai.endpoints.kepler.ai.cloud.ovh.net/v1", "doc": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog//", "env": [ "OVHCLOUD_API_KEY" ], "iconURL": "https://models.dev/logos/ovhcloud.svg", "id": "ovhcloud", "models": { "gpt-oss-120b": { "attachment": false, "cost": { "input": 0.09, "output": 0.47 }, "description": "gpt-oss-120b is an AI model provided by ovhcloud.", "id": "gpt-oss-120b", "last_updated": "2025-08-28", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "gpt-oss-120b", "open_weights": true, "reasoning": true, "release_date": "2025-08-28", "structured_output": true, "tool_call": true }, "gpt-oss-20b": { "attachment": false, "cost": { "input": 0.05, "output": 0.18 }, "description": "gpt-oss-20b is an AI model provided by ovhcloud.", "id": "gpt-oss-20b", "last_updated": "2025-08-28", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "gpt-oss-20b", "open_weights": true, "reasoning": true, "release_date": "2025-08-28", "structured_output": true, "tool_call": true }, "llama-3.1-8b-instruct": { "attachment": false, "cost": { "input": 0.11, "output": 0.11 }, "description": "Llama-3.1-8B-Instruct is an AI model provided by ovhcloud.", "id": "llama-3.1-8b-instruct", "last_updated": "2025-06-11", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama-3.1-8B-Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-06-11", "structured_output": true, "temperature": true, "tool_call": true }, "meta-llama-3_3-70b-instruct": { "attachment": false, "cost": { "input": 0.74, "output": 0.74 }, "description": "Meta-Llama-3_3-70B-Instruct is an AI model provided by ovhcloud.", "id": "meta-llama-3_3-70b-instruct", "last_updated": "2025-04-01", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Meta-Llama-3_3-70B-Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-04-01", "structured_output": true, "temperature": true, "tool_call": true }, "mistral-7b-instruct-v0.3": { "attachment": false, "cost": { "input": 0.11, "output": 0.11 }, "description": "Mistral-7B-Instruct-v0.3 is an AI model provided by ovhcloud.", "id": "mistral-7b-instruct-v0.3", "last_updated": "2025-04-01", "limit": { "context": 65536, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral-7B-Instruct-v0.3", "open_weights": true, "reasoning": false, "release_date": "2025-04-01", "structured_output": true, "temperature": true, "tool_call": true }, "mistral-nemo-instruct-2407": { "attachment": false, "cost": { "input": 0.14, "output": 0.14 }, "description": "Mistral-Nemo-Instruct-2407 is an AI model provided by ovhcloud.", "id": "mistral-nemo-instruct-2407", "last_updated": "2024-11-20", "limit": { "context": 65536, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral-Nemo-Instruct-2407", "open_weights": true, "reasoning": false, "release_date": "2024-11-20", "structured_output": true, "temperature": true, "tool_call": true }, "mistral-small-3.2-24b-instruct-2506": { "attachment": true, "cost": { "input": 0.1, "output": 0.31 }, "description": "Mistral-Small-3.2-24B-Instruct-2506 is an AI model provided by ovhcloud.", "id": "mistral-small-3.2-24b-instruct-2506", "last_updated": "2025-07-16", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Mistral-Small-3.2-24B-Instruct-2506", "open_weights": true, "reasoning": false, "release_date": "2025-07-16", "structured_output": true, "temperature": true, "tool_call": true }, "qwen2.5-vl-72b-instruct": { "attachment": true, "cost": { "input": 1.01, "output": 1.01 }, "description": "Qwen2.5-VL-72B-Instruct is an AI model provided by ovhcloud.", "id": "qwen2.5-vl-72b-instruct", "last_updated": "2025-03-31", "limit": { "context": 32768, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen2.5-VL-72B-Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-03-31", "structured_output": true, "temperature": true, "tool_call": false }, "qwen3-32b": { "attachment": false, "cost": { "input": 0.09, "output": 0.25 }, "description": "Qwen3-32B is an AI model provided by ovhcloud.", "id": "qwen3-32b", "last_updated": "2025-07-16", "limit": { "context": 32768, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3-32B", "open_weights": true, "reasoning": true, "release_date": "2025-07-16", "structured_output": true, "temperature": true, "tool_call": true }, "qwen3-coder-30b-a3b-instruct": { "attachment": false, "cost": { "input": 0.07, "output": 0.26 }, "description": "Qwen3-Coder-30B-A3B-Instruct is an AI model provided by ovhcloud.", "id": "qwen3-coder-30b-a3b-instruct", "last_updated": "2025-10-28", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3-Coder-30B-A3B-Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-10-28", "structured_output": true, "temperature": true, "tool_call": true }, "qwen3.5-9b": { "attachment": true, "cost": { "input": 0.1, "output": 0.15 }, "description": "Qwen3.5-9B is an AI model provided by ovhcloud.", "id": "qwen3.5-9b", "last_updated": "2026-02-15", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen3.5-9B", "open_weights": true, "reasoning": false, "release_date": "2026-02-15", "structured_output": true, "temperature": true, "tool_call": true } }, "name": "OVHcloud AI Endpoints", "npm": "@ai-sdk/openai-compatible" }, "perplexity": { "doc": "https://docs.perplexity.ai", "env": [ "PERPLEXITY_API_KEY" ], "iconURL": "https://models.dev/logos/perplexity.svg", "id": "perplexity", "models": { "sonar": { "attachment": false, "cost": { "input": 1, "output": 1 }, "description": "Sonar is an AI model provided by perplexity.", "family": "sonar", "id": "sonar", "knowledge": "2025-09-01", "last_updated": "2025-09-01", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Sonar", "open_weights": false, "reasoning": false, "release_date": "2024-01-01", "temperature": true, "tool_call": false }, "sonar-deep-research": { "attachment": false, "cost": { "input": 2, "output": 8, "reasoning": 3 }, "description": "Perplexity Sonar Deep Research is an AI model provided by perplexity.", "id": "sonar-deep-research", "knowledge": "2025-01", "last_updated": "2025-09-01", "limit": { "context": 128000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Perplexity Sonar Deep Research", "open_weights": false, "reasoning": true, "release_date": "2025-02-01", "temperature": false, "tool_call": false }, "sonar-pro": { "attachment": true, "cost": { "input": 3, "output": 15 }, "description": "Sonar Pro is an AI model provided by perplexity.", "family": "sonar-pro", "id": "sonar-pro", "knowledge": "2025-09-01", "last_updated": "2025-09-01", "limit": { "context": 200000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Sonar Pro", "open_weights": false, "reasoning": false, "release_date": "2024-01-01", "temperature": true, "tool_call": false }, "sonar-reasoning-pro": { "attachment": true, "cost": { "input": 2, "output": 8 }, "description": "Sonar Reasoning Pro is an AI model provided by perplexity.", "family": "sonar-reasoning", "id": "sonar-reasoning-pro", "knowledge": "2025-09-01", "last_updated": "2025-09-01", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Sonar Reasoning Pro", "open_weights": false, "reasoning": true, "release_date": "2024-01-01", "temperature": true, "tool_call": false } }, "name": "Perplexity", "npm": "@ai-sdk/perplexity" }, "perplexity-agent": { "api": "https://api.perplexity.ai/v1", "doc": "https://docs.perplexity.ai/docs/agent-api/models", "env": [ "PERPLEXITY_API_KEY" ], "iconURL": "https://models.dev/logos/perplexity-agent.svg", "id": "perplexity-agent", "models": { "anthropic/claude-haiku-4-5": { "attachment": true, "cost": { "cache_read": 0.1, "input": 1, "output": 5 }, "description": "Claude Haiku 4.5 is an AI model provided by perplexity-agent.", "family": "claude-haiku", "id": "anthropic/claude-haiku-4-5", "knowledge": "2025-02-28", "last_updated": "2025-10-15", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Haiku 4.5", "open_weights": false, "reasoning": true, "release_date": "2025-10-15", "temperature": true, "tool_call": true }, "anthropic/claude-opus-4-5": { "attachment": true, "cost": { "cache_read": 0.5, "input": 5, "output": 25 }, "description": "Claude Opus 4.5 is an AI model provided by perplexity-agent.", "family": "claude-opus", "id": "anthropic/claude-opus-4-5", "knowledge": "2025-03-31", "last_updated": "2025-11-24", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.5", "open_weights": false, "reasoning": true, "release_date": "2025-11-24", "temperature": true, "tool_call": true }, "anthropic/claude-opus-4-6": { "attachment": true, "cost": { "cache_read": 0.5, "input": 5, "output": 25 }, "description": "Claude Opus 4.6 is an AI model provided by perplexity-agent.", "family": "claude-opus", "id": "anthropic/claude-opus-4-6", "knowledge": "2025-05-31", "last_updated": "2026-02-05", "limit": { "context": 200000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.6", "open_weights": false, "reasoning": true, "release_date": "2026-02-05", "temperature": true, "tool_call": true }, "anthropic/claude-opus-4-7": { "attachment": true, "cost": { "cache_read": 0.5, "input": 5, "output": 25 }, "description": "Claude Opus 4.7 is an AI model provided by perplexity-agent.", "family": "claude-opus", "id": "anthropic/claude-opus-4-7", "knowledge": "2026-01-31", "last_updated": "2026-04-16", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.7", "open_weights": false, "reasoning": true, "release_date": "2026-04-16", "temperature": false, "tool_call": true }, "anthropic/claude-sonnet-4-5": { "attachment": true, "cost": { "cache_read": 0.3, "input": 3, "output": 15 }, "description": "Claude Sonnet 4.5 is an AI model provided by perplexity-agent.", "family": "claude-sonnet", "id": "anthropic/claude-sonnet-4-5", "knowledge": "2025-07-31", "last_updated": "2025-09-29", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.5", "open_weights": false, "reasoning": true, "release_date": "2025-09-29", "temperature": true, "tool_call": true }, "anthropic/claude-sonnet-4-6": { "attachment": true, "cost": { "cache_read": 0.3, "input": 3, "output": 15 }, "description": "Claude Sonnet 4.6 is an AI model provided by perplexity-agent.", "family": "claude-sonnet", "id": "anthropic/claude-sonnet-4-6", "knowledge": "2025-08-31", "last_updated": "2026-02-17", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.6", "open_weights": false, "reasoning": true, "release_date": "2026-02-17", "temperature": true, "tool_call": true }, "google/gemini-2.5-flash": { "attachment": true, "cost": { "cache_read": 0.03, "input": 0.3, "output": 2.5 }, "description": "Gemini 2.5 Flash is an AI model provided by perplexity-agent.", "family": "gemini-flash", "id": "google/gemini-2.5-flash", "knowledge": "2025-01", "last_updated": "2025-06-05", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Flash", "open_weights": false, "reasoning": true, "release_date": "2025-03-20", "temperature": true, "tool_call": true }, "google/gemini-2.5-pro": { "attachment": true, "cost": { "cache_read": 0.125, "context_over_200k": { "cache_read": 0.25, "input": 2.5, "output": 15 }, "input": 1.25, "output": 10, "tiers": [ { "cache_read": 0.25, "input": 2.5, "output": 15, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Gemini 2.5 Pro is an AI model provided by perplexity-agent.", "family": "gemini-pro", "id": "google/gemini-2.5-pro", "knowledge": "2025-01", "last_updated": "2025-06-05", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Pro", "open_weights": false, "reasoning": true, "release_date": "2025-03-20", "temperature": true, "tool_call": true }, "google/gemini-3-flash-preview": { "attachment": true, "cost": { "cache_read": 0.05, "context_over_200k": { "cache_read": 0.05, "input": 0.5, "output": 3 }, "input": 0.5, "output": 3, "tiers": [ { "cache_read": 0.05, "input": 0.5, "output": 3, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Gemini 3 Flash Preview is an AI model provided by perplexity-agent.", "family": "gemini-flash", "id": "google/gemini-3-flash-preview", "knowledge": "2025-01", "last_updated": "2025-12-17", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "name": "Gemini 3 Flash Preview", "open_weights": false, "reasoning": true, "release_date": "2025-12-17", "temperature": true, "tool_call": true }, "google/gemini-3.1-pro-preview": { "attachment": true, "cost": { "cache_read": 0.2, "context_over_200k": { "cache_read": 0.4, "input": 4, "output": 18 }, "input": 2, "output": 12, "tiers": [ { "cache_read": 0.4, "input": 4, "output": 18, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Gemini 3.1 Pro Preview is an AI model provided by perplexity-agent.", "family": "gemini-pro", "id": "google/gemini-3.1-pro-preview", "knowledge": "2025-01", "last_updated": "2026-02-19", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "name": "Gemini 3.1 Pro Preview", "open_weights": false, "reasoning": true, "release_date": "2026-02-19", "temperature": true, "tool_call": true }, "nvidia/nemotron-3-super-120b-a12b": { "attachment": false, "cost": { "input": 0.25, "output": 2.5 }, "description": "Nemotron 3 Super 120B is an AI model provided by perplexity-agent.", "family": "nemotron", "id": "nvidia/nemotron-3-super-120b-a12b", "knowledge": "2026-02", "last_updated": "2026-03-11", "limit": { "context": 1000000, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Nemotron 3 Super 120B", "open_weights": true, "reasoning": true, "release_date": "2026-03-11", "temperature": true, "tool_call": true }, "openai/gpt-5-mini": { "attachment": true, "cost": { "cache_read": 0.025, "input": 0.25, "output": 2 }, "description": "GPT-5 Mini is an AI model provided by perplexity-agent.", "family": "gpt-mini", "id": "openai/gpt-5-mini", "knowledge": "2024-05-30", "last_updated": "2025-08-07", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5 Mini", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "temperature": false, "tool_call": true }, "openai/gpt-5.1": { "attachment": true, "cost": { "cache_read": 0.125, "input": 1.25, "output": 10 }, "description": "GPT-5.1 is an AI model provided by perplexity-agent.", "family": "gpt", "id": "openai/gpt-5.1", "knowledge": "2024-09-30", "last_updated": "2025-11-13", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.1", "open_weights": false, "reasoning": true, "release_date": "2025-11-13", "temperature": false, "tool_call": true }, "openai/gpt-5.2": { "attachment": true, "cost": { "cache_read": 0.175, "input": 1.75, "output": 14 }, "description": "GPT-5.2 is an AI model provided by perplexity-agent.", "family": "gpt", "id": "openai/gpt-5.2", "knowledge": "2025-08-31", "last_updated": "2025-12-11", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.2", "open_weights": false, "reasoning": true, "release_date": "2025-12-11", "temperature": false, "tool_call": true }, "openai/gpt-5.4": { "attachment": true, "cost": { "cache_read": 0.25, "input": 2.5, "output": 15 }, "description": "GPT-5.4 is an AI model provided by perplexity-agent.", "family": "gpt", "id": "openai/gpt-5.4", "knowledge": "2025-08-31", "last_updated": "2026-03-05", "limit": { "context": 1050000, "input": 922000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.4", "open_weights": false, "reasoning": true, "release_date": "2026-03-05", "temperature": false, "tool_call": true }, "openai/gpt-5.5": { "attachment": true, "cost": { "cache_read": 0.5, "input": 5, "output": 30 }, "description": "GPT-5.5 is an AI model provided by perplexity-agent.", "family": "gpt", "id": "openai/gpt-5.5", "knowledge": "2025-12-01", "last_updated": "2026-04-23", "limit": { "context": 1050000, "input": 922000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.5", "open_weights": false, "reasoning": true, "release_date": "2026-04-23", "temperature": false, "tool_call": true }, "perplexity/sonar": { "attachment": false, "cost": { "cache_read": 0.0625, "input": 0.25, "output": 2.5 }, "description": "Sonar is an AI model provided by perplexity-agent.", "family": "sonar", "id": "perplexity/sonar", "knowledge": "2025-09-01", "last_updated": "2025-09-01", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Sonar", "open_weights": false, "reasoning": false, "release_date": "2024-01-01", "temperature": true, "tool_call": true }, "xai/grok-4-1-fast-non-reasoning": { "attachment": true, "cost": { "cache_read": 0.05, "input": 0.2, "output": 0.5 }, "description": "Grok 4.1 Fast (Non-Reasoning) is an AI model provided by perplexity-agent.", "family": "grok", "id": "xai/grok-4-1-fast-non-reasoning", "knowledge": "2025-07", "last_updated": "2025-11-19", "limit": { "context": 2000000, "output": 30000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 4.1 Fast (Non-Reasoning)", "open_weights": false, "reasoning": false, "release_date": "2025-11-19", "temperature": true, "tool_call": true } }, "name": "Perplexity Agent", "npm": "@ai-sdk/openai" }, "poe": { "api": "https://api.poe.com/v1", "doc": "https://creator.poe.com/docs/external-applications/openai-compatible-api", "env": [ "POE_API_KEY" ], "iconURL": "https://models.dev/logos/poe.svg", "id": "poe", "models": { "anthropic/claude-haiku-3": { "attachment": true, "cost": { "cache_read": 0.021, "cache_write": 0.26, "input": 0.21, "output": 1.1 }, "description": "Claude-Haiku-3 is an AI model provided by poe.", "family": "claude-haiku", "id": "anthropic/claude-haiku-3", "last_updated": "2024-03-09", "limit": { "context": 189096, "output": 8192 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude-Haiku-3", "open_weights": false, "reasoning": false, "release_date": "2024-03-09", "temperature": false, "tool_call": true }, "anthropic/claude-haiku-3.5": { "attachment": true, "cost": { "cache_read": 0.068, "cache_write": 0.85, "input": 0.68, "output": 3.4 }, "description": "Claude-Haiku-3.5 is an AI model provided by poe.", "family": "claude-haiku", "id": "anthropic/claude-haiku-3.5", "last_updated": "2024-10-01", "limit": { "context": 189096, "output": 8192 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude-Haiku-3.5", "open_weights": false, "reasoning": false, "release_date": "2024-10-01", "temperature": false, "tool_call": true }, "anthropic/claude-haiku-4.5": { "attachment": true, "cost": { "cache_read": 0.085, "cache_write": 1.1, "input": 0.85, "output": 4.3 }, "description": "Claude-Haiku-4.5 is an AI model provided by poe.", "family": "claude-haiku", "id": "anthropic/claude-haiku-4.5", "last_updated": "2025-10-15", "limit": { "context": 192000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude-Haiku-4.5", "open_weights": false, "reasoning": true, "release_date": "2025-10-15", "temperature": false, "tool_call": true }, "anthropic/claude-opus-4": { "attachment": true, "cost": { "cache_read": 1.3, "cache_write": 16, "input": 13, "output": 64 }, "description": "Claude-Opus-4 is an AI model provided by poe.", "family": "claude-opus", "id": "anthropic/claude-opus-4", "last_updated": "2025-05-21", "limit": { "context": 192512, "output": 28672 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude-Opus-4", "open_weights": false, "reasoning": true, "release_date": "2025-05-21", "temperature": false, "tool_call": true }, "anthropic/claude-opus-4.1": { "attachment": true, "cost": { "cache_read": 1.3, "cache_write": 16, "input": 13, "output": 64 }, "description": "Claude-Opus-4.1 is an AI model provided by poe.", "family": "claude-opus", "id": "anthropic/claude-opus-4.1", "last_updated": "2025-08-05", "limit": { "context": 196608, "output": 32000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude-Opus-4.1", "open_weights": false, "reasoning": true, "release_date": "2025-08-05", "temperature": false, "tool_call": true }, "anthropic/claude-opus-4.5": { "attachment": true, "cost": { "cache_read": 0.43, "cache_write": 5.3, "input": 4.3, "output": 21 }, "description": "Claude-Opus-4.5 is an AI model provided by poe.", "family": "claude-opus", "id": "anthropic/claude-opus-4.5", "last_updated": "2025-11-21", "limit": { "context": 196608, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude-Opus-4.5", "open_weights": false, "reasoning": true, "release_date": "2025-11-21", "temperature": false, "tool_call": true }, "anthropic/claude-opus-4.6": { "attachment": true, "cost": { "cache_read": 0.43, "cache_write": 5.3, "input": 4.3, "output": 21 }, "description": "Claude-Opus-4.6 is an AI model provided by poe.", "id": "anthropic/claude-opus-4.6", "last_updated": "2026-02-04", "limit": { "context": 983040, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude-Opus-4.6", "open_weights": false, "reasoning": true, "release_date": "2026-02-04", "temperature": false, "tool_call": true }, "anthropic/claude-opus-4.7": { "attachment": true, "cost": { "cache_read": 0.43, "cache_write": 5.4, "input": 4.3, "output": 21 }, "description": "Claude-Opus-4.7 is an AI model provided by poe.", "id": "anthropic/claude-opus-4.7", "last_updated": "2026-04-15", "limit": { "context": 1048576, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude-Opus-4.7", "open_weights": false, "reasoning": true, "release_date": "2026-04-15", "temperature": false, "tool_call": true }, "anthropic/claude-sonnet-3.5": { "attachment": true, "cost": { "cache_read": 0.26, "cache_write": 3.2, "input": 2.6, "output": 13 }, "description": "Claude-Sonnet-3.5 is an AI model provided by poe.", "family": "claude-sonnet", "id": "anthropic/claude-sonnet-3.5", "last_updated": "2024-06-05", "limit": { "context": 189096, "output": 8192 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude-Sonnet-3.5", "open_weights": false, "reasoning": false, "release_date": "2024-06-05", "status": "deprecated", "temperature": false, "tool_call": true }, "anthropic/claude-sonnet-3.5-june": { "attachment": true, "cost": { "cache_read": 0.26, "cache_write": 3.2, "input": 2.6, "output": 13 }, "description": "Claude-Sonnet-3.5-June is an AI model provided by poe.", "family": "claude-sonnet", "id": "anthropic/claude-sonnet-3.5-june", "last_updated": "2024-11-18", "limit": { "context": 189096, "output": 8192 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude-Sonnet-3.5-June", "open_weights": false, "reasoning": false, "release_date": "2024-11-18", "status": "deprecated", "temperature": false, "tool_call": true }, "anthropic/claude-sonnet-3.7": { "attachment": true, "cost": { "cache_read": 0.26, "cache_write": 3.2, "input": 2.6, "output": 13 }, "description": "Claude-Sonnet-3.7 is an AI model provided by poe.", "family": "claude-sonnet", "id": "anthropic/claude-sonnet-3.7", "last_updated": "2025-02-19", "limit": { "context": 196608, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude-Sonnet-3.7", "open_weights": false, "reasoning": true, "release_date": "2025-02-19", "temperature": false, "tool_call": true }, "anthropic/claude-sonnet-4": { "attachment": true, "cost": { "cache_read": 0.26, "cache_write": 3.2, "input": 2.6, "output": 13 }, "description": "Claude-Sonnet-4 is an AI model provided by poe.", "family": "claude-sonnet", "id": "anthropic/claude-sonnet-4", "last_updated": "2025-05-21", "limit": { "context": 983040, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude-Sonnet-4", "open_weights": false, "reasoning": true, "release_date": "2025-05-21", "temperature": false, "tool_call": true }, "anthropic/claude-sonnet-4.5": { "attachment": true, "cost": { "cache_read": 0.26, "cache_write": 3.2, "input": 2.6, "output": 13 }, "description": "Claude-Sonnet-4.5 is an AI model provided by poe.", "family": "claude-sonnet", "id": "anthropic/claude-sonnet-4.5", "last_updated": "2025-09-26", "limit": { "context": 983040, "output": 32768 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude-Sonnet-4.5", "open_weights": false, "reasoning": true, "release_date": "2025-09-26", "temperature": false, "tool_call": true }, "anthropic/claude-sonnet-4.6": { "attachment": true, "cost": { "cache_read": 0.26, "cache_write": 3.2, "input": 2.6, "output": 13 }, "description": "Claude-Sonnet-4.6 is an AI model provided by poe.", "id": "anthropic/claude-sonnet-4.6", "last_updated": "2026-02-05", "limit": { "context": 983040, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude-Sonnet-4.6", "open_weights": false, "reasoning": true, "release_date": "2026-02-05", "temperature": false, "tool_call": true }, "cerebras/gpt-oss-120b-cs": { "attachment": true, "cost": { "input": 0.35, "output": 0.75 }, "description": "GPT-OSS-120B-CS is an AI model provided by poe.", "id": "cerebras/gpt-oss-120b-cs", "last_updated": "2025-08-06", "limit": { "context": 128000, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT-OSS-120B-CS", "open_weights": false, "reasoning": true, "release_date": "2025-08-06", "temperature": false, "tool_call": true }, "cerebras/llama-3.1-8b-cs": { "attachment": true, "cost": { "input": 0.1, "output": 0.1 }, "description": "Llama-3.1-8B-CS is an AI model provided by poe.", "id": "cerebras/llama-3.1-8b-cs", "last_updated": "2025-05-13", "limit": { "context": 128000, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama-3.1-8B-CS", "open_weights": false, "reasoning": false, "release_date": "2025-05-13", "temperature": false, "tool_call": true }, "cerebras/llama-3.3-70b-cs": { "attachment": true, "description": "llama-3.3-70b-cs is an AI model provided by poe.", "id": "cerebras/llama-3.3-70b-cs", "last_updated": "2025-05-13", "limit": { "context": 0, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "llama-3.3-70b-cs", "open_weights": false, "reasoning": false, "release_date": "2025-05-13", "status": "deprecated", "temperature": false, "tool_call": false }, "cerebras/qwen3-235b-2507-cs": { "attachment": true, "description": "qwen3-235b-2507-cs is an AI model provided by poe.", "id": "cerebras/qwen3-235b-2507-cs", "last_updated": "2025-08-06", "limit": { "context": 0, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "qwen3-235b-2507-cs", "open_weights": false, "reasoning": true, "release_date": "2025-08-06", "status": "deprecated", "temperature": false, "tool_call": true }, "cerebras/qwen3-32b-cs": { "attachment": true, "description": "qwen3-32b-cs is an AI model provided by poe.", "id": "cerebras/qwen3-32b-cs", "last_updated": "2025-05-15", "limit": { "context": 0, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "qwen3-32b-cs", "open_weights": false, "reasoning": true, "release_date": "2025-05-15", "status": "deprecated", "temperature": false, "tool_call": true }, "elevenlabs/elevenlabs-music": { "attachment": true, "description": "ElevenLabs-Music is an AI model provided by poe.", "family": "elevenlabs", "id": "elevenlabs/elevenlabs-music", "last_updated": "2025-08-29", "limit": { "context": 2000, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "name": "ElevenLabs-Music", "open_weights": false, "reasoning": false, "release_date": "2025-08-29", "temperature": false, "tool_call": true }, "elevenlabs/elevenlabs-v2.5-turbo": { "attachment": true, "description": "ElevenLabs-v2.5-Turbo is an AI model provided by poe.", "family": "elevenlabs", "id": "elevenlabs/elevenlabs-v2.5-turbo", "last_updated": "2024-10-28", "limit": { "context": 128000, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "name": "ElevenLabs-v2.5-Turbo", "open_weights": false, "reasoning": false, "release_date": "2024-10-28", "temperature": false, "tool_call": true }, "elevenlabs/elevenlabs-v3": { "attachment": true, "description": "ElevenLabs-v3 is an AI model provided by poe.", "family": "elevenlabs", "id": "elevenlabs/elevenlabs-v3", "last_updated": "2025-06-05", "limit": { "context": 128000, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "name": "ElevenLabs-v3", "open_weights": false, "reasoning": false, "release_date": "2025-06-05", "temperature": false, "tool_call": true }, "empiriolabs/deepseek-v4-flash-el": { "attachment": true, "cost": { "input": 0.14, "output": 0.28 }, "description": "DeepSeek-V4-Flash-EL is an AI model provided by poe.", "id": "empiriolabs/deepseek-v4-flash-el", "last_updated": "2026-05-02", "limit": { "context": 1000000, "input": 1000000, "output": 384000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek-V4-Flash-EL", "open_weights": true, "reasoning": true, "release_date": "2026-04-24", "tool_call": true }, "empiriolabs/deepseek-v4-pro-el": { "attachment": true, "cost": { "input": 1.67, "output": 3.33 }, "description": "DeepSeek-V4-Pro-EL is an AI model provided by poe.", "id": "empiriolabs/deepseek-v4-pro-el", "last_updated": "2026-05-02", "limit": { "context": 1000000, "input": 1000000, "output": 384000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek-V4-Pro-EL", "open_weights": true, "reasoning": true, "release_date": "2026-04-24", "tool_call": true }, "fireworks-ai/kimi-k2.5-fw": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Kimi-K2.5-FW is an AI model provided by poe.", "id": "fireworks-ai/kimi-k2.5-fw", "last_updated": "2026-01-27", "limit": { "context": 262144, "input": 245760, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Kimi-K2.5-FW", "open_weights": false, "reasoning": false, "release_date": "2026-01-27", "temperature": false, "tool_call": true }, "google/gemini-2.0-flash": { "attachment": true, "cost": { "input": 0.1, "output": 0.42 }, "description": "Gemini-2.0-Flash is an AI model provided by poe.", "family": "gemini-flash", "id": "google/gemini-2.0-flash", "last_updated": "2024-12-11", "limit": { "context": 990000, "output": 8192 }, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text" ] }, "name": "Gemini-2.0-Flash", "open_weights": false, "reasoning": false, "release_date": "2024-12-11", "temperature": false, "tool_call": true }, "google/gemini-2.0-flash-lite": { "attachment": true, "cost": { "input": 0.052, "output": 0.21 }, "description": "Gemini-2.0-Flash-Lite is an AI model provided by poe.", "family": "gemini-flash-lite", "id": "google/gemini-2.0-flash-lite", "last_updated": "2025-02-05", "limit": { "context": 990000, "output": 8192 }, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text" ] }, "name": "Gemini-2.0-Flash-Lite", "open_weights": false, "reasoning": false, "release_date": "2025-02-05", "temperature": false, "tool_call": true }, "google/gemini-2.5-flash": { "attachment": true, "cost": { "cache_read": 0.021, "input": 0.21, "output": 1.8 }, "description": "Gemini-2.5-Flash is an AI model provided by poe.", "family": "gemini-flash", "id": "google/gemini-2.5-flash", "last_updated": "2025-04-26", "limit": { "context": 1065535, "output": 65535 }, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text" ] }, "name": "Gemini-2.5-Flash", "open_weights": false, "reasoning": true, "release_date": "2025-04-26", "temperature": false, "tool_call": true }, "google/gemini-2.5-flash-lite": { "attachment": true, "cost": { "input": 0.07, "output": 0.28 }, "description": "Gemini-2.5-Flash-Lite is an AI model provided by poe.", "family": "gemini-flash-lite", "id": "google/gemini-2.5-flash-lite", "last_updated": "2025-06-19", "limit": { "context": 1024000, "output": 64000 }, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text" ] }, "name": "Gemini-2.5-Flash-Lite", "open_weights": false, "reasoning": true, "release_date": "2025-06-19", "temperature": false, "tool_call": true }, "google/gemini-2.5-pro": { "attachment": true, "cost": { "cache_read": 0.087, "input": 0.87, "output": 7 }, "description": "Gemini-2.5-Pro is an AI model provided by poe.", "family": "gemini-pro", "id": "google/gemini-2.5-pro", "last_updated": "2025-02-05", "limit": { "context": 1065535, "output": 65535 }, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text" ] }, "name": "Gemini-2.5-Pro", "open_weights": false, "reasoning": true, "release_date": "2025-02-05", "temperature": false, "tool_call": true }, "google/gemini-3-flash": { "attachment": true, "cost": { "cache_read": 0.04, "input": 0.4, "output": 2.4 }, "description": "Gemini-3-Flash is an AI model provided by poe.", "id": "google/gemini-3-flash", "last_updated": "2025-10-07", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text" ] }, "name": "Gemini-3-Flash", "open_weights": false, "reasoning": true, "release_date": "2025-10-07", "temperature": false, "tool_call": true }, "google/gemini-3-pro": { "attachment": true, "cost": { "cache_read": 0.16, "input": 1.6, "output": 9.6 }, "description": "Gemini-3-Pro is an AI model provided by poe.", "family": "gemini-pro", "id": "google/gemini-3-pro", "last_updated": "2025-10-22", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text" ] }, "name": "Gemini-3-Pro", "open_weights": false, "reasoning": true, "release_date": "2025-10-22", "status": "deprecated", "temperature": false, "tool_call": true }, "google/gemini-3.1-flash-lite": { "attachment": true, "cost": { "input": 0.25, "output": 1.5 }, "description": "Gemini-3.1-Flash-Lite is an AI model provided by poe.", "id": "google/gemini-3.1-flash-lite", "last_updated": "2026-02-18", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text" ] }, "name": "Gemini-3.1-Flash-Lite", "open_weights": false, "reasoning": true, "release_date": "2026-02-18", "temperature": false, "tool_call": true }, "google/gemini-3.1-pro": { "attachment": true, "cost": { "cache_read": 0.2, "input": 2, "output": 12 }, "description": "Gemini-3.1-Pro is an AI model provided by poe.", "id": "google/gemini-3.1-pro", "last_updated": "2026-02-19", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text" ] }, "name": "Gemini-3.1-Pro", "open_weights": false, "reasoning": true, "release_date": "2026-02-19", "temperature": false, "tool_call": true }, "google/gemini-deep-research": { "attachment": true, "cost": { "input": 1.6, "output": 9.6 }, "description": "gemini-deep-research is an AI model provided by poe.", "id": "google/gemini-deep-research", "last_updated": "2025-12-11", "limit": { "context": 1048576, "output": 0 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "gemini-deep-research", "open_weights": false, "reasoning": true, "release_date": "2025-12-11", "status": "deprecated", "temperature": false, "tool_call": true }, "google/gemma-4-31b": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Gemma-4-31B is an AI model provided by poe.", "id": "google/gemma-4-31b", "last_updated": "2026-04-02", "limit": { "context": 262144, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemma-4-31B", "open_weights": false, "reasoning": false, "release_date": "2026-04-02", "temperature": false, "tool_call": true }, "google/imagen-3": { "attachment": true, "description": "Imagen-3 is an AI model provided by poe.", "family": "imagen", "id": "google/imagen-3", "last_updated": "2024-10-15", "limit": { "context": 480, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "name": "Imagen-3", "open_weights": false, "reasoning": false, "release_date": "2024-10-15", "temperature": false, "tool_call": true }, "google/imagen-3-fast": { "attachment": true, "description": "Imagen-3-Fast is an AI model provided by poe.", "family": "imagen", "id": "google/imagen-3-fast", "last_updated": "2024-10-17", "limit": { "context": 480, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "name": "Imagen-3-Fast", "open_weights": false, "reasoning": false, "release_date": "2024-10-17", "temperature": false, "tool_call": true }, "google/imagen-4": { "attachment": true, "description": "Imagen-4 is an AI model provided by poe.", "family": "imagen", "id": "google/imagen-4", "last_updated": "2025-05-22", "limit": { "context": 480, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "name": "Imagen-4", "open_weights": false, "reasoning": false, "release_date": "2025-05-22", "temperature": false, "tool_call": true }, "google/imagen-4-fast": { "attachment": true, "description": "Imagen-4-Fast is an AI model provided by poe.", "family": "imagen", "id": "google/imagen-4-fast", "last_updated": "2025-06-25", "limit": { "context": 480, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "name": "Imagen-4-Fast", "open_weights": false, "reasoning": false, "release_date": "2025-06-25", "temperature": false, "tool_call": true }, "google/imagen-4-ultra": { "attachment": true, "description": "Imagen-4-Ultra is an AI model provided by poe.", "family": "imagen", "id": "google/imagen-4-ultra", "last_updated": "2025-05-24", "limit": { "context": 480, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "name": "Imagen-4-Ultra", "open_weights": false, "reasoning": false, "release_date": "2025-05-24", "temperature": false, "tool_call": true }, "google/lyria": { "attachment": true, "description": "Lyria is an AI model provided by poe.", "family": "lyria", "id": "google/lyria", "last_updated": "2025-06-04", "limit": { "context": 0, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "name": "Lyria", "open_weights": false, "reasoning": false, "release_date": "2025-06-04", "temperature": false, "tool_call": true }, "google/nano-banana": { "attachment": true, "cost": { "cache_read": 0.021, "input": 0.21, "output": 1.8 }, "description": "Nano-Banana is an AI model provided by poe.", "family": "nano-banana", "id": "google/nano-banana", "last_updated": "2025-08-21", "limit": { "context": 65536, "output": 0 }, "modalities": { "input": [ "text", "image" ], "output": [ "text", "image" ] }, "name": "Nano-Banana", "open_weights": false, "reasoning": false, "release_date": "2025-08-21", "temperature": false, "tool_call": true }, "google/nano-banana-pro": { "attachment": true, "cost": { "cache_read": 0.2, "input": 2, "output": 12 }, "description": "Nano-Banana-Pro is an AI model provided by poe.", "family": "nano-banana", "id": "google/nano-banana-pro", "last_updated": "2025-11-19", "limit": { "context": 65536, "output": 0 }, "modalities": { "input": [ "text", "image" ], "output": [ "image" ] }, "name": "Nano-Banana-Pro", "open_weights": false, "reasoning": false, "release_date": "2025-11-19", "temperature": false, "tool_call": true }, "google/veo-2": { "attachment": true, "description": "Veo-2 is an AI model provided by poe.", "family": "veo", "id": "google/veo-2", "last_updated": "2024-12-02", "limit": { "context": 480, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "video" ] }, "name": "Veo-2", "open_weights": false, "reasoning": false, "release_date": "2024-12-02", "temperature": false, "tool_call": true }, "google/veo-3": { "attachment": true, "description": "Veo-3 is an AI model provided by poe.", "family": "veo", "id": "google/veo-3", "last_updated": "2025-05-21", "limit": { "context": 480, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "video" ] }, "name": "Veo-3", "open_weights": false, "reasoning": false, "release_date": "2025-05-21", "temperature": false, "tool_call": true }, "google/veo-3-fast": { "attachment": true, "description": "Veo-3-Fast is an AI model provided by poe.", "family": "veo", "id": "google/veo-3-fast", "last_updated": "2025-10-13", "limit": { "context": 480, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "video" ] }, "name": "Veo-3-Fast", "open_weights": false, "reasoning": false, "release_date": "2025-10-13", "temperature": false, "tool_call": true }, "google/veo-3.1": { "attachment": true, "description": "Veo-3.1 is an AI model provided by poe.", "family": "veo", "id": "google/veo-3.1", "last_updated": "2025-10-15", "limit": { "context": 480, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "video" ] }, "name": "Veo-3.1", "open_weights": false, "reasoning": false, "release_date": "2025-10-15", "temperature": false, "tool_call": true }, "google/veo-3.1-fast": { "attachment": true, "description": "Veo-3.1-Fast is an AI model provided by poe.", "family": "veo", "id": "google/veo-3.1-fast", "last_updated": "2025-10-15", "limit": { "context": 480, "output": 0 }, "modalities": { "input": [ "text", "image" ], "output": [ "video" ] }, "name": "Veo-3.1-Fast", "open_weights": false, "reasoning": false, "release_date": "2025-10-15", "temperature": false, "tool_call": true }, "ideogramai/ideogram": { "attachment": true, "description": "Ideogram is an AI model provided by poe.", "family": "ideogram", "id": "ideogramai/ideogram", "last_updated": "2024-04-03", "limit": { "context": 150, "output": 0 }, "modalities": { "input": [ "text", "image" ], "output": [ "image" ] }, "name": "Ideogram", "open_weights": false, "reasoning": false, "release_date": "2024-04-03", "temperature": false, "tool_call": true }, "ideogramai/ideogram-v2": { "attachment": true, "description": "Ideogram-v2 is an AI model provided by poe.", "family": "ideogram", "id": "ideogramai/ideogram-v2", "last_updated": "2024-08-21", "limit": { "context": 150, "output": 0 }, "modalities": { "input": [ "text", "image" ], "output": [ "image" ] }, "name": "Ideogram-v2", "open_weights": false, "reasoning": false, "release_date": "2024-08-21", "temperature": false, "tool_call": true }, "ideogramai/ideogram-v2a": { "attachment": true, "description": "Ideogram-v2a is an AI model provided by poe.", "family": "ideogram", "id": "ideogramai/ideogram-v2a", "last_updated": "2025-02-27", "limit": { "context": 150, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "name": "Ideogram-v2a", "open_weights": false, "reasoning": false, "release_date": "2025-02-27", "temperature": false, "tool_call": true }, "ideogramai/ideogram-v2a-turbo": { "attachment": true, "description": "Ideogram-v2a-Turbo is an AI model provided by poe.", "family": "ideogram", "id": "ideogramai/ideogram-v2a-turbo", "last_updated": "2025-02-27", "limit": { "context": 150, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "name": "Ideogram-v2a-Turbo", "open_weights": false, "reasoning": false, "release_date": "2025-02-27", "temperature": false, "tool_call": true }, "lumalabs/ray2": { "attachment": true, "description": "Ray2 is an AI model provided by poe.", "family": "ray", "id": "lumalabs/ray2", "last_updated": "2025-02-20", "limit": { "context": 5000, "output": 0 }, "modalities": { "input": [ "text", "image" ], "output": [ "video" ] }, "name": "Ray2", "open_weights": false, "reasoning": false, "release_date": "2025-02-20", "temperature": false, "tool_call": true }, "novita/deepseek-v3.2": { "attachment": true, "cost": { "cache_read": 0.13, "input": 0.27, "output": 0.4 }, "description": "DeepSeek-V3.2 is an AI model provided by poe.", "id": "novita/deepseek-v3.2", "last_updated": "2025-12-01", "limit": { "context": 128000, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek-V3.2", "open_weights": true, "reasoning": true, "release_date": "2025-12-01", "temperature": true, "tool_call": true }, "novita/glm-4.6": { "attachment": true, "description": "GLM-4.6 is an AI model provided by poe.", "family": "glm", "id": "novita/glm-4.6", "last_updated": "2025-09-30", "limit": { "context": 0, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.6", "open_weights": false, "reasoning": false, "release_date": "2025-09-30", "temperature": false, "tool_call": true }, "novita/glm-4.6v": { "attachment": true, "description": "glm-4.6v is an AI model provided by poe.", "id": "novita/glm-4.6v", "last_updated": "2025-12-09", "limit": { "context": 131000, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "glm-4.6v", "open_weights": false, "reasoning": true, "release_date": "2025-12-09", "temperature": false, "tool_call": true }, "novita/glm-4.7": { "attachment": true, "description": "glm-4.7 is an AI model provided by poe.", "id": "novita/glm-4.7", "last_updated": "2025-12-22", "limit": { "context": 205000, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "glm-4.7", "open_weights": false, "reasoning": true, "release_date": "2025-12-22", "status": "deprecated", "temperature": true, "tool_call": true }, "novita/glm-4.7-flash": { "attachment": true, "description": "glm-4.7-flash is an AI model provided by poe.", "id": "novita/glm-4.7-flash", "last_updated": "2026-01-19", "limit": { "context": 200000, "output": 65500 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "glm-4.7-flash", "open_weights": false, "reasoning": true, "release_date": "2026-01-19", "temperature": false, "tool_call": true }, "novita/glm-4.7-n": { "attachment": true, "description": "glm-4.7-n is an AI model provided by poe.", "id": "novita/glm-4.7-n", "last_updated": "2025-12-22", "limit": { "context": 205000, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "glm-4.7-n", "open_weights": false, "reasoning": true, "release_date": "2025-12-22", "temperature": false, "tool_call": true }, "novita/glm-5": { "attachment": true, "cost": { "cache_read": 0.2, "input": 1, "output": 3.2 }, "description": "GLM-5 is an AI model provided by poe.", "id": "novita/glm-5", "last_updated": "2026-02-15", "limit": { "context": 205000, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5", "open_weights": false, "reasoning": true, "release_date": "2026-02-15", "temperature": true, "tool_call": true }, "novita/kimi-k2-thinking": { "attachment": true, "description": "kimi-k2-thinking is an AI model provided by poe.", "family": "kimi", "id": "novita/kimi-k2-thinking", "last_updated": "2025-11-07", "limit": { "context": 256000, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "kimi-k2-thinking", "open_weights": false, "reasoning": true, "release_date": "2025-11-07", "temperature": false, "tool_call": true }, "novita/kimi-k2.5": { "attachment": true, "cost": { "cache_read": 0.1, "input": 0.6, "output": 3 }, "description": "Kimi-K2.5 is an AI model provided by poe.", "id": "novita/kimi-k2.5", "last_updated": "2026-01-27", "limit": { "context": 128000, "output": 262144 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Kimi-K2.5", "open_weights": false, "reasoning": true, "release_date": "2026-01-27", "temperature": true, "tool_call": true }, "novita/kimi-k2.6": { "attachment": true, "cost": { "cache_read": 0.16, "input": 0.96, "output": 4.04 }, "description": "Kimi-K2.6 is an AI model provided by poe.", "id": "novita/kimi-k2.6", "knowledge": "2025-04", "last_updated": "2026-05-02", "limit": { "context": 262144, "input": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Kimi-K2.6", "open_weights": true, "reasoning": true, "release_date": "2026-04-20", "temperature": true, "tool_call": true }, "novita/minimax-m2.1": { "attachment": true, "description": "minimax-m2.1 is an AI model provided by poe.", "id": "novita/minimax-m2.1", "last_updated": "2025-12-26", "limit": { "context": 205000, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "minimax-m2.1", "open_weights": false, "reasoning": true, "release_date": "2025-12-26", "temperature": false, "tool_call": true }, "openai/chatgpt-4o-latest": { "attachment": true, "cost": { "input": 4.5, "output": 14 }, "description": "ChatGPT-4o-Latest is an AI model provided by poe.", "family": "gpt", "id": "openai/chatgpt-4o-latest", "last_updated": "2024-08-14", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "ChatGPT-4o-Latest", "open_weights": false, "reasoning": false, "release_date": "2024-08-14", "status": "deprecated", "temperature": false, "tool_call": true }, "openai/dall-e-3": { "attachment": true, "description": "DALL-E-3 is an AI model provided by poe.", "family": "dall-e", "id": "openai/dall-e-3", "last_updated": "2023-11-06", "limit": { "context": 800, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "name": "DALL-E-3", "open_weights": false, "reasoning": false, "release_date": "2023-11-06", "temperature": false, "tool_call": true }, "openai/gpt-3.5-turbo": { "attachment": true, "cost": { "input": 0.45, "output": 1.4 }, "description": "GPT-3.5-Turbo is an AI model provided by poe.", "family": "gpt", "id": "openai/gpt-3.5-turbo", "last_updated": "2023-09-13", "limit": { "context": 16384, "output": 2048 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-3.5-Turbo", "open_weights": false, "reasoning": false, "release_date": "2023-09-13", "temperature": false, "tool_call": true }, "openai/gpt-3.5-turbo-instruct": { "attachment": true, "cost": { "input": 1.4, "output": 1.8 }, "description": "GPT-3.5-Turbo-Instruct is an AI model provided by poe.", "family": "gpt", "id": "openai/gpt-3.5-turbo-instruct", "last_updated": "2023-09-20", "limit": { "context": 3500, "output": 1024 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-3.5-Turbo-Instruct", "open_weights": false, "reasoning": false, "release_date": "2023-09-20", "temperature": false, "tool_call": true }, "openai/gpt-3.5-turbo-raw": { "attachment": true, "cost": { "input": 0.45, "output": 1.4 }, "description": "GPT-3.5-Turbo-Raw is an AI model provided by poe.", "family": "gpt", "id": "openai/gpt-3.5-turbo-raw", "last_updated": "2023-09-27", "limit": { "context": 4524, "output": 2048 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-3.5-Turbo-Raw", "open_weights": false, "reasoning": false, "release_date": "2023-09-27", "temperature": false, "tool_call": true }, "openai/gpt-4-classic": { "attachment": true, "cost": { "input": 27, "output": 54 }, "description": "GPT-4-Classic is an AI model provided by poe.", "family": "gpt", "id": "openai/gpt-4-classic", "last_updated": "2024-03-25", "limit": { "context": 8192, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4-Classic", "open_weights": false, "reasoning": false, "release_date": "2024-03-25", "status": "deprecated", "temperature": false, "tool_call": true }, "openai/gpt-4-classic-0314": { "attachment": true, "cost": { "input": 27, "output": 54 }, "description": "GPT-4-Classic-0314 is an AI model provided by poe.", "family": "gpt", "id": "openai/gpt-4-classic-0314", "last_updated": "2024-08-26", "limit": { "context": 8192, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4-Classic-0314", "open_weights": false, "reasoning": false, "release_date": "2024-08-26", "status": "deprecated", "temperature": false, "tool_call": true }, "openai/gpt-4-turbo": { "attachment": true, "cost": { "input": 9, "output": 27 }, "description": "GPT-4-Turbo is an AI model provided by poe.", "family": "gpt", "id": "openai/gpt-4-turbo", "last_updated": "2023-09-13", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4-Turbo", "open_weights": false, "reasoning": false, "release_date": "2023-09-13", "temperature": false, "tool_call": true }, "openai/gpt-4.1": { "attachment": true, "cost": { "cache_read": 0.45, "input": 1.8, "output": 7.2 }, "description": "GPT-4.1 is an AI model provided by poe.", "family": "gpt", "id": "openai/gpt-4.1", "last_updated": "2025-04-14", "limit": { "context": 1047576, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4.1", "open_weights": false, "reasoning": false, "release_date": "2025-04-14", "temperature": false, "tool_call": true }, "openai/gpt-4.1-mini": { "attachment": true, "cost": { "cache_read": 0.09, "input": 0.36, "output": 1.4 }, "description": "GPT-4.1-mini is an AI model provided by poe.", "family": "gpt-mini", "id": "openai/gpt-4.1-mini", "last_updated": "2025-04-15", "limit": { "context": 1047576, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4.1-mini", "open_weights": false, "reasoning": false, "release_date": "2025-04-15", "temperature": false, "tool_call": true }, "openai/gpt-4.1-nano": { "attachment": true, "cost": { "cache_read": 0.022, "input": 0.09, "output": 0.36 }, "description": "GPT-4.1-nano is an AI model provided by poe.", "family": "gpt-nano", "id": "openai/gpt-4.1-nano", "last_updated": "2025-04-15", "limit": { "context": 1047576, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4.1-nano", "open_weights": false, "reasoning": false, "release_date": "2025-04-15", "temperature": false, "tool_call": true }, "openai/gpt-4o": { "attachment": true, "description": "GPT-4o is an AI model provided by poe.", "family": "gpt", "id": "openai/gpt-4o", "last_updated": "2024-05-13", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4o", "open_weights": false, "reasoning": false, "release_date": "2024-05-13", "temperature": false, "tool_call": true }, "openai/gpt-4o-aug": { "attachment": true, "cost": { "cache_read": 1.1, "input": 2.2, "output": 9 }, "description": "GPT-4o-Aug is an AI model provided by poe.", "family": "gpt", "id": "openai/gpt-4o-aug", "last_updated": "2024-11-21", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4o-Aug", "open_weights": false, "reasoning": false, "release_date": "2024-11-21", "temperature": false, "tool_call": true }, "openai/gpt-4o-mini": { "attachment": true, "cost": { "cache_read": 0.068, "input": 0.14, "output": 0.54 }, "description": "GPT-4o-mini is an AI model provided by poe.", "family": "gpt-mini", "id": "openai/gpt-4o-mini", "last_updated": "2024-07-18", "limit": { "context": 124096, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4o-mini", "open_weights": false, "reasoning": false, "release_date": "2024-07-18", "temperature": false, "tool_call": true }, "openai/gpt-4o-mini-search": { "attachment": true, "cost": { "input": 0.14, "output": 0.54 }, "description": "GPT-4o-mini-Search is an AI model provided by poe.", "family": "gpt-mini", "id": "openai/gpt-4o-mini-search", "last_updated": "2025-03-11", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT-4o-mini-Search", "open_weights": false, "reasoning": false, "release_date": "2025-03-11", "temperature": false, "tool_call": true }, "openai/gpt-4o-search": { "attachment": true, "cost": { "input": 2.2, "output": 9 }, "description": "GPT-4o-Search is an AI model provided by poe.", "family": "gpt", "id": "openai/gpt-4o-search", "last_updated": "2025-03-11", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT-4o-Search", "open_weights": false, "reasoning": false, "release_date": "2025-03-11", "temperature": false, "tool_call": true }, "openai/gpt-5": { "attachment": true, "cost": { "cache_read": 0.11, "input": 1.1, "output": 9 }, "description": "GPT-5 is an AI model provided by poe.", "family": "gpt", "id": "openai/gpt-5", "last_updated": "2025-08-05", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5", "open_weights": false, "reasoning": true, "release_date": "2025-08-05", "temperature": false, "tool_call": true }, "openai/gpt-5-chat": { "attachment": true, "cost": { "cache_read": 0.11, "input": 1.1, "output": 9 }, "description": "GPT-5-Chat is an AI model provided by poe.", "family": "gpt-codex", "id": "openai/gpt-5-chat", "last_updated": "2025-08-07", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5-Chat", "open_weights": false, "reasoning": false, "release_date": "2025-08-07", "temperature": false, "tool_call": true }, "openai/gpt-5-codex": { "attachment": true, "cost": { "input": 1.1, "output": 9 }, "description": "GPT-5-Codex is an AI model provided by poe.", "family": "gpt-codex", "id": "openai/gpt-5-codex", "last_updated": "2025-09-23", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5-Codex", "open_weights": false, "reasoning": true, "release_date": "2025-09-23", "temperature": false, "tool_call": true }, "openai/gpt-5-mini": { "attachment": true, "cost": { "cache_read": 0.022, "input": 0.22, "output": 1.8 }, "description": "GPT-5-mini is an AI model provided by poe.", "family": "gpt-mini", "id": "openai/gpt-5-mini", "last_updated": "2025-06-25", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5-mini", "open_weights": false, "reasoning": true, "release_date": "2025-06-25", "temperature": false, "tool_call": true }, "openai/gpt-5-nano": { "attachment": true, "cost": { "cache_read": 0.0045, "input": 0.045, "output": 0.36 }, "description": "GPT-5-nano is an AI model provided by poe.", "family": "gpt-nano", "id": "openai/gpt-5-nano", "last_updated": "2025-08-05", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5-nano", "open_weights": false, "reasoning": true, "release_date": "2025-08-05", "temperature": false, "tool_call": true }, "openai/gpt-5-pro": { "attachment": true, "cost": { "input": 14, "output": 110 }, "description": "GPT-5-Pro is an AI model provided by poe.", "family": "gpt-pro", "id": "openai/gpt-5-pro", "last_updated": "2025-10-06", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5-Pro", "open_weights": false, "reasoning": true, "release_date": "2025-10-06", "temperature": false, "tool_call": true }, "openai/gpt-5.1": { "attachment": true, "cost": { "cache_read": 0.11, "input": 1.1, "output": 9 }, "description": "GPT-5.1 is an AI model provided by poe.", "family": "gpt", "id": "openai/gpt-5.1", "last_updated": "2025-11-12", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.1", "open_weights": false, "reasoning": true, "release_date": "2025-11-12", "temperature": false, "tool_call": true }, "openai/gpt-5.1-codex": { "attachment": true, "cost": { "cache_read": 0.11, "input": 1.1, "output": 9 }, "description": "GPT-5.1-Codex is an AI model provided by poe.", "family": "gpt-codex", "id": "openai/gpt-5.1-codex", "last_updated": "2025-11-12", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.1-Codex", "open_weights": false, "reasoning": true, "release_date": "2025-11-12", "temperature": false, "tool_call": true }, "openai/gpt-5.1-codex-max": { "attachment": true, "cost": { "cache_read": 0.11, "input": 1.1, "output": 9 }, "description": "GPT-5.1-Codex-Max is an AI model provided by poe.", "id": "openai/gpt-5.1-codex-max", "last_updated": "2025-12-08", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.1-Codex-Max", "open_weights": false, "reasoning": true, "release_date": "2025-12-08", "temperature": false, "tool_call": true }, "openai/gpt-5.1-codex-mini": { "attachment": true, "cost": { "cache_read": 0.022, "input": 0.22, "output": 1.8 }, "description": "GPT-5.1-Codex-Mini is an AI model provided by poe.", "family": "gpt-codex", "id": "openai/gpt-5.1-codex-mini", "last_updated": "2025-11-12", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT-5.1-Codex-Mini", "open_weights": false, "reasoning": true, "release_date": "2025-11-12", "temperature": false, "tool_call": true }, "openai/gpt-5.1-instant": { "attachment": true, "cost": { "cache_read": 0.11, "input": 1.1, "output": 9 }, "description": "GPT-5.1-Instant is an AI model provided by poe.", "family": "gpt", "id": "openai/gpt-5.1-instant", "last_updated": "2025-11-12", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.1-Instant", "open_weights": false, "reasoning": true, "release_date": "2025-11-12", "temperature": false, "tool_call": true }, "openai/gpt-5.2": { "attachment": true, "cost": { "cache_read": 0.16, "input": 1.6, "output": 13 }, "description": "GPT-5.2 is an AI model provided by poe.", "id": "openai/gpt-5.2", "last_updated": "2025-12-08", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.2", "open_weights": false, "reasoning": true, "release_date": "2025-12-08", "temperature": false, "tool_call": true }, "openai/gpt-5.2-codex": { "attachment": true, "cost": { "cache_read": 0.16, "input": 1.6, "output": 13 }, "description": "GPT-5.2-Codex is an AI model provided by poe.", "id": "openai/gpt-5.2-codex", "last_updated": "2026-01-14", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.2-Codex", "open_weights": false, "reasoning": true, "release_date": "2026-01-14", "temperature": false, "tool_call": true }, "openai/gpt-5.2-instant": { "attachment": true, "cost": { "cache_read": 0.16, "input": 1.6, "output": 13 }, "description": "GPT-5.2-Instant is an AI model provided by poe.", "id": "openai/gpt-5.2-instant", "last_updated": "2025-12-11", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.2-Instant", "open_weights": false, "reasoning": false, "release_date": "2025-12-11", "temperature": false, "tool_call": true }, "openai/gpt-5.2-pro": { "attachment": true, "cost": { "input": 19, "output": 150 }, "description": "GPT-5.2-Pro is an AI model provided by poe.", "id": "openai/gpt-5.2-pro", "last_updated": "2025-12-11", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.2-Pro", "open_weights": false, "reasoning": true, "release_date": "2025-12-11", "temperature": false, "tool_call": true }, "openai/gpt-5.3-codex": { "attachment": true, "cost": { "cache_read": 0.16, "input": 1.6, "output": 13 }, "description": "GPT-5.3-Codex is an AI model provided by poe.", "id": "openai/gpt-5.3-codex", "last_updated": "2026-02-10", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.3-Codex", "open_weights": false, "reasoning": true, "release_date": "2026-02-10", "temperature": false, "tool_call": true }, "openai/gpt-5.3-codex-spark": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "GPT-5.3-Codex-Spark is an AI model provided by poe.", "id": "openai/gpt-5.3-codex-spark", "last_updated": "2026-03-04", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT-5.3-Codex-Spark", "open_weights": false, "reasoning": true, "release_date": "2026-03-04", "temperature": false, "tool_call": true }, "openai/gpt-5.3-instant": { "attachment": true, "cost": { "cache_read": 0.16, "input": 1.6, "output": 13 }, "description": "GPT-5.3-Instant is an AI model provided by poe.", "id": "openai/gpt-5.3-instant", "last_updated": "2026-03-03", "limit": { "context": 128000, "input": 111616, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.3-Instant", "open_weights": false, "reasoning": false, "release_date": "2026-03-03", "temperature": false, "tool_call": true }, "openai/gpt-5.4": { "attachment": true, "cost": { "cache_read": 0.22, "input": 2.2, "output": 14 }, "description": "GPT-5.4 is an AI model provided by poe.", "id": "openai/gpt-5.4", "last_updated": "2026-02-26", "limit": { "context": 1050000, "input": 922000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "image" ] }, "name": "GPT-5.4", "open_weights": false, "reasoning": true, "release_date": "2026-02-26", "temperature": false, "tool_call": true }, "openai/gpt-5.4-mini": { "attachment": true, "cost": { "cache_read": 0.068, "input": 0.68, "output": 4 }, "description": "GPT-5.4-Mini is an AI model provided by poe.", "id": "openai/gpt-5.4-mini", "last_updated": "2026-03-12", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.4-Mini", "open_weights": false, "reasoning": true, "release_date": "2026-03-12", "temperature": false, "tool_call": true }, "openai/gpt-5.4-nano": { "attachment": true, "cost": { "cache_read": 0.018, "input": 0.18, "output": 1.1 }, "description": "GPT-5.4-Nano is an AI model provided by poe.", "id": "openai/gpt-5.4-nano", "last_updated": "2026-03-11", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.4-Nano", "open_weights": false, "reasoning": true, "release_date": "2026-03-11", "temperature": false, "tool_call": true }, "openai/gpt-5.4-pro": { "attachment": true, "cost": { "input": 27, "output": 160 }, "description": "GPT-5.4-Pro is an AI model provided by poe.", "id": "openai/gpt-5.4-pro", "last_updated": "2026-03-05", "limit": { "context": 1050000, "input": 922000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "image" ] }, "name": "GPT-5.4-Pro", "open_weights": false, "reasoning": true, "release_date": "2026-03-05", "temperature": false, "tool_call": true }, "openai/gpt-5.5": { "attachment": true, "cost": { "cache_read": 0.4545, "input": 4.5455, "output": 27.2727 }, "description": "GPT-5.5 is an AI model provided by poe.", "family": "gpt", "id": "openai/gpt-5.5", "knowledge": "2025-12-01", "last_updated": "2026-04-08", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text", "image" ] }, "name": "GPT-5.5", "open_weights": false, "reasoning": true, "release_date": "2026-04-08", "structured_output": true, "temperature": false, "tool_call": true }, "openai/gpt-5.5-pro": { "attachment": true, "cost": { "input": 27.2727, "output": 163.6364 }, "description": "GPT-5.5-Pro is an AI model provided by poe.", "family": "gpt-pro", "id": "openai/gpt-5.5-pro", "knowledge": "2025-12-01", "last_updated": "2026-04-08", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text", "image" ] }, "name": "GPT-5.5-Pro", "open_weights": false, "reasoning": true, "release_date": "2026-04-08", "structured_output": false, "temperature": false, "tool_call": true }, "openai/gpt-image-1": { "attachment": true, "description": "GPT-Image-1 is an AI model provided by poe.", "family": "gpt", "id": "openai/gpt-image-1", "last_updated": "2025-03-31", "limit": { "context": 128000, "output": 0 }, "modalities": { "input": [ "text", "image" ], "output": [ "image" ] }, "name": "GPT-Image-1", "open_weights": false, "reasoning": false, "release_date": "2025-03-31", "temperature": false, "tool_call": true }, "openai/gpt-image-1-mini": { "attachment": true, "description": "GPT-Image-1-Mini is an AI model provided by poe.", "family": "gpt", "id": "openai/gpt-image-1-mini", "last_updated": "2025-08-26", "limit": { "context": 0, "output": 0 }, "modalities": { "input": [ "text", "image" ], "output": [ "image" ] }, "name": "GPT-Image-1-Mini", "open_weights": false, "reasoning": false, "release_date": "2025-08-26", "temperature": false, "tool_call": true }, "openai/gpt-image-1.5": { "attachment": true, "description": "gpt-image-1.5 is an AI model provided by poe.", "id": "openai/gpt-image-1.5", "last_updated": "2025-12-16", "limit": { "context": 128000, "output": 0 }, "modalities": { "input": [ "text", "image" ], "output": [ "image" ] }, "name": "gpt-image-1.5", "open_weights": false, "reasoning": false, "release_date": "2025-12-16", "temperature": false, "tool_call": false }, "openai/gpt-image-2": { "attachment": true, "cost": { "cache_read": 1.2626, "input": 5.0505, "output": 32.3232 }, "description": "GPT-Image-2 is an AI model provided by poe.", "id": "openai/gpt-image-2", "last_updated": "2026-04-21", "limit": { "context": 0, "output": 0 }, "modalities": { "input": [ "text", "image" ], "output": [ "image" ] }, "name": "GPT-Image-2", "open_weights": false, "reasoning": false, "release_date": "2026-04-21", "temperature": false, "tool_call": false }, "openai/o1": { "attachment": true, "cost": { "input": 14, "output": 54 }, "description": "o1 is an AI model provided by poe.", "family": "o", "id": "openai/o1", "last_updated": "2024-12-18", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "o1", "open_weights": false, "reasoning": true, "release_date": "2024-12-18", "temperature": false, "tool_call": true }, "openai/o1-pro": { "attachment": true, "cost": { "input": 140, "output": 540 }, "description": "o1-pro is an AI model provided by poe.", "family": "o-pro", "id": "openai/o1-pro", "last_updated": "2025-03-19", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "o1-pro", "open_weights": false, "reasoning": true, "release_date": "2025-03-19", "temperature": false, "tool_call": true }, "openai/o3": { "attachment": true, "cost": { "cache_read": 0.45, "input": 1.8, "output": 7.2 }, "description": "o3 is an AI model provided by poe.", "family": "o", "id": "openai/o3", "last_updated": "2025-04-16", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "o3", "open_weights": false, "reasoning": true, "release_date": "2025-04-16", "temperature": false, "tool_call": true }, "openai/o3-deep-research": { "attachment": true, "cost": { "cache_read": 2.2, "input": 9, "output": 36 }, "description": "o3-deep-research is an AI model provided by poe.", "family": "o", "id": "openai/o3-deep-research", "last_updated": "2025-06-27", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "o3-deep-research", "open_weights": false, "reasoning": true, "release_date": "2025-06-27", "temperature": false, "tool_call": true }, "openai/o3-mini": { "attachment": true, "cost": { "input": 0.99, "output": 4 }, "description": "o3-mini is an AI model provided by poe.", "family": "o-mini", "id": "openai/o3-mini", "last_updated": "2025-01-31", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "o3-mini", "open_weights": false, "reasoning": true, "release_date": "2025-01-31", "temperature": false, "tool_call": true }, "openai/o3-mini-high": { "attachment": true, "cost": { "input": 0.99, "output": 4 }, "description": "o3-mini-high is an AI model provided by poe.", "family": "o-mini", "id": "openai/o3-mini-high", "last_updated": "2025-01-31", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "o3-mini-high", "open_weights": false, "reasoning": true, "release_date": "2025-01-31", "temperature": false, "tool_call": true }, "openai/o3-pro": { "attachment": true, "cost": { "input": 18, "output": 72 }, "description": "o3-pro is an AI model provided by poe.", "family": "o-pro", "id": "openai/o3-pro", "last_updated": "2025-06-10", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "o3-pro", "open_weights": false, "reasoning": true, "release_date": "2025-06-10", "temperature": false, "tool_call": true }, "openai/o4-mini": { "attachment": true, "cost": { "cache_read": 0.25, "input": 0.99, "output": 4 }, "description": "o4-mini is an AI model provided by poe.", "family": "o-mini", "id": "openai/o4-mini", "last_updated": "2025-04-16", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "o4-mini", "open_weights": false, "reasoning": true, "release_date": "2025-04-16", "temperature": false, "tool_call": true }, "openai/o4-mini-deep-research": { "attachment": true, "cost": { "cache_read": 0.45, "input": 1.8, "output": 7.2 }, "description": "o4-mini-deep-research is an AI model provided by poe.", "family": "o-mini", "id": "openai/o4-mini-deep-research", "last_updated": "2025-06-27", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "o4-mini-deep-research", "open_weights": false, "reasoning": true, "release_date": "2025-06-27", "temperature": false, "tool_call": true }, "openai/sora-2": { "attachment": true, "description": "Sora-2 is an AI model provided by poe.", "family": "sora", "id": "openai/sora-2", "last_updated": "2025-10-06", "limit": { "context": 0, "output": 0 }, "modalities": { "input": [ "text", "image" ], "output": [ "video" ] }, "name": "Sora-2", "open_weights": false, "reasoning": false, "release_date": "2025-10-06", "temperature": false, "tool_call": true }, "openai/sora-2-pro": { "attachment": true, "description": "Sora-2-Pro is an AI model provided by poe.", "family": "sora", "id": "openai/sora-2-pro", "last_updated": "2025-10-06", "limit": { "context": 0, "output": 0 }, "modalities": { "input": [ "text", "image" ], "output": [ "video" ] }, "name": "Sora-2-Pro", "open_weights": false, "reasoning": false, "release_date": "2025-10-06", "temperature": false, "tool_call": true }, "poetools/claude-code": { "attachment": true, "description": "claude-code is an AI model provided by poe.", "id": "poetools/claude-code", "last_updated": "2025-11-27", "limit": { "context": 0, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "claude-code", "open_weights": false, "reasoning": true, "release_date": "2025-11-27", "temperature": false, "tool_call": true }, "runwayml/runway": { "attachment": true, "description": "Runway is an AI model provided by poe.", "family": "runway", "id": "runwayml/runway", "last_updated": "2024-10-11", "limit": { "context": 256, "output": 0 }, "modalities": { "input": [ "text", "image" ], "output": [ "video" ] }, "name": "Runway", "open_weights": false, "reasoning": false, "release_date": "2024-10-11", "temperature": false, "tool_call": true }, "runwayml/runway-gen-4-turbo": { "attachment": true, "description": "Runway-Gen-4-Turbo is an AI model provided by poe.", "family": "runway", "id": "runwayml/runway-gen-4-turbo", "last_updated": "2025-05-09", "limit": { "context": 256, "output": 0 }, "modalities": { "input": [ "text", "image" ], "output": [ "video" ] }, "name": "Runway-Gen-4-Turbo", "open_weights": false, "reasoning": false, "release_date": "2025-05-09", "temperature": false, "tool_call": true }, "stabilityai/stablediffusionxl": { "attachment": true, "description": "StableDiffusionXL is an AI model provided by poe.", "family": "stable-diffusion", "id": "stabilityai/stablediffusionxl", "last_updated": "2023-07-09", "limit": { "context": 200, "output": 0 }, "modalities": { "input": [ "text", "image" ], "output": [ "image" ] }, "name": "StableDiffusionXL", "open_weights": false, "reasoning": false, "release_date": "2023-07-09", "temperature": false, "tool_call": true }, "topazlabs-co/topazlabs": { "attachment": true, "description": "TopazLabs is an AI model provided by poe.", "family": "topazlabs", "id": "topazlabs-co/topazlabs", "last_updated": "2024-12-03", "limit": { "context": 204, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "name": "TopazLabs", "open_weights": false, "reasoning": false, "release_date": "2024-12-03", "temperature": false, "tool_call": true }, "trytako/tako": { "attachment": true, "description": "Tako is an AI model provided by poe.", "family": "tako", "id": "trytako/tako", "last_updated": "2024-08-15", "limit": { "context": 2048, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Tako", "open_weights": false, "reasoning": false, "release_date": "2024-08-15", "temperature": false, "tool_call": true }, "xai/grok-3": { "attachment": true, "cost": { "cache_read": 0.75, "input": 3, "output": 15 }, "description": "Grok 3 is an AI model provided by poe.", "family": "grok", "id": "xai/grok-3", "last_updated": "2025-04-11", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok 3", "open_weights": false, "reasoning": false, "release_date": "2025-04-11", "temperature": false, "tool_call": true }, "xai/grok-3-mini": { "attachment": true, "cost": { "cache_read": 0.075, "input": 0.3, "output": 0.5 }, "description": "Grok 3 Mini is an AI model provided by poe.", "family": "grok", "id": "xai/grok-3-mini", "last_updated": "2025-04-11", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok 3 Mini", "open_weights": false, "reasoning": true, "release_date": "2025-04-11", "temperature": false, "tool_call": true }, "xai/grok-4": { "attachment": true, "cost": { "cache_read": 0.75, "input": 3, "output": 15 }, "description": "Grok-4 is an AI model provided by poe.", "family": "grok", "id": "xai/grok-4", "last_updated": "2025-07-10", "limit": { "context": 256000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok-4", "open_weights": false, "reasoning": true, "release_date": "2025-07-10", "temperature": false, "tool_call": true }, "xai/grok-4-fast-non-reasoning": { "attachment": true, "cost": { "cache_read": 0.05, "input": 0.2, "output": 0.5 }, "description": "Grok-4-Fast-Non-Reasoning is an AI model provided by poe.", "family": "grok", "id": "xai/grok-4-fast-non-reasoning", "last_updated": "2025-09-16", "limit": { "context": 2000000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok-4-Fast-Non-Reasoning", "open_weights": false, "reasoning": false, "release_date": "2025-09-16", "temperature": false, "tool_call": true }, "xai/grok-4-fast-reasoning": { "attachment": true, "cost": { "cache_read": 0.05, "input": 0.2, "output": 0.5 }, "description": "Grok-4-Fast-Reasoning is an AI model provided by poe.", "family": "grok", "id": "xai/grok-4-fast-reasoning", "last_updated": "2025-09-16", "limit": { "context": 2000000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok-4-Fast-Reasoning", "open_weights": false, "reasoning": true, "release_date": "2025-09-16", "temperature": false, "tool_call": true }, "xai/grok-4.1-fast-non-reasoning": { "attachment": true, "description": "Grok-4.1-Fast-Non-Reasoning is an AI model provided by poe.", "family": "grok", "id": "xai/grok-4.1-fast-non-reasoning", "last_updated": "2025-11-19", "limit": { "context": 2000000, "output": 30000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok-4.1-Fast-Non-Reasoning", "open_weights": false, "reasoning": false, "release_date": "2025-11-19", "temperature": false, "tool_call": true }, "xai/grok-4.1-fast-reasoning": { "attachment": true, "description": "Grok-4.1-Fast-Reasoning is an AI model provided by poe.", "family": "grok", "id": "xai/grok-4.1-fast-reasoning", "last_updated": "2025-11-19", "limit": { "context": 2000000, "output": 30000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok-4.1-Fast-Reasoning", "open_weights": false, "reasoning": true, "release_date": "2025-11-19", "temperature": false, "tool_call": true }, "xai/grok-4.20-multi-agent": { "attachment": true, "cost": { "cache_read": 0.2, "input": 2, "output": 6 }, "description": "Grok-4.20-Multi-Agent is an AI model provided by poe.", "id": "xai/grok-4.20-multi-agent", "last_updated": "2026-03-13", "limit": { "context": 128000, "output": 0 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok-4.20-Multi-Agent", "open_weights": false, "reasoning": false, "release_date": "2026-03-13", "temperature": false, "tool_call": true }, "xai/grok-code-fast-1": { "attachment": true, "cost": { "cache_read": 0.02, "input": 0.2, "output": 1.5 }, "description": "Grok Code Fast 1 is an AI model provided by poe.", "family": "grok", "id": "xai/grok-code-fast-1", "last_updated": "2025-08-22", "limit": { "context": 256000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok Code Fast 1", "open_weights": false, "reasoning": true, "release_date": "2025-08-22", "temperature": false, "tool_call": true } }, "name": "Poe", "npm": "@ai-sdk/openai-compatible" }, "privatemode-ai": { "api": "http://localhost:8080/v1", "doc": "https://docs.privatemode.ai/api/overview", "env": [ "PRIVATEMODE_API_KEY", "PRIVATEMODE_ENDPOINT" ], "iconURL": "https://models.dev/logos/privatemode-ai.svg", "id": "privatemode-ai", "models": { "gemma-3-27b": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Gemma 3 27B is an AI model provided by privatemode-ai.", "family": "gemma", "id": "gemma-3-27b", "knowledge": "2024-08", "last_updated": "2025-03-12", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemma 3 27B", "open_weights": true, "reasoning": false, "release_date": "2025-03-12", "structured_output": true, "temperature": true, "tool_call": true }, "gpt-oss-120b": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "gpt-oss-120b is an AI model provided by privatemode-ai.", "family": "gpt-oss", "id": "gpt-oss-120b", "knowledge": "2025-08", "last_updated": "2025-08-14", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "gpt-oss-120b", "open_weights": true, "reasoning": true, "release_date": "2025-08-04", "structured_output": true, "temperature": true, "tool_call": true }, "qwen3-coder-30b-a3b": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Qwen3-Coder 30B-A3B is an AI model provided by privatemode-ai.", "family": "qwen", "id": "qwen3-coder-30b-a3b", "knowledge": "2025-04", "last_updated": "2025-04", "limit": { "context": 128000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3-Coder 30B-A3B", "open_weights": true, "reasoning": false, "release_date": "2025-04", "structured_output": true, "temperature": true, "tool_call": true }, "qwen3-embedding-4b": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Qwen3-Embedding 4B is an AI model provided by privatemode-ai.", "family": "qwen", "id": "qwen3-embedding-4b", "knowledge": "2025-06", "last_updated": "2025-06-06", "limit": { "context": 32000, "output": 2560 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3-Embedding 4B", "open_weights": true, "reasoning": false, "release_date": "2025-06-06", "structured_output": false, "temperature": true, "tool_call": false }, "whisper-large-v3": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Whisper large-v3 is an AI model provided by privatemode-ai.", "family": "whisper", "id": "whisper-large-v3", "knowledge": "2023-09", "last_updated": "2023-09-01", "limit": { "context": 0, "output": 4096 }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "name": "Whisper large-v3", "open_weights": true, "reasoning": false, "release_date": "2023-09-01", "structured_output": false, "temperature": true, "tool_call": false } }, "name": "Privatemode AI", "npm": "@ai-sdk/openai-compatible" }, "qihang-ai": { "api": "https://api.qhaigc.net/v1", "doc": "https://www.qhaigc.net/docs", "env": [ "QIHANG_API_KEY" ], "iconURL": "https://models.dev/logos/qihang-ai.svg", "id": "qihang-ai", "models": { "claude-haiku-4-5-20251001": { "attachment": true, "cost": { "input": 0.14, "output": 0.71 }, "description": "Claude Haiku 4.5 is an AI model provided by qihang-ai.", "family": "claude-haiku", "id": "claude-haiku-4-5-20251001", "knowledge": "2025-07-31", "last_updated": "2025-10-01", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Haiku 4.5", "open_weights": false, "reasoning": true, "release_date": "2025-10-01", "temperature": true, "tool_call": true }, "claude-opus-4-5-20251101": { "attachment": true, "cost": { "input": 0.71, "output": 3.57 }, "description": "Claude Opus 4.5 is an AI model provided by qihang-ai.", "family": "claude-opus", "id": "claude-opus-4-5-20251101", "knowledge": "2025-03", "last_updated": "2025-11-01", "limit": { "context": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Claude Opus 4.5", "open_weights": false, "reasoning": true, "release_date": "2025-11-01", "temperature": true, "tool_call": true }, "claude-sonnet-4-5-20250929": { "attachment": true, "cost": { "input": 0.43, "output": 2.14 }, "description": "Claude Sonnet 4.5 is an AI model provided by qihang-ai.", "family": "claude-sonnet", "id": "claude-sonnet-4-5-20250929", "knowledge": "2025-07-31", "last_updated": "2025-09-29", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.5", "open_weights": false, "reasoning": true, "release_date": "2025-09-29", "temperature": true, "tool_call": true }, "gemini-2.5-flash": { "attachment": true, "cost": { "context_over_200k": { "input": 0.09, "output": 0.71 }, "input": 0.09, "output": 0.71, "tiers": [ { "input": 0.09, "output": 0.71, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Gemini 2.5 Flash is an AI model provided by qihang-ai.", "family": "gemini-flash", "id": "gemini-2.5-flash", "knowledge": "2025-01", "last_updated": "2025-12-17", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Flash", "open_weights": false, "reasoning": true, "release_date": "2025-12-17", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-3-flash-preview": { "attachment": true, "cost": { "context_over_200k": { "input": 0.07, "output": 0.43 }, "input": 0.07, "output": 0.43, "tiers": [ { "input": 0.07, "output": 0.43, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Gemini 3 Flash Preview is an AI model provided by qihang-ai.", "family": "gemini-flash", "id": "gemini-3-flash-preview", "knowledge": "2025-01", "last_updated": "2025-12-17", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "name": "Gemini 3 Flash Preview", "open_weights": false, "reasoning": true, "release_date": "2025-12-17", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-3-pro-preview": { "attachment": true, "cost": { "input": 0.57, "output": 3.43 }, "description": "Gemini 3 Pro Preview is an AI model provided by qihang-ai.", "family": "gemini-pro", "id": "gemini-3-pro-preview", "knowledge": "2025-11", "last_updated": "2025-11-19", "limit": { "context": 1000000, "output": 65000 }, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "name": "Gemini 3 Pro Preview", "open_weights": false, "reasoning": true, "release_date": "2025-11-19", "temperature": true, "tool_call": true }, "gpt-5-mini": { "attachment": true, "cost": { "input": 0.04, "output": 0.29 }, "description": "GPT-5-Mini is an AI model provided by qihang-ai.", "family": "gpt-mini", "id": "gpt-5-mini", "knowledge": "2024-09-30", "last_updated": "2025-09-15", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5-Mini", "open_weights": false, "reasoning": true, "release_date": "2025-09-15", "temperature": true, "tool_call": true }, "gpt-5.2": { "attachment": true, "cost": { "input": 0.25, "output": 2 }, "description": "GPT-5.2 is an AI model provided by qihang-ai.", "family": "gpt", "id": "gpt-5.2", "knowledge": "2025-08-31", "last_updated": "2025-12-11", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.2", "open_weights": false, "reasoning": true, "release_date": "2025-12-11", "structured_output": true, "temperature": true, "tool_call": true }, "gpt-5.2-codex": { "attachment": true, "cost": { "input": 0.14, "output": 1.14 }, "description": "GPT-5.2 Codex is an AI model provided by qihang-ai.", "family": "gpt-codex", "id": "gpt-5.2-codex", "knowledge": "2025-08-31", "last_updated": "2025-12-11", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.2 Codex", "open_weights": false, "reasoning": true, "release_date": "2025-12-11", "structured_output": true, "temperature": false, "tool_call": true } }, "name": "QiHang", "npm": "@ai-sdk/openai-compatible" }, "qiniu-ai": { "api": "https://api.qnaigc.com/v1", "doc": "https://developer.qiniu.com/aitokenapi", "env": [ "QINIU_API_KEY" ], "iconURL": "https://models.dev/logos/qiniu-ai.svg", "id": "qiniu-ai", "models": { "MiniMax-M1": { "attachment": false, "description": "MiniMax M1 is an AI model provided by qiniu-ai.", "id": "MiniMax-M1", "last_updated": "2025-08-05", "limit": { "context": 1000000, "output": 80000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M1", "open_weights": false, "reasoning": true, "release_date": "2025-08-05", "structured_output": false, "temperature": true, "tool_call": true }, "claude-3.5-haiku": { "attachment": true, "description": "Claude 3.5 Haiku is an AI model provided by qiniu-ai.", "id": "claude-3.5-haiku", "last_updated": "2025-08-26", "limit": { "context": 200000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Claude 3.5 Haiku", "open_weights": false, "reasoning": false, "release_date": "2025-08-26", "structured_output": false, "temperature": true, "tool_call": true }, "claude-3.5-sonnet": { "attachment": true, "description": "Claude 3.5 Sonnet is an AI model provided by qiniu-ai.", "id": "claude-3.5-sonnet", "last_updated": "2025-09-09", "limit": { "context": 200000, "output": 8200 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Claude 3.5 Sonnet", "open_weights": false, "reasoning": true, "release_date": "2025-09-09", "structured_output": false, "temperature": true, "tool_call": true }, "claude-3.7-sonnet": { "attachment": true, "description": "Claude 3.7 Sonnet is an AI model provided by qiniu-ai.", "id": "claude-3.7-sonnet", "last_updated": "2025-08-05", "limit": { "context": 200000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Claude 3.7 Sonnet", "open_weights": false, "reasoning": true, "release_date": "2025-08-05", "structured_output": false, "temperature": true, "tool_call": true }, "claude-4.0-opus": { "attachment": true, "description": "Claude 4.0 Opus is an AI model provided by qiniu-ai.", "id": "claude-4.0-opus", "last_updated": "2025-08-05", "limit": { "context": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Claude 4.0 Opus", "open_weights": false, "reasoning": true, "release_date": "2025-08-05", "structured_output": false, "temperature": true, "tool_call": true }, "claude-4.0-sonnet": { "attachment": true, "description": "Claude 4.0 Sonnet is an AI model provided by qiniu-ai.", "id": "claude-4.0-sonnet", "last_updated": "2025-08-05", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Claude 4.0 Sonnet", "open_weights": false, "reasoning": true, "release_date": "2025-08-05", "structured_output": false, "temperature": true, "tool_call": true }, "claude-4.1-opus": { "attachment": true, "description": "Claude 4.1 Opus is an AI model provided by qiniu-ai.", "id": "claude-4.1-opus", "last_updated": "2025-08-06", "limit": { "context": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Claude 4.1 Opus", "open_weights": false, "reasoning": true, "release_date": "2025-08-06", "structured_output": false, "temperature": true, "tool_call": true }, "claude-4.5-haiku": { "attachment": true, "description": "Claude 4.5 Haiku is an AI model provided by qiniu-ai.", "id": "claude-4.5-haiku", "last_updated": "2025-10-16", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Claude 4.5 Haiku", "open_weights": false, "reasoning": true, "release_date": "2025-10-16", "structured_output": false, "temperature": true, "tool_call": true }, "claude-4.5-opus": { "attachment": true, "description": "Claude 4.5 Opus is an AI model provided by qiniu-ai.", "id": "claude-4.5-opus", "last_updated": "2025-11-25", "limit": { "context": 200000, "output": 200000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Claude 4.5 Opus", "open_weights": false, "reasoning": true, "release_date": "2025-11-25", "structured_output": false, "temperature": true, "tool_call": true }, "claude-4.5-sonnet": { "attachment": true, "description": "Claude 4.5 Sonnet is an AI model provided by qiniu-ai.", "id": "claude-4.5-sonnet", "last_updated": "2025-09-30", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Claude 4.5 Sonnet", "open_weights": false, "reasoning": true, "release_date": "2025-09-30", "structured_output": false, "temperature": true, "tool_call": true }, "deepseek-r1": { "attachment": false, "description": "DeepSeek-R1 is an AI model provided by qiniu-ai.", "id": "deepseek-r1", "last_updated": "2025-08-05", "limit": { "context": 128000, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek-R1", "open_weights": false, "reasoning": true, "release_date": "2025-08-05", "structured_output": false, "temperature": true, "tool_call": true }, "deepseek-r1-0528": { "attachment": false, "description": "DeepSeek-R1-0528 is an AI model provided by qiniu-ai.", "id": "deepseek-r1-0528", "last_updated": "2025-08-05", "limit": { "context": 128000, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek-R1-0528", "open_weights": false, "reasoning": true, "release_date": "2025-08-05", "structured_output": false, "temperature": true, "tool_call": true }, "deepseek-v3": { "attachment": false, "description": "DeepSeek-V3 is an AI model provided by qiniu-ai.", "id": "deepseek-v3", "last_updated": "2025-08-13", "limit": { "context": 128000, "output": 16000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek-V3", "open_weights": false, "reasoning": false, "release_date": "2025-08-13", "structured_output": false, "temperature": true, "tool_call": false }, "deepseek-v3-0324": { "attachment": false, "description": "DeepSeek-V3-0324 is an AI model provided by qiniu-ai.", "id": "deepseek-v3-0324", "last_updated": "2025-08-05", "limit": { "context": 128000, "output": 16000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek-V3-0324", "open_weights": false, "reasoning": false, "release_date": "2025-08-05", "structured_output": false, "temperature": true, "tool_call": true }, "deepseek-v3.1": { "attachment": false, "description": "DeepSeek-V3.1 is an AI model provided by qiniu-ai.", "id": "deepseek-v3.1", "last_updated": "2025-08-19", "limit": { "context": 128000, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek-V3.1", "open_weights": false, "reasoning": true, "release_date": "2025-08-19", "structured_output": false, "temperature": true, "tool_call": true }, "deepseek/deepseek-math-v2": { "attachment": false, "description": "Deepseek/Deepseek-Math-V2 is an AI model provided by qiniu-ai.", "id": "deepseek/deepseek-math-v2", "last_updated": "2025-12-04", "limit": { "context": 160000, "output": 160000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Deepseek/Deepseek-Math-V2", "open_weights": false, "reasoning": true, "release_date": "2025-12-04", "structured_output": false, "temperature": true, "tool_call": false }, "deepseek/deepseek-v3.1-terminus": { "attachment": false, "description": "DeepSeek/DeepSeek-V3.1-Terminus is an AI model provided by qiniu-ai.", "id": "deepseek/deepseek-v3.1-terminus", "last_updated": "2025-09-22", "limit": { "context": 128000, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek/DeepSeek-V3.1-Terminus", "open_weights": false, "reasoning": false, "release_date": "2025-09-22", "structured_output": false, "temperature": true, "tool_call": true }, "deepseek/deepseek-v3.1-terminus-thinking": { "attachment": false, "description": "DeepSeek/DeepSeek-V3.1-Terminus-Thinking is an AI model provided by qiniu-ai.", "id": "deepseek/deepseek-v3.1-terminus-thinking", "last_updated": "2025-09-22", "limit": { "context": 128000, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek/DeepSeek-V3.1-Terminus-Thinking", "open_weights": false, "reasoning": true, "release_date": "2025-09-22", "structured_output": false, "temperature": true, "tool_call": false }, "deepseek/deepseek-v3.2-251201": { "attachment": false, "description": "Deepseek/DeepSeek-V3.2 is an AI model provided by qiniu-ai.", "id": "deepseek/deepseek-v3.2-251201", "last_updated": "2025-12-01", "limit": { "context": 128000, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Deepseek/DeepSeek-V3.2", "open_weights": false, "reasoning": true, "release_date": "2025-12-01", "structured_output": false, "temperature": true, "tool_call": true }, "deepseek/deepseek-v3.2-exp": { "attachment": false, "description": "DeepSeek/DeepSeek-V3.2-Exp is an AI model provided by qiniu-ai.", "id": "deepseek/deepseek-v3.2-exp", "last_updated": "2025-09-29", "limit": { "context": 128000, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek/DeepSeek-V3.2-Exp", "open_weights": false, "reasoning": false, "release_date": "2025-09-29", "structured_output": false, "temperature": true, "tool_call": true }, "deepseek/deepseek-v3.2-exp-thinking": { "attachment": false, "description": "DeepSeek/DeepSeek-V3.2-Exp-Thinking is an AI model provided by qiniu-ai.", "id": "deepseek/deepseek-v3.2-exp-thinking", "last_updated": "2025-09-29", "limit": { "context": 128000, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek/DeepSeek-V3.2-Exp-Thinking", "open_weights": false, "reasoning": true, "release_date": "2025-09-29", "structured_output": false, "temperature": true, "tool_call": false }, "doubao-1.5-pro-32k": { "attachment": false, "description": "Doubao 1.5 Pro 32k is an AI model provided by qiniu-ai.", "id": "doubao-1.5-pro-32k", "last_updated": "2025-08-05", "limit": { "context": 128000, "output": 12000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Doubao 1.5 Pro 32k", "open_weights": false, "reasoning": false, "release_date": "2025-08-05", "structured_output": false, "temperature": true, "tool_call": true }, "doubao-1.5-thinking-pro": { "attachment": false, "description": "Doubao 1.5 Thinking Pro is an AI model provided by qiniu-ai.", "id": "doubao-1.5-thinking-pro", "last_updated": "2025-08-05", "limit": { "context": 128000, "output": 16000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Doubao 1.5 Thinking Pro", "open_weights": false, "reasoning": true, "release_date": "2025-08-05", "structured_output": false, "temperature": true, "tool_call": true }, "doubao-1.5-vision-pro": { "attachment": true, "description": "Doubao 1.5 Vision Pro is an AI model provided by qiniu-ai.", "id": "doubao-1.5-vision-pro", "last_updated": "2025-08-05", "limit": { "context": 128000, "output": 16000 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Doubao 1.5 Vision Pro", "open_weights": false, "reasoning": false, "release_date": "2025-08-05", "structured_output": false, "temperature": true, "tool_call": false }, "doubao-seed-1.6": { "attachment": true, "description": "Doubao-Seed 1.6 is an AI model provided by qiniu-ai.", "id": "doubao-seed-1.6", "last_updated": "2025-08-15", "limit": { "context": 256000, "output": 32000 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Doubao-Seed 1.6", "open_weights": false, "reasoning": true, "release_date": "2025-08-15", "structured_output": false, "temperature": true, "tool_call": true }, "doubao-seed-1.6-flash": { "attachment": true, "description": "Doubao-Seed 1.6 Flash is an AI model provided by qiniu-ai.", "id": "doubao-seed-1.6-flash", "last_updated": "2025-08-15", "limit": { "context": 256000, "output": 32000 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Doubao-Seed 1.6 Flash", "open_weights": false, "reasoning": true, "release_date": "2025-08-15", "structured_output": false, "temperature": true, "tool_call": true }, "doubao-seed-1.6-thinking": { "attachment": true, "description": "Doubao-Seed 1.6 Thinking is an AI model provided by qiniu-ai.", "id": "doubao-seed-1.6-thinking", "last_updated": "2025-08-15", "limit": { "context": 256000, "output": 32000 }, "modalities": { "input": [ "image", "text", "video" ], "output": [ "text" ] }, "name": "Doubao-Seed 1.6 Thinking", "open_weights": false, "reasoning": true, "release_date": "2025-08-15", "structured_output": false, "temperature": true, "tool_call": true }, "doubao-seed-2.0-code": { "attachment": true, "description": "Doubao Seed 2.0 Code is an AI model provided by qiniu-ai.", "id": "doubao-seed-2.0-code", "last_updated": "2026-02-14", "limit": { "context": 256000, "output": 128000 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Doubao Seed 2.0 Code", "open_weights": false, "reasoning": true, "release_date": "2026-02-14", "structured_output": false, "temperature": true, "tool_call": true }, "doubao-seed-2.0-lite": { "attachment": true, "description": "Doubao Seed 2.0 Lite is an AI model provided by qiniu-ai.", "id": "doubao-seed-2.0-lite", "last_updated": "2026-02-14", "limit": { "context": 256000, "output": 32000 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Doubao Seed 2.0 Lite", "open_weights": false, "reasoning": true, "release_date": "2026-02-14", "structured_output": false, "temperature": true, "tool_call": true }, "doubao-seed-2.0-mini": { "attachment": true, "description": "Doubao Seed 2.0 Mini is an AI model provided by qiniu-ai.", "id": "doubao-seed-2.0-mini", "last_updated": "2026-02-14", "limit": { "context": 256000, "output": 32000 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Doubao Seed 2.0 Mini", "open_weights": false, "reasoning": true, "release_date": "2026-02-14", "structured_output": false, "temperature": true, "tool_call": true }, "doubao-seed-2.0-pro": { "attachment": true, "description": "Doubao Seed 2.0 Pro is an AI model provided by qiniu-ai.", "id": "doubao-seed-2.0-pro", "last_updated": "2026-02-14", "limit": { "context": 256000, "output": 128000 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Doubao Seed 2.0 Pro", "open_weights": false, "reasoning": true, "release_date": "2026-02-14", "structured_output": false, "temperature": true, "tool_call": true }, "gemini-2.0-flash": { "attachment": true, "description": "Gemini 2.0 Flash is an AI model provided by qiniu-ai.", "id": "gemini-2.0-flash", "last_updated": "2025-08-05", "limit": { "context": 1048576, "output": 8192 }, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "name": "Gemini 2.0 Flash", "open_weights": false, "reasoning": false, "release_date": "2025-08-05", "structured_output": false, "temperature": true, "tool_call": true }, "gemini-2.0-flash-lite": { "attachment": true, "description": "Gemini 2.0 Flash Lite is an AI model provided by qiniu-ai.", "id": "gemini-2.0-flash-lite", "last_updated": "2025-08-05", "limit": { "context": 1048576, "output": 8192 }, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "name": "Gemini 2.0 Flash Lite", "open_weights": false, "reasoning": true, "release_date": "2025-08-05", "structured_output": false, "temperature": true, "tool_call": true }, "gemini-2.5-flash": { "attachment": true, "description": "Gemini 2.5 Flash is an AI model provided by qiniu-ai.", "id": "gemini-2.5-flash", "last_updated": "2025-08-05", "limit": { "context": 1048576, "output": 64000 }, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "name": "Gemini 2.5 Flash", "open_weights": false, "reasoning": true, "release_date": "2025-08-05", "structured_output": false, "temperature": true, "tool_call": true }, "gemini-2.5-flash-image": { "attachment": true, "description": "Gemini 2.5 Flash Image is an AI model provided by qiniu-ai.", "id": "gemini-2.5-flash-image", "last_updated": "2025-10-22", "limit": { "context": 32768, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "image" ] }, "name": "Gemini 2.5 Flash Image", "open_weights": false, "reasoning": false, "release_date": "2025-10-22", "structured_output": false, "temperature": true, "tool_call": false }, "gemini-2.5-flash-lite": { "attachment": true, "description": "Gemini 2.5 Flash Lite is an AI model provided by qiniu-ai.", "id": "gemini-2.5-flash-lite", "last_updated": "2025-08-05", "limit": { "context": 1048576, "output": 64000 }, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "name": "Gemini 2.5 Flash Lite", "open_weights": false, "reasoning": false, "release_date": "2025-08-05", "structured_output": false, "temperature": true, "tool_call": true }, "gemini-2.5-pro": { "attachment": true, "description": "Gemini 2.5 Pro is an AI model provided by qiniu-ai.", "id": "gemini-2.5-pro", "last_updated": "2025-08-05", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text" ] }, "name": "Gemini 2.5 Pro", "open_weights": false, "reasoning": true, "release_date": "2025-08-05", "structured_output": false, "temperature": true, "tool_call": true }, "gemini-3.0-flash-preview": { "attachment": true, "description": "Gemini 3.0 Flash Preview is an AI model provided by qiniu-ai.", "id": "gemini-3.0-flash-preview", "last_updated": "2025-12-18", "limit": { "context": 1000000, "output": 64000 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 3.0 Flash Preview", "open_weights": false, "reasoning": true, "release_date": "2025-12-18", "structured_output": false, "temperature": true, "tool_call": true }, "gemini-3.0-pro-image-preview": { "attachment": true, "description": "Gemini 3.0 Pro Image Preview is an AI model provided by qiniu-ai.", "id": "gemini-3.0-pro-image-preview", "last_updated": "2025-11-20", "limit": { "context": 32768, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text", "image" ] }, "name": "Gemini 3.0 Pro Image Preview", "open_weights": false, "reasoning": false, "release_date": "2025-11-20", "structured_output": false, "temperature": true, "tool_call": false }, "gemini-3.0-pro-preview": { "attachment": true, "description": "Gemini 3.0 Pro Preview is an AI model provided by qiniu-ai.", "id": "gemini-3.0-pro-preview", "last_updated": "2025-11-19", "limit": { "context": 1000000, "output": 64000 }, "modalities": { "input": [ "text", "image", "video", "pdf", "audio" ], "output": [ "text" ] }, "name": "Gemini 3.0 Pro Preview", "open_weights": false, "reasoning": true, "release_date": "2025-11-19", "structured_output": false, "temperature": true, "tool_call": true }, "glm-4.5": { "attachment": false, "description": "GLM 4.5 is an AI model provided by qiniu-ai.", "id": "glm-4.5", "last_updated": "2025-08-05", "limit": { "context": 131072, "output": 98304 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.5", "open_weights": false, "reasoning": true, "release_date": "2025-08-05", "structured_output": false, "temperature": true, "tool_call": true }, "glm-4.5-air": { "attachment": false, "description": "GLM 4.5 Air is an AI model provided by qiniu-ai.", "id": "glm-4.5-air", "last_updated": "2025-08-05", "limit": { "context": 131000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.5 Air", "open_weights": false, "reasoning": true, "release_date": "2025-08-05", "structured_output": false, "temperature": true, "tool_call": true }, "gpt-oss-120b": { "attachment": false, "description": "gpt-oss-120b is an AI model provided by qiniu-ai.", "id": "gpt-oss-120b", "last_updated": "2025-08-06", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "gpt-oss-120b", "open_weights": false, "reasoning": true, "release_date": "2025-08-06", "structured_output": false, "temperature": true, "tool_call": true }, "gpt-oss-20b": { "attachment": false, "description": "gpt-oss-20b is an AI model provided by qiniu-ai.", "id": "gpt-oss-20b", "last_updated": "2025-08-06", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "gpt-oss-20b", "open_weights": false, "reasoning": true, "release_date": "2025-08-06", "structured_output": false, "temperature": true, "tool_call": true }, "kimi-k2": { "attachment": false, "description": "Kimi K2 is an AI model provided by qiniu-ai.", "id": "kimi-k2", "last_updated": "2025-08-05", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2", "open_weights": false, "reasoning": false, "release_date": "2025-08-05", "structured_output": false, "temperature": true, "tool_call": true }, "kling-v2-6": { "attachment": true, "description": "Kling-V2 6 is an AI model provided by qiniu-ai.", "id": "kling-v2-6", "last_updated": "2026-01-13", "limit": { "context": 99999999, "output": 99999999 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "video" ] }, "name": "Kling-V2 6", "open_weights": false, "reasoning": false, "release_date": "2026-01-13", "structured_output": false, "temperature": true, "tool_call": false }, "meituan/longcat-flash-chat": { "attachment": false, "description": "Meituan/Longcat-Flash-Chat is an AI model provided by qiniu-ai.", "id": "meituan/longcat-flash-chat", "last_updated": "2025-11-05", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Meituan/Longcat-Flash-Chat", "open_weights": false, "reasoning": false, "release_date": "2025-11-05", "structured_output": false, "temperature": true, "tool_call": false }, "meituan/longcat-flash-lite": { "attachment": false, "description": "Meituan/Longcat-Flash-Lite is an AI model provided by qiniu-ai.", "id": "meituan/longcat-flash-lite", "last_updated": "2026-02-06", "limit": { "context": 256000, "output": 320000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Meituan/Longcat-Flash-Lite", "open_weights": false, "reasoning": false, "release_date": "2026-02-06", "structured_output": false, "temperature": true, "tool_call": true }, "mimo-v2-flash": { "attachment": false, "cost": { "cache_read": 0.01, "input": 0.1, "output": 0.3 }, "description": "Mimo-V2-Flash is an AI model provided by qiniu-ai.", "family": "mimo", "id": "mimo-v2-flash", "knowledge": "2024-12-01", "last_updated": "2026-02-04", "limit": { "context": 256000, "output": 256000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mimo-V2-Flash", "open_weights": true, "reasoning": true, "release_date": "2025-12-16", "temperature": true, "tool_call": true }, "minimax/minimax-m2": { "attachment": false, "description": "Minimax/Minimax-M2 is an AI model provided by qiniu-ai.", "id": "minimax/minimax-m2", "last_updated": "2025-10-28", "limit": { "context": 200000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Minimax/Minimax-M2", "open_weights": false, "reasoning": true, "release_date": "2025-10-28", "structured_output": false, "temperature": true, "tool_call": true }, "minimax/minimax-m2.1": { "attachment": false, "description": "Minimax/Minimax-M2.1 is an AI model provided by qiniu-ai.", "id": "minimax/minimax-m2.1", "last_updated": "2025-12-23", "limit": { "context": 204800, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Minimax/Minimax-M2.1", "open_weights": false, "reasoning": true, "release_date": "2025-12-23", "structured_output": false, "temperature": true, "tool_call": true }, "minimax/minimax-m2.5": { "attachment": false, "description": "Minimax/Minimax-M2.5 is an AI model provided by qiniu-ai.", "id": "minimax/minimax-m2.5", "last_updated": "2026-02-12", "limit": { "context": 204800, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Minimax/Minimax-M2.5", "open_weights": false, "reasoning": true, "release_date": "2026-02-12", "structured_output": false, "temperature": true, "tool_call": true }, "minimax/minimax-m2.5-highspeed": { "attachment": false, "description": "Minimax/Minimax-M2.5 Highspeed is an AI model provided by qiniu-ai.", "id": "minimax/minimax-m2.5-highspeed", "last_updated": "2026-02-14", "limit": { "context": 204800, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Minimax/Minimax-M2.5 Highspeed", "open_weights": false, "reasoning": true, "release_date": "2026-02-14", "structured_output": false, "temperature": true, "tool_call": true }, "moonshotai/kimi-k2-0905": { "attachment": false, "description": "Kimi K2 0905 is an AI model provided by qiniu-ai.", "id": "moonshotai/kimi-k2-0905", "last_updated": "2025-09-08", "limit": { "context": 256000, "output": 100000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 0905", "open_weights": false, "reasoning": false, "release_date": "2025-09-08", "structured_output": false, "temperature": true, "tool_call": true }, "moonshotai/kimi-k2-thinking": { "attachment": false, "description": "Kimi K2 Thinking is an AI model provided by qiniu-ai.", "id": "moonshotai/kimi-k2-thinking", "last_updated": "2025-11-07", "limit": { "context": 256000, "output": 100000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 Thinking", "open_weights": false, "reasoning": false, "release_date": "2025-11-07", "structured_output": false, "temperature": true, "tool_call": true }, "moonshotai/kimi-k2.5": { "attachment": true, "description": "Moonshotai/Kimi-K2.5 is an AI model provided by qiniu-ai.", "id": "moonshotai/kimi-k2.5", "last_updated": "2026-01-28", "limit": { "context": 256000, "output": 256000 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Moonshotai/Kimi-K2.5", "open_weights": false, "reasoning": false, "release_date": "2026-01-28", "structured_output": false, "temperature": true, "tool_call": true }, "openai/gpt-5": { "attachment": false, "description": "OpenAI/GPT-5 is an AI model provided by qiniu-ai.", "id": "openai/gpt-5", "last_updated": "2025-09-19", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "OpenAI/GPT-5", "open_weights": false, "reasoning": false, "release_date": "2025-09-19", "structured_output": false, "temperature": true, "tool_call": true }, "openai/gpt-5.2": { "attachment": true, "description": "OpenAI/GPT-5.2 is an AI model provided by qiniu-ai.", "id": "openai/gpt-5.2", "last_updated": "2025-12-11", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "OpenAI/GPT-5.2", "open_weights": false, "reasoning": true, "release_date": "2025-12-11", "structured_output": false, "temperature": true, "tool_call": true }, "qwen-max-2025-01-25": { "attachment": false, "description": "Qwen2.5-Max-2025-01-25 is an AI model provided by qiniu-ai.", "id": "qwen-max-2025-01-25", "last_updated": "2025-08-05", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen2.5-Max-2025-01-25", "open_weights": false, "reasoning": false, "release_date": "2025-08-05", "structured_output": false, "temperature": true, "tool_call": true }, "qwen-turbo": { "attachment": false, "description": "Qwen-Turbo is an AI model provided by qiniu-ai.", "id": "qwen-turbo", "last_updated": "2025-08-05", "limit": { "context": 1000000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen-Turbo", "open_weights": false, "reasoning": true, "release_date": "2025-08-05", "structured_output": false, "temperature": true, "tool_call": true }, "qwen-vl-max-2025-01-25": { "attachment": true, "description": "Qwen VL-MAX-2025-01-25 is an AI model provided by qiniu-ai.", "id": "qwen-vl-max-2025-01-25", "last_updated": "2025-08-05", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "name": "Qwen VL-MAX-2025-01-25", "open_weights": false, "reasoning": false, "release_date": "2025-08-05", "structured_output": false, "temperature": true, "tool_call": true }, "qwen2.5-vl-72b-instruct": { "attachment": true, "description": "Qwen 2.5 VL 72B Instruct is an AI model provided by qiniu-ai.", "id": "qwen2.5-vl-72b-instruct", "last_updated": "2025-08-05", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "name": "Qwen 2.5 VL 72B Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-08-05", "structured_output": false, "temperature": true, "tool_call": true }, "qwen2.5-vl-7b-instruct": { "attachment": true, "description": "Qwen 2.5 VL 7B Instruct is an AI model provided by qiniu-ai.", "id": "qwen2.5-vl-7b-instruct", "last_updated": "2025-08-05", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "name": "Qwen 2.5 VL 7B Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-08-05", "structured_output": false, "temperature": true, "tool_call": true }, "qwen3-235b-a22b": { "attachment": false, "description": "Qwen 3 235B A22B is an AI model provided by qiniu-ai.", "id": "qwen3-235b-a22b", "last_updated": "2025-08-05", "limit": { "context": 128000, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen 3 235B A22B", "open_weights": false, "reasoning": false, "release_date": "2025-08-05", "structured_output": false, "temperature": true, "tool_call": true }, "qwen3-235b-a22b-instruct-2507": { "attachment": false, "description": "Qwen3 235b A22B Instruct 2507 is an AI model provided by qiniu-ai.", "id": "qwen3-235b-a22b-instruct-2507", "last_updated": "2025-08-12", "limit": { "context": 262144, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 235b A22B Instruct 2507", "open_weights": false, "reasoning": false, "release_date": "2025-08-12", "structured_output": false, "temperature": true, "tool_call": true }, "qwen3-235b-a22b-thinking-2507": { "attachment": false, "description": "Qwen3 235B A22B Thinking 2507 is an AI model provided by qiniu-ai.", "id": "qwen3-235b-a22b-thinking-2507", "last_updated": "2025-08-12", "limit": { "context": 262144, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 235B A22B Thinking 2507", "open_weights": false, "reasoning": true, "release_date": "2025-08-12", "structured_output": false, "temperature": true, "tool_call": true }, "qwen3-30b-a3b": { "attachment": false, "description": "Qwen3 30B A3B is an AI model provided by qiniu-ai.", "id": "qwen3-30b-a3b", "last_updated": "2025-08-05", "limit": { "context": 40000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 30B A3B", "open_weights": false, "reasoning": true, "release_date": "2025-08-05", "structured_output": false, "temperature": true, "tool_call": true }, "qwen3-30b-a3b-instruct-2507": { "attachment": false, "description": "Qwen3 30b A3b Instruct 2507 is an AI model provided by qiniu-ai.", "id": "qwen3-30b-a3b-instruct-2507", "last_updated": "2026-02-04", "limit": { "context": 128000, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 30b A3b Instruct 2507", "open_weights": false, "reasoning": false, "release_date": "2026-02-04", "structured_output": false, "temperature": true, "tool_call": true }, "qwen3-30b-a3b-thinking-2507": { "attachment": false, "description": "Qwen3 30b A3b Thinking 2507 is an AI model provided by qiniu-ai.", "id": "qwen3-30b-a3b-thinking-2507", "last_updated": "2026-02-04", "limit": { "context": 126000, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 30b A3b Thinking 2507", "open_weights": false, "reasoning": true, "release_date": "2026-02-04", "structured_output": false, "temperature": true, "tool_call": true }, "qwen3-32b": { "attachment": false, "description": "Qwen3 32B is an AI model provided by qiniu-ai.", "id": "qwen3-32b", "last_updated": "2025-08-05", "limit": { "context": 40000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 32B", "open_weights": false, "reasoning": true, "release_date": "2025-08-05", "structured_output": false, "temperature": true, "tool_call": true }, "qwen3-coder-480b-a35b-instruct": { "attachment": false, "description": "Qwen3 Coder 480B A35B Instruct is an AI model provided by qiniu-ai.", "id": "qwen3-coder-480b-a35b-instruct", "last_updated": "2025-08-14", "limit": { "context": 262000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Coder 480B A35B Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-08-14", "structured_output": false, "temperature": true, "tool_call": true }, "qwen3-max": { "attachment": false, "description": "Qwen3 Max is an AI model provided by qiniu-ai.", "id": "qwen3-max", "last_updated": "2025-09-24", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Max", "open_weights": false, "reasoning": false, "release_date": "2025-09-24", "structured_output": false, "temperature": true, "tool_call": true }, "qwen3-max-preview": { "attachment": false, "description": "Qwen3 Max Preview is an AI model provided by qiniu-ai.", "id": "qwen3-max-preview", "last_updated": "2025-09-06", "limit": { "context": 256000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Max Preview", "open_weights": false, "reasoning": false, "release_date": "2025-09-06", "structured_output": false, "temperature": true, "tool_call": true }, "qwen3-next-80b-a3b-instruct": { "attachment": false, "description": "Qwen3 Next 80B A3B Instruct is an AI model provided by qiniu-ai.", "id": "qwen3-next-80b-a3b-instruct", "last_updated": "2025-09-12", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Next 80B A3B Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-09-12", "structured_output": false, "temperature": true, "tool_call": true }, "qwen3-next-80b-a3b-thinking": { "attachment": false, "description": "Qwen3 Next 80B A3B Thinking is an AI model provided by qiniu-ai.", "id": "qwen3-next-80b-a3b-thinking", "last_updated": "2025-09-12", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Next 80B A3B Thinking", "open_weights": false, "reasoning": true, "release_date": "2025-09-12", "structured_output": false, "temperature": true, "tool_call": true }, "qwen3-vl-30b-a3b-thinking": { "attachment": true, "description": "Qwen3-Vl 30b A3b Thinking is an AI model provided by qiniu-ai.", "id": "qwen3-vl-30b-a3b-thinking", "last_updated": "2026-02-09", "limit": { "context": 128000, "output": 32000 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen3-Vl 30b A3b Thinking", "open_weights": false, "reasoning": false, "release_date": "2026-02-09", "structured_output": false, "temperature": true, "tool_call": true }, "qwen3.5-397b-a17b": { "attachment": true, "description": "Qwen3.5 397B A17B is an AI model provided by qiniu-ai.", "id": "qwen3.5-397b-a17b", "last_updated": "2026-02-22", "limit": { "context": 256000, "output": 64000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen3.5 397B A17B", "open_weights": false, "reasoning": true, "release_date": "2026-02-22", "structured_output": false, "temperature": true, "tool_call": true }, "stepfun-ai/gelab-zero-4b-preview": { "attachment": true, "description": "Stepfun-Ai/Gelab Zero 4b Preview is an AI model provided by qiniu-ai.", "id": "stepfun-ai/gelab-zero-4b-preview", "last_updated": "2025-12-23", "limit": { "context": 8192, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Stepfun-Ai/Gelab Zero 4b Preview", "open_weights": false, "reasoning": false, "release_date": "2025-12-23", "structured_output": false, "temperature": true, "tool_call": true }, "stepfun/step-3.5-flash": { "attachment": true, "description": "Stepfun/Step-3.5 Flash is an AI model provided by qiniu-ai.", "id": "stepfun/step-3.5-flash", "last_updated": "2026-02-02", "limit": { "context": 64000, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Stepfun/Step-3.5 Flash", "open_weights": false, "reasoning": false, "release_date": "2026-02-02", "structured_output": false, "temperature": true, "tool_call": false }, "x-ai/grok-4-fast": { "attachment": true, "description": "x-AI/Grok-4-Fast is an AI model provided by qiniu-ai.", "id": "x-ai/grok-4-fast", "last_updated": "2025-09-20", "limit": { "context": 2000000, "output": 2000000 }, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "name": "x-AI/Grok-4-Fast", "open_weights": false, "reasoning": true, "release_date": "2025-09-20", "structured_output": false, "temperature": true, "tool_call": true }, "x-ai/grok-4-fast-non-reasoning": { "attachment": true, "description": "X-Ai/Grok-4-Fast-Non-Reasoning is an AI model provided by qiniu-ai.", "id": "x-ai/grok-4-fast-non-reasoning", "last_updated": "2025-12-18", "limit": { "context": 2000000, "output": 2000000 }, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "name": "X-Ai/Grok-4-Fast-Non-Reasoning", "open_weights": false, "reasoning": true, "release_date": "2025-12-18", "structured_output": false, "temperature": true, "tool_call": true }, "x-ai/grok-4-fast-reasoning": { "attachment": true, "description": "X-Ai/Grok-4-Fast-Reasoning is an AI model provided by qiniu-ai.", "id": "x-ai/grok-4-fast-reasoning", "last_updated": "2025-12-18", "limit": { "context": 2000000, "output": 2000000 }, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "name": "X-Ai/Grok-4-Fast-Reasoning", "open_weights": false, "reasoning": true, "release_date": "2025-12-18", "structured_output": false, "temperature": true, "tool_call": true }, "x-ai/grok-4.1-fast": { "attachment": false, "description": "x-AI/Grok-4.1-Fast is an AI model provided by qiniu-ai.", "id": "x-ai/grok-4.1-fast", "last_updated": "2025-11-20", "limit": { "context": 2000000, "output": 2000000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "x-AI/Grok-4.1-Fast", "open_weights": false, "reasoning": true, "release_date": "2025-11-20", "structured_output": false, "temperature": true, "tool_call": true }, "x-ai/grok-4.1-fast-non-reasoning": { "attachment": true, "description": "X-Ai/Grok 4.1 Fast Non Reasoning is an AI model provided by qiniu-ai.", "id": "x-ai/grok-4.1-fast-non-reasoning", "last_updated": "2025-12-19", "limit": { "context": 2000000, "output": 2000000 }, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "name": "X-Ai/Grok 4.1 Fast Non Reasoning", "open_weights": false, "reasoning": true, "release_date": "2025-12-19", "structured_output": false, "temperature": true, "tool_call": true }, "x-ai/grok-4.1-fast-reasoning": { "attachment": true, "description": "X-Ai/Grok 4.1 Fast Reasoning is an AI model provided by qiniu-ai.", "id": "x-ai/grok-4.1-fast-reasoning", "last_updated": "2025-12-19", "limit": { "context": 20000000, "output": 2000000 }, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "name": "X-Ai/Grok 4.1 Fast Reasoning", "open_weights": false, "reasoning": true, "release_date": "2025-12-19", "structured_output": false, "temperature": true, "tool_call": true }, "x-ai/grok-code-fast-1": { "attachment": false, "description": "x-AI/Grok-Code-Fast 1 is an AI model provided by qiniu-ai.", "id": "x-ai/grok-code-fast-1", "last_updated": "2025-09-02", "limit": { "context": 256000, "output": 10000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "x-AI/Grok-Code-Fast 1", "open_weights": false, "reasoning": true, "release_date": "2025-09-02", "structured_output": false, "temperature": true, "tool_call": true }, "xiaomi/mimo-v2-flash": { "attachment": false, "cost": { "cache_read": 0.01, "input": 0.1, "output": 0.3 }, "description": "Xiaomi/Mimo-V2-Flash is an AI model provided by qiniu-ai.", "family": "mimo", "id": "xiaomi/mimo-v2-flash", "knowledge": "2024-12-01", "last_updated": "2026-02-04", "limit": { "context": 256000, "output": 256000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Xiaomi/Mimo-V2-Flash", "open_weights": true, "reasoning": true, "release_date": "2025-12-16", "temperature": true, "tool_call": true }, "z-ai/autoglm-phone-9b": { "attachment": true, "description": "Z-Ai/Autoglm Phone 9b is an AI model provided by qiniu-ai.", "id": "z-ai/autoglm-phone-9b", "last_updated": "2025-12-23", "limit": { "context": 12800, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Z-Ai/Autoglm Phone 9b", "open_weights": false, "reasoning": false, "release_date": "2025-12-23", "structured_output": false, "temperature": true, "tool_call": true }, "z-ai/glm-4.6": { "attachment": false, "description": "Z-AI/GLM 4.6 is an AI model provided by qiniu-ai.", "id": "z-ai/glm-4.6", "last_updated": "2025-10-11", "limit": { "context": 200000, "output": 200000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Z-AI/GLM 4.6", "open_weights": false, "reasoning": false, "release_date": "2025-10-11", "structured_output": false, "temperature": true, "tool_call": true }, "z-ai/glm-4.7": { "attachment": false, "description": "Z-Ai/GLM 4.7 is an AI model provided by qiniu-ai.", "id": "z-ai/glm-4.7", "last_updated": "2025-12-23", "limit": { "context": 200000, "output": 200000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Z-Ai/GLM 4.7", "open_weights": false, "reasoning": true, "release_date": "2025-12-23", "structured_output": false, "temperature": true, "tool_call": true }, "z-ai/glm-5": { "attachment": false, "description": "Z-Ai/GLM 5 is an AI model provided by qiniu-ai.", "id": "z-ai/glm-5", "last_updated": "2026-02-12", "limit": { "context": 200000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Z-Ai/GLM 5", "open_weights": false, "reasoning": true, "release_date": "2026-02-12", "structured_output": false, "temperature": true, "tool_call": true } }, "name": "Qiniu", "npm": "@ai-sdk/openai-compatible" }, "regolo-ai": { "api": "https://api.regolo.ai/v1", "doc": "https://docs.regolo.ai/", "env": [ "REGOLO_API_KEY" ], "iconURL": "https://models.dev/logos/regolo-ai.svg", "id": "regolo-ai", "models": { "gpt-oss-120b": { "attachment": false, "cost": { "input": 1, "output": 4.2 }, "description": "GPT-OSS-120B is an AI model provided by regolo-ai.", "family": "gpt-oss", "id": "gpt-oss-120b", "last_updated": "2025-08-05", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT-OSS-120B", "open_weights": false, "reasoning": true, "release_date": "2025-08-05", "temperature": true, "tool_call": true }, "gpt-oss-20b": { "attachment": false, "cost": { "input": 0.4, "output": 1.8 }, "description": "GPT-OSS-20B is an AI model provided by regolo-ai.", "family": "gpt-oss", "id": "gpt-oss-20b", "last_updated": "2026-03-01", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT-OSS-20B", "open_weights": true, "reasoning": true, "release_date": "2026-03-01", "temperature": true, "tool_call": true }, "llama-3.1-8b-instruct": { "attachment": false, "cost": { "input": 0.05, "output": 0.25 }, "description": "Llama 3.1 8B Instruct is an AI model provided by regolo-ai.", "family": "llama", "id": "llama-3.1-8b-instruct", "last_updated": "2025-04-07", "limit": { "context": 120000, "output": 120000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.1 8B Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-04-07", "temperature": true, "tool_call": true }, "llama-3.3-70b-instruct": { "attachment": false, "cost": { "input": 0.6, "output": 2.7 }, "description": "Llama 3.3 70B Instruct is an AI model provided by regolo-ai.", "family": "llama", "id": "llama-3.3-70b-instruct", "last_updated": "2025-04-28", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-04-28", "temperature": true, "tool_call": true }, "minimax-m2.5": { "attachment": false, "cost": { "input": 0.8, "output": 3.5 }, "description": "MiniMax 2.5 is an AI model provided by regolo-ai.", "family": "minimax", "id": "minimax-m2.5", "last_updated": "2026-03-10", "limit": { "context": 190000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax 2.5", "open_weights": false, "reasoning": true, "release_date": "2026-03-10", "temperature": true, "tool_call": true }, "mistral-small-4-119b": { "attachment": true, "cost": { "input": 0.75, "output": 3 }, "description": "Mistral Small 4 119B is an AI model provided by regolo-ai.", "family": "mistral-small", "id": "mistral-small-4-119b", "last_updated": "2026-03-15", "limit": { "context": 256000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Mistral Small 4 119B", "open_weights": false, "reasoning": true, "release_date": "2026-03-15", "temperature": true, "tool_call": true }, "mistral-small3.2": { "attachment": false, "cost": { "input": 0.5, "output": 2.2 }, "description": "Mistral Small 3.2 is an AI model provided by regolo-ai.", "family": "mistral-small", "id": "mistral-small3.2", "last_updated": "2025-01-31", "limit": { "context": 120000, "output": 120000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral Small 3.2", "open_weights": false, "reasoning": true, "release_date": "2025-01-31", "temperature": true, "tool_call": true }, "qwen-image": { "attachment": false, "cost": { "input": 0.5, "output": 2 }, "description": "Qwen-Image is an AI model provided by regolo-ai.", "family": "qwen", "id": "qwen-image", "last_updated": "2026-03-01", "limit": { "context": 8192, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "name": "Qwen-Image", "open_weights": false, "reasoning": false, "release_date": "2026-03-01", "temperature": true, "tool_call": false }, "qwen3-coder-next": { "attachment": false, "cost": { "input": 0.3, "output": 1.2 }, "description": "Qwen3-Coder-Next is an AI model provided by regolo-ai.", "family": "qwen", "id": "qwen3-coder-next", "last_updated": "2026-03-01", "limit": { "context": 262144, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3-Coder-Next", "open_weights": true, "reasoning": true, "release_date": "2026-03-01", "temperature": true, "tool_call": true }, "qwen3-embedding-8b": { "attachment": false, "cost": { "input": 0.1, "output": 0.1 }, "description": "Qwen3-Embedding-8B is an AI model provided by regolo-ai.", "family": "qwen", "id": "qwen3-embedding-8b", "last_updated": "2026-02-01", "limit": { "context": 32768, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3-Embedding-8B", "open_weights": true, "reasoning": false, "release_date": "2026-02-01", "temperature": false, "tool_call": false }, "qwen3-reranker-4b": { "attachment": false, "cost": { "input": 0.12, "output": 0.12 }, "description": "Qwen3-Reranker-4B is an AI model provided by regolo-ai.", "family": "qwen", "id": "qwen3-reranker-4b", "last_updated": "2026-02-01", "limit": { "context": 32768, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3-Reranker-4B", "open_weights": true, "reasoning": false, "release_date": "2026-02-01", "temperature": false, "tool_call": false }, "qwen3.5-122b": { "attachment": true, "cost": { "input": 0.9, "output": 3.6 }, "description": "Qwen3.5-122B is an AI model provided by regolo-ai.", "family": "qwen", "id": "qwen3.5-122b", "last_updated": "2026-02-01", "limit": { "context": 262144, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen3.5-122B", "open_weights": true, "reasoning": true, "release_date": "2026-02-01", "temperature": true, "tool_call": true }, "qwen3.5-9b": { "attachment": true, "cost": { "input": 0.15, "output": 0.6 }, "description": "Qwen3.5-9B is an AI model provided by regolo-ai.", "family": "qwen", "id": "qwen3.5-9b", "last_updated": "2026-02-01", "limit": { "context": 262144, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen3.5-9B", "open_weights": true, "reasoning": true, "release_date": "2026-02-01", "temperature": true, "tool_call": true } }, "name": "Regolo AI", "npm": "@ai-sdk/openai-compatible" }, "requesty": { "api": "https://router.requesty.ai/v1", "doc": "https://requesty.ai/solution/llm-routing/models", "env": [ "REQUESTY_API_KEY" ], "iconURL": "https://models.dev/logos/requesty.svg", "id": "requesty", "lobeIcon": "Requesty", "models": { "anthropic/claude-3-7-sonnet": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 3.7 is an AI model provided by requesty.", "family": "claude-sonnet", "id": "anthropic/claude-3-7-sonnet", "knowledge": "2024-01", "last_updated": "2025-02-19", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 3.7", "open_weights": false, "reasoning": true, "release_date": "2025-02-19", "temperature": true, "tool_call": true }, "anthropic/claude-haiku-4-5": { "attachment": true, "cost": { "cache_read": 0.1, "cache_write": 1.25, "input": 1, "output": 5 }, "description": "Claude Haiku 4.5 is an AI model provided by requesty.", "family": "claude-haiku", "id": "anthropic/claude-haiku-4-5", "knowledge": "2025-02-01", "last_updated": "2025-10-15", "limit": { "context": 200000, "output": 62000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Haiku 4.5", "open_weights": false, "reasoning": true, "release_date": "2025-10-15", "temperature": true, "tool_call": true }, "anthropic/claude-opus-4": { "attachment": true, "cost": { "cache_read": 1.5, "cache_write": 18.75, "input": 15, "output": 75 }, "description": "Claude Opus 4 is an AI model provided by requesty.", "family": "claude-opus", "id": "anthropic/claude-opus-4", "knowledge": "2025-03-31", "last_updated": "2025-05-22", "limit": { "context": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4", "open_weights": false, "reasoning": true, "release_date": "2025-05-22", "temperature": true, "tool_call": true }, "anthropic/claude-opus-4-1": { "attachment": true, "cost": { "cache_read": 1.5, "cache_write": 18.75, "input": 15, "output": 75 }, "description": "Claude Opus 4.1 is an AI model provided by requesty.", "family": "claude-opus", "id": "anthropic/claude-opus-4-1", "knowledge": "2025-03-31", "last_updated": "2025-08-05", "limit": { "context": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.1", "open_weights": false, "reasoning": true, "release_date": "2025-08-05", "temperature": true, "tool_call": true }, "anthropic/claude-opus-4-5": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "input": 5, "output": 25 }, "description": "Claude Opus 4.5 is an AI model provided by requesty.", "family": "claude-opus", "id": "anthropic/claude-opus-4-5", "knowledge": "2025-03-31", "last_updated": "2025-11-24", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.5", "open_weights": false, "reasoning": true, "release_date": "2025-11-24", "temperature": true, "tool_call": true }, "anthropic/claude-opus-4-6": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "context_over_200k": { "cache_read": 1, "cache_write": 12.5, "input": 10, "output": 37.5 }, "input": 5, "output": 25, "tiers": [ { "cache_read": 1, "cache_write": 12.5, "input": 10, "output": 37.5, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Claude Opus 4.6 is an AI model provided by requesty.", "family": "claude-opus", "id": "anthropic/claude-opus-4-6", "knowledge": "2025-05-31", "last_updated": "2026-02-05", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.6", "open_weights": false, "reasoning": true, "release_date": "2026-02-05", "structured_output": true, "temperature": true, "tool_call": true }, "anthropic/claude-sonnet-4": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 4 is an AI model provided by requesty.", "family": "claude-sonnet", "id": "anthropic/claude-sonnet-4", "knowledge": "2025-03-31", "last_updated": "2025-05-22", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4", "open_weights": false, "reasoning": true, "release_date": "2025-05-22", "temperature": true, "tool_call": true }, "anthropic/claude-sonnet-4-5": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 4.5 is an AI model provided by requesty.", "family": "claude-sonnet", "id": "anthropic/claude-sonnet-4-5", "knowledge": "2025-07-31", "last_updated": "2025-09-29", "limit": { "context": 1000000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.5", "open_weights": false, "reasoning": true, "release_date": "2025-09-29", "temperature": true, "tool_call": true }, "anthropic/claude-sonnet-4-6": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "context_over_200k": { "cache_read": 0.6, "cache_write": 7.5, "input": 6, "output": 22.5 }, "input": 3, "output": 15, "tiers": [ { "cache_read": 0.6, "cache_write": 7.5, "input": 6, "output": 22.5, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Claude Sonnet 4.6 is an AI model provided by requesty.", "family": "claude-sonnet", "id": "anthropic/claude-sonnet-4-6", "knowledge": "2025-08-31", "last_updated": "2026-02-17", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.6", "open_weights": false, "reasoning": true, "release_date": "2026-02-17", "structured_output": true, "temperature": true, "tool_call": true }, "google/gemini-2.5-flash": { "attachment": true, "cost": { "cache_read": 0.075, "cache_write": 0.55, "input": 0.3, "output": 2.5 }, "description": "Gemini 2.5 Flash is an AI model provided by requesty.", "family": "gemini-flash", "id": "google/gemini-2.5-flash", "knowledge": "2025-01", "last_updated": "2025-06-17", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Flash", "open_weights": false, "reasoning": true, "release_date": "2025-06-17", "temperature": true, "tool_call": true }, "google/gemini-2.5-pro": { "attachment": true, "cost": { "cache_read": 0.31, "cache_write": 2.375, "context_over_200k": { "cache_read": 0.25, "input": 2.5, "output": 15 }, "input": 1.25, "output": 10, "tiers": [ { "cache_read": 0.25, "input": 2.5, "output": 15, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Gemini 2.5 Pro is an AI model provided by requesty.", "family": "gemini-pro", "id": "google/gemini-2.5-pro", "knowledge": "2025-01", "last_updated": "2025-06-05", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Pro", "open_weights": false, "reasoning": true, "release_date": "2025-03-20", "temperature": true, "tool_call": true }, "google/gemini-3-flash-preview": { "attachment": true, "cost": { "cache_read": 0.05, "cache_write": 1, "input": 0.5, "output": 3 }, "description": "Gemini 3 Flash is an AI model provided by requesty.", "id": "google/gemini-3-flash-preview", "knowledge": "2025-01", "last_updated": "2025-12-17", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 3 Flash", "open_weights": false, "reasoning": true, "release_date": "2025-12-17", "temperature": true, "tool_call": true }, "google/gemini-3-pro-preview": { "attachment": true, "cost": { "cache_read": 0.2, "cache_write": 4.5, "input": 2, "output": 12 }, "description": "Gemini 3 Pro is an AI model provided by requesty.", "family": "gemini-pro", "id": "google/gemini-3-pro-preview", "knowledge": "2025-01", "last_updated": "2025-11-18", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 3 Pro", "open_weights": false, "reasoning": true, "release_date": "2025-11-18", "temperature": true, "tool_call": true }, "openai/gpt-4.1": { "attachment": true, "cost": { "cache_read": 0.5, "input": 2, "output": 8 }, "description": "GPT-4.1 is an AI model provided by requesty.", "family": "gpt", "id": "openai/gpt-4.1", "knowledge": "2024-04", "last_updated": "2025-04-14", "limit": { "context": 1047576, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4.1", "open_weights": false, "reasoning": false, "release_date": "2025-04-14", "temperature": true, "tool_call": true }, "openai/gpt-4.1-mini": { "attachment": true, "cost": { "cache_read": 0.1, "input": 0.4, "output": 1.6 }, "description": "GPT-4.1 Mini is an AI model provided by requesty.", "family": "gpt-mini", "id": "openai/gpt-4.1-mini", "knowledge": "2024-04", "last_updated": "2025-04-14", "limit": { "context": 1047576, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4.1 Mini", "open_weights": false, "reasoning": false, "release_date": "2025-04-14", "temperature": true, "tool_call": true }, "openai/gpt-4o-mini": { "attachment": true, "cost": { "cache_read": 0.08, "input": 0.15, "output": 0.6 }, "description": "GPT-4o Mini is an AI model provided by requesty.", "family": "gpt-mini", "id": "openai/gpt-4o-mini", "knowledge": "2024-10", "last_updated": "2024-07-18", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4o Mini", "open_weights": false, "reasoning": false, "release_date": "2024-07-18", "temperature": true, "tool_call": true }, "openai/gpt-5": { "attachment": true, "cost": { "cache_read": 0.13, "input": 1.25, "output": 10 }, "description": "GPT-5 is an AI model provided by requesty.", "family": "gpt", "id": "openai/gpt-5", "knowledge": "2024-09-30", "last_updated": "2025-08-07", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "audio", "image", "video" ], "output": [ "text", "audio", "image" ] }, "name": "GPT-5", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "temperature": false, "tool_call": true }, "openai/gpt-5-chat": { "attachment": true, "cost": { "input": 1.25, "output": 10 }, "description": "GPT-5 Chat (latest) is an AI model provided by requesty.", "family": "gpt-codex", "id": "openai/gpt-5-chat", "knowledge": "2024-09-30", "last_updated": "2025-08-07", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5 Chat (latest)", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "structured_output": true, "temperature": true, "tool_call": false }, "openai/gpt-5-codex": { "attachment": true, "cost": { "cache_read": 0.125, "input": 1.25, "output": 10 }, "description": "GPT-5 Codex is an AI model provided by requesty.", "family": "gpt-codex", "id": "openai/gpt-5-codex", "knowledge": "2024-10-01", "last_updated": "2025-09-15", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5 Codex", "open_weights": false, "reasoning": true, "release_date": "2025-09-15", "structured_output": true, "temperature": true, "tool_call": true }, "openai/gpt-5-image": { "attachment": true, "cost": { "cache_read": 1.25, "input": 5, "output": 10 }, "description": "GPT-5 Image is an AI model provided by requesty.", "family": "gpt", "id": "openai/gpt-5-image", "knowledge": "2024-10-01", "last_updated": "2025-10-14", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text", "image" ] }, "name": "GPT-5 Image", "open_weights": false, "reasoning": true, "release_date": "2025-10-14", "structured_output": true, "temperature": true, "tool_call": true }, "openai/gpt-5-mini": { "attachment": true, "cost": { "cache_read": 0.03, "input": 0.25, "output": 2 }, "description": "GPT-5 Mini is an AI model provided by requesty.", "family": "gpt-mini", "id": "openai/gpt-5-mini", "knowledge": "2024-05-30", "last_updated": "2025-08-07", "limit": { "context": 128000, "output": 32000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5 Mini", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "temperature": false, "tool_call": true }, "openai/gpt-5-nano": { "attachment": true, "cost": { "cache_read": 0.01, "input": 0.05, "output": 0.4 }, "description": "GPT-5 Nano is an AI model provided by requesty.", "family": "gpt-nano", "id": "openai/gpt-5-nano", "knowledge": "2024-05-30", "last_updated": "2025-08-07", "limit": { "context": 16000, "output": 4000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT-5 Nano", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "temperature": false, "tool_call": true }, "openai/gpt-5-pro": { "attachment": true, "cost": { "input": 15, "output": 120 }, "description": "GPT-5 Pro is an AI model provided by requesty.", "family": "gpt-pro", "id": "openai/gpt-5-pro", "knowledge": "2024-09-30", "last_updated": "2025-10-06", "limit": { "context": 400000, "output": 272000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5 Pro", "open_weights": false, "reasoning": true, "release_date": "2025-10-06", "structured_output": true, "temperature": false, "tool_call": true }, "openai/gpt-5.1": { "attachment": true, "cost": { "cache_read": 0.125, "input": 1.25, "output": 10 }, "description": "GPT-5.1 is an AI model provided by requesty.", "family": "gpt", "id": "openai/gpt-5.1", "knowledge": "2024-09-30", "last_updated": "2025-11-13", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.1", "open_weights": false, "reasoning": true, "release_date": "2025-11-13", "structured_output": true, "temperature": true, "tool_call": true }, "openai/gpt-5.1-chat": { "attachment": true, "cost": { "cache_read": 0.125, "input": 1.25, "output": 10 }, "description": "GPT-5.1 Chat is an AI model provided by requesty.", "family": "gpt-codex", "id": "openai/gpt-5.1-chat", "knowledge": "2024-09-30", "last_updated": "2025-11-13", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.1 Chat", "open_weights": false, "reasoning": true, "release_date": "2025-11-13", "structured_output": true, "temperature": true, "tool_call": true }, "openai/gpt-5.1-codex": { "attachment": true, "cost": { "cache_read": 0.125, "input": 1.25, "output": 10 }, "description": "GPT-5.1-Codex is an AI model provided by requesty.", "family": "gpt-codex", "id": "openai/gpt-5.1-codex", "knowledge": "2024-09-30", "last_updated": "2025-11-13", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.1-Codex", "open_weights": false, "reasoning": true, "release_date": "2025-11-13", "structured_output": true, "temperature": true, "tool_call": true }, "openai/gpt-5.1-codex-max": { "attachment": true, "cost": { "cache_read": 0.11, "input": 1.1, "output": 9 }, "description": "GPT-5.1-Codex-Max is an AI model provided by requesty.", "family": "gpt-codex", "id": "openai/gpt-5.1-codex-max", "knowledge": "2024-09-30", "last_updated": "2025-11-13", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.1-Codex-Max", "open_weights": false, "reasoning": true, "release_date": "2025-11-13", "structured_output": true, "temperature": true, "tool_call": true }, "openai/gpt-5.1-codex-mini": { "attachment": true, "cost": { "cache_read": 0.025, "input": 0.25, "output": 2 }, "description": "GPT-5.1-Codex-Mini is an AI model provided by requesty.", "family": "gpt-codex", "id": "openai/gpt-5.1-codex-mini", "knowledge": "2024-09-30", "last_updated": "2025-11-13", "limit": { "context": 400000, "output": 100000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.1-Codex-Mini", "open_weights": false, "reasoning": true, "release_date": "2025-11-13", "structured_output": true, "temperature": true, "tool_call": true }, "openai/gpt-5.2": { "attachment": true, "cost": { "cache_read": 0.175, "input": 1.75, "output": 14 }, "description": "GPT-5.2 is an AI model provided by requesty.", "family": "gpt", "id": "openai/gpt-5.2", "knowledge": "2025-08-31", "last_updated": "2025-12-11", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.2", "open_weights": false, "reasoning": true, "release_date": "2025-12-11", "structured_output": true, "temperature": false, "tool_call": true }, "openai/gpt-5.2-chat": { "attachment": true, "cost": { "cache_read": 0.175, "input": 1.75, "output": 14 }, "description": "GPT-5.2 Chat is an AI model provided by requesty.", "family": "gpt-codex", "id": "openai/gpt-5.2-chat", "knowledge": "2025-08-31", "last_updated": "2025-12-11", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.2 Chat", "open_weights": false, "reasoning": true, "release_date": "2025-12-11", "structured_output": true, "temperature": false, "tool_call": true }, "openai/gpt-5.2-codex": { "attachment": true, "cost": { "cache_read": 0.175, "input": 1.75, "output": 14 }, "description": "GPT-5.2-Codex is an AI model provided by requesty.", "family": "gpt-codex", "id": "openai/gpt-5.2-codex", "knowledge": "2025-08-31", "last_updated": "2026-01-14", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.2-Codex", "open_weights": false, "reasoning": true, "release_date": "2026-01-14", "structured_output": true, "temperature": true, "tool_call": true }, "openai/gpt-5.2-pro": { "attachment": true, "cost": { "input": 21, "output": 168 }, "description": "GPT-5.2 Pro is an AI model provided by requesty.", "family": "gpt-pro", "id": "openai/gpt-5.2-pro", "knowledge": "2025-08-31", "last_updated": "2025-12-11", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.2 Pro", "open_weights": false, "reasoning": true, "release_date": "2025-12-11", "structured_output": true, "temperature": false, "tool_call": true }, "openai/gpt-5.3-codex": { "attachment": true, "cost": { "cache_read": 0.175, "input": 1.75, "output": 14 }, "description": "GPT-5.3-Codex is an AI model provided by requesty.", "family": "gpt-codex", "id": "openai/gpt-5.3-codex", "knowledge": "2025-08-31", "last_updated": "2026-02-24", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.3-Codex", "open_weights": false, "reasoning": true, "release_date": "2026-02-24", "structured_output": true, "temperature": false, "tool_call": true }, "openai/gpt-5.4": { "attachment": true, "cost": { "cache_read": 0.25, "context_over_200k": { "cache_read": 0.5, "input": 5, "output": 22.5 }, "input": 2.5, "output": 15, "tiers": [ { "cache_read": 0.5, "input": 5, "output": 22.5, "tier": { "size": 272000, "type": "context" } } ] }, "description": "GPT-5.4 is an AI model provided by requesty.", "family": "gpt", "id": "openai/gpt-5.4", "knowledge": "2025-08-31", "last_updated": "2026-03-05", "limit": { "context": 1050000, "input": 922000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.4", "open_weights": false, "reasoning": true, "release_date": "2026-03-05", "structured_output": true, "temperature": false, "tool_call": true }, "openai/gpt-5.4-pro": { "attachment": true, "cost": { "cache_read": 30, "input": 30, "output": 180 }, "description": "GPT-5.4 Pro is an AI model provided by requesty.", "family": "gpt-pro", "id": "openai/gpt-5.4-pro", "knowledge": "2025-08-31", "last_updated": "2026-03-05", "limit": { "context": 1050000, "input": 922000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.4 Pro", "open_weights": false, "reasoning": true, "release_date": "2026-03-05", "structured_output": false, "temperature": false, "tool_call": true }, "openai/o4-mini": { "attachment": true, "cost": { "cache_read": 0.28, "input": 1.1, "output": 4.4 }, "description": "o4 Mini is an AI model provided by requesty.", "family": "o-mini", "id": "openai/o4-mini", "knowledge": "2024-06", "last_updated": "2025-04-16", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "o4 Mini", "open_weights": false, "reasoning": true, "release_date": "2025-04-16", "temperature": true, "tool_call": true }, "xai/grok-4": { "attachment": true, "cost": { "cache_read": 0.75, "cache_write": 3, "input": 3, "output": 15 }, "description": "Grok 4 is an AI model provided by requesty.", "family": "grok", "id": "xai/grok-4", "knowledge": "2025-01", "last_updated": "2025-09-09", "limit": { "context": 256000, "output": 64000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 4", "open_weights": false, "reasoning": true, "release_date": "2025-09-09", "temperature": true, "tool_call": true }, "xai/grok-4-fast": { "attachment": true, "cost": { "cache_read": 0.05, "cache_write": 0.2, "input": 0.2, "output": 0.5 }, "description": "Grok 4 Fast is an AI model provided by requesty.", "family": "grok", "id": "xai/grok-4-fast", "knowledge": "2025-01", "last_updated": "2025-09-19", "limit": { "context": 2000000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok 4 Fast", "open_weights": false, "reasoning": true, "release_date": "2025-09-19", "temperature": true, "tool_call": true } }, "name": "Requesty", "npm": "@ai-sdk/openai-compatible" }, "sap-ai-core": { "doc": "https://help.sap.com/docs/sap-ai-core", "env": [ "AICORE_SERVICE_KEY" ], "iconURL": "https://models.dev/logos/sap-ai-core.svg", "id": "sap-ai-core", "models": { "anthropic--claude-3-haiku": { "attachment": true, "cost": { "cache_read": 0.03, "cache_write": 0.3, "input": 0.25, "output": 1.25 }, "description": "anthropic--claude-3-haiku is an AI model provided by sap-ai-core.", "family": "claude-haiku", "id": "anthropic--claude-3-haiku", "knowledge": "2023-08-31", "last_updated": "2024-03-13", "limit": { "context": 200000, "output": 4096 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "anthropic--claude-3-haiku", "open_weights": false, "reasoning": false, "release_date": "2024-03-13", "temperature": true, "tool_call": true }, "anthropic--claude-3-opus": { "attachment": true, "cost": { "cache_read": 1.5, "cache_write": 18.75, "input": 15, "output": 75 }, "description": "anthropic--claude-3-opus is an AI model provided by sap-ai-core.", "family": "claude-opus", "id": "anthropic--claude-3-opus", "knowledge": "2023-08-31", "last_updated": "2024-02-29", "limit": { "context": 200000, "output": 4096 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "anthropic--claude-3-opus", "open_weights": false, "reasoning": false, "release_date": "2024-02-29", "temperature": true, "tool_call": true }, "anthropic--claude-3-sonnet": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "anthropic--claude-3-sonnet is an AI model provided by sap-ai-core.", "family": "claude-sonnet", "id": "anthropic--claude-3-sonnet", "knowledge": "2023-08-31", "last_updated": "2024-03-04", "limit": { "context": 200000, "output": 4096 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "anthropic--claude-3-sonnet", "open_weights": false, "reasoning": false, "release_date": "2024-03-04", "temperature": true, "tool_call": true }, "anthropic--claude-3.5-sonnet": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "anthropic--claude-3.5-sonnet is an AI model provided by sap-ai-core.", "family": "claude-sonnet", "id": "anthropic--claude-3.5-sonnet", "knowledge": "2024-04-30", "last_updated": "2024-10-22", "limit": { "context": 200000, "output": 8192 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "anthropic--claude-3.5-sonnet", "open_weights": false, "reasoning": false, "release_date": "2024-10-22", "temperature": true, "tool_call": true }, "anthropic--claude-3.7-sonnet": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "anthropic--claude-3.7-sonnet is an AI model provided by sap-ai-core.", "family": "claude-sonnet", "id": "anthropic--claude-3.7-sonnet", "knowledge": "2024-10-31", "last_updated": "2025-02-24", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "anthropic--claude-3.7-sonnet", "open_weights": false, "reasoning": true, "release_date": "2025-02-24", "temperature": true, "tool_call": true }, "anthropic--claude-4-opus": { "attachment": true, "cost": { "cache_read": 1.5, "cache_write": 18.75, "input": 15, "output": 75 }, "description": "anthropic--claude-4-opus is an AI model provided by sap-ai-core.", "family": "claude-opus", "id": "anthropic--claude-4-opus", "knowledge": "2025-03-31", "last_updated": "2025-05-22", "limit": { "context": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "anthropic--claude-4-opus", "open_weights": false, "reasoning": true, "release_date": "2025-05-22", "temperature": true, "tool_call": true }, "anthropic--claude-4-sonnet": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "anthropic--claude-4-sonnet is an AI model provided by sap-ai-core.", "family": "claude-sonnet", "id": "anthropic--claude-4-sonnet", "knowledge": "2025-03-31", "last_updated": "2025-05-22", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "anthropic--claude-4-sonnet", "open_weights": false, "reasoning": true, "release_date": "2025-05-22", "temperature": true, "tool_call": true }, "anthropic--claude-4.5-haiku": { "attachment": true, "cost": { "cache_read": 0.1, "cache_write": 1.25, "input": 1, "output": 5 }, "description": "anthropic--claude-4.5-haiku is an AI model provided by sap-ai-core.", "family": "claude-haiku", "id": "anthropic--claude-4.5-haiku", "knowledge": "2025-02-28", "last_updated": "2025-10-15", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "anthropic--claude-4.5-haiku", "open_weights": false, "reasoning": true, "release_date": "2025-10-15", "temperature": true, "tool_call": true }, "anthropic--claude-4.5-opus": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "input": 5, "output": 25 }, "description": "anthropic--claude-4.5-opus is an AI model provided by sap-ai-core.", "family": "claude-opus", "id": "anthropic--claude-4.5-opus", "knowledge": "2025-05", "last_updated": "2025-11-24", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "anthropic--claude-4.5-opus", "open_weights": false, "reasoning": true, "release_date": "2025-11-24", "temperature": true, "tool_call": true }, "anthropic--claude-4.5-sonnet": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "anthropic--claude-4.5-sonnet is an AI model provided by sap-ai-core.", "family": "claude-sonnet", "id": "anthropic--claude-4.5-sonnet", "knowledge": "2025-07-31", "last_updated": "2025-09-29", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "anthropic--claude-4.5-sonnet", "open_weights": false, "reasoning": true, "release_date": "2025-09-29", "temperature": true, "tool_call": true }, "anthropic--claude-4.6-opus": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "input": 5, "output": 25 }, "description": "anthropic--claude-4.6-opus is an AI model provided by sap-ai-core.", "family": "claude-opus", "id": "anthropic--claude-4.6-opus", "knowledge": "2025-05", "last_updated": "2026-03-13", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "anthropic--claude-4.6-opus", "open_weights": false, "reasoning": true, "release_date": "2026-02-05", "temperature": true, "tool_call": true }, "anthropic--claude-4.6-sonnet": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "anthropic--claude-4.6-sonnet is an AI model provided by sap-ai-core.", "family": "claude-sonnet", "id": "anthropic--claude-4.6-sonnet", "knowledge": "2025-08", "last_updated": "2026-03-13", "limit": { "context": 1000000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "anthropic--claude-4.6-sonnet", "open_weights": false, "reasoning": true, "release_date": "2026-02-17", "temperature": true, "tool_call": true }, "gemini-2.5-flash": { "attachment": true, "cost": { "cache_read": 0.03, "input": 0.3, "input_audio": 1, "output": 2.5 }, "description": "gemini-2.5-flash is an AI model provided by sap-ai-core.", "family": "gemini-flash", "id": "gemini-2.5-flash", "knowledge": "2025-01", "last_updated": "2025-06-05", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "gemini-2.5-flash", "open_weights": false, "reasoning": true, "release_date": "2025-03-25", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-2.5-flash-lite": { "attachment": true, "cost": { "cache_read": 0.025, "input": 0.1, "output": 0.4 }, "description": "gemini-2.5-flash-lite is an AI model provided by sap-ai-core.", "family": "gemini-flash-lite", "id": "gemini-2.5-flash-lite", "knowledge": "2025-01", "last_updated": "2025-06-17", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "gemini-2.5-flash-lite", "open_weights": false, "reasoning": true, "release_date": "2025-06-17", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-2.5-pro": { "attachment": true, "cost": { "cache_read": 0.125, "input": 1.25, "output": 10 }, "description": "gemini-2.5-pro is an AI model provided by sap-ai-core.", "family": "gemini-pro", "id": "gemini-2.5-pro", "knowledge": "2025-01", "last_updated": "2025-06-05", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "gemini-2.5-pro", "open_weights": false, "reasoning": true, "release_date": "2025-03-25", "structured_output": true, "temperature": true, "tool_call": true }, "gpt-4.1": { "attachment": true, "cost": { "cache_read": 0.5, "input": 2, "output": 8 }, "description": "gpt-4.1 is an AI model provided by sap-ai-core.", "family": "gpt", "id": "gpt-4.1", "knowledge": "2024-04", "last_updated": "2025-04-14", "limit": { "context": 1047576, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "gpt-4.1", "open_weights": false, "reasoning": false, "release_date": "2025-04-14", "structured_output": true, "temperature": true, "tool_call": true }, "gpt-4.1-mini": { "attachment": true, "cost": { "cache_read": 0.1, "input": 0.4, "output": 1.6 }, "description": "gpt-4.1-mini is an AI model provided by sap-ai-core.", "family": "gpt-mini", "id": "gpt-4.1-mini", "knowledge": "2024-04", "last_updated": "2025-04-14", "limit": { "context": 1047576, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "gpt-4.1-mini", "open_weights": false, "reasoning": false, "release_date": "2025-04-14", "structured_output": true, "temperature": true, "tool_call": true }, "gpt-5": { "attachment": true, "cost": { "cache_read": 0.125, "input": 1.25, "output": 10 }, "description": "gpt-5 is an AI model provided by sap-ai-core.", "family": "gpt", "id": "gpt-5", "knowledge": "2024-09-30", "last_updated": "2025-08-07", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "gpt-5", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5-mini": { "attachment": true, "cost": { "cache_read": 0.025, "input": 0.25, "output": 2 }, "description": "gpt-5-mini is an AI model provided by sap-ai-core.", "family": "gpt-mini", "id": "gpt-5-mini", "knowledge": "2024-05-30", "last_updated": "2025-08-07", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "gpt-5-mini", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5-nano": { "attachment": true, "cost": { "cache_read": 0.005, "input": 0.05, "output": 0.4 }, "description": "gpt-5-nano is an AI model provided by sap-ai-core.", "family": "gpt-nano", "id": "gpt-5-nano", "knowledge": "2024-05-30", "last_updated": "2025-08-07", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "gpt-5-nano", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "structured_output": true, "temperature": false, "tool_call": true }, "sonar": { "attachment": false, "cost": { "input": 1, "output": 1 }, "description": "sonar is an AI model provided by sap-ai-core.", "family": "sonar", "id": "sonar", "knowledge": "2025-09-01", "last_updated": "2025-09-01", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "sonar", "open_weights": false, "reasoning": false, "release_date": "2024-01-01", "temperature": true, "tool_call": false }, "sonar-deep-research": { "attachment": false, "cost": { "input": 2, "output": 8, "reasoning": 3 }, "description": "sonar-deep-research is an AI model provided by sap-ai-core.", "family": "sonar-deep-research", "id": "sonar-deep-research", "knowledge": "2025-01", "last_updated": "2025-09-01", "limit": { "context": 128000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "sonar-deep-research", "open_weights": false, "reasoning": true, "release_date": "2025-02-01", "temperature": false, "tool_call": false }, "sonar-pro": { "attachment": true, "cost": { "input": 3, "output": 15 }, "description": "sonar-pro is an AI model provided by sap-ai-core.", "family": "sonar-pro", "id": "sonar-pro", "knowledge": "2025-09-01", "last_updated": "2025-09-01", "limit": { "context": 200000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "sonar-pro", "open_weights": false, "reasoning": false, "release_date": "2024-01-01", "temperature": true, "tool_call": false } }, "name": "SAP AI Core", "npm": "@jerome-benoit/sap-ai-provider-v2" }, "sarvam": { "api": "https://api.sarvam.ai/v1", "doc": "https://docs.sarvam.ai/api-reference-docs/getting-started/models", "env": [ "SARVAM_API_KEY" ], "iconURL": "https://models.dev/logos/sarvam.svg", "id": "sarvam", "models": { "sarvam-105b": { "attachment": false, "description": "Sarvam-105B is an AI model provided by sarvam.", "family": "sarvam", "id": "sarvam-105b", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-03-06", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Sarvam-105B", "open_weights": true, "reasoning": true, "release_date": "2026-02-18", "temperature": true, "tool_call": true }, "sarvam-30b": { "attachment": false, "description": "Sarvam-30B is an AI model provided by sarvam.", "family": "sarvam", "id": "sarvam-30b", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-03-06", "limit": { "context": 65536, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Sarvam-30B", "open_weights": true, "reasoning": true, "release_date": "2026-02-18", "temperature": true, "tool_call": true } }, "name": "Sarvam AI", "npm": "@ai-sdk/openai-compatible" }, "scaleway": { "api": "https://api.scaleway.ai/v1", "doc": "https://www.scaleway.com/en/docs/generative-apis/", "env": [ "SCALEWAY_API_KEY" ], "iconURL": "https://models.dev/logos/scaleway.svg", "id": "scaleway", "models": { "bge-multilingual-gemma2": { "attachment": false, "cost": { "input": 0.1, "output": 0 }, "description": "BGE Multilingual Gemma2 is an AI model provided by scaleway.", "family": "gemma", "id": "bge-multilingual-gemma2", "last_updated": "2025-06-15", "limit": { "context": 8191, "output": 3072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "BGE Multilingual Gemma2", "open_weights": false, "reasoning": false, "release_date": "2024-07-26", "temperature": false, "tool_call": false }, "deepseek-r1-distill-llama-70b": { "attachment": false, "cost": { "input": 0.9, "output": 0.9 }, "description": "DeepSeek R1 Distill Llama 70B is an AI model provided by scaleway.", "family": "deepseek-thinking", "id": "deepseek-r1-distill-llama-70b", "knowledge": "2024-07", "last_updated": "2026-03-17", "limit": { "context": 32000, "output": 8196 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek R1 Distill Llama 70B", "open_weights": true, "reasoning": true, "release_date": "2025-01-20", "temperature": true, "tool_call": true }, "devstral-2-123b-instruct-2512": { "attachment": false, "cost": { "input": 0.4, "output": 2 }, "description": "Devstral 2 123B Instruct (2512) is an AI model provided by scaleway.", "family": "devstral", "id": "devstral-2-123b-instruct-2512", "last_updated": "2026-03-17", "limit": { "context": 256000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Devstral 2 123B Instruct (2512)", "open_weights": true, "reasoning": false, "release_date": "2026-01-07", "temperature": true, "tool_call": true }, "gemma-3-27b-it": { "attachment": true, "cost": { "input": 0.25, "output": 0.5 }, "description": "Gemma-3-27B-IT is an AI model provided by scaleway.", "family": "gemma", "id": "gemma-3-27b-it", "knowledge": "2024-12", "last_updated": "2026-03-17", "limit": { "context": 40000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemma-3-27B-IT", "open_weights": false, "reasoning": true, "release_date": "2024-12-01", "temperature": true, "tool_call": true }, "gpt-oss-120b": { "attachment": true, "cost": { "input": 0.15, "output": 0.6 }, "description": "GPT-OSS 120B is an AI model provided by scaleway.", "family": "gpt-oss", "id": "gpt-oss-120b", "last_updated": "2026-03-17", "limit": { "context": 128000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT-OSS 120B", "open_weights": true, "reasoning": false, "release_date": "2024-01-01", "temperature": true, "tool_call": true }, "llama-3.1-8b-instruct": { "attachment": false, "cost": { "input": 0.2, "output": 0.2 }, "description": "Llama 3.1 8B Instruct is an AI model provided by scaleway.", "family": "llama", "id": "llama-3.1-8b-instruct", "knowledge": "2023-12", "last_updated": "2026-03-17", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.1 8B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-01-01", "temperature": true, "tool_call": true }, "llama-3.3-70b-instruct": { "attachment": true, "cost": { "input": 0.9, "output": 0.9 }, "description": "Llama-3.3-70B-Instruct is an AI model provided by scaleway.", "family": "llama", "id": "llama-3.3-70b-instruct", "knowledge": "2023-12", "last_updated": "2026-03-17", "limit": { "context": 100000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama-3.3-70B-Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-12-06", "temperature": true, "tool_call": true }, "mistral-nemo-instruct-2407": { "attachment": true, "cost": { "input": 0.2, "output": 0.2 }, "description": "Mistral Nemo Instruct 2407 is an AI model provided by scaleway.", "family": "mistral-nemo", "id": "mistral-nemo-instruct-2407", "last_updated": "2026-03-17", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral Nemo Instruct 2407", "open_weights": true, "reasoning": false, "release_date": "2024-07-25", "temperature": true, "tool_call": true }, "mistral-small-3.2-24b-instruct-2506": { "attachment": false, "cost": { "input": 0.15, "output": 0.35 }, "description": "Mistral Small 3.2 24B Instruct (2506) is an AI model provided by scaleway.", "family": "mistral-small", "id": "mistral-small-3.2-24b-instruct-2506", "last_updated": "2026-03-17", "limit": { "context": 128000, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Mistral Small 3.2 24B Instruct (2506)", "open_weights": true, "reasoning": false, "release_date": "2025-06-20", "temperature": true, "tool_call": true }, "pixtral-12b-2409": { "attachment": true, "cost": { "input": 0.2, "output": 0.2 }, "description": "Pixtral 12B 2409 is an AI model provided by scaleway.", "family": "pixtral", "id": "pixtral-12b-2409", "last_updated": "2026-03-17", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Pixtral 12B 2409", "open_weights": true, "reasoning": false, "release_date": "2024-09-25", "temperature": true, "tool_call": true }, "qwen3-235b-a22b-instruct-2507": { "attachment": true, "cost": { "input": 0.75, "output": 2.25 }, "description": "Qwen3 235B A22B Instruct 2507 is an AI model provided by scaleway.", "family": "qwen", "id": "qwen3-235b-a22b-instruct-2507", "last_updated": "2026-03-17", "limit": { "context": 260000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 235B A22B Instruct 2507", "open_weights": true, "reasoning": false, "release_date": "2025-07-01", "temperature": true, "tool_call": true }, "qwen3-coder-30b-a3b-instruct": { "attachment": false, "cost": { "input": 0.2, "output": 0.8 }, "description": "Qwen3-Coder 30B-A3B Instruct is an AI model provided by scaleway.", "family": "qwen", "id": "qwen3-coder-30b-a3b-instruct", "knowledge": "2025-04", "last_updated": "2026-03-17", "limit": { "context": 128000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3-Coder 30B-A3B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-04", "temperature": true, "tool_call": true }, "qwen3-embedding-8b": { "attachment": false, "cost": { "input": 0.1, "output": 0 }, "description": "Qwen3 Embedding 8B is an AI model provided by scaleway.", "family": "qwen", "id": "qwen3-embedding-8b", "last_updated": "2026-03-17", "limit": { "context": 32768, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Embedding 8B", "open_weights": false, "reasoning": false, "release_date": "2025-25-11", "temperature": false, "tool_call": false }, "qwen3.5-397b-a17b": { "attachment": false, "cost": { "input": 0.6, "output": 3.6 }, "description": "Qwen3.5 397B A17B is an AI model provided by scaleway.", "family": "qwen", "id": "qwen3.5-397b-a17b", "knowledge": "2025-04", "last_updated": "2026-03-17", "limit": { "context": 256000, "output": 16384 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen3.5 397B A17B", "open_weights": true, "reasoning": true, "release_date": "2026-03-17", "temperature": true, "tool_call": true }, "voxtral-small-24b-2507": { "attachment": true, "cost": { "input": 0.15, "output": 0.35 }, "description": "Voxtral Small 24B 2507 is an AI model provided by scaleway.", "family": "voxtral", "id": "voxtral-small-24b-2507", "last_updated": "2026-03-17", "limit": { "context": 32000, "output": 16384 }, "modalities": { "input": [ "text", "audio" ], "output": [ "text" ] }, "name": "Voxtral Small 24B 2507", "open_weights": true, "reasoning": false, "release_date": "2025-07-01", "temperature": true, "tool_call": true }, "whisper-large-v3": { "attachment": false, "cost": { "input": 0.003, "output": 0 }, "description": "Whisper Large v3 is an AI model provided by scaleway.", "family": "whisper", "id": "whisper-large-v3", "knowledge": "2023-09", "last_updated": "2026-03-17", "limit": { "context": 0, "output": 8192 }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "name": "Whisper Large v3", "open_weights": true, "reasoning": false, "release_date": "2023-09-01", "temperature": false, "tool_call": false } }, "name": "Scaleway", "npm": "@ai-sdk/openai-compatible" }, "siliconflow": { "api": "https://api.siliconflow.com/v1", "doc": "https://cloud.siliconflow.com/models", "env": [ "SILICONFLOW_API_KEY" ], "iconURL": "https://models.dev/logos/siliconflow.svg", "id": "siliconflow", "models": { "ByteDance-Seed/Seed-OSS-36B-Instruct": { "attachment": false, "cost": { "input": 0.21, "output": 0.57 }, "description": "ByteDance-Seed/Seed-OSS-36B-Instruct is an AI model provided by siliconflow.", "family": "seed", "id": "ByteDance-Seed/Seed-OSS-36B-Instruct", "last_updated": "2025-11-25", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "ByteDance-Seed/Seed-OSS-36B-Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-09-04", "structured_output": true, "temperature": true, "tool_call": true }, "MiniMaxAI/MiniMax-M2.1": { "attachment": false, "cost": { "input": 0.3, "output": 1.2 }, "description": "MiniMaxAI/MiniMax-M2.1 is an AI model provided by siliconflow.", "family": "minimax", "id": "MiniMaxAI/MiniMax-M2.1", "last_updated": "2025-12-23", "limit": { "context": 197000, "output": 131000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMaxAI/MiniMax-M2.1", "open_weights": false, "reasoning": false, "release_date": "2025-12-23", "structured_output": true, "temperature": true, "tool_call": true }, "MiniMaxAI/MiniMax-M2.5": { "attachment": false, "cost": { "input": 0.3, "output": 1.2 }, "description": "MiniMaxAI/MiniMax-M2.5 is an AI model provided by siliconflow.", "family": "minimax", "id": "MiniMaxAI/MiniMax-M2.5", "last_updated": "2026-02-15", "limit": { "context": 197000, "output": 131000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMaxAI/MiniMax-M2.5", "open_weights": false, "reasoning": false, "release_date": "2026-02-15", "structured_output": false, "temperature": true, "tool_call": true }, "Qwen/QwQ-32B": { "attachment": false, "cost": { "input": 0.15, "output": 0.58 }, "description": "Qwen/QwQ-32B is an AI model provided by siliconflow.", "family": "qwen", "id": "Qwen/QwQ-32B", "last_updated": "2025-11-25", "limit": { "context": 131000, "output": 131000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen/QwQ-32B", "open_weights": false, "reasoning": true, "release_date": "2025-03-06", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen2.5-14B-Instruct": { "attachment": false, "cost": { "input": 0.1, "output": 0.1 }, "description": "Qwen/Qwen2.5-14B-Instruct is an AI model provided by siliconflow.", "family": "qwen", "id": "Qwen/Qwen2.5-14B-Instruct", "last_updated": "2025-11-25", "limit": { "context": 33000, "output": 4000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen/Qwen2.5-14B-Instruct", "open_weights": false, "reasoning": false, "release_date": "2024-09-18", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen2.5-32B-Instruct": { "attachment": false, "cost": { "input": 0.18, "output": 0.18 }, "description": "Qwen/Qwen2.5-32B-Instruct is an AI model provided by siliconflow.", "family": "qwen", "id": "Qwen/Qwen2.5-32B-Instruct", "last_updated": "2025-11-25", "limit": { "context": 33000, "output": 4000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen/Qwen2.5-32B-Instruct", "open_weights": false, "reasoning": false, "release_date": "2024-09-19", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen2.5-72B-Instruct": { "attachment": false, "cost": { "input": 0.59, "output": 0.59 }, "description": "Qwen/Qwen2.5-72B-Instruct is an AI model provided by siliconflow.", "family": "qwen", "id": "Qwen/Qwen2.5-72B-Instruct", "last_updated": "2025-11-25", "limit": { "context": 33000, "output": 4000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen/Qwen2.5-72B-Instruct", "open_weights": false, "reasoning": false, "release_date": "2024-09-18", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen2.5-72B-Instruct-128K": { "attachment": false, "cost": { "input": 0.59, "output": 0.59 }, "description": "Qwen/Qwen2.5-72B-Instruct-128K is an AI model provided by siliconflow.", "family": "qwen", "id": "Qwen/Qwen2.5-72B-Instruct-128K", "last_updated": "2025-11-25", "limit": { "context": 131000, "output": 4000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen/Qwen2.5-72B-Instruct-128K", "open_weights": false, "reasoning": false, "release_date": "2024-09-18", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen2.5-7B-Instruct": { "attachment": false, "cost": { "input": 0.05, "output": 0.05 }, "description": "Qwen/Qwen2.5-7B-Instruct is an AI model provided by siliconflow.", "family": "qwen", "id": "Qwen/Qwen2.5-7B-Instruct", "last_updated": "2025-11-25", "limit": { "context": 33000, "output": 4000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen/Qwen2.5-7B-Instruct", "open_weights": false, "reasoning": false, "release_date": "2024-09-18", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen2.5-Coder-32B-Instruct": { "attachment": false, "cost": { "input": 0.18, "output": 0.18 }, "description": "Qwen/Qwen2.5-Coder-32B-Instruct is an AI model provided by siliconflow.", "family": "qwen", "id": "Qwen/Qwen2.5-Coder-32B-Instruct", "last_updated": "2025-11-25", "limit": { "context": 33000, "output": 4000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen/Qwen2.5-Coder-32B-Instruct", "open_weights": false, "reasoning": false, "release_date": "2024-11-11", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen2.5-VL-32B-Instruct": { "attachment": true, "cost": { "input": 0.27, "output": 0.27 }, "description": "Qwen/Qwen2.5-VL-32B-Instruct is an AI model provided by siliconflow.", "family": "qwen", "id": "Qwen/Qwen2.5-VL-32B-Instruct", "last_updated": "2025-11-25", "limit": { "context": 131000, "output": 131000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen/Qwen2.5-VL-32B-Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-03-24", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen2.5-VL-72B-Instruct": { "attachment": true, "cost": { "input": 0.59, "output": 0.59 }, "description": "Qwen/Qwen2.5-VL-72B-Instruct is an AI model provided by siliconflow.", "family": "qwen", "id": "Qwen/Qwen2.5-VL-72B-Instruct", "last_updated": "2025-11-25", "limit": { "context": 131000, "output": 4000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen/Qwen2.5-VL-72B-Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-01-28", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen2.5-VL-7B-Instruct": { "attachment": true, "cost": { "input": 0.05, "output": 0.05 }, "description": "Qwen/Qwen2.5-VL-7B-Instruct is an AI model provided by siliconflow.", "family": "qwen", "id": "Qwen/Qwen2.5-VL-7B-Instruct", "last_updated": "2025-11-25", "limit": { "context": 33000, "output": 4000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen/Qwen2.5-VL-7B-Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-01-28", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-14B": { "attachment": false, "cost": { "input": 0.07, "output": 0.28 }, "description": "Qwen/Qwen3-14B is an AI model provided by siliconflow.", "family": "qwen", "id": "Qwen/Qwen3-14B", "last_updated": "2025-11-25", "limit": { "context": 131000, "output": 131000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen/Qwen3-14B", "open_weights": false, "reasoning": false, "release_date": "2025-04-30", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-235B-A22B": { "attachment": false, "cost": { "input": 0.35, "output": 1.42 }, "description": "Qwen/Qwen3-235B-A22B is an AI model provided by siliconflow.", "family": "qwen", "id": "Qwen/Qwen3-235B-A22B", "last_updated": "2025-11-25", "limit": { "context": 131000, "output": 131000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen/Qwen3-235B-A22B", "open_weights": false, "reasoning": false, "release_date": "2025-04-30", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-235B-A22B-Instruct-2507": { "attachment": false, "cost": { "input": 0.09, "output": 0.6 }, "description": "Qwen/Qwen3-235B-A22B-Instruct-2507 is an AI model provided by siliconflow.", "family": "qwen", "id": "Qwen/Qwen3-235B-A22B-Instruct-2507", "last_updated": "2025-11-25", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen/Qwen3-235B-A22B-Instruct-2507", "open_weights": false, "reasoning": false, "release_date": "2025-07-23", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-235B-A22B-Thinking-2507": { "attachment": false, "cost": { "input": 0.13, "output": 0.6 }, "description": "Qwen/Qwen3-235B-A22B-Thinking-2507 is an AI model provided by siliconflow.", "family": "qwen", "id": "Qwen/Qwen3-235B-A22B-Thinking-2507", "last_updated": "2025-11-25", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen/Qwen3-235B-A22B-Thinking-2507", "open_weights": false, "reasoning": true, "release_date": "2025-07-28", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-30B-A3B-Instruct-2507": { "attachment": false, "cost": { "input": 0.09, "output": 0.3 }, "description": "Qwen/Qwen3-30B-A3B-Instruct-2507 is an AI model provided by siliconflow.", "family": "qwen", "id": "Qwen/Qwen3-30B-A3B-Instruct-2507", "last_updated": "2025-11-25", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen/Qwen3-30B-A3B-Instruct-2507", "open_weights": false, "reasoning": false, "release_date": "2025-07-30", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-30B-A3B-Thinking-2507": { "attachment": false, "cost": { "input": 0.09, "output": 0.3 }, "description": "Qwen/Qwen3-30B-A3B-Thinking-2507 is an AI model provided by siliconflow.", "family": "qwen", "id": "Qwen/Qwen3-30B-A3B-Thinking-2507", "last_updated": "2025-11-25", "limit": { "context": 262000, "output": 131000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen/Qwen3-30B-A3B-Thinking-2507", "open_weights": false, "reasoning": true, "release_date": "2025-07-31", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-32B": { "attachment": false, "cost": { "input": 0.14, "output": 0.57 }, "description": "Qwen/Qwen3-32B is an AI model provided by siliconflow.", "family": "qwen", "id": "Qwen/Qwen3-32B", "last_updated": "2025-11-25", "limit": { "context": 131000, "output": 131000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen/Qwen3-32B", "open_weights": false, "reasoning": false, "release_date": "2025-04-30", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-8B": { "attachment": false, "cost": { "input": 0.06, "output": 0.06 }, "description": "Qwen/Qwen3-8B is an AI model provided by siliconflow.", "family": "qwen", "id": "Qwen/Qwen3-8B", "last_updated": "2025-11-25", "limit": { "context": 131000, "output": 131000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen/Qwen3-8B", "open_weights": false, "reasoning": false, "release_date": "2025-04-30", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-Coder-30B-A3B-Instruct": { "attachment": false, "cost": { "input": 0.07, "output": 0.28 }, "description": "Qwen/Qwen3-Coder-30B-A3B-Instruct is an AI model provided by siliconflow.", "family": "qwen", "id": "Qwen/Qwen3-Coder-30B-A3B-Instruct", "last_updated": "2025-11-25", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen/Qwen3-Coder-30B-A3B-Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-08-01", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-Coder-480B-A35B-Instruct": { "attachment": false, "cost": { "input": 0.25, "output": 1 }, "description": "Qwen/Qwen3-Coder-480B-A35B-Instruct is an AI model provided by siliconflow.", "family": "qwen", "id": "Qwen/Qwen3-Coder-480B-A35B-Instruct", "last_updated": "2025-11-25", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen/Qwen3-Coder-480B-A35B-Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-07-31", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-Next-80B-A3B-Instruct": { "attachment": false, "cost": { "input": 0.14, "output": 1.4 }, "description": "Qwen/Qwen3-Next-80B-A3B-Instruct is an AI model provided by siliconflow.", "family": "qwen", "id": "Qwen/Qwen3-Next-80B-A3B-Instruct", "last_updated": "2025-11-25", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen/Qwen3-Next-80B-A3B-Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-09-18", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-Next-80B-A3B-Thinking": { "attachment": false, "cost": { "input": 0.14, "output": 0.57 }, "description": "Qwen/Qwen3-Next-80B-A3B-Thinking is an AI model provided by siliconflow.", "family": "qwen", "id": "Qwen/Qwen3-Next-80B-A3B-Thinking", "last_updated": "2025-11-25", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen/Qwen3-Next-80B-A3B-Thinking", "open_weights": false, "reasoning": true, "release_date": "2025-09-25", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-Omni-30B-A3B-Captioner": { "attachment": true, "cost": { "input": 0.1, "output": 0.4 }, "description": "Qwen/Qwen3-Omni-30B-A3B-Captioner is an AI model provided by siliconflow.", "family": "qwen", "id": "Qwen/Qwen3-Omni-30B-A3B-Captioner", "last_updated": "2025-11-25", "limit": { "context": 66000, "output": 66000 }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "name": "Qwen/Qwen3-Omni-30B-A3B-Captioner", "open_weights": false, "reasoning": false, "release_date": "2025-10-04", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-Omni-30B-A3B-Instruct": { "attachment": true, "cost": { "input": 0.1, "output": 0.4 }, "description": "Qwen/Qwen3-Omni-30B-A3B-Instruct is an AI model provided by siliconflow.", "family": "qwen", "id": "Qwen/Qwen3-Omni-30B-A3B-Instruct", "last_updated": "2025-11-25", "limit": { "context": 66000, "output": 66000 }, "modalities": { "input": [ "text", "image", "audio" ], "output": [ "text" ] }, "name": "Qwen/Qwen3-Omni-30B-A3B-Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-10-04", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-Omni-30B-A3B-Thinking": { "attachment": true, "cost": { "input": 0.1, "output": 0.4 }, "description": "Qwen/Qwen3-Omni-30B-A3B-Thinking is an AI model provided by siliconflow.", "family": "qwen", "id": "Qwen/Qwen3-Omni-30B-A3B-Thinking", "last_updated": "2025-11-25", "limit": { "context": 66000, "output": 66000 }, "modalities": { "input": [ "text", "image", "audio" ], "output": [ "text" ] }, "name": "Qwen/Qwen3-Omni-30B-A3B-Thinking", "open_weights": false, "reasoning": true, "release_date": "2025-10-04", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-VL-235B-A22B-Instruct": { "attachment": true, "cost": { "input": 0.3, "output": 1.5 }, "description": "Qwen/Qwen3-VL-235B-A22B-Instruct is an AI model provided by siliconflow.", "family": "qwen", "id": "Qwen/Qwen3-VL-235B-A22B-Instruct", "last_updated": "2025-11-25", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen/Qwen3-VL-235B-A22B-Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-10-04", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-VL-235B-A22B-Thinking": { "attachment": true, "cost": { "input": 0.45, "output": 3.5 }, "description": "Qwen/Qwen3-VL-235B-A22B-Thinking is an AI model provided by siliconflow.", "family": "qwen", "id": "Qwen/Qwen3-VL-235B-A22B-Thinking", "last_updated": "2025-11-25", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen/Qwen3-VL-235B-A22B-Thinking", "open_weights": false, "reasoning": true, "release_date": "2025-10-04", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-VL-30B-A3B-Instruct": { "attachment": true, "cost": { "input": 0.29, "output": 1 }, "description": "Qwen/Qwen3-VL-30B-A3B-Instruct is an AI model provided by siliconflow.", "family": "qwen", "id": "Qwen/Qwen3-VL-30B-A3B-Instruct", "last_updated": "2025-11-25", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen/Qwen3-VL-30B-A3B-Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-10-05", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-VL-30B-A3B-Thinking": { "attachment": true, "cost": { "input": 0.29, "output": 1 }, "description": "Qwen/Qwen3-VL-30B-A3B-Thinking is an AI model provided by siliconflow.", "family": "qwen", "id": "Qwen/Qwen3-VL-30B-A3B-Thinking", "last_updated": "2025-11-25", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen/Qwen3-VL-30B-A3B-Thinking", "open_weights": false, "reasoning": true, "release_date": "2025-10-11", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-VL-32B-Instruct": { "attachment": true, "cost": { "input": 0.2, "output": 0.6 }, "description": "Qwen/Qwen3-VL-32B-Instruct is an AI model provided by siliconflow.", "family": "qwen", "id": "Qwen/Qwen3-VL-32B-Instruct", "last_updated": "2025-11-25", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen/Qwen3-VL-32B-Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-10-21", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-VL-32B-Thinking": { "attachment": true, "cost": { "input": 0.2, "output": 1.5 }, "description": "Qwen/Qwen3-VL-32B-Thinking is an AI model provided by siliconflow.", "family": "qwen", "id": "Qwen/Qwen3-VL-32B-Thinking", "last_updated": "2025-11-25", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen/Qwen3-VL-32B-Thinking", "open_weights": false, "reasoning": true, "release_date": "2025-10-21", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-VL-8B-Instruct": { "attachment": true, "cost": { "input": 0.18, "output": 0.68 }, "description": "Qwen/Qwen3-VL-8B-Instruct is an AI model provided by siliconflow.", "family": "qwen", "id": "Qwen/Qwen3-VL-8B-Instruct", "last_updated": "2025-11-25", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen/Qwen3-VL-8B-Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-10-15", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-VL-8B-Thinking": { "attachment": true, "cost": { "input": 0.18, "output": 2 }, "description": "Qwen/Qwen3-VL-8B-Thinking is an AI model provided by siliconflow.", "family": "qwen", "id": "Qwen/Qwen3-VL-8B-Thinking", "last_updated": "2025-11-25", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen/Qwen3-VL-8B-Thinking", "open_weights": false, "reasoning": true, "release_date": "2025-10-15", "structured_output": true, "temperature": true, "tool_call": true }, "THUDM/GLM-4-32B-0414": { "attachment": false, "cost": { "input": 0.27, "output": 0.27 }, "description": "THUDM/GLM-4-32B-0414 is an AI model provided by siliconflow.", "family": "glm", "id": "THUDM/GLM-4-32B-0414", "last_updated": "2025-11-25", "limit": { "context": 33000, "output": 33000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "THUDM/GLM-4-32B-0414", "open_weights": false, "reasoning": false, "release_date": "2025-04-18", "structured_output": true, "temperature": true, "tool_call": true }, "THUDM/GLM-4-9B-0414": { "attachment": false, "cost": { "input": 0.086, "output": 0.086 }, "description": "THUDM/GLM-4-9B-0414 is an AI model provided by siliconflow.", "family": "glm", "id": "THUDM/GLM-4-9B-0414", "last_updated": "2025-11-25", "limit": { "context": 33000, "output": 33000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "THUDM/GLM-4-9B-0414", "open_weights": false, "reasoning": false, "release_date": "2025-04-18", "structured_output": true, "temperature": true, "tool_call": true }, "THUDM/GLM-Z1-32B-0414": { "attachment": false, "cost": { "input": 0.14, "output": 0.57 }, "description": "THUDM/GLM-Z1-32B-0414 is an AI model provided by siliconflow.", "family": "glm-z", "id": "THUDM/GLM-Z1-32B-0414", "last_updated": "2025-11-25", "limit": { "context": 131000, "output": 131000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "THUDM/GLM-Z1-32B-0414", "open_weights": false, "reasoning": true, "release_date": "2025-04-18", "structured_output": true, "temperature": true, "tool_call": true }, "THUDM/GLM-Z1-9B-0414": { "attachment": false, "cost": { "input": 0.086, "output": 0.086 }, "description": "THUDM/GLM-Z1-9B-0414 is an AI model provided by siliconflow.", "family": "glm-z", "id": "THUDM/GLM-Z1-9B-0414", "last_updated": "2025-11-25", "limit": { "context": 131000, "output": 131000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "THUDM/GLM-Z1-9B-0414", "open_weights": false, "reasoning": true, "release_date": "2025-04-18", "structured_output": true, "temperature": true, "tool_call": true }, "baidu/ERNIE-4.5-300B-A47B": { "attachment": false, "cost": { "input": 0.28, "output": 1.1 }, "description": "baidu/ERNIE-4.5-300B-A47B is an AI model provided by siliconflow.", "family": "ernie", "id": "baidu/ERNIE-4.5-300B-A47B", "last_updated": "2025-11-25", "limit": { "context": 131000, "output": 131000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "baidu/ERNIE-4.5-300B-A47B", "open_weights": false, "reasoning": false, "release_date": "2025-07-02", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek-ai/DeepSeek-R1": { "attachment": false, "cost": { "input": 0.5, "output": 2.18 }, "description": "deepseek-ai/DeepSeek-R1 is an AI model provided by siliconflow.", "family": "deepseek-thinking", "id": "deepseek-ai/DeepSeek-R1", "last_updated": "2025-11-25", "limit": { "context": 164000, "output": 164000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "deepseek-ai/DeepSeek-R1", "open_weights": false, "reasoning": true, "release_date": "2025-05-28", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": { "attachment": false, "cost": { "input": 0.1, "output": 0.1 }, "description": "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B is an AI model provided by siliconflow.", "family": "qwen", "id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B", "last_updated": "2025-11-25", "limit": { "context": 131000, "output": 131000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B", "open_weights": false, "reasoning": true, "release_date": "2025-01-20", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": { "attachment": false, "cost": { "input": 0.18, "output": 0.18 }, "description": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B is an AI model provided by siliconflow.", "family": "qwen", "id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B", "last_updated": "2025-11-25", "limit": { "context": 131000, "output": 131000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B", "open_weights": false, "reasoning": true, "release_date": "2025-01-20", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek-ai/DeepSeek-V3": { "attachment": false, "cost": { "input": 0.25, "output": 1 }, "description": "deepseek-ai/DeepSeek-V3 is an AI model provided by siliconflow.", "family": "deepseek", "id": "deepseek-ai/DeepSeek-V3", "last_updated": "2025-11-25", "limit": { "context": 164000, "output": 164000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "deepseek-ai/DeepSeek-V3", "open_weights": false, "reasoning": false, "release_date": "2024-12-26", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek-ai/DeepSeek-V3.1": { "attachment": false, "cost": { "input": 0.27, "output": 1 }, "description": "deepseek-ai/DeepSeek-V3.1 is an AI model provided by siliconflow.", "family": "deepseek", "id": "deepseek-ai/DeepSeek-V3.1", "last_updated": "2025-11-25", "limit": { "context": 164000, "output": 164000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "deepseek-ai/DeepSeek-V3.1", "open_weights": false, "reasoning": true, "release_date": "2025-08-25", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek-ai/DeepSeek-V3.1-Terminus": { "attachment": false, "cost": { "input": 0.27, "output": 1 }, "description": "deepseek-ai/DeepSeek-V3.1-Terminus is an AI model provided by siliconflow.", "family": "deepseek", "id": "deepseek-ai/DeepSeek-V3.1-Terminus", "last_updated": "2025-11-25", "limit": { "context": 164000, "output": 164000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "deepseek-ai/DeepSeek-V3.1-Terminus", "open_weights": false, "reasoning": true, "release_date": "2025-09-29", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek-ai/DeepSeek-V3.2": { "attachment": false, "cost": { "input": 0.27, "output": 0.42 }, "description": "deepseek-ai/DeepSeek-V3.2 is an AI model provided by siliconflow.", "family": "deepseek", "id": "deepseek-ai/DeepSeek-V3.2", "last_updated": "2025-12-03", "limit": { "context": 164000, "output": 164000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "deepseek-ai/DeepSeek-V3.2", "open_weights": false, "reasoning": true, "release_date": "2025-12-03", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek-ai/DeepSeek-V3.2-Exp": { "attachment": false, "cost": { "input": 0.27, "output": 0.41 }, "description": "deepseek-ai/DeepSeek-V3.2-Exp is an AI model provided by siliconflow.", "family": "deepseek", "id": "deepseek-ai/DeepSeek-V3.2-Exp", "last_updated": "2025-11-25", "limit": { "context": 164000, "output": 164000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "deepseek-ai/DeepSeek-V3.2-Exp", "open_weights": false, "reasoning": true, "release_date": "2025-10-10", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek-ai/deepseek-vl2": { "attachment": true, "cost": { "input": 0.15, "output": 0.15 }, "description": "deepseek-ai/deepseek-vl2 is an AI model provided by siliconflow.", "family": "deepseek", "id": "deepseek-ai/deepseek-vl2", "last_updated": "2025-11-25", "limit": { "context": 4000, "output": 4000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "deepseek-ai/deepseek-vl2", "open_weights": false, "reasoning": false, "release_date": "2024-12-13", "structured_output": true, "temperature": true, "tool_call": true }, "inclusionAI/Ling-flash-2.0": { "attachment": false, "cost": { "input": 0.14, "output": 0.57 }, "description": "inclusionAI/Ling-flash-2.0 is an AI model provided by siliconflow.", "family": "ling", "id": "inclusionAI/Ling-flash-2.0", "last_updated": "2025-11-25", "limit": { "context": 131000, "output": 131000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "inclusionAI/Ling-flash-2.0", "open_weights": false, "reasoning": false, "release_date": "2025-09-18", "structured_output": true, "temperature": true, "tool_call": true }, "inclusionAI/Ling-mini-2.0": { "attachment": false, "cost": { "input": 0.07, "output": 0.28 }, "description": "inclusionAI/Ling-mini-2.0 is an AI model provided by siliconflow.", "family": "ling", "id": "inclusionAI/Ling-mini-2.0", "last_updated": "2025-11-25", "limit": { "context": 131000, "output": 131000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "inclusionAI/Ling-mini-2.0", "open_weights": false, "reasoning": false, "release_date": "2025-09-10", "structured_output": true, "temperature": true, "tool_call": true }, "inclusionAI/Ring-flash-2.0": { "attachment": false, "cost": { "input": 0.14, "output": 0.57 }, "description": "inclusionAI/Ring-flash-2.0 is an AI model provided by siliconflow.", "family": "ring", "id": "inclusionAI/Ring-flash-2.0", "last_updated": "2025-11-25", "limit": { "context": 131000, "output": 131000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "inclusionAI/Ring-flash-2.0", "open_weights": false, "reasoning": true, "release_date": "2025-09-29", "structured_output": true, "temperature": true, "tool_call": true }, "meta-llama/Meta-Llama-3.1-8B-Instruct": { "attachment": false, "cost": { "input": 0.06, "output": 0.06 }, "description": "meta-llama/Meta-Llama-3.1-8B-Instruct is an AI model provided by siliconflow.", "family": "llama", "id": "meta-llama/Meta-Llama-3.1-8B-Instruct", "last_updated": "2025-11-25", "limit": { "context": 33000, "output": 4000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "meta-llama/Meta-Llama-3.1-8B-Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-04-23", "structured_output": true, "temperature": true, "tool_call": true }, "moonshotai/Kimi-K2-Instruct": { "attachment": false, "cost": { "input": 0.58, "output": 2.29 }, "description": "moonshotai/Kimi-K2-Instruct is an AI model provided by siliconflow.", "family": "kimi", "id": "moonshotai/Kimi-K2-Instruct", "last_updated": "2025-11-25", "limit": { "context": 131000, "output": 131000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "moonshotai/Kimi-K2-Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-07-13", "structured_output": true, "temperature": true, "tool_call": true }, "moonshotai/Kimi-K2-Instruct-0905": { "attachment": false, "cost": { "input": 0.4, "output": 2 }, "description": "moonshotai/Kimi-K2-Instruct-0905 is an AI model provided by siliconflow.", "family": "kimi", "id": "moonshotai/Kimi-K2-Instruct-0905", "last_updated": "2025-11-25", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "moonshotai/Kimi-K2-Instruct-0905", "open_weights": false, "reasoning": false, "release_date": "2025-09-08", "structured_output": true, "temperature": true, "tool_call": true }, "moonshotai/Kimi-K2-Thinking": { "attachment": false, "cost": { "input": 0.55, "output": 2.5 }, "description": "moonshotai/Kimi-K2-Thinking is an AI model provided by siliconflow.", "family": "kimi-thinking", "id": "moonshotai/Kimi-K2-Thinking", "last_updated": "2025-11-25", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "moonshotai/Kimi-K2-Thinking", "open_weights": false, "reasoning": true, "release_date": "2025-11-07", "structured_output": true, "temperature": true, "tool_call": true }, "moonshotai/Kimi-K2.5": { "attachment": false, "cost": { "input": 0.45, "output": 2.25 }, "description": "moonshotai/Kimi-K2.5 is an AI model provided by siliconflow.", "family": "kimi", "id": "moonshotai/Kimi-K2.5", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-01-27", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "moonshotai/Kimi-K2.5", "open_weights": true, "reasoning": true, "release_date": "2026-01-27", "structured_output": true, "temperature": true, "tool_call": true }, "moonshotai/Kimi-K2.6": { "attachment": false, "cost": { "cache_read": 0.16, "input": 0.95, "output": 4 }, "description": "moonshotai/Kimi-K2.6 is an AI model provided by siliconflow.", "family": "kimi", "id": "moonshotai/Kimi-K2.6", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-21", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "moonshotai/Kimi-K2.6", "open_weights": true, "reasoning": true, "release_date": "2026-04-21", "structured_output": true, "temperature": true, "tool_call": true }, "nex-agi/DeepSeek-V3.1-Nex-N1": { "attachment": false, "cost": { "input": 0.5, "output": 2 }, "description": "nex-agi/DeepSeek-V3.1-Nex-N1 is an AI model provided by siliconflow.", "family": "deepseek", "id": "nex-agi/DeepSeek-V3.1-Nex-N1", "last_updated": "2025-11-25", "limit": { "context": 131000, "output": 131000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "nex-agi/DeepSeek-V3.1-Nex-N1", "open_weights": false, "reasoning": true, "release_date": "2025-01-01", "structured_output": true, "temperature": true, "tool_call": true }, "openai/gpt-oss-120b": { "attachment": false, "cost": { "input": 0.05, "output": 0.45 }, "description": "openai/gpt-oss-120b is an AI model provided by siliconflow.", "family": "gpt-oss", "id": "openai/gpt-oss-120b", "last_updated": "2025-11-25", "limit": { "context": 131000, "output": 8000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "openai/gpt-oss-120b", "open_weights": false, "reasoning": true, "release_date": "2025-08-13", "structured_output": true, "temperature": true, "tool_call": true }, "openai/gpt-oss-20b": { "attachment": false, "cost": { "input": 0.04, "output": 0.18 }, "description": "openai/gpt-oss-20b is an AI model provided by siliconflow.", "family": "gpt-oss", "id": "openai/gpt-oss-20b", "last_updated": "2025-11-25", "limit": { "context": 131000, "output": 8000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "openai/gpt-oss-20b", "open_weights": false, "reasoning": false, "release_date": "2025-08-13", "structured_output": true, "temperature": true, "tool_call": true }, "stepfun-ai/Step-3.5-Flash": { "attachment": false, "cost": { "input": 0.1, "output": 0.3 }, "description": "stepfun-ai/Step-3.5-Flash is an AI model provided by siliconflow.", "family": "step", "id": "stepfun-ai/Step-3.5-Flash", "last_updated": "2026-02-11", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "stepfun-ai/Step-3.5-Flash", "open_weights": false, "reasoning": true, "release_date": "2026-02-11", "structured_output": true, "temperature": true, "tool_call": true }, "tencent/Hunyuan-A13B-Instruct": { "attachment": false, "cost": { "input": 0.14, "output": 0.57 }, "description": "tencent/Hunyuan-A13B-Instruct is an AI model provided by siliconflow.", "family": "hunyuan", "id": "tencent/Hunyuan-A13B-Instruct", "last_updated": "2025-11-25", "limit": { "context": 131000, "output": 131000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "tencent/Hunyuan-A13B-Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-06-30", "structured_output": true, "temperature": true, "tool_call": true }, "tencent/Hunyuan-MT-7B": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "tencent/Hunyuan-MT-7B is an AI model provided by siliconflow.", "family": "hunyuan", "id": "tencent/Hunyuan-MT-7B", "last_updated": "2025-11-25", "limit": { "context": 33000, "output": 33000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "tencent/Hunyuan-MT-7B", "open_weights": false, "reasoning": false, "release_date": "2025-09-18", "structured_output": true, "temperature": true, "tool_call": true }, "zai-org/GLM-4.5": { "attachment": false, "cost": { "input": 0.4, "output": 2 }, "description": "zai-org/GLM-4.5 is an AI model provided by siliconflow.", "family": "glm", "id": "zai-org/GLM-4.5", "last_updated": "2025-11-25", "limit": { "context": 131000, "output": 131000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "zai-org/GLM-4.5", "open_weights": false, "reasoning": false, "release_date": "2025-07-28", "structured_output": true, "temperature": true, "tool_call": true }, "zai-org/GLM-4.5-Air": { "attachment": false, "cost": { "input": 0.14, "output": 0.86 }, "description": "zai-org/GLM-4.5-Air is an AI model provided by siliconflow.", "family": "glm-air", "id": "zai-org/GLM-4.5-Air", "last_updated": "2025-11-25", "limit": { "context": 131000, "output": 131000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "zai-org/GLM-4.5-Air", "open_weights": false, "reasoning": false, "release_date": "2025-07-28", "structured_output": true, "temperature": true, "tool_call": true }, "zai-org/GLM-4.5V": { "attachment": true, "cost": { "input": 0.14, "output": 0.86 }, "description": "zai-org/GLM-4.5V is an AI model provided by siliconflow.", "family": "glm", "id": "zai-org/GLM-4.5V", "last_updated": "2025-11-25", "limit": { "context": 66000, "output": 66000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "zai-org/GLM-4.5V", "open_weights": false, "reasoning": false, "release_date": "2025-08-13", "structured_output": true, "temperature": true, "tool_call": true }, "zai-org/GLM-4.6": { "attachment": false, "cost": { "input": 0.5, "output": 1.9 }, "description": "zai-org/GLM-4.6 is an AI model provided by siliconflow.", "family": "glm", "id": "zai-org/GLM-4.6", "last_updated": "2025-11-25", "limit": { "context": 205000, "output": 205000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "zai-org/GLM-4.6", "open_weights": false, "reasoning": false, "release_date": "2025-10-04", "structured_output": true, "temperature": true, "tool_call": true }, "zai-org/GLM-4.6V": { "attachment": true, "cost": { "input": 0.3, "output": 0.9 }, "description": "zai-org/GLM-4.6V is an AI model provided by siliconflow.", "family": "glm", "id": "zai-org/GLM-4.6V", "last_updated": "2025-12-07", "limit": { "context": 131000, "output": 131000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "zai-org/GLM-4.6V", "open_weights": false, "reasoning": true, "release_date": "2025-12-07", "structured_output": false, "temperature": true, "tool_call": true }, "zai-org/GLM-4.7": { "attachment": false, "cost": { "input": 0.6, "output": 2.2 }, "description": "zai-org/GLM-4.7 is an AI model provided by siliconflow.", "family": "glm", "id": "zai-org/GLM-4.7", "interleaved": { "field": "reasoning_content" }, "last_updated": "2025-12-22", "limit": { "context": 205000, "output": 205000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "zai-org/GLM-4.7", "open_weights": false, "reasoning": true, "release_date": "2025-12-22", "structured_output": true, "temperature": true, "tool_call": true }, "zai-org/GLM-5": { "attachment": false, "cost": { "input": 1, "output": 3.2 }, "description": "zai-org/GLM-5 is an AI model provided by siliconflow.", "family": "glm", "id": "zai-org/GLM-5", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-02-12", "limit": { "context": 205000, "output": 205000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "zai-org/GLM-5", "open_weights": true, "reasoning": true, "release_date": "2026-02-12", "structured_output": true, "temperature": true, "tool_call": true }, "zai-org/GLM-5.1": { "attachment": false, "cost": { "cache_write": 0, "input": 1.4, "output": 4.4 }, "description": "zai-org/GLM-5.1 is an AI model provided by siliconflow.", "family": "glm", "id": "zai-org/GLM-5.1", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-08", "limit": { "context": 205000, "output": 205000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "zai-org/GLM-5.1", "open_weights": true, "reasoning": true, "release_date": "2026-04-08", "structured_output": true, "temperature": true, "tool_call": true }, "zai-org/GLM-5V-Turbo": { "attachment": true, "cost": { "cache_write": 0, "input": 1.2, "output": 4 }, "description": "zai-org/GLM-5V-Turbo is an AI model provided by siliconflow.", "family": "glm", "id": "zai-org/GLM-5V-Turbo", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-01", "limit": { "context": 200000, "output": 131072 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "zai-org/GLM-5V-Turbo", "open_weights": false, "reasoning": true, "release_date": "2026-04-01", "temperature": true, "tool_call": true } }, "name": "SiliconFlow", "npm": "@ai-sdk/openai-compatible" }, "siliconflow-cn": { "api": "https://api.siliconflow.cn/v1", "doc": "https://cloud.siliconflow.com/models", "env": [ "SILICONFLOW_CN_API_KEY" ], "iconURL": "https://models.dev/logos/siliconflow-cn.svg", "id": "siliconflow-cn", "models": { "ByteDance-Seed/Seed-OSS-36B-Instruct": { "attachment": false, "cost": { "input": 0.21, "output": 0.57 }, "description": "ByteDance-Seed/Seed-OSS-36B-Instruct is an AI model provided by siliconflow-cn.", "family": "seed", "id": "ByteDance-Seed/Seed-OSS-36B-Instruct", "last_updated": "2025-11-25", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "ByteDance-Seed/Seed-OSS-36B-Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-09-04", "structured_output": true, "temperature": true, "tool_call": true }, "Kwaipilot/KAT-Dev": { "attachment": false, "cost": { "input": 0.2, "output": 0.6 }, "description": "Kwaipilot/KAT-Dev is an AI model provided by siliconflow-cn.", "family": "kat-coder", "id": "Kwaipilot/KAT-Dev", "last_updated": "2026-01-16", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kwaipilot/KAT-Dev", "open_weights": false, "reasoning": false, "release_date": "2025-09-27", "structured_output": true, "temperature": true, "tool_call": true }, "PaddlePaddle/PaddleOCR-VL": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "PaddlePaddle/PaddleOCR-VL is an AI model provided by siliconflow-cn.", "id": "PaddlePaddle/PaddleOCR-VL", "last_updated": "2025-10-16", "limit": { "context": 16384, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "PaddlePaddle/PaddleOCR-VL", "open_weights": true, "reasoning": false, "release_date": "2025-10-16", "temperature": true, "tool_call": false }, "PaddlePaddle/PaddleOCR-VL-1.5": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "PaddlePaddle/PaddleOCR-VL-1.5 is an AI model provided by siliconflow-cn.", "id": "PaddlePaddle/PaddleOCR-VL-1.5", "last_updated": "2026-01-29", "limit": { "context": 16384, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "PaddlePaddle/PaddleOCR-VL-1.5", "open_weights": true, "reasoning": false, "release_date": "2026-01-29", "temperature": true, "tool_call": false }, "Pro/MiniMaxAI/MiniMax-M2.1": { "attachment": false, "cost": { "input": 0.3, "output": 1.2 }, "description": "Pro/MiniMaxAI/MiniMax-M2.1 is an AI model provided by siliconflow-cn.", "family": "minimax", "id": "Pro/MiniMaxAI/MiniMax-M2.1", "last_updated": "2025-12-23", "limit": { "context": 197000, "output": 131000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Pro/MiniMaxAI/MiniMax-M2.1", "open_weights": false, "reasoning": false, "release_date": "2025-12-23", "structured_output": true, "temperature": true, "tool_call": true }, "Pro/MiniMaxAI/MiniMax-M2.5": { "attachment": false, "cost": { "input": 0.3, "output": 1.22 }, "description": "Pro/MiniMaxAI/MiniMax-M2.5 is an AI model provided by siliconflow-cn.", "family": "minimax", "id": "Pro/MiniMaxAI/MiniMax-M2.5", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-02-13", "limit": { "context": 192000, "output": 131000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Pro/MiniMaxAI/MiniMax-M2.5", "open_weights": false, "reasoning": false, "release_date": "2026-02-13", "structured_output": true, "temperature": true, "tool_call": true }, "Pro/deepseek-ai/DeepSeek-R1": { "attachment": false, "cost": { "input": 0.5, "output": 2.18 }, "description": "Pro/deepseek-ai/DeepSeek-R1 is an AI model provided by siliconflow-cn.", "family": "deepseek-thinking", "id": "Pro/deepseek-ai/DeepSeek-R1", "last_updated": "2025-11-25", "limit": { "context": 164000, "output": 164000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Pro/deepseek-ai/DeepSeek-R1", "open_weights": false, "reasoning": true, "release_date": "2025-05-28", "structured_output": true, "temperature": true, "tool_call": true }, "Pro/deepseek-ai/DeepSeek-V3": { "attachment": false, "cost": { "input": 0.25, "output": 1 }, "description": "Pro/deepseek-ai/DeepSeek-V3 is an AI model provided by siliconflow-cn.", "family": "deepseek", "id": "Pro/deepseek-ai/DeepSeek-V3", "last_updated": "2025-11-25", "limit": { "context": 164000, "output": 164000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Pro/deepseek-ai/DeepSeek-V3", "open_weights": false, "reasoning": false, "release_date": "2024-12-26", "structured_output": true, "temperature": true, "tool_call": true }, "Pro/deepseek-ai/DeepSeek-V3.1-Terminus": { "attachment": false, "cost": { "input": 0.27, "output": 1 }, "description": "Pro/deepseek-ai/DeepSeek-V3.1-Terminus is an AI model provided by siliconflow-cn.", "family": "deepseek", "id": "Pro/deepseek-ai/DeepSeek-V3.1-Terminus", "last_updated": "2025-11-25", "limit": { "context": 164000, "output": 164000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Pro/deepseek-ai/DeepSeek-V3.1-Terminus", "open_weights": false, "reasoning": true, "release_date": "2025-09-29", "structured_output": true, "temperature": true, "tool_call": true }, "Pro/deepseek-ai/DeepSeek-V3.2": { "attachment": false, "cost": { "input": 0.27, "output": 0.42 }, "description": "Pro/deepseek-ai/DeepSeek-V3.2 is an AI model provided by siliconflow-cn.", "family": "deepseek", "id": "Pro/deepseek-ai/DeepSeek-V3.2", "last_updated": "2025-12-03", "limit": { "context": 164000, "output": 164000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Pro/deepseek-ai/DeepSeek-V3.2", "open_weights": false, "reasoning": true, "release_date": "2025-12-03", "structured_output": true, "temperature": true, "tool_call": true }, "Pro/moonshotai/Kimi-K2-Instruct-0905": { "attachment": false, "cost": { "input": 0.4, "output": 2 }, "description": "Pro/moonshotai/Kimi-K2-Instruct-0905 is an AI model provided by siliconflow-cn.", "family": "kimi", "id": "Pro/moonshotai/Kimi-K2-Instruct-0905", "last_updated": "2025-11-25", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Pro/moonshotai/Kimi-K2-Instruct-0905", "open_weights": false, "reasoning": false, "release_date": "2025-09-08", "structured_output": true, "temperature": true, "tool_call": true }, "Pro/moonshotai/Kimi-K2-Thinking": { "attachment": false, "cost": { "input": 0.55, "output": 2.5 }, "description": "Pro/moonshotai/Kimi-K2-Thinking is an AI model provided by siliconflow-cn.", "family": "kimi-thinking", "id": "Pro/moonshotai/Kimi-K2-Thinking", "last_updated": "2025-11-25", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Pro/moonshotai/Kimi-K2-Thinking", "open_weights": false, "reasoning": true, "release_date": "2025-11-07", "structured_output": true, "temperature": true, "tool_call": true }, "Pro/moonshotai/Kimi-K2.5": { "attachment": false, "cost": { "input": 0.45, "output": 2.25 }, "description": "Pro/moonshotai/Kimi-K2.5 is an AI model provided by siliconflow-cn.", "family": "kimi", "id": "Pro/moonshotai/Kimi-K2.5", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-01-27", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Pro/moonshotai/Kimi-K2.5", "open_weights": true, "reasoning": true, "release_date": "2026-01-27", "structured_output": true, "temperature": true, "tool_call": true }, "Pro/moonshotai/Kimi-K2.6": { "attachment": false, "cost": { "cache_read": 0.16, "input": 0.95, "output": 4 }, "description": "Pro/moonshotai/Kimi-K2.6 is an AI model provided by siliconflow-cn.", "family": "kimi", "id": "Pro/moonshotai/Kimi-K2.6", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-21", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Pro/moonshotai/Kimi-K2.6", "open_weights": true, "reasoning": true, "release_date": "2026-04-21", "structured_output": true, "temperature": true, "tool_call": true }, "Pro/zai-org/GLM-4.7": { "attachment": false, "cost": { "input": 0.6, "output": 2.2 }, "description": "Pro/zai-org/GLM-4.7 is an AI model provided by siliconflow-cn.", "family": "glm", "id": "Pro/zai-org/GLM-4.7", "interleaved": { "field": "reasoning_content" }, "last_updated": "2025-12-22", "limit": { "context": 205000, "output": 205000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Pro/zai-org/GLM-4.7", "open_weights": false, "reasoning": true, "release_date": "2025-12-22", "structured_output": true, "temperature": true, "tool_call": true }, "Pro/zai-org/GLM-5": { "attachment": false, "cost": { "input": 1, "output": 3.2 }, "description": "Pro/zai-org/GLM-5 is an AI model provided by siliconflow-cn.", "family": "glm", "id": "Pro/zai-org/GLM-5", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-02-12", "limit": { "context": 205000, "output": 205000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Pro/zai-org/GLM-5", "open_weights": true, "reasoning": true, "release_date": "2026-02-12", "structured_output": true, "temperature": true, "tool_call": true }, "Pro/zai-org/GLM-5.1": { "attachment": false, "cost": { "cache_write": 0, "input": 1.4, "output": 4.4 }, "description": "Pro/zai-org/GLM-5.1 is an AI model provided by siliconflow-cn.", "family": "glm", "id": "Pro/zai-org/GLM-5.1", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-08", "limit": { "context": 205000, "output": 205000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Pro/zai-org/GLM-5.1", "open_weights": true, "reasoning": true, "release_date": "2026-04-08", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/QwQ-32B": { "attachment": false, "cost": { "input": 0.15, "output": 0.58 }, "description": "Qwen/QwQ-32B is an AI model provided by siliconflow-cn.", "family": "qwen", "id": "Qwen/QwQ-32B", "last_updated": "2025-11-25", "limit": { "context": 131000, "output": 131000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen/QwQ-32B", "open_weights": false, "reasoning": true, "release_date": "2025-03-06", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen2.5-14B-Instruct": { "attachment": false, "cost": { "input": 0.1, "output": 0.1 }, "description": "Qwen/Qwen2.5-14B-Instruct is an AI model provided by siliconflow-cn.", "family": "qwen", "id": "Qwen/Qwen2.5-14B-Instruct", "last_updated": "2025-11-25", "limit": { "context": 33000, "output": 4000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen/Qwen2.5-14B-Instruct", "open_weights": false, "reasoning": false, "release_date": "2024-09-18", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen2.5-32B-Instruct": { "attachment": false, "cost": { "input": 0.18, "output": 0.18 }, "description": "Qwen/Qwen2.5-32B-Instruct is an AI model provided by siliconflow-cn.", "family": "qwen", "id": "Qwen/Qwen2.5-32B-Instruct", "last_updated": "2025-11-25", "limit": { "context": 33000, "output": 4000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen/Qwen2.5-32B-Instruct", "open_weights": false, "reasoning": false, "release_date": "2024-09-19", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen2.5-72B-Instruct": { "attachment": false, "cost": { "input": 0.59, "output": 0.59 }, "description": "Qwen/Qwen2.5-72B-Instruct is an AI model provided by siliconflow-cn.", "family": "qwen", "id": "Qwen/Qwen2.5-72B-Instruct", "last_updated": "2025-11-25", "limit": { "context": 33000, "output": 4000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen/Qwen2.5-72B-Instruct", "open_weights": false, "reasoning": false, "release_date": "2024-09-18", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen2.5-72B-Instruct-128K": { "attachment": false, "cost": { "input": 0.59, "output": 0.59 }, "description": "Qwen/Qwen2.5-72B-Instruct-128K is an AI model provided by siliconflow-cn.", "family": "qwen", "id": "Qwen/Qwen2.5-72B-Instruct-128K", "last_updated": "2025-11-25", "limit": { "context": 131000, "output": 4000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen/Qwen2.5-72B-Instruct-128K", "open_weights": false, "reasoning": false, "release_date": "2024-09-18", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen2.5-7B-Instruct": { "attachment": false, "cost": { "input": 0.05, "output": 0.05 }, "description": "Qwen/Qwen2.5-7B-Instruct is an AI model provided by siliconflow-cn.", "family": "qwen", "id": "Qwen/Qwen2.5-7B-Instruct", "last_updated": "2025-11-25", "limit": { "context": 33000, "output": 4000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen/Qwen2.5-7B-Instruct", "open_weights": false, "reasoning": false, "release_date": "2024-09-18", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen2.5-Coder-32B-Instruct": { "attachment": false, "cost": { "input": 0.18, "output": 0.18 }, "description": "Qwen/Qwen2.5-Coder-32B-Instruct is an AI model provided by siliconflow-cn.", "family": "qwen", "id": "Qwen/Qwen2.5-Coder-32B-Instruct", "last_updated": "2025-11-25", "limit": { "context": 33000, "output": 4000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen/Qwen2.5-Coder-32B-Instruct", "open_weights": false, "reasoning": false, "release_date": "2024-11-11", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen2.5-VL-32B-Instruct": { "attachment": true, "cost": { "input": 0.27, "output": 0.27 }, "description": "Qwen/Qwen2.5-VL-32B-Instruct is an AI model provided by siliconflow-cn.", "family": "qwen", "id": "Qwen/Qwen2.5-VL-32B-Instruct", "last_updated": "2025-11-25", "limit": { "context": 131000, "output": 131000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen/Qwen2.5-VL-32B-Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-03-24", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen2.5-VL-72B-Instruct": { "attachment": true, "cost": { "input": 0.59, "output": 0.59 }, "description": "Qwen/Qwen2.5-VL-72B-Instruct is an AI model provided by siliconflow-cn.", "family": "qwen", "id": "Qwen/Qwen2.5-VL-72B-Instruct", "last_updated": "2025-11-25", "limit": { "context": 131000, "output": 4000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen/Qwen2.5-VL-72B-Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-01-28", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-14B": { "attachment": false, "cost": { "input": 0.07, "output": 0.28 }, "description": "Qwen/Qwen3-14B is an AI model provided by siliconflow-cn.", "family": "qwen", "id": "Qwen/Qwen3-14B", "last_updated": "2025-11-25", "limit": { "context": 131000, "output": 131000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen/Qwen3-14B", "open_weights": false, "reasoning": false, "release_date": "2025-04-30", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-235B-A22B-Instruct-2507": { "attachment": false, "cost": { "input": 0.09, "output": 0.6 }, "description": "Qwen/Qwen3-235B-A22B-Instruct-2507 is an AI model provided by siliconflow-cn.", "family": "qwen", "id": "Qwen/Qwen3-235B-A22B-Instruct-2507", "last_updated": "2025-11-25", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen/Qwen3-235B-A22B-Instruct-2507", "open_weights": false, "reasoning": false, "release_date": "2025-07-23", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-235B-A22B-Thinking-2507": { "attachment": false, "cost": { "input": 0.13, "output": 0.6 }, "description": "Qwen/Qwen3-235B-A22B-Thinking-2507 is an AI model provided by siliconflow-cn.", "family": "qwen", "id": "Qwen/Qwen3-235B-A22B-Thinking-2507", "last_updated": "2025-11-25", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen/Qwen3-235B-A22B-Thinking-2507", "open_weights": false, "reasoning": true, "release_date": "2025-07-28", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-30B-A3B-Instruct-2507": { "attachment": false, "cost": { "input": 0.09, "output": 0.3 }, "description": "Qwen/Qwen3-30B-A3B-Instruct-2507 is an AI model provided by siliconflow-cn.", "family": "qwen", "id": "Qwen/Qwen3-30B-A3B-Instruct-2507", "last_updated": "2025-11-25", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen/Qwen3-30B-A3B-Instruct-2507", "open_weights": false, "reasoning": false, "release_date": "2025-07-30", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-30B-A3B-Thinking-2507": { "attachment": false, "cost": { "input": 0.09, "output": 0.3 }, "description": "Qwen/Qwen3-30B-A3B-Thinking-2507 is an AI model provided by siliconflow-cn.", "family": "qwen", "id": "Qwen/Qwen3-30B-A3B-Thinking-2507", "last_updated": "2025-11-25", "limit": { "context": 262000, "output": 131000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen/Qwen3-30B-A3B-Thinking-2507", "open_weights": false, "reasoning": true, "release_date": "2025-07-31", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-32B": { "attachment": false, "cost": { "input": 0.14, "output": 0.57 }, "description": "Qwen/Qwen3-32B is an AI model provided by siliconflow-cn.", "family": "qwen", "id": "Qwen/Qwen3-32B", "last_updated": "2025-11-25", "limit": { "context": 131000, "output": 131000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen/Qwen3-32B", "open_weights": false, "reasoning": false, "release_date": "2025-04-30", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-8B": { "attachment": false, "cost": { "input": 0.06, "output": 0.06 }, "description": "Qwen/Qwen3-8B is an AI model provided by siliconflow-cn.", "family": "qwen", "id": "Qwen/Qwen3-8B", "last_updated": "2025-11-25", "limit": { "context": 131000, "output": 131000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen/Qwen3-8B", "open_weights": false, "reasoning": false, "release_date": "2025-04-30", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-Coder-30B-A3B-Instruct": { "attachment": false, "cost": { "input": 0.07, "output": 0.28 }, "description": "Qwen/Qwen3-Coder-30B-A3B-Instruct is an AI model provided by siliconflow-cn.", "family": "qwen", "id": "Qwen/Qwen3-Coder-30B-A3B-Instruct", "last_updated": "2025-11-25", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen/Qwen3-Coder-30B-A3B-Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-08-01", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-Coder-480B-A35B-Instruct": { "attachment": false, "cost": { "input": 0.25, "output": 1 }, "description": "Qwen/Qwen3-Coder-480B-A35B-Instruct is an AI model provided by siliconflow-cn.", "family": "qwen", "id": "Qwen/Qwen3-Coder-480B-A35B-Instruct", "last_updated": "2025-11-25", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen/Qwen3-Coder-480B-A35B-Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-07-31", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-Next-80B-A3B-Instruct": { "attachment": false, "cost": { "input": 0.14, "output": 1.4 }, "description": "Qwen/Qwen3-Next-80B-A3B-Instruct is an AI model provided by siliconflow-cn.", "family": "qwen", "id": "Qwen/Qwen3-Next-80B-A3B-Instruct", "last_updated": "2025-11-25", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen/Qwen3-Next-80B-A3B-Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-09-18", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-Next-80B-A3B-Thinking": { "attachment": false, "cost": { "input": 0.14, "output": 0.57 }, "description": "Qwen/Qwen3-Next-80B-A3B-Thinking is an AI model provided by siliconflow-cn.", "family": "qwen", "id": "Qwen/Qwen3-Next-80B-A3B-Thinking", "last_updated": "2025-11-25", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen/Qwen3-Next-80B-A3B-Thinking", "open_weights": false, "reasoning": true, "release_date": "2025-09-25", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-Omni-30B-A3B-Captioner": { "attachment": true, "cost": { "input": 0.1, "output": 0.4 }, "description": "Qwen/Qwen3-Omni-30B-A3B-Captioner is an AI model provided by siliconflow-cn.", "family": "qwen", "id": "Qwen/Qwen3-Omni-30B-A3B-Captioner", "last_updated": "2025-11-25", "limit": { "context": 66000, "output": 66000 }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "name": "Qwen/Qwen3-Omni-30B-A3B-Captioner", "open_weights": false, "reasoning": false, "release_date": "2025-10-04", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-Omni-30B-A3B-Instruct": { "attachment": true, "cost": { "input": 0.1, "output": 0.4 }, "description": "Qwen/Qwen3-Omni-30B-A3B-Instruct is an AI model provided by siliconflow-cn.", "family": "qwen", "id": "Qwen/Qwen3-Omni-30B-A3B-Instruct", "last_updated": "2025-11-25", "limit": { "context": 66000, "output": 66000 }, "modalities": { "input": [ "text", "image", "audio" ], "output": [ "text" ] }, "name": "Qwen/Qwen3-Omni-30B-A3B-Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-10-04", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-Omni-30B-A3B-Thinking": { "attachment": true, "cost": { "input": 0.1, "output": 0.4 }, "description": "Qwen/Qwen3-Omni-30B-A3B-Thinking is an AI model provided by siliconflow-cn.", "family": "qwen", "id": "Qwen/Qwen3-Omni-30B-A3B-Thinking", "last_updated": "2025-11-25", "limit": { "context": 66000, "output": 66000 }, "modalities": { "input": [ "text", "image", "audio" ], "output": [ "text" ] }, "name": "Qwen/Qwen3-Omni-30B-A3B-Thinking", "open_weights": false, "reasoning": true, "release_date": "2025-10-04", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-VL-235B-A22B-Instruct": { "attachment": true, "cost": { "input": 0.3, "output": 1.5 }, "description": "Qwen/Qwen3-VL-235B-A22B-Instruct is an AI model provided by siliconflow-cn.", "family": "qwen", "id": "Qwen/Qwen3-VL-235B-A22B-Instruct", "last_updated": "2025-11-25", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen/Qwen3-VL-235B-A22B-Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-10-04", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-VL-235B-A22B-Thinking": { "attachment": true, "cost": { "input": 0.45, "output": 3.5 }, "description": "Qwen/Qwen3-VL-235B-A22B-Thinking is an AI model provided by siliconflow-cn.", "family": "qwen", "id": "Qwen/Qwen3-VL-235B-A22B-Thinking", "last_updated": "2025-11-25", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen/Qwen3-VL-235B-A22B-Thinking", "open_weights": false, "reasoning": true, "release_date": "2025-10-04", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-VL-30B-A3B-Instruct": { "attachment": true, "cost": { "input": 0.29, "output": 1 }, "description": "Qwen/Qwen3-VL-30B-A3B-Instruct is an AI model provided by siliconflow-cn.", "family": "qwen", "id": "Qwen/Qwen3-VL-30B-A3B-Instruct", "last_updated": "2025-11-25", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen/Qwen3-VL-30B-A3B-Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-10-05", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-VL-30B-A3B-Thinking": { "attachment": true, "cost": { "input": 0.29, "output": 1 }, "description": "Qwen/Qwen3-VL-30B-A3B-Thinking is an AI model provided by siliconflow-cn.", "family": "qwen", "id": "Qwen/Qwen3-VL-30B-A3B-Thinking", "last_updated": "2025-11-25", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen/Qwen3-VL-30B-A3B-Thinking", "open_weights": false, "reasoning": true, "release_date": "2025-10-11", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-VL-32B-Instruct": { "attachment": true, "cost": { "input": 0.2, "output": 0.6 }, "description": "Qwen/Qwen3-VL-32B-Instruct is an AI model provided by siliconflow-cn.", "family": "qwen", "id": "Qwen/Qwen3-VL-32B-Instruct", "last_updated": "2025-11-25", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen/Qwen3-VL-32B-Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-10-21", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-VL-32B-Thinking": { "attachment": true, "cost": { "input": 0.2, "output": 1.5 }, "description": "Qwen/Qwen3-VL-32B-Thinking is an AI model provided by siliconflow-cn.", "family": "qwen", "id": "Qwen/Qwen3-VL-32B-Thinking", "last_updated": "2025-11-25", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen/Qwen3-VL-32B-Thinking", "open_weights": false, "reasoning": true, "release_date": "2025-10-21", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-VL-8B-Instruct": { "attachment": true, "cost": { "input": 0.18, "output": 0.68 }, "description": "Qwen/Qwen3-VL-8B-Instruct is an AI model provided by siliconflow-cn.", "family": "qwen", "id": "Qwen/Qwen3-VL-8B-Instruct", "last_updated": "2025-11-25", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen/Qwen3-VL-8B-Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-10-15", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-VL-8B-Thinking": { "attachment": true, "cost": { "input": 0.18, "output": 2 }, "description": "Qwen/Qwen3-VL-8B-Thinking is an AI model provided by siliconflow-cn.", "family": "qwen", "id": "Qwen/Qwen3-VL-8B-Thinking", "last_updated": "2025-11-25", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen/Qwen3-VL-8B-Thinking", "open_weights": false, "reasoning": true, "release_date": "2025-10-15", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3.5-122B-A10B": { "attachment": false, "cost": { "input": 0.29, "output": 2.32 }, "description": "Qwen/Qwen3.5-122B-A10B is an AI model provided by siliconflow-cn.", "family": "qwen", "id": "Qwen/Qwen3.5-122B-A10B", "knowledge": "2025-04", "last_updated": "2026-02-26", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen/Qwen3.5-122B-A10B", "open_weights": true, "reasoning": true, "release_date": "2026-02-26", "temperature": true, "tool_call": true }, "Qwen/Qwen3.5-27B": { "attachment": false, "cost": { "input": 0.26, "output": 2.09 }, "description": "Qwen/Qwen3.5-27B is an AI model provided by siliconflow-cn.", "family": "qwen", "id": "Qwen/Qwen3.5-27B", "knowledge": "2025-04", "last_updated": "2026-02-25", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen/Qwen3.5-27B", "open_weights": true, "reasoning": true, "release_date": "2026-02-25", "temperature": true, "tool_call": true }, "Qwen/Qwen3.5-35B-A3B": { "attachment": false, "cost": { "input": 0.23, "output": 1.86 }, "description": "Qwen/Qwen3.5-35B-A3B is an AI model provided by siliconflow-cn.", "family": "qwen", "id": "Qwen/Qwen3.5-35B-A3B", "knowledge": "2025-04", "last_updated": "2026-02-25", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen/Qwen3.5-35B-A3B", "open_weights": true, "reasoning": true, "release_date": "2026-02-25", "temperature": true, "tool_call": true }, "Qwen/Qwen3.5-397B-A17B": { "attachment": false, "cost": { "input": 0.29, "output": 1.74 }, "description": "Qwen/Qwen3.5-397B-A17B is an AI model provided by siliconflow-cn.", "family": "qwen", "id": "Qwen/Qwen3.5-397B-A17B", "knowledge": "2025-04", "last_updated": "2026-02-16", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen/Qwen3.5-397B-A17B", "open_weights": true, "reasoning": true, "release_date": "2026-02-16", "temperature": true, "tool_call": true }, "Qwen/Qwen3.5-4B": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Qwen/Qwen3.5-4B is an AI model provided by siliconflow-cn.", "family": "qwen", "id": "Qwen/Qwen3.5-4B", "knowledge": "2025-04", "last_updated": "2026-03-03", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen/Qwen3.5-4B", "open_weights": true, "reasoning": true, "release_date": "2026-03-03", "temperature": true, "tool_call": true }, "Qwen/Qwen3.5-9B": { "attachment": false, "cost": { "input": 0.22, "output": 1.74 }, "description": "Qwen/Qwen3.5-9B is an AI model provided by siliconflow-cn.", "family": "qwen", "id": "Qwen/Qwen3.5-9B", "knowledge": "2025-04", "last_updated": "2026-03-03", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen/Qwen3.5-9B", "open_weights": true, "reasoning": true, "release_date": "2026-03-03", "temperature": true, "tool_call": true }, "Qwen/Qwen3.6-35B-A3B": { "attachment": false, "cost": { "input": 0.23, "output": 1.86 }, "description": "Qwen/Qwen3.6-35B-A3B is an AI model provided by siliconflow-cn.", "family": "qwen", "id": "Qwen/Qwen3.6-35B-A3B", "knowledge": "2025-04", "last_updated": "2026-04-17", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen/Qwen3.6-35B-A3B", "open_weights": true, "reasoning": true, "release_date": "2026-04-17", "temperature": true, "tool_call": true }, "THUDM/GLM-4-32B-0414": { "attachment": false, "cost": { "input": 0.27, "output": 0.27 }, "description": "THUDM/GLM-4-32B-0414 is an AI model provided by siliconflow-cn.", "family": "glm", "id": "THUDM/GLM-4-32B-0414", "last_updated": "2025-11-25", "limit": { "context": 33000, "output": 33000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "THUDM/GLM-4-32B-0414", "open_weights": false, "reasoning": false, "release_date": "2025-04-18", "structured_output": true, "temperature": true, "tool_call": true }, "THUDM/GLM-4-9B-0414": { "attachment": false, "cost": { "input": 0.086, "output": 0.086 }, "description": "THUDM/GLM-4-9B-0414 is an AI model provided by siliconflow-cn.", "family": "glm", "id": "THUDM/GLM-4-9B-0414", "last_updated": "2025-11-25", "limit": { "context": 33000, "output": 33000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "THUDM/GLM-4-9B-0414", "open_weights": false, "reasoning": false, "release_date": "2025-04-18", "structured_output": true, "temperature": true, "tool_call": true }, "THUDM/GLM-Z1-32B-0414": { "attachment": false, "cost": { "input": 0.14, "output": 0.57 }, "description": "THUDM/GLM-Z1-32B-0414 is an AI model provided by siliconflow-cn.", "family": "glm-z", "id": "THUDM/GLM-Z1-32B-0414", "last_updated": "2025-11-25", "limit": { "context": 131000, "output": 131000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "THUDM/GLM-Z1-32B-0414", "open_weights": false, "reasoning": true, "release_date": "2025-04-18", "structured_output": true, "temperature": true, "tool_call": true }, "THUDM/GLM-Z1-9B-0414": { "attachment": false, "cost": { "input": 0.086, "output": 0.086 }, "description": "THUDM/GLM-Z1-9B-0414 is an AI model provided by siliconflow-cn.", "family": "glm-z", "id": "THUDM/GLM-Z1-9B-0414", "last_updated": "2025-11-25", "limit": { "context": 131000, "output": 131000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "THUDM/GLM-Z1-9B-0414", "open_weights": false, "reasoning": true, "release_date": "2025-04-18", "structured_output": true, "temperature": true, "tool_call": true }, "ascend-tribe/pangu-pro-moe": { "attachment": false, "cost": { "input": 0.2, "output": 0.6 }, "description": "ascend-tribe/pangu-pro-moe is an AI model provided by siliconflow-cn.", "family": "pangu", "id": "ascend-tribe/pangu-pro-moe", "last_updated": "2026-01-16", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "ascend-tribe/pangu-pro-moe", "open_weights": false, "reasoning": true, "release_date": "2025-07-02", "structured_output": true, "temperature": true, "tool_call": false }, "baidu/ERNIE-4.5-300B-A47B": { "attachment": false, "cost": { "input": 0.28, "output": 1.1 }, "description": "baidu/ERNIE-4.5-300B-A47B is an AI model provided by siliconflow-cn.", "family": "ernie", "id": "baidu/ERNIE-4.5-300B-A47B", "last_updated": "2025-11-25", "limit": { "context": 131000, "output": 131000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "baidu/ERNIE-4.5-300B-A47B", "open_weights": false, "reasoning": false, "release_date": "2025-07-02", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek-ai/DeepSeek-OCR": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "deepseek-ai/DeepSeek-OCR is an AI model provided by siliconflow-cn.", "id": "deepseek-ai/DeepSeek-OCR", "last_updated": "2025-10-20", "limit": { "context": 8192, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "deepseek-ai/DeepSeek-OCR", "open_weights": true, "reasoning": false, "release_date": "2025-10-20", "temperature": true, "tool_call": false }, "deepseek-ai/DeepSeek-R1": { "attachment": false, "cost": { "input": 0.5, "output": 2.18 }, "description": "deepseek-ai/DeepSeek-R1 is an AI model provided by siliconflow-cn.", "family": "deepseek-thinking", "id": "deepseek-ai/DeepSeek-R1", "last_updated": "2025-11-25", "limit": { "context": 164000, "output": 164000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "deepseek-ai/DeepSeek-R1", "open_weights": false, "reasoning": true, "release_date": "2025-05-28", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": { "attachment": false, "cost": { "input": 0.1, "output": 0.1 }, "description": "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B is an AI model provided by siliconflow-cn.", "family": "qwen", "id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B", "last_updated": "2025-11-25", "limit": { "context": 131000, "output": 131000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B", "open_weights": false, "reasoning": true, "release_date": "2025-01-20", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": { "attachment": false, "cost": { "input": 0.18, "output": 0.18 }, "description": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B is an AI model provided by siliconflow-cn.", "family": "qwen", "id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B", "last_updated": "2025-11-25", "limit": { "context": 131000, "output": 131000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B", "open_weights": false, "reasoning": true, "release_date": "2025-01-20", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek-ai/DeepSeek-V3": { "attachment": false, "cost": { "input": 0.25, "output": 1 }, "description": "deepseek-ai/DeepSeek-V3 is an AI model provided by siliconflow-cn.", "family": "deepseek", "id": "deepseek-ai/DeepSeek-V3", "last_updated": "2025-11-25", "limit": { "context": 164000, "output": 164000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "deepseek-ai/DeepSeek-V3", "open_weights": false, "reasoning": false, "release_date": "2024-12-26", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek-ai/DeepSeek-V3.1-Terminus": { "attachment": false, "cost": { "input": 0.27, "output": 1 }, "description": "deepseek-ai/DeepSeek-V3.1-Terminus is an AI model provided by siliconflow-cn.", "family": "deepseek", "id": "deepseek-ai/DeepSeek-V3.1-Terminus", "last_updated": "2025-11-25", "limit": { "context": 164000, "output": 164000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "deepseek-ai/DeepSeek-V3.1-Terminus", "open_weights": false, "reasoning": true, "release_date": "2025-09-29", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek-ai/DeepSeek-V3.2": { "attachment": false, "cost": { "input": 0.27, "output": 0.42 }, "description": "deepseek-ai/DeepSeek-V3.2 is an AI model provided by siliconflow-cn.", "family": "deepseek", "id": "deepseek-ai/DeepSeek-V3.2", "last_updated": "2025-12-03", "limit": { "context": 164000, "output": 164000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "deepseek-ai/DeepSeek-V3.2", "open_weights": false, "reasoning": true, "release_date": "2025-12-03", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek-ai/deepseek-vl2": { "attachment": true, "cost": { "input": 0.15, "output": 0.15 }, "description": "deepseek-ai/deepseek-vl2 is an AI model provided by siliconflow-cn.", "family": "deepseek", "id": "deepseek-ai/deepseek-vl2", "last_updated": "2025-11-25", "limit": { "context": 4000, "output": 4000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "deepseek-ai/deepseek-vl2", "open_weights": false, "reasoning": false, "release_date": "2024-12-13", "structured_output": true, "temperature": true, "tool_call": true }, "inclusionAI/Ling-flash-2.0": { "attachment": false, "cost": { "input": 0.14, "output": 0.57 }, "description": "inclusionAI/Ling-flash-2.0 is an AI model provided by siliconflow-cn.", "family": "ling", "id": "inclusionAI/Ling-flash-2.0", "last_updated": "2025-11-25", "limit": { "context": 131000, "output": 131000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "inclusionAI/Ling-flash-2.0", "open_weights": false, "reasoning": false, "release_date": "2025-09-18", "structured_output": true, "temperature": true, "tool_call": true }, "inclusionAI/Ling-mini-2.0": { "attachment": false, "cost": { "input": 0.07, "output": 0.28 }, "description": "inclusionAI/Ling-mini-2.0 is an AI model provided by siliconflow-cn.", "family": "ling", "id": "inclusionAI/Ling-mini-2.0", "last_updated": "2025-11-25", "limit": { "context": 131000, "output": 131000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "inclusionAI/Ling-mini-2.0", "open_weights": false, "reasoning": false, "release_date": "2025-09-10", "structured_output": true, "temperature": true, "tool_call": true }, "inclusionAI/Ring-flash-2.0": { "attachment": false, "cost": { "input": 0.14, "output": 0.57 }, "description": "inclusionAI/Ring-flash-2.0 is an AI model provided by siliconflow-cn.", "family": "ring", "id": "inclusionAI/Ring-flash-2.0", "last_updated": "2025-11-25", "limit": { "context": 131000, "output": 131000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "inclusionAI/Ring-flash-2.0", "open_weights": false, "reasoning": true, "release_date": "2025-09-29", "structured_output": true, "temperature": true, "tool_call": true }, "moonshotai/Kimi-K2-Instruct-0905": { "attachment": false, "cost": { "input": 0.4, "output": 2 }, "description": "moonshotai/Kimi-K2-Instruct-0905 is an AI model provided by siliconflow-cn.", "family": "kimi", "id": "moonshotai/Kimi-K2-Instruct-0905", "last_updated": "2025-11-25", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "moonshotai/Kimi-K2-Instruct-0905", "open_weights": false, "reasoning": false, "release_date": "2025-09-08", "structured_output": true, "temperature": true, "tool_call": true }, "moonshotai/Kimi-K2-Thinking": { "attachment": false, "cost": { "input": 0.55, "output": 2.5 }, "description": "moonshotai/Kimi-K2-Thinking is an AI model provided by siliconflow-cn.", "family": "kimi-thinking", "id": "moonshotai/Kimi-K2-Thinking", "last_updated": "2025-11-25", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "moonshotai/Kimi-K2-Thinking", "open_weights": false, "reasoning": true, "release_date": "2025-11-07", "structured_output": true, "temperature": true, "tool_call": true }, "stepfun-ai/Step-3.5-Flash": { "attachment": false, "cost": { "input": 0.1, "output": 0.3 }, "description": "stepfun-ai/Step-3.5-Flash is an AI model provided by siliconflow-cn.", "family": "step", "id": "stepfun-ai/Step-3.5-Flash", "last_updated": "2026-02-11", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "stepfun-ai/Step-3.5-Flash", "open_weights": false, "reasoning": true, "release_date": "2026-02-11", "structured_output": true, "temperature": true, "tool_call": true }, "tencent/Hunyuan-A13B-Instruct": { "attachment": false, "cost": { "input": 0.14, "output": 0.57 }, "description": "tencent/Hunyuan-A13B-Instruct is an AI model provided by siliconflow-cn.", "family": "hunyuan", "id": "tencent/Hunyuan-A13B-Instruct", "last_updated": "2025-11-25", "limit": { "context": 131000, "output": 131000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "tencent/Hunyuan-A13B-Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-06-30", "structured_output": true, "temperature": true, "tool_call": true }, "tencent/Hunyuan-MT-7B": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "tencent/Hunyuan-MT-7B is an AI model provided by siliconflow-cn.", "family": "hunyuan", "id": "tencent/Hunyuan-MT-7B", "last_updated": "2025-11-25", "limit": { "context": 33000, "output": 33000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "tencent/Hunyuan-MT-7B", "open_weights": false, "reasoning": false, "release_date": "2025-09-18", "structured_output": true, "temperature": true, "tool_call": true }, "zai-org/GLM-4.5-Air": { "attachment": false, "cost": { "input": 0.14, "output": 0.86 }, "description": "zai-org/GLM-4.5-Air is an AI model provided by siliconflow-cn.", "family": "glm-air", "id": "zai-org/GLM-4.5-Air", "last_updated": "2025-11-25", "limit": { "context": 131000, "output": 131000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "zai-org/GLM-4.5-Air", "open_weights": false, "reasoning": false, "release_date": "2025-07-28", "structured_output": true, "temperature": true, "tool_call": true }, "zai-org/GLM-4.5V": { "attachment": true, "cost": { "input": 0.14, "output": 0.86 }, "description": "zai-org/GLM-4.5V is an AI model provided by siliconflow-cn.", "family": "glm", "id": "zai-org/GLM-4.5V", "last_updated": "2025-11-25", "limit": { "context": 66000, "output": 66000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "zai-org/GLM-4.5V", "open_weights": false, "reasoning": false, "release_date": "2025-08-13", "structured_output": true, "temperature": true, "tool_call": true }, "zai-org/GLM-4.6": { "attachment": false, "cost": { "input": 0.5, "output": 1.9 }, "description": "zai-org/GLM-4.6 is an AI model provided by siliconflow-cn.", "family": "glm", "id": "zai-org/GLM-4.6", "last_updated": "2025-11-25", "limit": { "context": 205000, "output": 205000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "zai-org/GLM-4.6", "open_weights": false, "reasoning": false, "release_date": "2025-10-04", "structured_output": true, "temperature": true, "tool_call": true }, "zai-org/GLM-4.6V": { "attachment": true, "cost": { "input": 0.3, "output": 0.9 }, "description": "zai-org/GLM-4.6V is an AI model provided by siliconflow-cn.", "family": "glm", "id": "zai-org/GLM-4.6V", "last_updated": "2025-12-07", "limit": { "context": 131000, "output": 131000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "zai-org/GLM-4.6V", "open_weights": false, "reasoning": true, "release_date": "2025-12-07", "structured_output": false, "temperature": true, "tool_call": true } }, "name": "SiliconFlow (China)", "npm": "@ai-sdk/openai-compatible" }, "stackit": { "api": "https://api.openai-compat.model-serving.eu01.onstackit.cloud/v1", "doc": "https://docs.stackit.cloud/products/data-and-ai/ai-model-serving/basics/available-shared-models", "env": [ "STACKIT_API_KEY" ], "iconURL": "https://models.dev/logos/stackit.svg", "id": "stackit", "models": { "Qwen/Qwen3-VL-235B-A22B-Instruct-FP8": { "attachment": true, "cost": { "input": 1.64, "output": 1.91 }, "description": "Qwen3-VL 235B is an AI model provided by stackit.", "family": "qwen", "id": "Qwen/Qwen3-VL-235B-A22B-Instruct-FP8", "last_updated": "2024-11-01", "limit": { "context": 218000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen3-VL 235B", "open_weights": true, "reasoning": false, "release_date": "2024-11-01", "structured_output": false, "temperature": true, "tool_call": true }, "Qwen/Qwen3-VL-Embedding-8B": { "attachment": true, "cost": { "input": 0.09, "output": 0.09 }, "description": "Qwen3-VL Embedding 8B is an AI model provided by stackit.", "family": "qwen", "id": "Qwen/Qwen3-VL-Embedding-8B", "last_updated": "2026-02-05", "limit": { "context": 32000, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen3-VL Embedding 8B", "open_weights": true, "reasoning": false, "release_date": "2026-02-05", "structured_output": false, "temperature": false, "tool_call": false }, "cortecs/Llama-3.3-70B-Instruct-FP8-Dynamic": { "attachment": false, "cost": { "input": 0.49, "output": 0.71 }, "description": "Llama 3.3 70B is an AI model provided by stackit.", "family": "llama", "id": "cortecs/Llama-3.3-70B-Instruct-FP8-Dynamic", "last_updated": "2024-12-05", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B", "open_weights": true, "reasoning": false, "release_date": "2024-12-05", "structured_output": false, "temperature": true, "tool_call": true }, "google/gemma-3-27b-it": { "attachment": true, "cost": { "input": 0.49, "output": 0.71 }, "description": "Gemma 3 27B is an AI model provided by stackit.", "family": "gemma", "id": "google/gemma-3-27b-it", "last_updated": "2025-05-17", "limit": { "context": 37000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemma 3 27B", "open_weights": true, "reasoning": false, "release_date": "2025-05-17", "structured_output": false, "temperature": true, "tool_call": false }, "intfloat/e5-mistral-7b-instruct": { "attachment": false, "cost": { "input": 0.02, "output": 0.02 }, "description": "E5 Mistral 7B is an AI model provided by stackit.", "family": "mistral", "id": "intfloat/e5-mistral-7b-instruct", "last_updated": "2023-12-11", "limit": { "context": 4096, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "E5 Mistral 7B", "open_weights": true, "reasoning": false, "release_date": "2023-12-11", "structured_output": false, "temperature": false, "tool_call": false }, "neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8": { "attachment": false, "cost": { "input": 0.16, "output": 0.27 }, "description": "Llama 3.1 8B is an AI model provided by stackit.", "family": "llama", "id": "neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "last_updated": "2024-07-23", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.1 8B", "open_weights": true, "reasoning": false, "release_date": "2024-07-23", "structured_output": true, "temperature": true, "tool_call": true }, "neuralmagic/Mistral-Nemo-Instruct-2407-FP8": { "attachment": false, "cost": { "input": 0.49, "output": 0.71 }, "description": "Mistral Nemo is an AI model provided by stackit.", "family": "mistral", "id": "neuralmagic/Mistral-Nemo-Instruct-2407-FP8", "last_updated": "2024-07-01", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral Nemo", "open_weights": true, "reasoning": false, "release_date": "2024-07-01", "structured_output": false, "temperature": true, "tool_call": true }, "openai/gpt-oss-120b": { "attachment": false, "cost": { "input": 0.49, "output": 0.71 }, "description": "GPT-OSS 120B is an AI model provided by stackit.", "family": "gpt", "id": "openai/gpt-oss-120b", "last_updated": "2025-08-05", "limit": { "context": 131000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT-OSS 120B", "open_weights": true, "reasoning": true, "release_date": "2025-08-05", "structured_output": false, "temperature": true, "tool_call": true } }, "name": "STACKIT", "npm": "@ai-sdk/openai-compatible" }, "stepfun": { "api": "https://api.stepfun.com/v1", "doc": "https://platform.stepfun.com/docs/zh/overview/concept", "env": [ "STEPFUN_API_KEY" ], "iconURL": "https://models.dev/logos/stepfun.svg", "id": "stepfun", "models": { "step-1-32k": { "attachment": false, "cost": { "cache_read": 0.41, "input": 2.05, "output": 9.59 }, "description": "Step 1 (32K) is an AI model provided by stepfun.", "id": "step-1-32k", "knowledge": "2024-06", "last_updated": "2026-02-13", "limit": { "context": 32768, "input": 32768, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Step 1 (32K)", "open_weights": false, "reasoning": true, "release_date": "2025-01-01", "temperature": true, "tool_call": true }, "step-2-16k": { "attachment": false, "cost": { "cache_read": 1.04, "input": 5.21, "output": 16.44 }, "description": "Step 2 (16K) is an AI model provided by stepfun.", "id": "step-2-16k", "knowledge": "2024-06", "last_updated": "2026-02-13", "limit": { "context": 16384, "input": 16384, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Step 2 (16K)", "open_weights": false, "reasoning": true, "release_date": "2025-01-01", "temperature": true, "tool_call": true }, "step-3.5-flash": { "attachment": false, "cost": { "cache_read": 0.019, "input": 0.096, "output": 0.288 }, "description": "Step 3.5 Flash is an AI model provided by stepfun.", "id": "step-3.5-flash", "knowledge": "2025-01", "last_updated": "2026-02-13", "limit": { "context": 256000, "input": 256000, "output": 256000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Step 3.5 Flash", "open_weights": true, "reasoning": true, "release_date": "2026-01-29", "temperature": true, "tool_call": true }, "step-3.5-flash-2603": { "attachment": false, "cost": { "cache_read": 0.02, "input": 0.1, "output": 0.3 }, "description": "Step 3.5 Flash 2603 is an AI model provided by stepfun.", "id": "step-3.5-flash-2603", "knowledge": "2025-01", "last_updated": "2026-04-02", "limit": { "context": 256000, "input": 256000, "output": 256000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Step 3.5 Flash 2603", "open_weights": true, "reasoning": true, "release_date": "2026-04-02", "temperature": true, "tool_call": true } }, "name": "StepFun", "npm": "@ai-sdk/openai-compatible" }, "submodel": { "api": "https://llm.submodel.ai/v1", "doc": "https://submodel.gitbook.io", "env": [ "SUBMODEL_INSTAGEN_ACCESS_KEY" ], "iconURL": "https://models.dev/logos/submodel.svg", "id": "submodel", "lobeIcon": "Submodel", "models": { "Qwen/Qwen3-235B-A22B-Instruct-2507": { "attachment": false, "cost": { "input": 0.2, "output": 0.3 }, "description": "Qwen3 235B A22B Instruct 2507 is an AI model provided by submodel.", "family": "qwen", "id": "Qwen/Qwen3-235B-A22B-Instruct-2507", "last_updated": "2025-08-23", "limit": { "context": 262144, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 235B A22B Instruct 2507", "open_weights": true, "reasoning": false, "release_date": "2025-08-23", "temperature": true, "tool_call": true }, "Qwen/Qwen3-235B-A22B-Thinking-2507": { "attachment": false, "cost": { "input": 0.2, "output": 0.6 }, "description": "Qwen3 235B A22B Thinking 2507 is an AI model provided by submodel.", "family": "qwen", "id": "Qwen/Qwen3-235B-A22B-Thinking-2507", "last_updated": "2025-08-23", "limit": { "context": 262144, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 235B A22B Thinking 2507", "open_weights": true, "reasoning": true, "release_date": "2025-08-23", "temperature": true, "tool_call": true }, "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": { "attachment": false, "cost": { "input": 0.2, "output": 0.8 }, "description": "Qwen3 Coder 480B A35B Instruct is an AI model provided by submodel.", "family": "qwen", "id": "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8", "last_updated": "2025-08-23", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Coder 480B A35B Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-08-23", "temperature": true, "tool_call": true }, "deepseek-ai/DeepSeek-R1-0528": { "attachment": false, "cost": { "input": 0.5, "output": 2.15 }, "description": "DeepSeek R1 0528 is an AI model provided by submodel.", "family": "deepseek-thinking", "id": "deepseek-ai/DeepSeek-R1-0528", "last_updated": "2025-08-23", "limit": { "context": 75000, "output": 163840 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek R1 0528", "open_weights": false, "reasoning": true, "release_date": "2025-08-23", "temperature": true, "tool_call": true }, "deepseek-ai/DeepSeek-V3-0324": { "attachment": false, "cost": { "input": 0.2, "output": 0.8 }, "description": "DeepSeek V3 0324 is an AI model provided by submodel.", "family": "deepseek", "id": "deepseek-ai/DeepSeek-V3-0324", "last_updated": "2025-08-23", "limit": { "context": 75000, "output": 163840 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3 0324", "open_weights": false, "reasoning": false, "release_date": "2025-08-23", "temperature": true, "tool_call": true }, "deepseek-ai/DeepSeek-V3.1": { "attachment": false, "cost": { "input": 0.2, "output": 0.8 }, "description": "DeepSeek V3.1 is an AI model provided by submodel.", "family": "deepseek", "id": "deepseek-ai/DeepSeek-V3.1", "last_updated": "2025-08-23", "limit": { "context": 75000, "output": 163840 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3.1", "open_weights": false, "reasoning": true, "release_date": "2025-08-23", "temperature": true, "tool_call": true }, "openai/gpt-oss-120b": { "attachment": false, "cost": { "input": 0.1, "output": 0.5 }, "description": "GPT OSS 120B is an AI model provided by submodel.", "family": "gpt-oss", "id": "openai/gpt-oss-120b", "last_updated": "2025-08-23", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT OSS 120B", "open_weights": true, "reasoning": true, "release_date": "2025-08-23", "temperature": true, "tool_call": true }, "zai-org/GLM-4.5-Air": { "attachment": false, "cost": { "input": 0.1, "output": 0.5 }, "description": "GLM 4.5 Air is an AI model provided by submodel.", "family": "glm-air", "id": "zai-org/GLM-4.5-Air", "last_updated": "2025-07-28", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.5 Air", "open_weights": true, "reasoning": false, "release_date": "2025-07-28", "temperature": true, "tool_call": true }, "zai-org/GLM-4.5-FP8": { "attachment": false, "cost": { "input": 0.2, "output": 0.8 }, "description": "GLM 4.5 FP8 is an AI model provided by submodel.", "family": "glm", "id": "zai-org/GLM-4.5-FP8", "last_updated": "2025-07-28", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.5 FP8", "open_weights": true, "reasoning": true, "release_date": "2025-07-28", "temperature": true, "tool_call": true } }, "name": "submodel", "npm": "@ai-sdk/openai-compatible" }, "synthetic": { "api": "https://api.synthetic.new/openai/v1", "doc": "https://synthetic.new/pricing", "env": [ "SYNTHETIC_API_KEY" ], "iconURL": "https://models.dev/logos/synthetic.svg", "id": "synthetic", "lobeIcon": "Synthetic", "models": { "hf:MiniMaxAI/MiniMax-M2": { "attachment": false, "cost": { "input": 0.55, "output": 2.19 }, "description": "MiniMax-M2 is an AI model provided by synthetic.", "family": "minimax", "id": "hf:MiniMaxAI/MiniMax-M2", "last_updated": "2025-10-27", "limit": { "context": 196608, "output": 131000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2", "open_weights": true, "reasoning": true, "release_date": "2025-10-27", "temperature": true, "tool_call": true }, "hf:MiniMaxAI/MiniMax-M2.1": { "attachment": false, "cost": { "input": 0.55, "output": 2.19 }, "description": "MiniMax-M2.1 is an AI model provided by synthetic.", "family": "minimax", "id": "hf:MiniMaxAI/MiniMax-M2.1", "interleaved": { "field": "reasoning_content" }, "last_updated": "2025-12-23", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.1", "open_weights": true, "reasoning": true, "release_date": "2025-12-23", "temperature": true, "tool_call": true }, "hf:MiniMaxAI/MiniMax-M2.5": { "attachment": false, "cost": { "cache_read": 0.6, "input": 0.6, "output": 3 }, "description": "MiniMax-M2.5 is an AI model provided by synthetic.", "family": "minimax", "id": "hf:MiniMaxAI/MiniMax-M2.5", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-02-07", "limit": { "context": 191488, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.5", "open_weights": true, "reasoning": true, "release_date": "2026-02-07", "structured_output": true, "temperature": true, "tool_call": true }, "hf:Qwen/Qwen2.5-Coder-32B-Instruct": { "attachment": false, "cost": { "input": 0.8, "output": 0.8 }, "description": "Qwen2.5-Coder-32B-Instruct is an AI model provided by synthetic.", "family": "qwen", "id": "hf:Qwen/Qwen2.5-Coder-32B-Instruct", "knowledge": "2024-10", "last_updated": "2024-11-11", "limit": { "context": 32768, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen2.5-Coder-32B-Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-11-11", "temperature": true, "tool_call": false }, "hf:Qwen/Qwen3-235B-A22B-Instruct-2507": { "attachment": false, "cost": { "input": 0.2, "output": 0.6 }, "description": "Qwen 3 235B Instruct is an AI model provided by synthetic.", "family": "qwen", "id": "hf:Qwen/Qwen3-235B-A22B-Instruct-2507", "knowledge": "2025-04", "last_updated": "2025-07-21", "limit": { "context": 256000, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen 3 235B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-04-28", "temperature": true, "tool_call": true }, "hf:Qwen/Qwen3-235B-A22B-Thinking-2507": { "attachment": false, "cost": { "input": 0.65, "output": 3 }, "description": "Qwen3 235B A22B Thinking 2507 is an AI model provided by synthetic.", "family": "qwen", "id": "hf:Qwen/Qwen3-235B-A22B-Thinking-2507", "knowledge": "2025-04", "last_updated": "2025-07-25", "limit": { "context": 256000, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 235B A22B Thinking 2507", "open_weights": true, "reasoning": true, "release_date": "2025-07-25", "temperature": true, "tool_call": true }, "hf:Qwen/Qwen3-Coder-480B-A35B-Instruct": { "attachment": false, "cost": { "input": 2, "output": 2 }, "description": "Qwen 3 Coder 480B is an AI model provided by synthetic.", "family": "qwen", "id": "hf:Qwen/Qwen3-Coder-480B-A35B-Instruct", "knowledge": "2025-04", "last_updated": "2025-07-23", "limit": { "context": 256000, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen 3 Coder 480B", "open_weights": true, "reasoning": false, "release_date": "2025-07-23", "temperature": true, "tool_call": true }, "hf:Qwen/Qwen3.5-397B-A17B": { "attachment": false, "cost": { "cache_read": 0.6, "input": 0.6, "output": 3 }, "description": "Qwen3.5-97B-A17B is an AI model provided by synthetic.", "family": "qwen", "id": "hf:Qwen/Qwen3.5-397B-A17B", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-02-11", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen3.5-97B-A17B", "open_weights": true, "reasoning": true, "release_date": "2026-02-11", "status": "beta", "structured_output": true, "temperature": true, "tool_call": true }, "hf:deepseek-ai/DeepSeek-R1": { "attachment": false, "cost": { "input": 0.55, "output": 2.19 }, "description": "DeepSeek R1 is an AI model provided by synthetic.", "family": "deepseek-thinking", "id": "hf:deepseek-ai/DeepSeek-R1", "knowledge": "2025-01", "last_updated": "2025-01-20", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek R1", "open_weights": true, "reasoning": true, "release_date": "2025-01-20", "temperature": true, "tool_call": true }, "hf:deepseek-ai/DeepSeek-R1-0528": { "attachment": false, "cost": { "input": 3, "output": 8 }, "description": "DeepSeek R1 (0528) is an AI model provided by synthetic.", "family": "deepseek-thinking", "id": "hf:deepseek-ai/DeepSeek-R1-0528", "last_updated": "2025-08-01", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek R1 (0528)", "open_weights": false, "reasoning": true, "release_date": "2025-08-01", "temperature": true, "tool_call": true }, "hf:deepseek-ai/DeepSeek-V3": { "attachment": false, "cost": { "input": 1.25, "output": 1.25 }, "description": "DeepSeek V3 is an AI model provided by synthetic.", "family": "deepseek", "id": "hf:deepseek-ai/DeepSeek-V3", "knowledge": "2024-07", "last_updated": "2025-05-29", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3", "open_weights": true, "reasoning": true, "release_date": "2025-01-20", "temperature": true, "tool_call": true }, "hf:deepseek-ai/DeepSeek-V3-0324": { "attachment": false, "cost": { "input": 1.2, "output": 1.2 }, "description": "DeepSeek V3 (0324) is an AI model provided by synthetic.", "family": "deepseek", "id": "hf:deepseek-ai/DeepSeek-V3-0324", "last_updated": "2025-08-01", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3 (0324)", "open_weights": false, "reasoning": false, "release_date": "2025-08-01", "temperature": true, "tool_call": true }, "hf:deepseek-ai/DeepSeek-V3.1": { "attachment": false, "cost": { "input": 0.56, "output": 1.68 }, "description": "DeepSeek V3.1 is an AI model provided by synthetic.", "family": "deepseek", "id": "hf:deepseek-ai/DeepSeek-V3.1", "last_updated": "2025-08-21", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3.1", "open_weights": false, "reasoning": true, "release_date": "2025-08-21", "temperature": true, "tool_call": true }, "hf:deepseek-ai/DeepSeek-V3.1-Terminus": { "attachment": false, "cost": { "input": 1.2, "output": 1.2 }, "description": "DeepSeek V3.1 Terminus is an AI model provided by synthetic.", "family": "deepseek", "id": "hf:deepseek-ai/DeepSeek-V3.1-Terminus", "last_updated": "2025-09-25", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3.1 Terminus", "open_weights": false, "reasoning": true, "release_date": "2025-09-22", "temperature": true, "tool_call": true }, "hf:deepseek-ai/DeepSeek-V3.2": { "attachment": false, "cost": { "cache_read": 0.27, "cache_write": 0, "input": 0.27, "output": 0.4 }, "description": "DeepSeek V3.2 is an AI model provided by synthetic.", "family": "deepseek", "id": "hf:deepseek-ai/DeepSeek-V3.2", "last_updated": "2025-12-01", "limit": { "context": 162816, "input": 162816, "output": 8000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3.2", "open_weights": true, "reasoning": true, "release_date": "2025-12-01", "structured_output": true, "temperature": true, "tool_call": true }, "hf:meta-llama/Llama-3.1-405B-Instruct": { "attachment": false, "cost": { "input": 3, "output": 3 }, "description": "Llama-3.1-405B-Instruct is an AI model provided by synthetic.", "family": "llama", "id": "hf:meta-llama/Llama-3.1-405B-Instruct", "knowledge": "2023-12", "last_updated": "2024-07-23", "limit": { "context": 128000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama-3.1-405B-Instruct", "open_weights": true, "reasoning": true, "release_date": "2024-07-23", "temperature": true, "tool_call": true }, "hf:meta-llama/Llama-3.1-70B-Instruct": { "attachment": false, "cost": { "input": 0.9, "output": 0.9 }, "description": "Llama-3.1-70B-Instruct is an AI model provided by synthetic.", "family": "llama", "id": "hf:meta-llama/Llama-3.1-70B-Instruct", "knowledge": "2023-12", "last_updated": "2024-07-23", "limit": { "context": 128000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama-3.1-70B-Instruct", "open_weights": true, "reasoning": true, "release_date": "2024-07-23", "temperature": true, "tool_call": true }, "hf:meta-llama/Llama-3.1-8B-Instruct": { "attachment": false, "cost": { "input": 0.2, "output": 0.2 }, "description": "Llama-3.1-8B-Instruct is an AI model provided by synthetic.", "family": "llama", "id": "hf:meta-llama/Llama-3.1-8B-Instruct", "knowledge": "2023-12", "last_updated": "2024-07-23", "limit": { "context": 128000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama-3.1-8B-Instruct", "open_weights": true, "reasoning": true, "release_date": "2024-07-23", "temperature": true, "tool_call": true }, "hf:meta-llama/Llama-3.3-70B-Instruct": { "attachment": false, "cost": { "input": 0.9, "output": 0.9 }, "description": "Llama-3.3-70B-Instruct is an AI model provided by synthetic.", "family": "llama", "id": "hf:meta-llama/Llama-3.3-70B-Instruct", "knowledge": "2023-12", "last_updated": "2024-12-06", "limit": { "context": 128000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama-3.3-70B-Instruct", "open_weights": true, "reasoning": true, "release_date": "2024-12-06", "temperature": true, "tool_call": true }, "hf:meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { "attachment": true, "cost": { "input": 0.22, "output": 0.88 }, "description": "Llama-4-Maverick-17B-128E-Instruct-FP8 is an AI model provided by synthetic.", "family": "llama", "id": "hf:meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8", "knowledge": "2024-08", "last_updated": "2025-04-05", "limit": { "context": 524000, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Llama-4-Maverick-17B-128E-Instruct-FP8", "open_weights": true, "reasoning": false, "release_date": "2025-04-05", "temperature": true, "tool_call": true }, "hf:meta-llama/Llama-4-Scout-17B-16E-Instruct": { "attachment": true, "cost": { "input": 0.15, "output": 0.6 }, "description": "Llama-4-Scout-17B-16E-Instruct is an AI model provided by synthetic.", "family": "llama", "id": "hf:meta-llama/Llama-4-Scout-17B-16E-Instruct", "knowledge": "2024-08", "last_updated": "2025-04-05", "limit": { "context": 328000, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Llama-4-Scout-17B-16E-Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-04-05", "temperature": true, "tool_call": true }, "hf:moonshotai/Kimi-K2-Instruct-0905": { "attachment": false, "cost": { "input": 1.2, "output": 1.2 }, "description": "Kimi K2 0905 is an AI model provided by synthetic.", "family": "kimi", "id": "hf:moonshotai/Kimi-K2-Instruct-0905", "knowledge": "2024-10", "last_updated": "2025-09-05", "limit": { "context": 262144, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 0905", "open_weights": true, "reasoning": false, "release_date": "2025-09-05", "temperature": true, "tool_call": true }, "hf:moonshotai/Kimi-K2-Thinking": { "attachment": false, "cost": { "input": 0.55, "output": 2.19 }, "description": "Kimi K2 Thinking is an AI model provided by synthetic.", "family": "kimi-thinking", "id": "hf:moonshotai/Kimi-K2-Thinking", "knowledge": "2025-11", "last_updated": "2025-11-07", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 Thinking", "open_weights": true, "reasoning": true, "release_date": "2025-11-07", "temperature": true, "tool_call": true }, "hf:moonshotai/Kimi-K2.5": { "attachment": false, "cost": { "input": 0.55, "output": 2.19 }, "description": "Kimi K2.5 is an AI model provided by synthetic.", "family": "kimi", "id": "hf:moonshotai/Kimi-K2.5", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-01", "last_updated": "2026-01", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Kimi K2.5", "open_weights": true, "reasoning": true, "release_date": "2026-01", "temperature": true, "tool_call": true }, "hf:moonshotai/Kimi-K2.6": { "attachment": true, "cost": { "cache_read": 0.95, "input": 0.95, "output": 4 }, "description": "Kimi K2.6 is an AI model provided by synthetic.", "family": "kimi-k2.6", "id": "hf:moonshotai/Kimi-K2.6", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-01", "last_updated": "2026-04-21", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Kimi K2.6", "open_weights": true, "reasoning": true, "release_date": "2026-04-21", "structured_output": true, "temperature": true, "tool_call": true }, "hf:nvidia/Kimi-K2.5-NVFP4": { "attachment": false, "cost": { "input": 0.55, "output": 2.19 }, "description": "Kimi K2.5 (NVFP4) is an AI model provided by synthetic.", "family": "kimi", "id": "hf:nvidia/Kimi-K2.5-NVFP4", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-01", "last_updated": "2026-01", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Kimi K2.5 (NVFP4)", "open_weights": true, "reasoning": true, "release_date": "2026-01", "temperature": true, "tool_call": true }, "hf:nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4": { "attachment": false, "cost": { "cache_read": 0.3, "input": 0.3, "output": 1 }, "description": "Nemotron 3 Super 120B is an AI model provided by synthetic.", "family": "nemotron", "id": "hf:nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-04", "last_updated": "2026-04-03", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Nemotron 3 Super 120B", "open_weights": true, "reasoning": true, "release_date": "2026-03-11", "structured_output": true, "temperature": true, "tool_call": true }, "hf:openai/gpt-oss-120b": { "attachment": false, "cost": { "input": 0.1, "output": 0.1 }, "description": "GPT OSS 120B is an AI model provided by synthetic.", "family": "gpt-oss", "id": "hf:openai/gpt-oss-120b", "last_updated": "2025-08-05", "limit": { "context": 128000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT OSS 120B", "open_weights": true, "reasoning": true, "release_date": "2025-08-05", "temperature": true, "tool_call": true }, "hf:zai-org/GLM-4.6": { "attachment": false, "cost": { "input": 0.55, "output": 2.19 }, "description": "GLM 4.6 is an AI model provided by synthetic.", "family": "glm", "id": "hf:zai-org/GLM-4.6", "knowledge": "2025-04", "last_updated": "2025-09-30", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.6", "open_weights": true, "reasoning": true, "release_date": "2025-09-30", "temperature": true, "tool_call": true }, "hf:zai-org/GLM-4.7": { "attachment": false, "cost": { "input": 0.55, "output": 2.19 }, "description": "GLM 4.7 is an AI model provided by synthetic.", "family": "glm", "id": "hf:zai-org/GLM-4.7", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-04", "last_updated": "2025-12-22", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.7", "open_weights": true, "reasoning": true, "release_date": "2025-12-22", "temperature": true, "tool_call": true }, "hf:zai-org/GLM-4.7-Flash": { "attachment": false, "cost": { "cache_read": 0.06, "input": 0.06, "output": 0.4 }, "description": "GLM-4.7-Flash is an AI model provided by synthetic.", "family": "glm", "id": "hf:zai-org/GLM-4.7-Flash", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-01-18", "limit": { "context": 196608, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.7-Flash", "open_weights": true, "reasoning": true, "release_date": "2026-01-18", "structured_output": true, "temperature": true, "tool_call": true }, "hf:zai-org/GLM-5": { "attachment": false, "cost": { "cache_read": 1, "input": 1, "output": 3 }, "description": "GLM-5 is an AI model provided by synthetic.", "family": "glm", "id": "hf:zai-org/GLM-5", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-08", "limit": { "context": 196608, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5", "open_weights": true, "reasoning": true, "release_date": "2026-02-12", "structured_output": true, "temperature": true, "tool_call": true }, "hf:zai-org/GLM-5.1": { "attachment": false, "cost": { "cache_read": 1, "input": 1, "output": 3 }, "description": "GLM 5.1 is an AI model provided by synthetic.", "family": "glm", "id": "hf:zai-org/GLM-5.1", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-12", "limit": { "context": 196608, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 5.1", "open_weights": true, "reasoning": true, "release_date": "2026-03-27", "structured_output": true, "temperature": true, "tool_call": true } }, "name": "Synthetic", "npm": "@ai-sdk/openai-compatible" }, "tencent-coding-plan": { "api": "https://api.lkeap.cloud.tencent.com/coding/v3", "doc": "https://cloud.tencent.com/document/product/1772/128947", "env": [ "TENCENT_CODING_PLAN_API_KEY" ], "iconURL": "https://models.dev/logos/tencent-coding-plan.svg", "id": "tencent-coding-plan", "models": { "glm-5": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "GLM-5 is an AI model provided by tencent-coding-plan.", "family": "glm", "id": "glm-5", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-02-11", "limit": { "context": 202752, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5", "open_weights": false, "reasoning": true, "release_date": "2026-02-11", "temperature": true, "tool_call": true }, "hunyuan-2.0-instruct": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "Tencent HY 2.0 Instruct is an AI model provided by tencent-coding-plan.", "family": "hunyuan", "id": "hunyuan-2.0-instruct", "last_updated": "2026-03-08", "limit": { "context": 131072, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Tencent HY 2.0 Instruct", "open_weights": false, "reasoning": false, "release_date": "2026-03-08", "temperature": true, "tool_call": true }, "hunyuan-2.0-thinking": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "Tencent HY 2.0 Think is an AI model provided by tencent-coding-plan.", "family": "hunyuan", "id": "hunyuan-2.0-thinking", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-03-08", "limit": { "context": 131072, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Tencent HY 2.0 Think", "open_weights": false, "reasoning": true, "release_date": "2026-03-08", "temperature": true, "tool_call": true }, "hunyuan-t1": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "Hunyuan-T1 is an AI model provided by tencent-coding-plan.", "family": "hunyuan", "id": "hunyuan-t1", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-03-08", "limit": { "context": 131072, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Hunyuan-T1", "open_weights": false, "reasoning": true, "release_date": "2026-03-08", "temperature": true, "tool_call": true }, "hunyuan-turbos": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "Hunyuan-TurboS is an AI model provided by tencent-coding-plan.", "family": "hunyuan", "id": "hunyuan-turbos", "last_updated": "2026-03-08", "limit": { "context": 131072, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Hunyuan-TurboS", "open_weights": false, "reasoning": false, "release_date": "2026-03-08", "temperature": true, "tool_call": true }, "kimi-k2.5": { "attachment": true, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "Kimi-K2.5 is an AI model provided by tencent-coding-plan.", "family": "kimi", "id": "kimi-k2.5", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-01", "last_updated": "2026-01-27", "limit": { "context": 262144, "output": 32768 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Kimi-K2.5", "open_weights": true, "reasoning": true, "release_date": "2026-01-27", "temperature": true, "tool_call": true }, "minimax-m2.5": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "MiniMax-M2.5 is an AI model provided by tencent-coding-plan.", "family": "minimax", "id": "minimax-m2.5", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-02-12", "limit": { "context": 204800, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.5", "open_weights": true, "reasoning": true, "release_date": "2026-02-12", "temperature": true, "tool_call": true }, "tc-code-latest": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "Auto is an AI model provided by tencent-coding-plan.", "family": "auto", "id": "tc-code-latest", "last_updated": "2026-03-08", "limit": { "context": 131072, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Auto", "open_weights": false, "reasoning": false, "release_date": "2026-03-08", "temperature": true, "tool_call": true } }, "name": "Tencent Coding Plan (China)", "npm": "@ai-sdk/openai-compatible" }, "tencent-tokenhub": { "api": "https://tokenhub.tencentmaas.com/v1", "doc": "https://cloud.tencent.com/document/product/1823/130050", "env": [ "TENCENT_TOKENHUB_API_KEY" ], "iconURL": "https://models.dev/logos/tencent-tokenhub.svg", "id": "tencent-tokenhub", "models": { "hy3-preview": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "Hy3 preview is an AI model provided by tencent-tokenhub.", "family": "Hy", "id": "hy3-preview", "last_updated": "2026-04-20", "limit": { "context": 256000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Hy3 preview", "open_weights": true, "reasoning": true, "release_date": "2026-04-20", "temperature": true, "tool_call": true } }, "name": "Tencent TokenHub", "npm": "@ai-sdk/openai-compatible" }, "the-grid-ai": { "api": "https://api.thegrid.ai/v1", "doc": "https://thegrid.ai/docs", "env": [ "THEGRIDAI_API_KEY" ], "iconURL": "https://models.dev/logos/the-grid-ai.svg", "id": "the-grid-ai", "models": { "text-max": { "attachment": false, "description": "Text Max is an AI model provided by the-grid-ai.", "id": "text-max", "last_updated": "2026-03-24", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Text Max", "open_weights": false, "reasoning": true, "release_date": "2026-03-24", "status": "beta", "structured_output": true, "temperature": true, "tool_call": true }, "text-prime": { "attachment": false, "description": "Text Prime is an AI model provided by the-grid-ai.", "id": "text-prime", "last_updated": "2026-02-26", "limit": { "context": 128000, "output": 30000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Text Prime", "open_weights": false, "reasoning": true, "release_date": "2026-02-26", "status": "beta", "structured_output": true, "temperature": true, "tool_call": true }, "text-standard": { "attachment": false, "description": "Text Standard is an AI model provided by the-grid-ai.", "id": "text-standard", "last_updated": "2026-02-26", "limit": { "context": 128000, "output": 16000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Text Standard", "open_weights": false, "reasoning": true, "release_date": "2026-02-26", "status": "beta", "structured_output": true, "temperature": true, "tool_call": true } }, "name": "The Grid AI", "npm": "@ai-sdk/openai-compatible" }, "togetherai": { "doc": "https://docs.together.ai/docs/serverless-models", "env": [ "TOGETHER_API_KEY" ], "iconURL": "https://models.dev/logos/togetherai.svg", "id": "togetherai", "lobeIcon": "TogetherAI.Color", "models": { "MiniMaxAI/MiniMax-M2.5": { "attachment": false, "cost": { "cache_read": 0.06, "input": 0.3, "output": 1.2 }, "description": "MiniMax-M2.5 is an AI model provided by togetherai.", "family": "minimax", "id": "MiniMaxAI/MiniMax-M2.5", "last_updated": "2026-02-12", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.5", "open_weights": true, "reasoning": true, "release_date": "2026-02-12", "temperature": true, "tool_call": true }, "MiniMaxAI/MiniMax-M2.7": { "attachment": false, "cost": { "cache_read": 0.06, "input": 0.3, "output": 1.2 }, "description": "MiniMax-M2.7 is an AI model provided by togetherai.", "family": "minimax", "id": "MiniMaxAI/MiniMax-M2.7", "last_updated": "2026-03-18", "limit": { "context": 202752, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax-M2.7", "open_weights": true, "reasoning": true, "release_date": "2026-03-18", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-235B-A22B-Instruct-2507-tput": { "attachment": false, "cost": { "input": 0.2, "output": 0.6 }, "description": "Qwen3 235B A22B Instruct 2507 FP8 is an AI model provided by togetherai.", "family": "qwen", "id": "Qwen/Qwen3-235B-A22B-Instruct-2507-tput", "knowledge": "2025-07", "last_updated": "2025-07-25", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 235B A22B Instruct 2507 FP8", "open_weights": true, "reasoning": true, "release_date": "2025-07-25", "temperature": true, "tool_call": true }, "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": { "attachment": false, "cost": { "input": 2, "output": 2 }, "description": "Qwen3 Coder 480B A35B Instruct is an AI model provided by togetherai.", "family": "qwen", "id": "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8", "knowledge": "2025-04", "last_updated": "2025-07-23", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Coder 480B A35B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-07-23", "temperature": true, "tool_call": true }, "Qwen/Qwen3-Coder-Next-FP8": { "attachment": false, "cost": { "input": 0.5, "output": 1.2 }, "description": "Qwen3 Coder Next FP8 is an AI model provided by togetherai.", "family": "qwen", "id": "Qwen/Qwen3-Coder-Next-FP8", "knowledge": "2026-02-03", "last_updated": "2026-02-03", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Coder Next FP8", "open_weights": true, "reasoning": true, "release_date": "2026-02-03", "temperature": true, "tool_call": true }, "Qwen/Qwen3.5-397B-A17B": { "attachment": false, "cost": { "input": 0.6, "output": 3.6 }, "description": "Qwen3.5 397B A17B is an AI model provided by togetherai.", "family": "qwen", "id": "Qwen/Qwen3.5-397B-A17B", "last_updated": "2026-02-16", "limit": { "context": 262144, "output": 130000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen3.5 397B A17B", "open_weights": true, "reasoning": true, "release_date": "2026-02-16", "temperature": true, "tool_call": true }, "Qwen/Qwen3.6-Plus": { "attachment": false, "cost": { "input": 0.5, "output": 3 }, "description": "Qwen3.6 Plus is an AI model provided by togetherai.", "family": "qwen", "id": "Qwen/Qwen3.6-Plus", "last_updated": "2026-04-30", "limit": { "context": 1000000, "output": 500000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3.6 Plus", "open_weights": true, "reasoning": true, "release_date": "2026-04-30", "temperature": true, "tool_call": true }, "deepseek-ai/DeepSeek-R1": { "attachment": false, "cost": { "input": 3, "output": 7 }, "description": "DeepSeek R1 is an AI model provided by togetherai.", "family": "deepseek-thinking", "id": "deepseek-ai/DeepSeek-R1", "knowledge": "2024-07", "last_updated": "2025-03-24", "limit": { "context": 163839, "output": 163839 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek R1", "open_weights": true, "reasoning": true, "release_date": "2024-12-26", "temperature": true, "tool_call": false }, "deepseek-ai/DeepSeek-V3": { "attachment": false, "cost": { "input": 1.25, "output": 1.25 }, "description": "DeepSeek V3 is an AI model provided by togetherai.", "family": "deepseek", "id": "deepseek-ai/DeepSeek-V3", "knowledge": "2024-07", "last_updated": "2025-05-29", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3", "open_weights": true, "reasoning": true, "release_date": "2025-01-20", "temperature": true, "tool_call": true }, "deepseek-ai/DeepSeek-V3-1": { "attachment": false, "cost": { "input": 0.6, "output": 1.7 }, "description": "DeepSeek V3.1 is an AI model provided by togetherai.", "family": "deepseek", "id": "deepseek-ai/DeepSeek-V3-1", "knowledge": "2025-08", "last_updated": "2025-08-21", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3.1", "open_weights": true, "reasoning": true, "release_date": "2025-08-21", "temperature": true, "tool_call": true }, "deepseek-ai/DeepSeek-V4-Pro": { "attachment": false, "cost": { "cache_read": 0.2, "input": 2.1, "output": 4.4 }, "description": "DeepSeek V4 Pro is an AI model provided by togetherai.", "family": "deepseek", "id": "deepseek-ai/DeepSeek-V4-Pro", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-24", "limit": { "context": 512000, "output": 384000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V4 Pro", "open_weights": true, "reasoning": true, "release_date": "2026-04-24", "structured_output": true, "temperature": true, "tool_call": true }, "essentialai/Rnj-1-Instruct": { "attachment": false, "cost": { "input": 0.15, "output": 0.15 }, "description": "Rnj-1 Instruct is an AI model provided by togetherai.", "family": "rnj", "id": "essentialai/Rnj-1-Instruct", "knowledge": "2024-10", "last_updated": "2025-12-05", "limit": { "context": 32768, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Rnj-1 Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-12-05", "temperature": true, "tool_call": true }, "google/gemma-4-31B-it": { "attachment": true, "cost": { "input": 0.2, "output": 0.5 }, "description": "Gemma 4 31B Instruct is an AI model provided by togetherai.", "family": "gemma", "id": "google/gemma-4-31B-it", "knowledge": "2025-01", "last_updated": "2026-04-07", "limit": { "context": 262144, "output": 131072 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemma 4 31B Instruct", "open_weights": true, "reasoning": true, "release_date": "2026-04-07", "temperature": true, "tool_call": true }, "meta-llama/Llama-3.3-70B-Instruct-Turbo": { "attachment": false, "cost": { "input": 0.88, "output": 0.88 }, "description": "Llama 3.3 70B is an AI model provided by togetherai.", "family": "llama", "id": "meta-llama/Llama-3.3-70B-Instruct-Turbo", "knowledge": "2023-12", "last_updated": "2024-12-06", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B", "open_weights": true, "reasoning": false, "release_date": "2024-12-06", "temperature": true, "tool_call": true }, "moonshotai/Kimi-K2.5": { "attachment": false, "cost": { "input": 0.5, "output": 2.8 }, "description": "Kimi K2.5 is an AI model provided by togetherai.", "family": "kimi", "id": "moonshotai/Kimi-K2.5", "interleaved": true, "knowledge": "2026-01", "last_updated": "2026-01-27", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Kimi K2.5", "open_weights": true, "reasoning": true, "release_date": "2026-01-27", "temperature": true, "tool_call": true }, "moonshotai/Kimi-K2.6": { "attachment": true, "cost": { "cache_read": 0.2, "input": 1.2, "output": 4.5 }, "description": "Kimi K2.6 is an AI model provided by togetherai.", "family": "kimi-k2.6", "id": "moonshotai/Kimi-K2.6", "knowledge": "2025-01", "last_updated": "2026-04-21", "limit": { "context": 262144, "output": 131000 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Kimi K2.6", "open_weights": true, "reasoning": true, "release_date": "2026-04-21", "structured_output": true, "temperature": true, "tool_call": true }, "openai/gpt-oss-120b": { "attachment": false, "cost": { "input": 0.15, "output": 0.6 }, "description": "GPT OSS 120B is an AI model provided by togetherai.", "family": "gpt-oss", "id": "openai/gpt-oss-120b", "knowledge": "2025-08", "last_updated": "2025-08-05", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT OSS 120B", "open_weights": true, "reasoning": true, "release_date": "2025-08-05", "temperature": true, "tool_call": true }, "zai-org/GLM-5.1": { "attachment": false, "cost": { "input": 1.4, "output": 4.4 }, "description": "GLM-5.1 is an AI model provided by togetherai.", "family": "glm", "id": "zai-org/GLM-5.1", "knowledge": "2025-11", "last_updated": "2026-04-07", "limit": { "context": 202752, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5.1", "open_weights": true, "reasoning": true, "release_date": "2026-04-07", "structured_output": true, "temperature": true, "tool_call": true } }, "name": "Together AI", "npm": "@ai-sdk/togetherai" }, "upstage": { "api": "https://api.upstage.ai/v1/solar", "doc": "https://developers.upstage.ai/docs/apis/chat", "env": [ "UPSTAGE_API_KEY" ], "iconURL": "https://models.dev/logos/upstage.svg", "id": "upstage", "lobeIcon": "Upstage", "models": { "solar-mini": { "attachment": false, "cost": { "input": 0.15, "output": 0.15 }, "description": "solar-mini is an AI model provided by upstage.", "family": "solar-mini", "id": "solar-mini", "knowledge": "2024-09", "last_updated": "2025-04-22", "limit": { "context": 32768, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "solar-mini", "open_weights": false, "reasoning": false, "release_date": "2024-06-12", "temperature": true, "tool_call": true }, "solar-pro2": { "attachment": false, "cost": { "input": 0.25, "output": 0.25 }, "description": "solar-pro2 is an AI model provided by upstage.", "family": "solar-pro", "id": "solar-pro2", "knowledge": "2025-03", "last_updated": "2025-05-20", "limit": { "context": 65536, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "solar-pro2", "open_weights": false, "reasoning": true, "release_date": "2025-05-20", "temperature": true, "tool_call": true }, "solar-pro3": { "attachment": false, "cost": { "input": 0.25, "output": 0.25 }, "description": "solar-pro3 is an AI model provided by upstage.", "family": "solar-pro", "id": "solar-pro3", "knowledge": "2025-03", "last_updated": "2026-01", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "solar-pro3", "open_weights": false, "reasoning": true, "release_date": "2026-01", "temperature": true, "tool_call": true } }, "name": "Upstage", "npm": "@ai-sdk/openai-compatible" }, "v0": { "doc": "https://sdk.vercel.ai/providers/ai-sdk-providers/vercel", "env": [ "V0_API_KEY" ], "iconURL": "https://models.dev/logos/v0.svg", "id": "v0", "lobeIcon": "Vercel.Color", "models": { "v0-1.0-md": { "attachment": true, "cost": { "input": 3, "output": 15 }, "description": "v0-1.0-md is an AI model provided by v0.", "family": "v0", "id": "v0-1.0-md", "last_updated": "2025-05-22", "limit": { "context": 128000, "output": 32000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "v0-1.0-md", "open_weights": false, "reasoning": true, "release_date": "2025-05-22", "temperature": true, "tool_call": true }, "v0-1.5-lg": { "attachment": true, "cost": { "input": 15, "output": 75 }, "description": "v0-1.5-lg is an AI model provided by v0.", "family": "v0", "id": "v0-1.5-lg", "last_updated": "2025-06-09", "limit": { "context": 512000, "output": 32000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "v0-1.5-lg", "open_weights": false, "reasoning": true, "release_date": "2025-06-09", "temperature": true, "tool_call": true }, "v0-1.5-md": { "attachment": true, "cost": { "input": 3, "output": 15 }, "description": "v0-1.5-md is an AI model provided by v0.", "family": "v0", "id": "v0-1.5-md", "last_updated": "2025-06-09", "limit": { "context": 128000, "output": 32000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "v0-1.5-md", "open_weights": false, "reasoning": true, "release_date": "2025-06-09", "temperature": true, "tool_call": true } }, "name": "v0", "npm": "@ai-sdk/vercel" }, "venice": { "doc": "https://docs.venice.ai", "env": [ "VENICE_API_KEY" ], "iconURL": "https://models.dev/logos/venice.svg", "id": "venice", "lobeIcon": "VeniceAI", "models": { "aion-labs-aion-2-0": { "attachment": false, "cost": { "cache_read": 0.25, "input": 1, "output": 2 }, "description": "Aion 2.0 is an AI model provided by venice.", "family": "o", "id": "aion-labs-aion-2-0", "last_updated": "2026-04-12", "limit": { "context": 128000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Aion 2.0", "open_weights": false, "reasoning": true, "release_date": "2026-03-24", "temperature": true, "tool_call": false }, "arcee-trinity-large-thinking": { "attachment": false, "cost": { "cache_read": 0.075, "input": 0.3125, "output": 1.125 }, "description": "Trinity Large Thinking is an AI model provided by venice.", "family": "trinity", "id": "arcee-trinity-large-thinking", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-04", "limit": { "context": 256000, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Trinity Large Thinking", "open_weights": true, "reasoning": true, "release_date": "2026-04-02", "structured_output": true, "temperature": true, "tool_call": true }, "claude-opus-4-5": { "attachment": true, "cost": { "cache_read": 0.6, "cache_write": 7.5, "input": 6, "output": 30 }, "description": "Claude Opus 4.5 is an AI model provided by venice.", "family": "claude-opus", "id": "claude-opus-4-5", "last_updated": "2026-04-12", "limit": { "context": 198000, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Claude Opus 4.5", "open_weights": false, "reasoning": true, "release_date": "2025-12-06", "structured_output": true, "temperature": true, "tool_call": true }, "claude-opus-4-6": { "attachment": true, "cost": { "cache_read": 0.6, "cache_write": 7.5, "input": 6, "output": 30 }, "description": "Claude Opus 4.6 is an AI model provided by venice.", "family": "claude-opus", "id": "claude-opus-4-6", "knowledge": "2025-05-31", "last_updated": "2026-03-16", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Claude Opus 4.6", "open_weights": false, "reasoning": true, "release_date": "2026-02-05", "structured_output": true, "temperature": true, "tool_call": true }, "claude-opus-4-6-fast": { "attachment": true, "cost": { "cache_read": 3.6, "cache_write": 45, "input": 36, "output": 180 }, "description": "Claude Opus 4.6 Fast is an AI model provided by venice.", "family": "claude-opus", "id": "claude-opus-4-6-fast", "knowledge": "2025-05-31", "last_updated": "2026-04-08", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Claude Opus 4.6 Fast", "open_weights": false, "reasoning": true, "release_date": "2026-04-08", "structured_output": true, "temperature": true, "tool_call": true }, "claude-opus-4-7": { "attachment": true, "cost": { "cache_read": 0.6, "cache_write": 7.5, "input": 6, "output": 30 }, "description": "Claude Opus 4.7 is an AI model provided by venice.", "family": "claude-opus", "id": "claude-opus-4-7", "last_updated": "2026-04-16", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Claude Opus 4.7", "open_weights": false, "reasoning": true, "release_date": "2026-04-16", "structured_output": true, "temperature": false, "tool_call": true }, "claude-sonnet-4-5": { "attachment": true, "cost": { "cache_read": 0.375, "cache_write": 4.69, "input": 3.75, "output": 18.75 }, "description": "Claude Sonnet 4.5 is an AI model provided by venice.", "family": "claude-sonnet", "id": "claude-sonnet-4-5", "last_updated": "2026-04-12", "limit": { "context": 198000, "output": 64000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.5", "open_weights": false, "reasoning": true, "release_date": "2025-01-15", "structured_output": true, "temperature": true, "tool_call": true }, "claude-sonnet-4-6": { "attachment": true, "cost": { "cache_read": 0.36, "cache_write": 4.5, "input": 3.6, "output": 18 }, "description": "Claude Sonnet 4.6 is an AI model provided by venice.", "family": "claude-sonnet", "id": "claude-sonnet-4-6", "knowledge": "2025-08-31", "last_updated": "2026-03-16", "limit": { "context": 1000000, "output": 64000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.6", "open_weights": false, "reasoning": true, "release_date": "2026-02-17", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek-v3.2": { "attachment": false, "cost": { "cache_read": 0.16, "input": 0.33, "output": 0.48 }, "description": "DeepSeek V3.2 is an AI model provided by venice.", "family": "deepseek", "id": "deepseek-v3.2", "knowledge": "2025-10", "last_updated": "2026-03-24", "limit": { "context": 160000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3.2", "open_weights": true, "reasoning": true, "release_date": "2025-12-04", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek-v4-flash": { "attachment": false, "cost": { "cache_read": 0.028, "input": 0.17, "output": 0.35 }, "description": "DeepSeek V4 Flash is an AI model provided by venice.", "family": "deepseek-flash", "id": "deepseek-v4-flash", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-29", "limit": { "context": 1000000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V4 Flash", "open_weights": true, "reasoning": true, "release_date": "2026-04-24", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek-v4-pro": { "attachment": false, "cost": { "cache_read": 0.33, "input": 1.73, "output": 3.796 }, "description": "DeepSeek V4 Pro is an AI model provided by venice.", "family": "deepseek", "id": "deepseek-v4-pro", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-29", "limit": { "context": 1000000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V4 Pro", "open_weights": true, "reasoning": true, "release_date": "2026-04-24", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-3-1-pro-preview": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 0.5, "context_over_200k": { "cache_read": 0.5, "input": 5, "output": 22.5 }, "input": 2.5, "output": 15, "tiers": [ { "cache_read": 0.5, "input": 5, "output": 22.5, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Gemini 3.1 Pro Preview is an AI model provided by venice.", "family": "gemini-pro", "id": "gemini-3-1-pro-preview", "last_updated": "2026-03-12", "limit": { "context": 1000000, "output": 32768 }, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "name": "Gemini 3.1 Pro Preview", "open_weights": false, "reasoning": true, "release_date": "2026-02-19", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-3-flash-preview": { "attachment": true, "cost": { "cache_read": 0.07, "input": 0.7, "output": 3.75 }, "description": "Gemini 3 Flash Preview is an AI model provided by venice.", "family": "gemini-flash", "id": "gemini-3-flash-preview", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-01", "last_updated": "2026-03-12", "limit": { "context": 256000, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 3 Flash Preview", "open_weights": false, "reasoning": true, "release_date": "2025-12-19", "structured_output": true, "temperature": true, "tool_call": true }, "gemma-4-uncensored": { "attachment": true, "cost": { "input": 0.1625, "output": 0.5 }, "description": "Gemma 4 Uncensored is an AI model provided by venice.", "family": "gemma", "id": "gemma-4-uncensored", "last_updated": "2026-04-19", "limit": { "context": 256000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Gemma 4 Uncensored", "open_weights": true, "reasoning": false, "release_date": "2026-04-13", "structured_output": true, "temperature": true, "tool_call": true }, "google-gemma-3-27b-it": { "attachment": true, "cost": { "input": 0.12, "output": 0.2 }, "description": "Google Gemma 3 27B Instruct is an AI model provided by venice.", "family": "gemma", "id": "google-gemma-3-27b-it", "knowledge": "2025-07", "last_updated": "2026-03-12", "limit": { "context": 198000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Google Gemma 3 27B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-11-04", "structured_output": true, "temperature": true, "tool_call": true }, "google-gemma-4-26b-a4b-it": { "attachment": true, "cost": { "input": 0.1625, "output": 0.5 }, "description": "Google Gemma 4 26B A4B Instruct is an AI model provided by venice.", "family": "gemma", "id": "google-gemma-4-26b-a4b-it", "last_updated": "2026-04-12", "limit": { "context": 256000, "output": 8192 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Google Gemma 4 26B A4B Instruct", "open_weights": true, "reasoning": true, "release_date": "2026-04-02", "structured_output": true, "temperature": true, "tool_call": true }, "google-gemma-4-31b-it": { "attachment": true, "cost": { "input": 0.175, "output": 0.5 }, "description": "Google Gemma 4 31B Instruct is an AI model provided by venice.", "family": "gemma", "id": "google-gemma-4-31b-it", "last_updated": "2026-04-12", "limit": { "context": 256000, "output": 8192 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Google Gemma 4 31B Instruct", "open_weights": true, "reasoning": true, "release_date": "2026-04-03", "structured_output": true, "temperature": true, "tool_call": true }, "grok-4-20": { "attachment": true, "cost": { "cache_read": 0.23, "context_over_200k": { "cache_read": 0.45, "input": 2.83, "output": 5.67 }, "input": 1.42, "output": 2.83, "tiers": [ { "cache_read": 0.45, "input": 2.83, "output": 5.67, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Grok 4.20 is an AI model provided by venice.", "family": "grok", "id": "grok-4-20", "last_updated": "2026-05-07", "limit": { "context": 2000000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 4.20", "open_weights": false, "reasoning": true, "release_date": "2026-03-12", "structured_output": true, "temperature": true, "tool_call": true }, "grok-4-20-multi-agent": { "attachment": true, "cost": { "cache_read": 0.23, "context_over_200k": { "cache_read": 0.45, "input": 2.83, "output": 5.67 }, "input": 1.42, "output": 2.83, "tiers": [ { "cache_read": 0.45, "input": 2.83, "output": 5.67, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Grok 4.20 Multi-Agent is an AI model provided by venice.", "family": "grok", "id": "grok-4-20-multi-agent", "last_updated": "2026-05-07", "limit": { "context": 2000000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 4.20 Multi-Agent", "open_weights": false, "reasoning": true, "release_date": "2026-03-12", "structured_output": true, "temperature": true, "tool_call": false }, "grok-4-3": { "attachment": true, "cost": { "cache_read": 0.23, "context_over_200k": { "cache_read": 0.45, "input": 2.83, "output": 5.67 }, "input": 1.42, "output": 2.83, "tiers": [ { "cache_read": 0.45, "input": 2.83, "output": 5.67, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Grok 4.3 is an AI model provided by venice.", "family": "grok", "id": "grok-4-3", "last_updated": "2026-05-04", "limit": { "context": 1000000, "output": 32000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 4.3", "open_weights": false, "reasoning": true, "release_date": "2026-04-18", "structured_output": true, "temperature": true, "tool_call": true }, "grok-41-fast": { "attachment": true, "cost": { "cache_read": 0.06, "input": 0.23, "output": 0.57 }, "description": "Grok 4.1 Fast is an AI model provided by venice.", "family": "grok", "id": "grok-41-fast", "knowledge": "2025-07", "last_updated": "2026-04-09", "limit": { "context": 1000000, "output": 30000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 4.1 Fast", "open_weights": false, "reasoning": true, "release_date": "2025-12-01", "structured_output": true, "temperature": true, "tool_call": true }, "hermes-3-llama-3.1-405b": { "attachment": false, "cost": { "input": 1.1, "output": 3 }, "description": "Hermes 3 Llama 3.1 405b is an AI model provided by venice.", "family": "hermes", "id": "hermes-3-llama-3.1-405b", "knowledge": "2024-04", "last_updated": "2026-03-12", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Hermes 3 Llama 3.1 405b", "open_weights": true, "reasoning": false, "release_date": "2025-09-25", "temperature": true, "tool_call": false }, "kimi-k2-5": { "attachment": true, "cost": { "cache_read": 0.22, "input": 0.56, "output": 3.5 }, "description": "Kimi K2.5 is an AI model provided by venice.", "family": "kimi", "id": "kimi-k2-5", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-04", "last_updated": "2026-04-30", "limit": { "context": 256000, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Kimi K2.5", "open_weights": false, "reasoning": true, "release_date": "2026-01-27", "structured_output": true, "temperature": true, "tool_call": true }, "kimi-k2-6": { "attachment": true, "cost": { "cache_read": 0.22, "input": 0.85, "output": 4.655 }, "description": "Kimi K2.6 is an AI model provided by venice.", "family": "kimi", "id": "kimi-k2-6", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-30", "limit": { "context": 256000, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Kimi K2.6", "open_weights": true, "reasoning": true, "release_date": "2026-04-20", "structured_output": true, "temperature": true, "tool_call": true }, "llama-3.2-3b": { "attachment": false, "cost": { "input": 0.15, "output": 0.6 }, "description": "Llama 3.2 3B is an AI model provided by venice.", "family": "llama", "id": "llama-3.2-3b", "knowledge": "2023-12", "last_updated": "2026-03-12", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.2 3B", "open_weights": true, "reasoning": false, "release_date": "2024-10-03", "temperature": true, "tool_call": true }, "llama-3.3-70b": { "attachment": false, "cost": { "input": 0.7, "output": 2.8 }, "description": "Llama 3.3 70B is an AI model provided by venice.", "family": "llama", "id": "llama-3.3-70b", "knowledge": "2023-12", "last_updated": "2026-03-12", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.3 70B", "open_weights": true, "reasoning": false, "release_date": "2025-04-06", "temperature": true, "tool_call": true }, "mercury-2": { "attachment": false, "cost": { "cache_read": 0.03125, "input": 0.3125, "output": 0.9375 }, "description": "Mercury 2 is an AI model provided by venice.", "family": "mercury", "id": "mercury-2", "last_updated": "2026-04-09", "limit": { "context": 128000, "output": 50000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mercury 2", "open_weights": false, "reasoning": true, "release_date": "2026-02-20", "structured_output": true, "temperature": true, "tool_call": true }, "minimax-m25": { "attachment": false, "cost": { "cache_read": 0.04, "input": 0.34, "output": 1.19 }, "description": "MiniMax M2.5 is an AI model provided by venice.", "family": "minimax", "id": "minimax-m25", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-12", "limit": { "context": 198000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M2.5", "open_weights": false, "reasoning": true, "release_date": "2026-02-12", "temperature": true, "tool_call": true }, "minimax-m27": { "attachment": false, "cost": { "cache_read": 0.075, "input": 0.375, "output": 1.5 }, "description": "MiniMax M2.7 is an AI model provided by venice.", "family": "minimax", "id": "minimax-m27", "last_updated": "2026-04-12", "limit": { "context": 198000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M2.7", "open_weights": false, "reasoning": true, "release_date": "2026-03-18", "temperature": true, "tool_call": true }, "mistral-small-2603": { "attachment": true, "cost": { "input": 0.1875, "output": 0.75 }, "description": "Mistral Small 4 is an AI model provided by venice.", "family": "mistral-small", "id": "mistral-small-2603", "last_updated": "2026-04-09", "limit": { "context": 256000, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Mistral Small 4", "open_weights": true, "reasoning": true, "release_date": "2026-03-16", "structured_output": true, "temperature": true, "tool_call": true }, "mistral-small-3-2-24b-instruct": { "attachment": false, "cost": { "input": 0.09375, "output": 0.25 }, "description": "Mistral Small 3.2 24B Instruct is an AI model provided by venice.", "family": "mistral-small", "id": "mistral-small-3-2-24b-instruct", "last_updated": "2026-03-16", "limit": { "context": 256000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral Small 3.2 24B Instruct", "open_weights": true, "reasoning": false, "release_date": "2026-01-15", "structured_output": true, "temperature": true, "tool_call": true }, "nvidia-nemotron-3-nano-30b-a3b": { "attachment": false, "cost": { "input": 0.075, "output": 0.3 }, "description": "NVIDIA Nemotron 3 Nano 30B is an AI model provided by venice.", "family": "nemotron", "id": "nvidia-nemotron-3-nano-30b-a3b", "last_updated": "2026-03-12", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "NVIDIA Nemotron 3 Nano 30B", "open_weights": true, "reasoning": false, "release_date": "2026-01-27", "structured_output": true, "temperature": true, "tool_call": true }, "nvidia-nemotron-cascade-2-30b-a3b": { "attachment": false, "cost": { "input": 0.14, "output": 0.8 }, "description": "Nemotron Cascade 2 30B A3B is an AI model provided by venice.", "family": "nemotron", "id": "nvidia-nemotron-cascade-2-30b-a3b", "last_updated": "2026-04-09", "limit": { "context": 256000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Nemotron Cascade 2 30B A3B", "open_weights": true, "reasoning": true, "release_date": "2026-03-24", "structured_output": true, "temperature": true, "tool_call": true }, "olafangensan-glm-4.7-flash-heretic": { "attachment": false, "cost": { "input": 0.14, "output": 0.8 }, "description": "GLM 4.7 Flash Heretic is an AI model provided by venice.", "family": "glm-flash", "id": "olafangensan-glm-4.7-flash-heretic", "last_updated": "2026-03-12", "limit": { "context": 200000, "output": 24000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.7 Flash Heretic", "open_weights": true, "reasoning": true, "release_date": "2026-02-04", "structured_output": true, "temperature": true, "tool_call": true }, "openai-gpt-4o-2024-11-20": { "attachment": true, "cost": { "input": 3.125, "output": 12.5 }, "description": "GPT-4o is an AI model provided by venice.", "family": "gpt", "id": "openai-gpt-4o-2024-11-20", "last_updated": "2026-03-06", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4o", "open_weights": false, "reasoning": false, "release_date": "2026-02-28", "structured_output": true, "temperature": true, "tool_call": true }, "openai-gpt-4o-mini-2024-07-18": { "attachment": true, "cost": { "cache_read": 0.09375, "input": 0.1875, "output": 0.75 }, "description": "GPT-4o Mini is an AI model provided by venice.", "family": "gpt-mini", "id": "openai-gpt-4o-mini-2024-07-18", "last_updated": "2026-03-06", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4o Mini", "open_weights": false, "reasoning": false, "release_date": "2026-02-28", "structured_output": true, "temperature": true, "tool_call": true }, "openai-gpt-52": { "attachment": false, "cost": { "cache_read": 0.219, "input": 2.19, "output": 17.5 }, "description": "GPT-5.2 is an AI model provided by venice.", "family": "gpt", "id": "openai-gpt-52", "knowledge": "2025-08-31", "last_updated": "2026-03-12", "limit": { "context": 256000, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT-5.2", "open_weights": false, "reasoning": true, "release_date": "2025-12-13", "structured_output": true, "temperature": true, "tool_call": true }, "openai-gpt-52-codex": { "attachment": true, "cost": { "cache_read": 0.219, "input": 2.19, "output": 17.5 }, "description": "GPT-5.2 Codex is an AI model provided by venice.", "family": "gpt-codex", "id": "openai-gpt-52-codex", "knowledge": "2025-08", "last_updated": "2026-03-12", "limit": { "context": 256000, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.2 Codex", "open_weights": false, "reasoning": true, "release_date": "2025-01-15", "structured_output": true, "temperature": true, "tool_call": true }, "openai-gpt-53-codex": { "attachment": true, "cost": { "cache_read": 0.219, "input": 2.19, "output": 17.5 }, "description": "GPT-5.3 Codex is an AI model provided by venice.", "family": "gpt-codex", "id": "openai-gpt-53-codex", "last_updated": "2026-03-12", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.3 Codex", "open_weights": false, "reasoning": true, "release_date": "2026-02-24", "structured_output": true, "temperature": true, "tool_call": true }, "openai-gpt-54": { "attachment": true, "cost": { "cache_read": 0.313, "input": 3.13, "output": 18.8 }, "description": "GPT-5.4 is an AI model provided by venice.", "family": "gpt", "id": "openai-gpt-54", "last_updated": "2026-03-09", "limit": { "context": 1000000, "output": 131072 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.4", "open_weights": false, "reasoning": true, "release_date": "2026-03-05", "structured_output": true, "temperature": true, "tool_call": true }, "openai-gpt-54-mini": { "attachment": true, "cost": { "cache_read": 0.09375, "input": 0.9375, "output": 5.625 }, "description": "GPT-5.4 Mini is an AI model provided by venice.", "family": "gpt-mini", "id": "openai-gpt-54-mini", "last_updated": "2026-03-31", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.4 Mini", "open_weights": false, "reasoning": true, "release_date": "2026-03-27", "structured_output": true, "temperature": true, "tool_call": true }, "openai-gpt-54-pro": { "attachment": true, "cost": { "context_over_200k": { "input": 75, "output": 337.5 }, "input": 37.5, "output": 225, "tiers": [ { "input": 75, "output": 337.5, "tier": { "size": 272000, "type": "context" } } ] }, "description": "GPT-5.4 Pro is an AI model provided by venice.", "family": "gpt-pro", "id": "openai-gpt-54-pro", "last_updated": "2026-03-09", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.4 Pro", "open_weights": false, "reasoning": true, "release_date": "2026-03-05", "structured_output": true, "temperature": true, "tool_call": true }, "openai-gpt-55": { "attachment": true, "cost": { "cache_read": 0.625, "context_over_200k": { "cache_read": 1.25, "input": 12.5, "output": 56.25 }, "input": 6.25, "output": 37.5, "tiers": [ { "cache_read": 1.25, "input": 12.5, "output": 56.25, "tier": { "size": 272000, "type": "context" } } ] }, "description": "GPT-5.5 is an AI model provided by venice.", "family": "gpt", "id": "openai-gpt-55", "last_updated": "2026-04-25", "limit": { "context": 1000000, "output": 131072 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.5", "open_weights": false, "reasoning": true, "release_date": "2026-04-23", "structured_output": true, "temperature": true, "tool_call": true }, "openai-gpt-55-pro": { "attachment": true, "cost": { "input": 37.5, "output": 225 }, "description": "GPT-5.5 Pro is an AI model provided by venice.", "family": "gpt-pro", "id": "openai-gpt-55-pro", "last_updated": "2026-04-25", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.5 Pro", "open_weights": false, "reasoning": true, "release_date": "2026-04-24", "structured_output": true, "temperature": true, "tool_call": true }, "openai-gpt-oss-120b": { "attachment": false, "cost": { "input": 0.07, "output": 0.3 }, "description": "OpenAI GPT OSS 120B is an AI model provided by venice.", "family": "gpt-oss", "id": "openai-gpt-oss-120b", "knowledge": "2025-07", "last_updated": "2026-05-06", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "OpenAI GPT OSS 120B", "open_weights": true, "reasoning": true, "release_date": "2025-11-06", "temperature": true, "tool_call": true }, "qwen-3-6-plus": { "attachment": true, "cost": { "cache_read": 0.0625, "cache_write": 0.78, "context_over_200k": { "cache_read": 0.0625, "cache_write": 0.78, "input": 2.5, "output": 7.5 }, "input": 0.625, "output": 3.75, "tiers": [ { "cache_read": 0.0625, "cache_write": 0.78, "input": 2.5, "output": 7.5, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Qwen 3.6 Plus Uncensored is an AI model provided by venice.", "family": "qwen", "id": "qwen-3-6-plus", "last_updated": "2026-04-12", "limit": { "context": 1000000, "output": 65536 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen 3.6 Plus Uncensored", "open_weights": false, "reasoning": true, "release_date": "2026-04-06", "structured_output": true, "temperature": true, "tool_call": true }, "qwen3-235b-a22b-instruct-2507": { "attachment": false, "cost": { "input": 0.15, "output": 0.75 }, "description": "Qwen 3 235B A22B Instruct 2507 is an AI model provided by venice.", "family": "qwen", "id": "qwen3-235b-a22b-instruct-2507", "knowledge": "2025-07", "last_updated": "2026-03-12", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen 3 235B A22B Instruct 2507", "open_weights": true, "reasoning": false, "release_date": "2025-04-29", "structured_output": true, "temperature": true, "tool_call": true }, "qwen3-235b-a22b-thinking-2507": { "attachment": false, "cost": { "input": 0.45, "output": 3.5 }, "description": "Qwen 3 235B A22B Thinking 2507 is an AI model provided by venice.", "family": "qwen", "id": "qwen3-235b-a22b-thinking-2507", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-07", "last_updated": "2026-03-12", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen 3 235B A22B Thinking 2507", "open_weights": true, "reasoning": true, "release_date": "2025-04-29", "structured_output": true, "temperature": true, "tool_call": true }, "qwen3-5-35b-a3b": { "attachment": true, "cost": { "cache_read": 0.15625, "input": 0.3125, "output": 1.25 }, "description": "Qwen 3.5 35B A3B is an AI model provided by venice.", "family": "qwen", "id": "qwen3-5-35b-a3b", "last_updated": "2026-04-16", "limit": { "context": 256000, "output": 65536 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen 3.5 35B A3B", "open_weights": true, "reasoning": true, "release_date": "2026-02-25", "structured_output": true, "temperature": true, "tool_call": true }, "qwen3-5-397b-a17b": { "attachment": true, "cost": { "input": 0.75, "output": 4.5 }, "description": "Qwen 3.5 397B is an AI model provided by venice.", "family": "qwen", "id": "qwen3-5-397b-a17b", "last_updated": "2026-04-16", "limit": { "context": 128000, "output": 32768 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen 3.5 397B", "open_weights": true, "reasoning": true, "release_date": "2026-02-16", "structured_output": true, "temperature": true, "tool_call": true }, "qwen3-5-9b": { "attachment": true, "cost": { "input": 0.1, "output": 0.15 }, "description": "Qwen 3.5 9B is an AI model provided by venice.", "family": "qwen", "id": "qwen3-5-9b", "last_updated": "2026-04-19", "limit": { "context": 256000, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen 3.5 9B", "open_weights": true, "reasoning": true, "release_date": "2026-03-05", "structured_output": true, "temperature": true, "tool_call": true }, "qwen3-6-27b": { "attachment": true, "cost": { "input": 0.325, "output": 3.25 }, "description": "Qwen 3.6 27B is an AI model provided by venice.", "family": "qwen", "id": "qwen3-6-27b", "last_updated": "2026-04-29", "limit": { "context": 256000, "output": 65536 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen 3.6 27B", "open_weights": false, "reasoning": true, "release_date": "2026-04-24", "structured_output": true, "temperature": true, "tool_call": true }, "qwen3-coder-480b-a35b-instruct-turbo": { "attachment": false, "cost": { "cache_read": 0.04, "input": 0.35, "output": 1.5 }, "description": "Qwen 3 Coder 480B Turbo is an AI model provided by venice.", "family": "qwen", "id": "qwen3-coder-480b-a35b-instruct-turbo", "last_updated": "2026-02-26", "limit": { "context": 256000, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen 3 Coder 480B Turbo", "open_weights": true, "reasoning": false, "release_date": "2026-01-27", "structured_output": true, "temperature": true, "tool_call": true }, "qwen3-next-80b": { "attachment": false, "cost": { "input": 0.35, "output": 1.9 }, "description": "Qwen 3 Next 80b is an AI model provided by venice.", "family": "qwen", "id": "qwen3-next-80b", "knowledge": "2025-07", "last_updated": "2026-03-12", "limit": { "context": 256000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen 3 Next 80b", "open_weights": true, "reasoning": false, "release_date": "2025-04-29", "structured_output": true, "temperature": true, "tool_call": true }, "qwen3-vl-235b-a22b": { "attachment": true, "cost": { "input": 0.25, "output": 1.5 }, "description": "Qwen3 VL 235B is an AI model provided by venice.", "family": "qwen", "id": "qwen3-vl-235b-a22b", "last_updated": "2026-03-12", "limit": { "context": 256000, "output": 16384 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen3 VL 235B", "open_weights": true, "reasoning": false, "release_date": "2026-01-16", "structured_output": true, "temperature": true, "tool_call": true }, "venice-uncensored-1-2": { "attachment": true, "cost": { "input": 0.2, "output": 0.9 }, "description": "Venice Uncensored 1.2 is an AI model provided by venice.", "family": "venice", "id": "venice-uncensored-1-2", "last_updated": "2026-04-19", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Venice Uncensored 1.2", "open_weights": true, "reasoning": false, "release_date": "2026-04-01", "structured_output": true, "temperature": true, "tool_call": true }, "venice-uncensored-role-play": { "attachment": true, "cost": { "input": 0.5, "output": 2 }, "description": "Venice Role Play Uncensored is an AI model provided by venice.", "family": "venice", "id": "venice-uncensored-role-play", "last_updated": "2026-03-16", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Venice Role Play Uncensored", "open_weights": true, "reasoning": false, "release_date": "2026-02-20", "structured_output": true, "temperature": true, "tool_call": true }, "z-ai-glm-5-turbo": { "attachment": false, "cost": { "cache_read": 0.24, "input": 1.2, "output": 4 }, "description": "GLM 5 Turbo is an AI model provided by venice.", "family": "glm", "id": "z-ai-glm-5-turbo", "last_updated": "2026-04-12", "limit": { "context": 200000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 5 Turbo", "open_weights": true, "reasoning": true, "release_date": "2026-03-15", "structured_output": true, "temperature": true, "tool_call": true }, "z-ai-glm-5v-turbo": { "attachment": true, "cost": { "cache_read": 0.3, "input": 1.5, "output": 5 }, "description": "GLM 5V Turbo is an AI model provided by venice.", "family": "glmv", "id": "z-ai-glm-5v-turbo", "last_updated": "2026-04-12", "limit": { "context": 200000, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GLM 5V Turbo", "open_weights": false, "reasoning": true, "release_date": "2026-04-01", "structured_output": true, "temperature": true, "tool_call": true }, "zai-org-glm-4.6": { "attachment": false, "cost": { "cache_read": 0.3, "input": 0.85, "output": 2.75 }, "description": "GLM 4.6 is an AI model provided by venice.", "family": "glm", "id": "zai-org-glm-4.6", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-04", "limit": { "context": 198000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.6", "open_weights": true, "reasoning": true, "release_date": "2024-04-01", "structured_output": true, "temperature": true, "tool_call": true }, "zai-org-glm-4.7": { "attachment": false, "cost": { "cache_read": 0.11, "input": 0.55, "output": 2.65 }, "description": "GLM 4.7 is an AI model provided by venice.", "family": "glm", "id": "zai-org-glm-4.7", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-04", "last_updated": "2026-03-12", "limit": { "context": 198000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.7", "open_weights": true, "reasoning": true, "release_date": "2025-12-24", "structured_output": true, "temperature": true, "tool_call": true }, "zai-org-glm-4.7-flash": { "attachment": false, "cost": { "input": 0.125, "output": 0.5 }, "description": "GLM 4.7 Flash is an AI model provided by venice.", "family": "glm-flash", "id": "zai-org-glm-4.7-flash", "last_updated": "2026-03-12", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.7 Flash", "open_weights": true, "reasoning": true, "release_date": "2026-01-29", "structured_output": true, "temperature": true, "tool_call": true }, "zai-org-glm-5": { "attachment": false, "cost": { "cache_read": 0.2, "input": 1, "output": 3.2 }, "description": "GLM 5 is an AI model provided by venice.", "family": "glm", "id": "zai-org-glm-5", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-03-12", "limit": { "context": 198000, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 5", "open_weights": true, "reasoning": true, "release_date": "2026-02-11", "structured_output": true, "temperature": true, "tool_call": true }, "zai-org-glm-5-1": { "attachment": false, "cost": { "cache_read": 0.325, "input": 1.75, "output": 5.5 }, "description": "GLM 5.1 is an AI model provided by venice.", "family": "glm", "id": "zai-org-glm-5-1", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-08", "limit": { "context": 200000, "output": 24000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 5.1", "open_weights": true, "reasoning": true, "release_date": "2026-04-07", "structured_output": true, "temperature": true, "tool_call": true } }, "name": "Venice AI", "npm": "venice-ai-sdk-provider" }, "vercel": { "doc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway", "env": [ "AI_GATEWAY_API_KEY" ], "iconURL": "https://models.dev/logos/vercel.svg", "id": "vercel", "lobeIcon": "Vercel.Color", "models": { "alibaba/qwen-3-14b": { "attachment": false, "cost": { "input": 0.06, "output": 0.24 }, "description": "Qwen3-14B is an AI model provided by vercel.", "family": "qwen", "id": "alibaba/qwen-3-14b", "knowledge": "2025-04", "last_updated": "2025-04", "limit": { "context": 40960, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3-14B", "open_weights": false, "reasoning": true, "release_date": "2025-04", "temperature": true, "tool_call": true }, "alibaba/qwen-3-235b": { "attachment": false, "cost": { "input": 0.13, "output": 0.6 }, "description": "Qwen3 235B A22B Instruct 2507 is an AI model provided by vercel.", "family": "qwen", "id": "alibaba/qwen-3-235b", "knowledge": "2025-04", "last_updated": "2025-04", "limit": { "context": 40960, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 235B A22B Instruct 2507", "open_weights": false, "reasoning": false, "release_date": "2025-04", "temperature": true, "tool_call": true }, "alibaba/qwen-3-30b": { "attachment": false, "cost": { "input": 0.08, "output": 0.29 }, "description": "Qwen3-30B-A3B is an AI model provided by vercel.", "family": "qwen", "id": "alibaba/qwen-3-30b", "knowledge": "2025-04", "last_updated": "2025-04", "limit": { "context": 40960, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3-30B-A3B", "open_weights": false, "reasoning": true, "release_date": "2025-04", "temperature": true, "tool_call": true }, "alibaba/qwen-3-32b": { "attachment": false, "cost": { "input": 0.1, "output": 0.3 }, "description": "Qwen 3.32B is an AI model provided by vercel.", "family": "qwen", "id": "alibaba/qwen-3-32b", "knowledge": "2025-04", "last_updated": "2025-04", "limit": { "context": 40960, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen 3.32B", "open_weights": false, "reasoning": true, "release_date": "2025-04", "temperature": true, "tool_call": true }, "alibaba/qwen-3.6-max-preview": { "attachment": true, "cost": { "cache_read": 0.26, "cache_write": 1.625, "input": 1.3, "output": 7.8 }, "description": "Qwen 3.6 Max Preview is an AI model provided by vercel.", "family": "qwen", "id": "alibaba/qwen-3.6-max-preview", "last_updated": "2026-04-24", "limit": { "context": 240000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Qwen 3.6 Max Preview", "open_weights": true, "reasoning": true, "release_date": "2026-04-20", "temperature": true, "tool_call": true }, "alibaba/qwen3-235b-a22b-thinking": { "attachment": true, "cost": { "input": 0.3, "output": 2.9 }, "description": "Qwen3 235B A22B Thinking 2507 is an AI model provided by vercel.", "family": "qwen", "id": "alibaba/qwen3-235b-a22b-thinking", "knowledge": "2025-04", "last_updated": "2025-04", "limit": { "context": 262114, "output": 262114 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Qwen3 235B A22B Thinking 2507", "open_weights": false, "reasoning": true, "release_date": "2025-04", "temperature": true, "tool_call": true }, "alibaba/qwen3-coder": { "attachment": false, "cost": { "input": 0.38, "output": 1.53 }, "description": "Qwen3 Coder 480B A35B Instruct is an AI model provided by vercel.", "family": "qwen", "id": "alibaba/qwen3-coder", "knowledge": "2025-04", "last_updated": "2025-04", "limit": { "context": 262144, "output": 66536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Coder 480B A35B Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-04", "temperature": true, "tool_call": true }, "alibaba/qwen3-coder-30b-a3b": { "attachment": false, "cost": { "input": 0.07, "output": 0.27 }, "description": "Qwen 3 Coder 30B A3B Instruct is an AI model provided by vercel.", "family": "qwen", "id": "alibaba/qwen3-coder-30b-a3b", "knowledge": "2025-04", "last_updated": "2025-04", "limit": { "context": 160000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen 3 Coder 30B A3B Instruct", "open_weights": false, "reasoning": true, "release_date": "2025-04", "temperature": true, "tool_call": true }, "alibaba/qwen3-coder-next": { "attachment": false, "cost": { "input": 0.5, "output": 1.2 }, "description": "Qwen3 Coder Next is an AI model provided by vercel.", "family": "qwen", "id": "alibaba/qwen3-coder-next", "last_updated": "2026-02-19", "limit": { "context": 256000, "output": 256000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Coder Next", "open_weights": false, "reasoning": true, "release_date": "2025-07-22", "temperature": true, "tool_call": true }, "alibaba/qwen3-coder-plus": { "attachment": false, "cost": { "input": 1, "output": 5 }, "description": "Qwen3 Coder Plus is an AI model provided by vercel.", "family": "qwen", "id": "alibaba/qwen3-coder-plus", "knowledge": "2025-04", "last_updated": "2025-07-23", "limit": { "context": 1000000, "output": 1000000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Coder Plus", "open_weights": true, "reasoning": false, "release_date": "2025-07-23", "temperature": true, "tool_call": true }, "alibaba/qwen3-embedding-0.6b": { "attachment": false, "cost": { "input": 0.01, "output": 0 }, "description": "Qwen3 Embedding 0.6B is an AI model provided by vercel.", "family": "qwen", "id": "alibaba/qwen3-embedding-0.6b", "last_updated": "2025-11-14", "limit": { "context": 32768, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Embedding 0.6B", "open_weights": false, "reasoning": false, "release_date": "2025-11-14", "temperature": false, "tool_call": false }, "alibaba/qwen3-embedding-4b": { "attachment": false, "cost": { "input": 0.02, "output": 0 }, "description": "Qwen3 Embedding 4B is an AI model provided by vercel.", "family": "qwen", "id": "alibaba/qwen3-embedding-4b", "last_updated": "2025-06-05", "limit": { "context": 32768, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Embedding 4B", "open_weights": false, "reasoning": false, "release_date": "2025-06-05", "temperature": false, "tool_call": false }, "alibaba/qwen3-embedding-8b": { "attachment": false, "cost": { "input": 0.05, "output": 0 }, "description": "Qwen3 Embedding 8B is an AI model provided by vercel.", "family": "qwen", "id": "alibaba/qwen3-embedding-8b", "last_updated": "2025-06-05", "limit": { "context": 32768, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Embedding 8B", "open_weights": false, "reasoning": false, "release_date": "2025-06-05", "temperature": false, "tool_call": false }, "alibaba/qwen3-max": { "attachment": false, "cost": { "input": 1.2, "output": 6 }, "description": "Qwen3 Max is an AI model provided by vercel.", "family": "qwen", "id": "alibaba/qwen3-max", "knowledge": "2025-04", "last_updated": "2025-09-23", "limit": { "context": 262144, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Max", "open_weights": false, "reasoning": false, "release_date": "2025-09-23", "temperature": true, "tool_call": true }, "alibaba/qwen3-max-preview": { "attachment": false, "cost": { "cache_read": 0.24, "input": 1.2, "output": 6 }, "description": "Qwen3 Max Preview is an AI model provided by vercel.", "family": "qwen", "id": "alibaba/qwen3-max-preview", "knowledge": "2025-04", "last_updated": "2025-09-23", "limit": { "context": 262144, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Max Preview", "open_weights": false, "reasoning": false, "release_date": "2025-09-23", "temperature": true, "tool_call": true }, "alibaba/qwen3-max-thinking": { "attachment": false, "cost": { "cache_read": 0.24, "input": 1.2, "output": 6 }, "description": "Qwen 3 Max Thinking is an AI model provided by vercel.", "family": "qwen", "id": "alibaba/qwen3-max-thinking", "knowledge": "2025-01", "last_updated": "2025-01", "limit": { "context": 256000, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen 3 Max Thinking", "open_weights": true, "reasoning": true, "release_date": "2025-01", "temperature": true, "tool_call": true }, "alibaba/qwen3-next-80b-a3b-instruct": { "attachment": false, "cost": { "input": 0.09, "output": 1.1 }, "description": "Qwen3 Next 80B A3B Instruct is an AI model provided by vercel.", "family": "qwen", "id": "alibaba/qwen3-next-80b-a3b-instruct", "knowledge": "2025-04", "last_updated": "2025-09-12", "limit": { "context": 262144, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Next 80B A3B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-09-12", "temperature": true, "tool_call": true }, "alibaba/qwen3-next-80b-a3b-thinking": { "attachment": false, "cost": { "input": 0.15, "output": 1.5 }, "description": "Qwen3 Next 80B A3B Thinking is an AI model provided by vercel.", "family": "qwen", "id": "alibaba/qwen3-next-80b-a3b-thinking", "knowledge": "2025-09", "last_updated": "2025-09-12", "limit": { "context": 131072, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 Next 80B A3B Thinking", "open_weights": true, "reasoning": true, "release_date": "2025-09-12", "temperature": true, "tool_call": true }, "alibaba/qwen3-vl-235b-a22b-instruct": { "attachment": true, "cost": { "input": 0.39999999999999997, "output": 1.5999999999999999 }, "description": "Qwen3 VL 235B A22B Instruct is an AI model provided by vercel.", "family": "qwen", "id": "alibaba/qwen3-vl-235b-a22b-instruct", "last_updated": "2026-05-01", "limit": { "context": 131072, "output": 129024 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen3 VL 235B A22B Instruct", "open_weights": false, "reasoning": false, "release_date": "2025-09-24", "temperature": true, "tool_call": false }, "alibaba/qwen3-vl-instruct": { "attachment": true, "cost": { "input": 0.7, "output": 2.8 }, "description": "Qwen3 VL Instruct is an AI model provided by vercel.", "family": "qwen", "id": "alibaba/qwen3-vl-instruct", "knowledge": "2025-04", "last_updated": "2025-09-24", "limit": { "context": 131072, "output": 129024 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen3 VL Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-09-24", "temperature": true, "tool_call": true }, "alibaba/qwen3-vl-thinking": { "attachment": true, "cost": { "input": 0.7, "output": 8.4 }, "description": "Qwen3 VL Thinking is an AI model provided by vercel.", "family": "qwen", "id": "alibaba/qwen3-vl-thinking", "knowledge": "2025-09", "last_updated": "2025-09-24", "limit": { "context": 131072, "output": 129024 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen3 VL Thinking", "open_weights": true, "reasoning": true, "release_date": "2025-09-24", "temperature": true, "tool_call": true }, "alibaba/qwen3.5-flash": { "attachment": true, "cost": { "cache_read": 0.001, "cache_write": 0.125, "input": 0.1, "output": 0.4 }, "description": "Qwen 3.5 Flash is an AI model provided by vercel.", "family": "qwen", "id": "alibaba/qwen3.5-flash", "last_updated": "2026-02-24", "limit": { "context": 1000000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Qwen 3.5 Flash", "open_weights": false, "reasoning": true, "release_date": "2026-02-24", "temperature": true, "tool_call": true }, "alibaba/qwen3.5-plus": { "attachment": true, "cost": { "cache_read": 0.04, "cache_write": 0.5, "input": 0.4, "output": 2.4 }, "description": "Qwen 3.5 Plus is an AI model provided by vercel.", "family": "qwen", "id": "alibaba/qwen3.5-plus", "last_updated": "2026-02-19", "limit": { "context": 1000000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Qwen 3.5 Plus", "open_weights": false, "reasoning": true, "release_date": "2026-02-16", "temperature": true, "tool_call": true }, "alibaba/qwen3.6-27b": { "attachment": true, "cost": { "input": 0.6, "output": 3.5999999999999996 }, "description": "Qwen 3.6 27B is an AI model provided by vercel.", "family": "qwen3.6", "id": "alibaba/qwen3.6-27b", "last_updated": "2026-05-01", "limit": { "context": 256000, "output": 256000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Qwen 3.6 27B", "open_weights": false, "reasoning": true, "release_date": "2026-04-22", "temperature": true, "tool_call": true }, "alibaba/qwen3.6-plus": { "attachment": true, "cost": { "cache_read": 0.09999999999999999, "cache_write": 0.625, "input": 0.5, "output": 3 }, "description": "Qwen 3.6 Plus is an AI model provided by vercel.", "family": "qwen", "id": "alibaba/qwen3.6-plus", "last_updated": "2026-04-03", "limit": { "context": 1000000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Qwen 3.6 Plus", "open_weights": false, "reasoning": true, "release_date": "2026-04-02", "temperature": true, "tool_call": true }, "amazon/nova-2-lite": { "attachment": true, "cost": { "input": 0.3, "output": 2.5 }, "description": "Nova 2 Lite is an AI model provided by vercel.", "family": "nova", "id": "amazon/nova-2-lite", "knowledge": "2024-10", "last_updated": "2024-12-01", "limit": { "context": 1000000, "output": 1000000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Nova 2 Lite", "open_weights": false, "reasoning": true, "release_date": "2024-12-01", "temperature": true, "tool_call": false }, "amazon/nova-lite": { "attachment": true, "cost": { "cache_read": 0.015, "input": 0.06, "output": 0.24 }, "description": "Nova Lite is an AI model provided by vercel.", "family": "nova-lite", "id": "amazon/nova-lite", "knowledge": "2024-10", "last_updated": "2024-12-03", "limit": { "context": 300000, "output": 8192 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Nova Lite", "open_weights": false, "reasoning": false, "release_date": "2024-12-03", "temperature": true, "tool_call": true }, "amazon/nova-micro": { "attachment": false, "cost": { "cache_read": 0.00875, "input": 0.035, "output": 0.14 }, "description": "Nova Micro is an AI model provided by vercel.", "family": "nova-micro", "id": "amazon/nova-micro", "knowledge": "2024-10", "last_updated": "2024-12-03", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Nova Micro", "open_weights": false, "reasoning": false, "release_date": "2024-12-03", "temperature": true, "tool_call": true }, "amazon/nova-pro": { "attachment": true, "cost": { "cache_read": 0.2, "input": 0.8, "output": 3.2 }, "description": "Nova Pro is an AI model provided by vercel.", "family": "nova-pro", "id": "amazon/nova-pro", "knowledge": "2024-10", "last_updated": "2024-12-03", "limit": { "context": 300000, "output": 8192 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Nova Pro", "open_weights": false, "reasoning": false, "release_date": "2024-12-03", "temperature": true, "tool_call": true }, "amazon/titan-embed-text-v2": { "attachment": false, "cost": { "input": 0.02, "output": 0 }, "description": "Titan Text Embeddings V2 is an AI model provided by vercel.", "family": "titan-embed", "id": "amazon/titan-embed-text-v2", "last_updated": "2024-04", "limit": { "context": 8192, "output": 1536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Titan Text Embeddings V2", "open_weights": false, "reasoning": false, "release_date": "2024-04", "temperature": false, "tool_call": false }, "anthropic/claude-3-haiku": { "attachment": true, "cost": { "cache_read": 0.03, "cache_write": 0.3, "input": 0.25, "output": 1.25 }, "description": "Claude Haiku 3 is an AI model provided by vercel.", "family": "claude-haiku", "id": "anthropic/claude-3-haiku", "knowledge": "2023-08-31", "last_updated": "2024-03-13", "limit": { "context": 200000, "output": 4096 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Haiku 3", "open_weights": false, "reasoning": false, "release_date": "2024-03-13", "temperature": true, "tool_call": true }, "anthropic/claude-3-opus": { "attachment": true, "cost": { "cache_read": 1.5, "cache_write": 18.75, "input": 15, "output": 75 }, "description": "Claude Opus 3 is an AI model provided by vercel.", "family": "claude-opus", "id": "anthropic/claude-3-opus", "knowledge": "2023-08-31", "last_updated": "2024-02-29", "limit": { "context": 200000, "output": 4096 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 3", "open_weights": false, "reasoning": false, "release_date": "2024-02-29", "temperature": true, "tool_call": true }, "anthropic/claude-3.5-haiku": { "attachment": true, "cost": { "cache_read": 0.08, "cache_write": 1, "input": 0.8, "output": 4 }, "description": "Claude Haiku 3.5 is an AI model provided by vercel.", "family": "claude-haiku", "id": "anthropic/claude-3.5-haiku", "knowledge": "2024-07-31", "last_updated": "2024-10-22", "limit": { "context": 200000, "output": 8192 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Haiku 3.5", "open_weights": false, "reasoning": false, "release_date": "2024-10-22", "temperature": true, "tool_call": true }, "anthropic/claude-3.5-sonnet": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 3.5 v2 is an AI model provided by vercel.", "family": "claude-sonnet", "id": "anthropic/claude-3.5-sonnet", "knowledge": "2024-04-30", "last_updated": "2024-10-22", "limit": { "context": 200000, "output": 8192 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 3.5 v2", "open_weights": false, "reasoning": false, "release_date": "2024-10-22", "temperature": true, "tool_call": true }, "anthropic/claude-3.5-sonnet-20240620": { "attachment": true, "cost": { "input": 3, "output": 15 }, "description": "Claude 3.5 Sonnet (2024-06-20) is an AI model provided by vercel.", "family": "claude-sonnet", "id": "anthropic/claude-3.5-sonnet-20240620", "knowledge": "2024-04", "last_updated": "2024-06-20", "limit": { "context": 200000, "output": 8192 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude 3.5 Sonnet (2024-06-20)", "open_weights": false, "reasoning": false, "release_date": "2024-06-20", "temperature": true, "tool_call": true }, "anthropic/claude-3.7-sonnet": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 3.7 is an AI model provided by vercel.", "family": "claude-sonnet", "id": "anthropic/claude-3.7-sonnet", "knowledge": "2024-10-31", "last_updated": "2025-02-19", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 3.7", "open_weights": false, "reasoning": true, "release_date": "2025-02-19", "temperature": true, "tool_call": true }, "anthropic/claude-haiku-4.5": { "attachment": true, "cost": { "cache_read": 0.1, "cache_write": 1.25, "input": 1, "output": 5 }, "description": "Claude Haiku 4.5 is an AI model provided by vercel.", "family": "claude-haiku", "id": "anthropic/claude-haiku-4.5", "interleaved": true, "knowledge": "2025-02-28", "last_updated": "2025-10-15", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Haiku 4.5", "open_weights": false, "reasoning": true, "release_date": "2025-10-15", "temperature": true, "tool_call": true }, "anthropic/claude-opus-4": { "attachment": true, "cost": { "cache_read": 1.5, "cache_write": 18.75, "input": 15, "output": 75 }, "description": "Claude Opus 4 is an AI model provided by vercel.", "family": "claude-opus", "id": "anthropic/claude-opus-4", "knowledge": "2025-03-31", "last_updated": "2025-05-22", "limit": { "context": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4", "open_weights": false, "reasoning": true, "release_date": "2025-05-22", "temperature": true, "tool_call": true }, "anthropic/claude-opus-4.1": { "attachment": true, "cost": { "cache_read": 1.5, "cache_write": 18.75, "input": 15, "output": 75 }, "description": "Claude Opus 4 is an AI model provided by vercel.", "family": "claude-opus", "id": "anthropic/claude-opus-4.1", "knowledge": "2025-03-31", "last_updated": "2025-05-22", "limit": { "context": 200000, "output": 32000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4", "open_weights": false, "reasoning": true, "release_date": "2025-05-22", "temperature": true, "tool_call": true }, "anthropic/claude-opus-4.5": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 18.75, "input": 5, "output": 25 }, "description": "Claude Opus 4.5 is an AI model provided by vercel.", "family": "claude-opus", "id": "anthropic/claude-opus-4.5", "interleaved": true, "knowledge": "2025-03-31", "last_updated": "2025-11-24", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.5", "open_weights": false, "reasoning": true, "release_date": "2025-11-24", "temperature": true, "tool_call": true }, "anthropic/claude-opus-4.6": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "input": 5, "output": 25 }, "description": "Claude Opus 4.6 is an AI model provided by vercel.", "family": "claude-opus", "id": "anthropic/claude-opus-4.6", "interleaved": true, "knowledge": "2025-05-31", "last_updated": "2026-02", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.6", "open_weights": false, "reasoning": true, "release_date": "2026-02", "temperature": true, "tool_call": true }, "anthropic/claude-opus-4.7": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "input": 5, "output": 25 }, "description": "Claude Opus 4.7 is an AI model provided by vercel.", "family": "claude-opus", "id": "anthropic/claude-opus-4.7", "last_updated": "2026-04-16", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.7", "open_weights": false, "reasoning": true, "release_date": "2026-04-16", "temperature": false, "tool_call": true }, "anthropic/claude-sonnet-4": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 4 is an AI model provided by vercel.", "family": "claude-sonnet", "id": "anthropic/claude-sonnet-4", "knowledge": "2025-03-31", "last_updated": "2025-05-22", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4", "open_weights": false, "reasoning": true, "release_date": "2025-05-22", "temperature": true, "tool_call": true }, "anthropic/claude-sonnet-4.5": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 4.5 is an AI model provided by vercel.", "family": "claude-sonnet", "id": "anthropic/claude-sonnet-4.5", "knowledge": "2025-07-31", "last_updated": "2025-09-29", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.5", "open_weights": false, "reasoning": true, "release_date": "2025-09-29", "temperature": true, "tool_call": true }, "anthropic/claude-sonnet-4.6": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "context_over_200k": { "cache_read": 0.6, "cache_write": 7.5, "input": 6, "output": 22.5 }, "input": 3, "output": 15, "tiers": [ { "cache_read": 0.6, "cache_write": 7.5, "input": 6, "output": 22.5, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Claude Sonnet 4.6 is an AI model provided by vercel.", "family": "claude-sonnet", "id": "anthropic/claude-sonnet-4.6", "interleaved": true, "knowledge": "2025-08-31", "last_updated": "2026-02-17", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.6", "open_weights": false, "reasoning": true, "release_date": "2026-02-17", "temperature": true, "tool_call": true }, "arcee-ai/trinity-large-preview": { "attachment": false, "cost": { "input": 0.25, "output": 1 }, "description": "Trinity Large Preview is an AI model provided by vercel.", "family": "trinity", "id": "arcee-ai/trinity-large-preview", "knowledge": "2024-10", "last_updated": "2025-01", "limit": { "context": 131000, "output": 131000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Trinity Large Preview", "open_weights": false, "reasoning": false, "release_date": "2025-01", "temperature": true, "tool_call": true }, "arcee-ai/trinity-large-thinking": { "attachment": false, "cost": { "input": 0.25, "output": 0.8999999999999999 }, "description": "Trinity Large Thinking is an AI model provided by vercel.", "family": "trinity", "id": "arcee-ai/trinity-large-thinking", "last_updated": "2026-04-03", "limit": { "context": 262100, "output": 80000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Trinity Large Thinking", "open_weights": true, "reasoning": true, "release_date": "2026-04-01", "temperature": true, "tool_call": true }, "arcee-ai/trinity-mini": { "attachment": false, "cost": { "input": 0.05, "output": 0.15 }, "description": "Trinity Mini is an AI model provided by vercel.", "family": "trinity", "id": "arcee-ai/trinity-mini", "knowledge": "2024-10", "last_updated": "2025-12", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Trinity Mini", "open_weights": false, "reasoning": false, "release_date": "2025-12", "temperature": true, "tool_call": false }, "bfl/flux-kontext-max": { "attachment": false, "description": "FLUX.1 Kontext Max is an AI model provided by vercel.", "family": "flux", "id": "bfl/flux-kontext-max", "last_updated": "2025-06", "limit": { "context": 512, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "name": "FLUX.1 Kontext Max", "open_weights": false, "reasoning": false, "release_date": "2025-06", "temperature": false, "tool_call": false }, "bfl/flux-kontext-pro": { "attachment": false, "description": "FLUX.1 Kontext Pro is an AI model provided by vercel.", "family": "flux", "id": "bfl/flux-kontext-pro", "last_updated": "2025-06", "limit": { "context": 512, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "name": "FLUX.1 Kontext Pro", "open_weights": false, "reasoning": false, "release_date": "2025-06", "temperature": false, "tool_call": false }, "bfl/flux-pro-1.0-fill": { "attachment": false, "description": "FLUX.1 Fill [pro] is an AI model provided by vercel.", "family": "flux", "id": "bfl/flux-pro-1.0-fill", "last_updated": "2024-10", "limit": { "context": 512, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "name": "FLUX.1 Fill [pro]", "open_weights": false, "reasoning": false, "release_date": "2024-10", "temperature": false, "tool_call": false }, "bfl/flux-pro-1.1": { "attachment": false, "description": "FLUX1.1 [pro] is an AI model provided by vercel.", "family": "flux", "id": "bfl/flux-pro-1.1", "last_updated": "2024-10", "limit": { "context": 512, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "name": "FLUX1.1 [pro]", "open_weights": false, "reasoning": false, "release_date": "2024-10", "temperature": false, "tool_call": false }, "bfl/flux-pro-1.1-ultra": { "attachment": false, "description": "FLUX1.1 [pro] Ultra is an AI model provided by vercel.", "family": "flux", "id": "bfl/flux-pro-1.1-ultra", "last_updated": "2024-11", "limit": { "context": 512, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "name": "FLUX1.1 [pro] Ultra", "open_weights": false, "reasoning": false, "release_date": "2024-11", "temperature": false, "tool_call": false }, "bytedance/seed-1.6": { "attachment": false, "cost": { "cache_read": 0.05, "input": 0.25, "output": 2 }, "description": "Seed 1.6 is an AI model provided by vercel.", "family": "seed", "id": "bytedance/seed-1.6", "knowledge": "2024-10", "last_updated": "2025-09", "limit": { "context": 256000, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Seed 1.6", "open_weights": false, "reasoning": true, "release_date": "2025-09", "temperature": true, "tool_call": true }, "bytedance/seed-1.8": { "attachment": false, "cost": { "cache_read": 0.05, "input": 0.25, "output": 2 }, "description": "Seed 1.8 is an AI model provided by vercel.", "family": "seed", "id": "bytedance/seed-1.8", "knowledge": "2024-10", "last_updated": "2025-10", "limit": { "context": 256000, "output": 64000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Seed 1.8", "open_weights": false, "reasoning": true, "release_date": "2025-10", "temperature": true, "tool_call": true }, "cohere/command-a": { "attachment": false, "cost": { "input": 2.5, "output": 10 }, "description": "Command A is an AI model provided by vercel.", "family": "command", "id": "cohere/command-a", "knowledge": "2024-10", "last_updated": "2025-03-13", "limit": { "context": 256000, "output": 8000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Command A", "open_weights": false, "reasoning": false, "release_date": "2025-03-13", "temperature": true, "tool_call": true }, "cohere/embed-v4.0": { "attachment": false, "cost": { "input": 0.12, "output": 0 }, "description": "Embed v4.0 is an AI model provided by vercel.", "family": "cohere-embed", "id": "cohere/embed-v4.0", "last_updated": "2025-04-15", "limit": { "context": 8192, "output": 1536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Embed v4.0", "open_weights": false, "reasoning": false, "release_date": "2025-04-15", "temperature": false, "tool_call": false }, "deepseek/deepseek-r1": { "attachment": false, "cost": { "input": 1.35, "output": 5.4 }, "description": "DeepSeek-R1 is an AI model provided by vercel.", "family": "deepseek-thinking", "id": "deepseek/deepseek-r1", "knowledge": "2024-07", "last_updated": "2025-05-29", "limit": { "context": 128000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek-R1", "open_weights": false, "reasoning": true, "release_date": "2025-01-20", "temperature": true, "tool_call": true }, "deepseek/deepseek-v3": { "attachment": false, "cost": { "input": 0.77, "output": 0.77 }, "description": "DeepSeek V3 0324 is an AI model provided by vercel.", "family": "deepseek", "id": "deepseek/deepseek-v3", "knowledge": "2024-07", "last_updated": "2024-12-26", "limit": { "context": 163840, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3 0324", "open_weights": false, "reasoning": false, "release_date": "2024-12-26", "temperature": true, "tool_call": true }, "deepseek/deepseek-v3.1": { "attachment": false, "cost": { "input": 0.3, "output": 1 }, "description": "DeepSeek-V3.1 is an AI model provided by vercel.", "family": "deepseek", "id": "deepseek/deepseek-v3.1", "knowledge": "2024-07", "last_updated": "2025-08-21", "limit": { "context": 163840, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek-V3.1", "open_weights": false, "reasoning": true, "release_date": "2025-08-21", "temperature": true, "tool_call": true }, "deepseek/deepseek-v3.1-terminus": { "attachment": false, "cost": { "input": 0.27, "output": 1 }, "description": "DeepSeek V3.1 Terminus is an AI model provided by vercel.", "family": "deepseek", "id": "deepseek/deepseek-v3.1-terminus", "knowledge": "2025-07", "last_updated": "2025-09-22", "limit": { "context": 131072, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3.1 Terminus", "open_weights": true, "reasoning": true, "release_date": "2025-09-22", "temperature": true, "tool_call": true }, "deepseek/deepseek-v3.2": { "attachment": false, "cost": { "cache_read": 0.22, "input": 0.27, "output": 0.4 }, "description": "DeepSeek V3.2 is an AI model provided by vercel.", "family": "deepseek", "id": "deepseek/deepseek-v3.2", "knowledge": "2024-07", "last_updated": "2025-12-01", "limit": { "context": 163842, "output": 8000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3.2", "open_weights": false, "reasoning": false, "release_date": "2025-12-01", "temperature": true, "tool_call": false }, "deepseek/deepseek-v3.2-exp": { "attachment": false, "cost": { "input": 0.27, "output": 0.4 }, "description": "DeepSeek V3.2 Exp is an AI model provided by vercel.", "family": "deepseek", "id": "deepseek/deepseek-v3.2-exp", "knowledge": "2025-09", "last_updated": "2025-09-29", "limit": { "context": 163840, "output": 163840 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3.2 Exp", "open_weights": false, "reasoning": true, "release_date": "2025-09-29", "temperature": true, "tool_call": true }, "deepseek/deepseek-v3.2-thinking": { "attachment": false, "cost": { "cache_read": 0.03, "input": 0.28, "output": 0.42 }, "description": "DeepSeek V3.2 Thinking is an AI model provided by vercel.", "family": "deepseek-thinking", "id": "deepseek/deepseek-v3.2-thinking", "interleaved": true, "knowledge": "2024-07", "last_updated": "2025-12-01", "limit": { "context": 128000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3.2 Thinking", "open_weights": false, "reasoning": true, "release_date": "2025-12-01", "temperature": true, "tool_call": true }, "deepseek/deepseek-v4-flash": { "attachment": false, "cost": { "cache_read": 0.028, "input": 0.14, "output": 0.28 }, "description": "DeepSeek V4 Flash is an AI model provided by vercel.", "family": "deepseek", "id": "deepseek/deepseek-v4-flash", "last_updated": "2026-04-24", "limit": { "context": 1000000, "output": 384000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V4 Flash", "open_weights": true, "reasoning": true, "release_date": "2026-04-23", "temperature": true, "tool_call": true }, "deepseek/deepseek-v4-pro": { "attachment": false, "cost": { "cache_read": 0.145, "input": 1.74, "output": 3.48 }, "description": "DeepSeek V4 Pro is an AI model provided by vercel.", "family": "deepseek", "id": "deepseek/deepseek-v4-pro", "last_updated": "2026-04-24", "limit": { "context": 1000000, "output": 384000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V4 Pro", "open_weights": true, "reasoning": true, "release_date": "2026-04-23", "temperature": true, "tool_call": true }, "google/gemini-2.0-flash": { "attachment": true, "cost": { "cache_read": 0.025, "input": 0.1, "output": 0.4 }, "description": "Gemini 2.0 Flash is an AI model provided by vercel.", "family": "gemini-flash", "id": "google/gemini-2.0-flash", "knowledge": "2024-06", "last_updated": "2024-12-11", "limit": { "context": 1048576, "output": 8192 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.0 Flash", "open_weights": false, "reasoning": false, "release_date": "2024-12-11", "structured_output": true, "temperature": true, "tool_call": true }, "google/gemini-2.0-flash-lite": { "attachment": true, "cost": { "input": 0.075, "output": 0.3 }, "description": "Gemini 2.0 Flash Lite is an AI model provided by vercel.", "family": "gemini-flash-lite", "id": "google/gemini-2.0-flash-lite", "knowledge": "2024-06", "last_updated": "2024-12-11", "limit": { "context": 1048576, "output": 8192 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.0 Flash Lite", "open_weights": false, "reasoning": false, "release_date": "2024-12-11", "structured_output": true, "temperature": true, "tool_call": true }, "google/gemini-2.5-flash": { "attachment": true, "cost": { "cache_read": 0.03, "input": 0.3, "input_audio": 1, "output": 2.5 }, "description": "Gemini 2.5 Flash is an AI model provided by vercel.", "family": "gemini-flash", "id": "google/gemini-2.5-flash", "knowledge": "2025-01", "last_updated": "2025-06-05", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Flash", "open_weights": false, "reasoning": true, "release_date": "2025-03-20", "structured_output": true, "temperature": true, "tool_call": true }, "google/gemini-2.5-flash-image": { "attachment": false, "cost": { "input": 0.3, "output": 2.5 }, "description": "Nano Banana (Gemini 2.5 Flash Image) is an AI model provided by vercel.", "family": "gemini-flash", "id": "google/gemini-2.5-flash-image", "knowledge": "2025-01", "last_updated": "2025-03-20", "limit": { "context": 32768, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text", "image" ] }, "name": "Nano Banana (Gemini 2.5 Flash Image)", "open_weights": false, "reasoning": false, "release_date": "2025-03-20", "temperature": true, "tool_call": false }, "google/gemini-2.5-flash-image-preview": { "attachment": false, "cost": { "input": 0.3, "output": 2.5 }, "description": "Nano Banana Preview (Gemini 2.5 Flash Image Preview) is an AI model provided by vercel.", "family": "gemini-flash", "id": "google/gemini-2.5-flash-image-preview", "knowledge": "2025-01", "last_updated": "2025-03-20", "limit": { "context": 32768, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text", "image" ] }, "name": "Nano Banana Preview (Gemini 2.5 Flash Image Preview)", "open_weights": false, "reasoning": false, "release_date": "2025-03-20", "temperature": true, "tool_call": false }, "google/gemini-2.5-flash-lite": { "attachment": true, "cost": { "cache_read": 0.01, "input": 0.1, "output": 0.4 }, "description": "Gemini 2.5 Flash Lite is an AI model provided by vercel.", "family": "gemini-flash-lite", "id": "google/gemini-2.5-flash-lite", "knowledge": "2025-01", "last_updated": "2025-06-17", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Flash Lite", "open_weights": false, "reasoning": true, "release_date": "2025-06-17", "temperature": true, "tool_call": true }, "google/gemini-2.5-flash-lite-preview-09-2025": { "attachment": true, "cost": { "cache_read": 0.01, "input": 0.1, "output": 0.4 }, "description": "Gemini 2.5 Flash Lite Preview 09-25 is an AI model provided by vercel.", "family": "gemini-flash-lite", "id": "google/gemini-2.5-flash-lite-preview-09-2025", "knowledge": "2025-01", "last_updated": "2025-09-25", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Flash Lite Preview 09-25", "open_weights": false, "reasoning": true, "release_date": "2025-09-25", "temperature": true, "tool_call": true }, "google/gemini-2.5-flash-preview-09-2025": { "attachment": true, "cost": { "cache_read": 0.03, "cache_write": 0.383, "input": 0.3, "output": 2.5 }, "description": "Gemini 2.5 Flash Preview 09-25 is an AI model provided by vercel.", "family": "gemini-flash", "id": "google/gemini-2.5-flash-preview-09-2025", "knowledge": "2025-01", "last_updated": "2025-09-25", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Flash Preview 09-25", "open_weights": false, "reasoning": true, "release_date": "2025-09-25", "temperature": true, "tool_call": true }, "google/gemini-2.5-pro": { "attachment": true, "cost": { "cache_read": 0.125, "context_over_200k": { "cache_read": 0.25, "input": 2.5, "output": 15 }, "input": 1.25, "output": 10, "tiers": [ { "cache_read": 0.25, "input": 2.5, "output": 15, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Gemini 2.5 Pro is an AI model provided by vercel.", "family": "gemini-pro", "id": "google/gemini-2.5-pro", "knowledge": "2025-01", "last_updated": "2025-06-05", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "Gemini 2.5 Pro", "open_weights": false, "reasoning": true, "release_date": "2025-03-20", "structured_output": true, "temperature": true, "tool_call": true }, "google/gemini-3-flash": { "attachment": true, "cost": { "cache_read": 0.05, "input": 0.5, "output": 3 }, "description": "Gemini 3 Flash is an AI model provided by vercel.", "family": "gemini-flash", "id": "google/gemini-3-flash", "knowledge": "2025-03", "last_updated": "2025-12-17", "limit": { "context": 1000000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Gemini 3 Flash", "open_weights": false, "reasoning": true, "release_date": "2025-12-17", "temperature": true, "tool_call": true }, "google/gemini-3-pro-image": { "attachment": false, "cost": { "input": 2, "output": 120 }, "description": "Nano Banana Pro (Gemini 3 Pro Image) is an AI model provided by vercel.", "family": "gemini-pro", "id": "google/gemini-3-pro-image", "knowledge": "2025-03", "last_updated": "2025-09", "limit": { "context": 65536, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text", "image" ] }, "name": "Nano Banana Pro (Gemini 3 Pro Image)", "open_weights": false, "reasoning": false, "release_date": "2025-09", "temperature": true, "tool_call": false }, "google/gemini-3-pro-preview": { "attachment": true, "cost": { "cache_read": 0.2, "context_over_200k": { "cache_read": 0.4, "input": 4, "output": 18 }, "input": 2, "output": 12, "tiers": [ { "cache_read": 0.4, "input": 4, "output": 18, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Gemini 3 Pro Preview is an AI model provided by vercel.", "family": "gemini-pro", "id": "google/gemini-3-pro-preview", "knowledge": "2025-01", "last_updated": "2025-11-18", "limit": { "context": 1000000, "output": 64000 }, "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "name": "Gemini 3 Pro Preview", "open_weights": false, "reasoning": true, "release_date": "2025-11-18", "temperature": true, "tool_call": true }, "google/gemini-3.1-flash-image-preview": { "attachment": true, "cost": { "input": 0.5, "output": 3 }, "description": "Gemini 3.1 Flash Image Preview (Nano Banana 2) is an AI model provided by vercel.", "family": "gemini", "id": "google/gemini-3.1-flash-image-preview", "last_updated": "2026-03-06", "limit": { "context": 131072, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text", "image" ] }, "name": "Gemini 3.1 Flash Image Preview (Nano Banana 2)", "open_weights": false, "reasoning": true, "release_date": "2026-02-26", "temperature": true, "tool_call": false }, "google/gemini-3.1-flash-lite": { "attachment": true, "cost": { "cache_read": 0.03, "input": 0.25, "output": 1.5 }, "description": "Gemini 3.1 Flash Lite is an AI model provided by vercel.", "family": "gemini", "id": "google/gemini-3.1-flash-lite", "last_updated": "2026-05-08", "limit": { "context": 1000000, "output": 65000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Gemini 3.1 Flash Lite", "open_weights": false, "reasoning": true, "release_date": "2026-05-07", "temperature": true, "tool_call": true }, "google/gemini-3.1-flash-lite-preview": { "attachment": true, "cost": { "cache_read": 0.025, "cache_write": 1, "input": 0.25, "output": 1.5 }, "description": "Gemini 3.1 Flash Lite Preview is an AI model provided by vercel.", "family": "gemini", "id": "google/gemini-3.1-flash-lite-preview", "last_updated": "2026-03-06", "limit": { "context": 1000000, "output": 65000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Gemini 3.1 Flash Lite Preview", "open_weights": false, "reasoning": true, "release_date": "2026-03-03", "temperature": true, "tool_call": true }, "google/gemini-3.1-pro-preview": { "attachment": true, "cost": { "cache_read": 0.2, "input": 2, "output": 12 }, "description": "Gemini 3.1 Pro Preview is an AI model provided by vercel.", "family": "gemini", "id": "google/gemini-3.1-pro-preview", "last_updated": "2026-02-24", "limit": { "context": 1000000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Gemini 3.1 Pro Preview", "open_weights": false, "reasoning": true, "release_date": "2026-02-19", "temperature": true, "tool_call": true }, "google/gemini-embedding-001": { "attachment": false, "cost": { "input": 0.15, "output": 0 }, "description": "Gemini Embedding 001 is an AI model provided by vercel.", "family": "gemini-embedding", "id": "google/gemini-embedding-001", "last_updated": "2025-05-20", "limit": { "context": 8192, "output": 1536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Gemini Embedding 001", "open_weights": false, "reasoning": false, "release_date": "2025-05-20", "temperature": false, "tool_call": false }, "google/gemini-embedding-2": { "attachment": false, "description": "Gemini Embedding 2 is an AI model provided by vercel.", "family": "gemini-embedding", "id": "google/gemini-embedding-2", "last_updated": "2026-03-23", "limit": { "context": 0, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Gemini Embedding 2", "open_weights": false, "reasoning": false, "release_date": "2026-03-10", "temperature": true, "tool_call": false }, "google/gemma-4-26b-a4b-it": { "attachment": true, "cost": { "input": 0.13, "output": 0.39999999999999997 }, "description": "Gemma 4 26B A4B IT is an AI model provided by vercel.", "family": "gemma", "id": "google/gemma-4-26b-a4b-it", "last_updated": "2026-04-03", "limit": { "context": 262144, "output": 131072 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Gemma 4 26B A4B IT", "open_weights": false, "reasoning": true, "release_date": "2026-04-02", "temperature": true, "tool_call": true }, "google/gemma-4-31b-it": { "attachment": true, "cost": { "input": 0.14, "output": 0.39999999999999997 }, "description": "Gemma 4 31B IT is an AI model provided by vercel.", "family": "gemma", "id": "google/gemma-4-31b-it", "last_updated": "2026-04-03", "limit": { "context": 262144, "output": 131072 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Gemma 4 31B IT", "open_weights": false, "reasoning": true, "release_date": "2026-04-02", "temperature": true, "tool_call": true }, "google/imagen-4.0-fast-generate-001": { "attachment": false, "description": "Imagen 4 Fast is an AI model provided by vercel.", "family": "imagen", "id": "google/imagen-4.0-fast-generate-001", "last_updated": "2025-06", "limit": { "context": 480, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "name": "Imagen 4 Fast", "open_weights": false, "reasoning": false, "release_date": "2025-06", "temperature": false, "tool_call": false }, "google/imagen-4.0-generate-001": { "attachment": false, "description": "Imagen 4 is an AI model provided by vercel.", "family": "imagen", "id": "google/imagen-4.0-generate-001", "last_updated": "2025-05-22", "limit": { "context": 480, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "name": "Imagen 4", "open_weights": false, "reasoning": false, "release_date": "2025-05-22", "temperature": false, "tool_call": false }, "google/imagen-4.0-ultra-generate-001": { "attachment": false, "description": "Imagen 4 Ultra is an AI model provided by vercel.", "family": "imagen", "id": "google/imagen-4.0-ultra-generate-001", "last_updated": "2025-05-24", "limit": { "context": 480, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "name": "Imagen 4 Ultra", "open_weights": false, "reasoning": false, "release_date": "2025-05-24", "temperature": false, "tool_call": false }, "google/text-embedding-005": { "attachment": false, "cost": { "input": 0.03, "output": 0 }, "description": "Text Embedding 005 is an AI model provided by vercel.", "family": "text-embedding", "id": "google/text-embedding-005", "last_updated": "2024-08", "limit": { "context": 8192, "output": 1536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Text Embedding 005", "open_weights": false, "reasoning": false, "release_date": "2024-08", "temperature": false, "tool_call": false }, "google/text-multilingual-embedding-002": { "attachment": false, "cost": { "input": 0.03, "output": 0 }, "description": "Text Multilingual Embedding 002 is an AI model provided by vercel.", "family": "text-embedding", "id": "google/text-multilingual-embedding-002", "last_updated": "2024-03", "limit": { "context": 8192, "output": 1536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Text Multilingual Embedding 002", "open_weights": false, "reasoning": false, "release_date": "2024-03", "temperature": false, "tool_call": false }, "inception/mercury-2": { "attachment": false, "cost": { "cache_read": 0.024999999999999998, "input": 0.25, "output": 0.75 }, "description": "Mercury 2 is an AI model provided by vercel.", "family": "mercury", "id": "inception/mercury-2", "last_updated": "2026-03-06", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mercury 2", "open_weights": false, "reasoning": true, "release_date": "2026-02-24", "temperature": true, "tool_call": true }, "inception/mercury-coder-small": { "attachment": false, "cost": { "input": 0.25, "output": 1 }, "description": "Mercury Coder Small Beta is an AI model provided by vercel.", "family": "mercury", "id": "inception/mercury-coder-small", "last_updated": "2026-05-01", "limit": { "context": 32000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mercury Coder Small Beta", "open_weights": false, "reasoning": false, "release_date": "2025-02-26", "temperature": true, "tool_call": true }, "inception/mercury-edit-2": { "attachment": false, "cost": { "cache_read": 0.025, "input": 0.25, "output": 0.75 }, "description": "Mercury Edit 2 is an AI model provided by vercel.", "id": "inception/mercury-edit-2", "last_updated": "2026-03-30", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mercury Edit 2", "open_weights": false, "reasoning": true, "release_date": "2026-03-30", "temperature": true, "tool_call": false }, "interfaze/interfaze-beta": { "attachment": false, "cost": { "input": 1.5, "output": 3.5 }, "description": "Interfaze Beta is an AI model provided by vercel.", "id": "interfaze/interfaze-beta", "last_updated": "2026-04-29", "limit": { "context": 1000000, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Interfaze Beta", "open_weights": false, "reasoning": true, "release_date": "2025-10-07", "temperature": true, "tool_call": false }, "kwaipilot/kat-coder-pro-v1": { "attachment": false, "description": "KAT-Coder-Pro V1 is an AI model provided by vercel.", "family": "kat-coder", "id": "kwaipilot/kat-coder-pro-v1", "knowledge": "2024-10", "last_updated": "2025-10-24", "limit": { "context": 256000, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "KAT-Coder-Pro V1", "open_weights": false, "reasoning": true, "release_date": "2025-10-24", "temperature": true, "tool_call": false }, "kwaipilot/kat-coder-pro-v2": { "attachment": false, "cost": { "cache_read": 0.06, "input": 0.3, "output": 1.2 }, "description": "Kat Coder Pro V2 is an AI model provided by vercel.", "family": "kat-coder", "id": "kwaipilot/kat-coder-pro-v2", "last_updated": "2026-03-30", "limit": { "context": 256000, "output": 256000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kat Coder Pro V2", "open_weights": false, "reasoning": true, "release_date": "2026-03-27", "temperature": true, "tool_call": true }, "meituan/longcat-flash-chat": { "attachment": false, "description": "LongCat Flash Chat is an AI model provided by vercel.", "family": "longcat", "id": "meituan/longcat-flash-chat", "knowledge": "2024-10", "last_updated": "2025-08-30", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "LongCat Flash Chat", "open_weights": false, "reasoning": false, "release_date": "2025-08-30", "temperature": true, "tool_call": true }, "meituan/longcat-flash-thinking": { "attachment": false, "cost": { "input": 0.15, "output": 1.5 }, "description": "LongCat Flash Thinking is an AI model provided by vercel.", "family": "longcat", "id": "meituan/longcat-flash-thinking", "knowledge": "2024-10", "last_updated": "2025-09-23", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "LongCat Flash Thinking", "open_weights": false, "reasoning": true, "release_date": "2025-09-23", "temperature": true, "tool_call": true }, "meituan/longcat-flash-thinking-2601": { "attachment": false, "description": "LongCat Flash Thinking 2601 is an AI model provided by vercel.", "family": "longcat", "id": "meituan/longcat-flash-thinking-2601", "last_updated": "2026-03-13", "limit": { "context": 32768, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "LongCat Flash Thinking 2601", "open_weights": false, "reasoning": true, "release_date": "2026-03-13", "temperature": true, "tool_call": false }, "meta/llama-3.1-70b": { "attachment": false, "cost": { "input": 0.4, "output": 0.4 }, "description": "Llama 3.1 70B Instruct is an AI model provided by vercel.", "family": "llama", "id": "meta/llama-3.1-70b", "knowledge": "2023-12", "last_updated": "2024-07-23", "limit": { "context": 131072, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.1 70B Instruct", "open_weights": false, "reasoning": false, "release_date": "2024-07-23", "temperature": true, "tool_call": true }, "meta/llama-3.1-8b": { "attachment": false, "cost": { "input": 0.03, "output": 0.05 }, "description": "Llama 3.1 8B Instruct is an AI model provided by vercel.", "family": "llama", "id": "meta/llama-3.1-8b", "knowledge": "2023-12", "last_updated": "2024-07-23", "limit": { "context": 131072, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.1 8B Instruct", "open_weights": false, "reasoning": false, "release_date": "2024-07-23", "temperature": true, "tool_call": true }, "meta/llama-3.2-11b": { "attachment": true, "cost": { "input": 0.16, "output": 0.16 }, "description": "Llama 3.2 11B Vision Instruct is an AI model provided by vercel.", "family": "llama", "id": "meta/llama-3.2-11b", "knowledge": "2023-12", "last_updated": "2024-09-25", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Llama 3.2 11B Vision Instruct", "open_weights": false, "reasoning": false, "release_date": "2024-09-25", "temperature": true, "tool_call": true }, "meta/llama-3.2-1b": { "attachment": false, "cost": { "input": 0.1, "output": 0.1 }, "description": "Llama 3.2 1B Instruct is an AI model provided by vercel.", "family": "llama", "id": "meta/llama-3.2-1b", "knowledge": "2023-12", "last_updated": "2024-09-18", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.2 1B Instruct", "open_weights": false, "reasoning": false, "release_date": "2024-09-18", "temperature": true, "tool_call": false }, "meta/llama-3.2-3b": { "attachment": false, "cost": { "input": 0.15, "output": 0.15 }, "description": "Llama 3.2 3B Instruct is an AI model provided by vercel.", "family": "llama", "id": "meta/llama-3.2-3b", "knowledge": "2023-12", "last_updated": "2024-09-18", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.2 3B Instruct", "open_weights": false, "reasoning": false, "release_date": "2024-09-18", "temperature": true, "tool_call": false }, "meta/llama-3.2-90b": { "attachment": true, "cost": { "input": 0.72, "output": 0.72 }, "description": "Llama 3.2 90B Vision Instruct is an AI model provided by vercel.", "family": "llama", "id": "meta/llama-3.2-90b", "knowledge": "2023-12", "last_updated": "2024-09-25", "limit": { "context": 128000, "output": 8192 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Llama 3.2 90B Vision Instruct", "open_weights": false, "reasoning": false, "release_date": "2024-09-25", "temperature": true, "tool_call": true }, "meta/llama-3.3-70b": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Llama-3.3-70B-Instruct is an AI model provided by vercel.", "family": "llama", "id": "meta/llama-3.3-70b", "knowledge": "2023-12", "last_updated": "2024-12-06", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama-3.3-70B-Instruct", "open_weights": true, "reasoning": false, "release_date": "2024-12-06", "temperature": true, "tool_call": true }, "meta/llama-4-maverick": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Llama-4-Maverick-17B-128E-Instruct-FP8 is an AI model provided by vercel.", "family": "llama", "id": "meta/llama-4-maverick", "knowledge": "2024-08", "last_updated": "2025-04-05", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Llama-4-Maverick-17B-128E-Instruct-FP8", "open_weights": true, "reasoning": false, "release_date": "2025-04-05", "temperature": true, "tool_call": true }, "meta/llama-4-scout": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "Llama-4-Scout-17B-16E-Instruct-FP8 is an AI model provided by vercel.", "family": "llama", "id": "meta/llama-4-scout", "knowledge": "2024-08", "last_updated": "2025-04-05", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Llama-4-Scout-17B-16E-Instruct-FP8", "open_weights": true, "reasoning": false, "release_date": "2025-04-05", "temperature": true, "tool_call": true }, "minimax/minimax-m2": { "attachment": false, "cost": { "cache_read": 0.03, "cache_write": 0.38, "input": 0.27, "output": 1.15 }, "description": "MiniMax M2 is an AI model provided by vercel.", "family": "minimax", "id": "minimax/minimax-m2", "interleaved": true, "knowledge": "2024-10", "last_updated": "2025-10-27", "limit": { "context": 262114, "output": 262114 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M2", "open_weights": true, "reasoning": true, "release_date": "2025-10-27", "temperature": true, "tool_call": true }, "minimax/minimax-m2.1": { "attachment": false, "cost": { "cache_read": 0.03, "cache_write": 0.38, "input": 0.3, "output": 1.2 }, "description": "MiniMax M2.1 is an AI model provided by vercel.", "family": "minimax", "id": "minimax/minimax-m2.1", "interleaved": true, "knowledge": "2024-10", "last_updated": "2025-10-27", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M2.1", "open_weights": false, "reasoning": true, "release_date": "2025-10-27", "temperature": true, "tool_call": true }, "minimax/minimax-m2.1-lightning": { "attachment": false, "cost": { "cache_read": 0.03, "cache_write": 0.38, "input": 0.3, "output": 2.4 }, "description": "MiniMax M2.1 Lightning is an AI model provided by vercel.", "family": "minimax", "id": "minimax/minimax-m2.1-lightning", "knowledge": "2024-10", "last_updated": "2025-10-27", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M2.1 Lightning", "open_weights": false, "reasoning": true, "release_date": "2025-10-27", "temperature": true, "tool_call": true }, "minimax/minimax-m2.5": { "attachment": false, "cost": { "cache_read": 0.03, "cache_write": 0.375, "input": 0.3, "output": 1.2 }, "description": "MiniMax M2.5 is an AI model provided by vercel.", "family": "minimax", "id": "minimax/minimax-m2.5", "last_updated": "2026-02-19", "limit": { "context": 204800, "output": 131000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M2.5", "open_weights": false, "reasoning": true, "release_date": "2026-02-12", "temperature": true, "tool_call": true }, "minimax/minimax-m2.5-highspeed": { "attachment": false, "cost": { "cache_read": 0.03, "cache_write": 0.375, "input": 0.6, "output": 2.4 }, "description": "MiniMax M2.5 High Speed is an AI model provided by vercel.", "family": "minimax", "id": "minimax/minimax-m2.5-highspeed", "last_updated": "2026-03-13", "limit": { "context": 0, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M2.5 High Speed", "open_weights": false, "reasoning": true, "release_date": "2026-02-12", "temperature": true, "tool_call": true }, "minimax/minimax-m2.7": { "attachment": true, "cost": { "cache_read": 0.06, "cache_write": 0.375, "input": 0.3, "output": 1.2 }, "description": "Minimax M2.7 is an AI model provided by vercel.", "family": "minimax", "id": "minimax/minimax-m2.7", "last_updated": "2026-03-18", "limit": { "context": 204800, "output": 131000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Minimax M2.7", "open_weights": true, "reasoning": true, "release_date": "2026-03-18", "temperature": true, "tool_call": true }, "minimax/minimax-m2.7-highspeed": { "attachment": true, "cost": { "cache_read": 0.06, "cache_write": 0.375, "input": 0.6, "output": 2.4 }, "description": "MiniMax M2.7 High Speed is an AI model provided by vercel.", "family": "minimax", "id": "minimax/minimax-m2.7-highspeed", "last_updated": "2026-03-18", "limit": { "context": 204800, "output": 131100 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "MiniMax M2.7 High Speed", "open_weights": true, "reasoning": true, "release_date": "2026-03-18", "temperature": true, "tool_call": true }, "mistral/codestral": { "attachment": false, "cost": { "input": 0.3, "output": 0.9 }, "description": "Codestral (latest) is an AI model provided by vercel.", "family": "codestral", "id": "mistral/codestral", "knowledge": "2024-10", "last_updated": "2025-01-04", "limit": { "context": 256000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Codestral (latest)", "open_weights": true, "reasoning": false, "release_date": "2024-05-29", "temperature": true, "tool_call": true }, "mistral/codestral-embed": { "attachment": false, "cost": { "input": 0.15, "output": 0 }, "description": "Codestral Embed is an AI model provided by vercel.", "family": "codestral-embed", "id": "mistral/codestral-embed", "last_updated": "2025-05-28", "limit": { "context": 8192, "output": 1536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Codestral Embed", "open_weights": false, "reasoning": false, "release_date": "2025-05-28", "temperature": false, "tool_call": false }, "mistral/devstral-2": { "attachment": false, "description": "Devstral 2 is an AI model provided by vercel.", "family": "devstral", "id": "mistral/devstral-2", "knowledge": "2024-10", "last_updated": "2025-12-09", "limit": { "context": 256000, "output": 256000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Devstral 2", "open_weights": false, "reasoning": false, "release_date": "2025-12-09", "temperature": true, "tool_call": true }, "mistral/devstral-small": { "attachment": false, "cost": { "input": 0.1, "output": 0.3 }, "description": "Devstral Small 1.1 is an AI model provided by vercel.", "family": "devstral", "id": "mistral/devstral-small", "knowledge": "2024-10", "last_updated": "2025-05-07", "limit": { "context": 128000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Devstral Small 1.1", "open_weights": false, "reasoning": false, "release_date": "2025-05-07", "temperature": true, "tool_call": true }, "mistral/devstral-small-2": { "attachment": false, "description": "Devstral Small 2 is an AI model provided by vercel.", "family": "devstral", "id": "mistral/devstral-small-2", "knowledge": "2024-10", "last_updated": "2025-05-07", "limit": { "context": 256000, "output": 256000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Devstral Small 2", "open_weights": false, "reasoning": false, "release_date": "2025-05-07", "temperature": true, "tool_call": true }, "mistral/magistral-medium": { "attachment": false, "cost": { "input": 2, "output": 5 }, "description": "Magistral Medium (latest) is an AI model provided by vercel.", "family": "magistral-medium", "id": "mistral/magistral-medium", "knowledge": "2025-06", "last_updated": "2025-03-20", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Magistral Medium (latest)", "open_weights": true, "reasoning": true, "release_date": "2025-03-17", "temperature": true, "tool_call": true }, "mistral/magistral-small": { "attachment": false, "cost": { "input": 0.5, "output": 1.5 }, "description": "Magistral Small is an AI model provided by vercel.", "family": "magistral-small", "id": "mistral/magistral-small", "knowledge": "2025-06", "last_updated": "2025-03-17", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Magistral Small", "open_weights": true, "reasoning": true, "release_date": "2025-03-17", "temperature": true, "tool_call": true }, "mistral/ministral-14b": { "attachment": true, "cost": { "input": 0.2, "output": 0.2 }, "description": "Ministral 14B is an AI model provided by vercel.", "family": "ministral", "id": "mistral/ministral-14b", "knowledge": "2024-10", "last_updated": "2025-12-01", "limit": { "context": 256000, "output": 256000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Ministral 14B", "open_weights": false, "reasoning": false, "release_date": "2025-12-01", "temperature": true, "tool_call": false }, "mistral/ministral-3b": { "attachment": false, "cost": { "input": 0.04, "output": 0.04 }, "description": "Ministral 3B (latest) is an AI model provided by vercel.", "family": "ministral", "id": "mistral/ministral-3b", "knowledge": "2024-10", "last_updated": "2024-10-04", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Ministral 3B (latest)", "open_weights": true, "reasoning": false, "release_date": "2024-10-01", "temperature": true, "tool_call": true }, "mistral/ministral-8b": { "attachment": false, "cost": { "input": 0.1, "output": 0.1 }, "description": "Ministral 8B (latest) is an AI model provided by vercel.", "family": "ministral", "id": "mistral/ministral-8b", "knowledge": "2024-10", "last_updated": "2024-10-04", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Ministral 8B (latest)", "open_weights": true, "reasoning": false, "release_date": "2024-10-01", "temperature": true, "tool_call": true }, "mistral/mistral-embed": { "attachment": false, "cost": { "input": 0.1, "output": 0 }, "description": "Mistral Embed is an AI model provided by vercel.", "family": "mistral-embed", "id": "mistral/mistral-embed", "last_updated": "2023-12-11", "limit": { "context": 8192, "output": 1536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral Embed", "open_weights": false, "reasoning": false, "release_date": "2023-12-11", "temperature": false, "tool_call": false }, "mistral/mistral-large-3": { "attachment": true, "cost": { "input": 0.5, "output": 1.5 }, "description": "Mistral Large 3 is an AI model provided by vercel.", "family": "mistral-large", "id": "mistral/mistral-large-3", "knowledge": "2024-10", "last_updated": "2025-12-02", "limit": { "context": 256000, "output": 256000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Mistral Large 3", "open_weights": false, "reasoning": false, "release_date": "2025-12-02", "temperature": true, "tool_call": false }, "mistral/mistral-medium": { "attachment": true, "cost": { "input": 0.4, "output": 2 }, "description": "Mistral Medium 3.1 is an AI model provided by vercel.", "family": "mistral-medium", "id": "mistral/mistral-medium", "knowledge": "2024-10", "last_updated": "2025-05-07", "limit": { "context": 128000, "output": 64000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Mistral Medium 3.1", "open_weights": false, "reasoning": false, "release_date": "2025-05-07", "temperature": true, "tool_call": true }, "mistral/mistral-nemo": { "attachment": false, "cost": { "input": 0.04, "output": 0.17 }, "description": "Mistral Nemo is an AI model provided by vercel.", "family": "mistral-nemo", "id": "mistral/mistral-nemo", "knowledge": "2024-04", "last_updated": "2024-07-01", "limit": { "context": 60288, "output": 16000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mistral Nemo", "open_weights": false, "reasoning": false, "release_date": "2024-07-01", "temperature": true, "tool_call": true }, "mistral/mistral-small": { "attachment": true, "cost": { "input": 0.15, "output": 0.6 }, "description": "Mistral Small (latest) is an AI model provided by vercel.", "family": "mistral-small", "id": "mistral/mistral-small", "knowledge": "2025-06", "last_updated": "2026-03-16", "limit": { "context": 256000, "output": 256000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Mistral Small (latest)", "open_weights": true, "reasoning": true, "release_date": "2026-03-16", "temperature": true, "tool_call": true }, "mistral/mixtral-8x22b-instruct": { "attachment": false, "cost": { "input": 2, "output": 6 }, "description": "Mixtral 8x22B is an AI model provided by vercel.", "family": "mixtral", "id": "mistral/mixtral-8x22b-instruct", "knowledge": "2024-04", "last_updated": "2024-04-17", "limit": { "context": 64000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Mixtral 8x22B", "open_weights": true, "reasoning": false, "release_date": "2024-04-17", "temperature": true, "tool_call": true }, "mistral/pixtral-12b": { "attachment": true, "cost": { "input": 0.15, "output": 0.15 }, "description": "Pixtral 12B is an AI model provided by vercel.", "family": "pixtral", "id": "mistral/pixtral-12b", "knowledge": "2024-09", "last_updated": "2024-09-01", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Pixtral 12B", "open_weights": true, "reasoning": false, "release_date": "2024-09-01", "temperature": true, "tool_call": true }, "mistral/pixtral-large": { "attachment": true, "cost": { "input": 2, "output": 6 }, "description": "Pixtral Large (latest) is an AI model provided by vercel.", "family": "pixtral", "id": "mistral/pixtral-large", "knowledge": "2024-11", "last_updated": "2024-11-04", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Pixtral Large (latest)", "open_weights": true, "reasoning": false, "release_date": "2024-11-01", "temperature": true, "tool_call": true }, "moonshotai/kimi-k2": { "attachment": false, "cost": { "input": 1, "output": 3 }, "description": "Kimi K2 Instruct is an AI model provided by vercel.", "family": "kimi", "id": "moonshotai/kimi-k2", "knowledge": "2024-10", "last_updated": "2025-07-14", "limit": { "context": 131072, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-07-14", "status": "deprecated", "temperature": true, "tool_call": true }, "moonshotai/kimi-k2-0905": { "attachment": false, "cost": { "input": 0.6, "output": 2.5 }, "description": "Kimi K2 0905 is an AI model provided by vercel.", "family": "kimi", "id": "moonshotai/kimi-k2-0905", "knowledge": "2024-10", "last_updated": "2025-09-05", "limit": { "context": 131072, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 0905", "open_weights": false, "reasoning": false, "release_date": "2025-09-05", "temperature": true, "tool_call": false }, "moonshotai/kimi-k2-thinking": { "attachment": false, "cost": { "cache_read": 0.14, "input": 0.47, "output": 2 }, "description": "Kimi K2 Thinking is an AI model provided by vercel.", "family": "kimi-thinking", "id": "moonshotai/kimi-k2-thinking", "interleaved": true, "knowledge": "2024-08", "last_updated": "2025-11-06", "limit": { "context": 216144, "output": 216144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 Thinking", "open_weights": false, "reasoning": true, "release_date": "2025-11-06", "temperature": true, "tool_call": true }, "moonshotai/kimi-k2-thinking-turbo": { "attachment": false, "cost": { "cache_read": 0.15, "input": 1.15, "output": 8 }, "description": "Kimi K2 Thinking Turbo is an AI model provided by vercel.", "family": "kimi-thinking", "id": "moonshotai/kimi-k2-thinking-turbo", "interleaved": true, "knowledge": "2024-08", "last_updated": "2025-11-06", "limit": { "context": 262114, "output": 262114 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 Thinking Turbo", "open_weights": false, "reasoning": true, "release_date": "2025-11-06", "temperature": true, "tool_call": true }, "moonshotai/kimi-k2-turbo": { "attachment": false, "cost": { "input": 2.4, "output": 10 }, "description": "Kimi K2 Turbo is an AI model provided by vercel.", "family": "kimi", "id": "moonshotai/kimi-k2-turbo", "knowledge": "2024-08", "last_updated": "2025-09-05", "limit": { "context": 256000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 Turbo", "open_weights": false, "reasoning": false, "release_date": "2025-09-05", "temperature": true, "tool_call": true }, "moonshotai/kimi-k2.5": { "attachment": true, "cost": { "input": 0.6, "output": 1.2 }, "description": "Kimi K2.5 is an AI model provided by vercel.", "family": "kimi", "id": "moonshotai/kimi-k2.5", "interleaved": true, "knowledge": "2025-01", "last_updated": "2026-01-26", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Kimi K2.5", "open_weights": true, "reasoning": true, "release_date": "2026-01-26", "temperature": true, "tool_call": true }, "moonshotai/kimi-k2.6": { "attachment": true, "cost": { "cache_read": 0.16, "input": 0.95, "output": 4 }, "description": "Kimi K2.6 is an AI model provided by vercel.", "family": "kimi-k2.6", "id": "moonshotai/kimi-k2.6", "last_updated": "2026-04-24", "limit": { "context": 262000, "output": 262000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Kimi K2.6", "open_weights": true, "reasoning": true, "release_date": "2026-04-20", "temperature": true, "tool_call": true }, "morph/morph-v3-fast": { "attachment": false, "cost": { "input": 0.8, "output": 1.2 }, "description": "Morph v3 Fast is an AI model provided by vercel.", "family": "morph", "id": "morph/morph-v3-fast", "last_updated": "2024-08-15", "limit": { "context": 16000, "output": 16000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Morph v3 Fast", "open_weights": false, "reasoning": false, "release_date": "2024-08-15", "temperature": false, "tool_call": false }, "morph/morph-v3-large": { "attachment": false, "cost": { "input": 0.9, "output": 1.9 }, "description": "Morph v3 Large is an AI model provided by vercel.", "family": "morph", "id": "morph/morph-v3-large", "last_updated": "2024-08-15", "limit": { "context": 32000, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Morph v3 Large", "open_weights": false, "reasoning": false, "release_date": "2024-08-15", "temperature": false, "tool_call": false }, "nvidia/nemotron-3-nano-30b-a3b": { "attachment": false, "cost": { "input": 0.06, "output": 0.24 }, "description": "Nemotron 3 Nano 30B A3B is an AI model provided by vercel.", "family": "nemotron", "id": "nvidia/nemotron-3-nano-30b-a3b", "knowledge": "2024-10", "last_updated": "2024-12", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Nemotron 3 Nano 30B A3B", "open_weights": false, "reasoning": true, "release_date": "2024-12", "temperature": true, "tool_call": false }, "nvidia/nemotron-3-super-120b-a12b": { "attachment": false, "cost": { "input": 0.15, "output": 0.65 }, "description": "NVIDIA Nemotron 3 Super 120B A12B is an AI model provided by vercel.", "family": "nemotron", "id": "nvidia/nemotron-3-super-120b-a12b", "last_updated": "2026-03-30", "limit": { "context": 256000, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "NVIDIA Nemotron 3 Super 120B A12B", "open_weights": false, "reasoning": false, "release_date": "2026-03-18", "temperature": true, "tool_call": false }, "nvidia/nemotron-nano-12b-v2-vl": { "attachment": true, "cost": { "input": 0.2, "output": 0.6 }, "description": "Nvidia Nemotron Nano 12B V2 VL is an AI model provided by vercel.", "family": "nemotron", "id": "nvidia/nemotron-nano-12b-v2-vl", "knowledge": "2024-10", "last_updated": "2024-12", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Nvidia Nemotron Nano 12B V2 VL", "open_weights": false, "reasoning": true, "release_date": "2024-12", "temperature": true, "tool_call": true }, "nvidia/nemotron-nano-9b-v2": { "attachment": false, "cost": { "input": 0.04, "output": 0.16 }, "description": "Nvidia Nemotron Nano 9B V2 is an AI model provided by vercel.", "family": "nemotron", "id": "nvidia/nemotron-nano-9b-v2", "knowledge": "2024-10", "last_updated": "2025-08-18", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Nvidia Nemotron Nano 9B V2", "open_weights": false, "reasoning": true, "release_date": "2025-08-18", "temperature": true, "tool_call": true }, "openai/codex-mini": { "attachment": true, "cost": { "cache_read": 0.38, "input": 1.5, "output": 6 }, "description": "Codex Mini is an AI model provided by vercel.", "family": "gpt-codex-mini", "id": "openai/codex-mini", "knowledge": "2024-10", "last_updated": "2025-05-16", "limit": { "context": 200000, "input": 100000, "output": 100000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Codex Mini", "open_weights": false, "reasoning": true, "release_date": "2025-05-16", "temperature": true, "tool_call": true }, "openai/gpt-3.5-turbo": { "attachment": false, "cost": { "input": 0.5, "output": 1.5 }, "description": "GPT-3.5 Turbo is an AI model provided by vercel.", "family": "gpt", "id": "openai/gpt-3.5-turbo", "knowledge": "2021-09", "last_updated": "2023-03-01", "limit": { "context": 16385, "input": 12289, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT-3.5 Turbo", "open_weights": false, "reasoning": false, "release_date": "2023-03-01", "temperature": true, "tool_call": false }, "openai/gpt-3.5-turbo-instruct": { "attachment": false, "cost": { "input": 1.5, "output": 2 }, "description": "GPT-3.5 Turbo Instruct is an AI model provided by vercel.", "family": "gpt", "id": "openai/gpt-3.5-turbo-instruct", "knowledge": "2021-09", "last_updated": "2023-03-01", "limit": { "context": 8192, "input": 4096, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT-3.5 Turbo Instruct", "open_weights": false, "reasoning": false, "release_date": "2023-03-01", "temperature": true, "tool_call": false }, "openai/gpt-4-turbo": { "attachment": true, "cost": { "input": 10, "output": 30 }, "description": "GPT-4 Turbo is an AI model provided by vercel.", "family": "gpt", "id": "openai/gpt-4-turbo", "knowledge": "2023-12", "last_updated": "2024-04-09", "limit": { "context": 128000, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4 Turbo", "open_weights": false, "reasoning": false, "release_date": "2023-11-06", "structured_output": false, "temperature": true, "tool_call": true }, "openai/gpt-4.1": { "attachment": true, "cost": { "cache_read": 0.5, "input": 2, "output": 8 }, "description": "GPT-4.1 is an AI model provided by vercel.", "family": "gpt", "id": "openai/gpt-4.1", "knowledge": "2024-04", "last_updated": "2025-04-14", "limit": { "context": 1047576, "output": 32768 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-4.1", "open_weights": false, "reasoning": false, "release_date": "2025-04-14", "structured_output": true, "temperature": true, "tool_call": true }, "openai/gpt-4.1-mini": { "attachment": true, "cost": { "cache_read": 0.1, "input": 0.4, "output": 1.6 }, "description": "GPT-4.1 mini is an AI model provided by vercel.", "family": "gpt-mini", "id": "openai/gpt-4.1-mini", "knowledge": "2024-04", "last_updated": "2025-04-14", "limit": { "context": 1047576, "output": 32768 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-4.1 mini", "open_weights": false, "reasoning": false, "release_date": "2025-04-14", "structured_output": true, "temperature": true, "tool_call": true }, "openai/gpt-4.1-nano": { "attachment": true, "cost": { "cache_read": 0.03, "input": 0.1, "output": 0.4 }, "description": "GPT-4.1 nano is an AI model provided by vercel.", "family": "gpt-nano", "id": "openai/gpt-4.1-nano", "knowledge": "2024-04", "last_updated": "2025-04-14", "limit": { "context": 1047576, "output": 32768 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-4.1 nano", "open_weights": false, "reasoning": false, "release_date": "2025-04-14", "structured_output": true, "temperature": true, "tool_call": true }, "openai/gpt-4o": { "attachment": true, "cost": { "cache_read": 1.25, "input": 2.5, "output": 10 }, "description": "GPT-4o is an AI model provided by vercel.", "family": "gpt", "id": "openai/gpt-4o", "knowledge": "2023-09", "last_updated": "2024-08-06", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-4o", "open_weights": false, "reasoning": false, "release_date": "2024-05-13", "structured_output": true, "temperature": true, "tool_call": true }, "openai/gpt-4o-mini": { "attachment": true, "cost": { "cache_read": 0.08, "input": 0.15, "output": 0.6 }, "description": "GPT-4o mini is an AI model provided by vercel.", "family": "gpt-mini", "id": "openai/gpt-4o-mini", "knowledge": "2023-09", "last_updated": "2024-07-18", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-4o mini", "open_weights": false, "reasoning": false, "release_date": "2024-07-18", "structured_output": true, "temperature": true, "tool_call": true }, "openai/gpt-4o-mini-search-preview": { "attachment": false, "cost": { "input": 0.15, "output": 0.6 }, "description": "GPT 4o Mini Search Preview is an AI model provided by vercel.", "family": "gpt-mini", "id": "openai/gpt-4o-mini-search-preview", "knowledge": "2023-09", "last_updated": "2025-01", "limit": { "context": 128000, "input": 111616, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT 4o Mini Search Preview", "open_weights": false, "reasoning": false, "release_date": "2025-01", "structured_output": false, "temperature": true, "tool_call": false }, "openai/gpt-5": { "attachment": true, "cost": { "cache_read": 0.125, "input": 1.25, "output": 10 }, "description": "GPT-5 is an AI model provided by vercel.", "family": "gpt", "id": "openai/gpt-5", "knowledge": "2024-09-30", "last_updated": "2025-08-07", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "structured_output": true, "temperature": false, "tool_call": true }, "openai/gpt-5-chat": { "attachment": true, "cost": { "cache_read": 0.13, "input": 1.25, "output": 10 }, "description": "GPT-5 Chat is an AI model provided by vercel.", "family": "gpt", "id": "openai/gpt-5-chat", "knowledge": "2024-10", "last_updated": "2025-08-07", "limit": { "context": 128000, "input": 111616, "output": 16384 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text", "image" ] }, "name": "GPT-5 Chat", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "temperature": true, "tool_call": true }, "openai/gpt-5-codex": { "attachment": false, "cost": { "cache_read": 0.125, "input": 1.25, "output": 10 }, "description": "GPT-5-Codex is an AI model provided by vercel.", "family": "gpt-codex", "id": "openai/gpt-5-codex", "knowledge": "2024-09-30", "last_updated": "2025-09-15", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5-Codex", "open_weights": false, "reasoning": true, "release_date": "2025-09-15", "structured_output": true, "temperature": false, "tool_call": true }, "openai/gpt-5-mini": { "attachment": true, "cost": { "cache_read": 0.025, "input": 0.25, "output": 2 }, "description": "GPT-5 Mini is an AI model provided by vercel.", "family": "gpt-mini", "id": "openai/gpt-5-mini", "knowledge": "2024-05-30", "last_updated": "2025-08-07", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5 Mini", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "structured_output": true, "temperature": false, "tool_call": true }, "openai/gpt-5-nano": { "attachment": true, "cost": { "cache_read": 0.005, "input": 0.05, "output": 0.4 }, "description": "GPT-5 Nano is an AI model provided by vercel.", "family": "gpt-nano", "id": "openai/gpt-5-nano", "knowledge": "2024-05-30", "last_updated": "2025-08-07", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5 Nano", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "structured_output": true, "temperature": false, "tool_call": true }, "openai/gpt-5-pro": { "attachment": true, "cost": { "input": 15, "output": 120 }, "description": "GPT-5 pro is an AI model provided by vercel.", "family": "gpt", "id": "openai/gpt-5-pro", "knowledge": "2024-10", "last_updated": "2025-08-07", "limit": { "context": 400000, "input": 128000, "output": 272000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text", "image" ] }, "name": "GPT-5 pro", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "temperature": true, "tool_call": true }, "openai/gpt-5.1-codex": { "attachment": true, "cost": { "cache_read": 0.13, "input": 1.25, "output": 10 }, "description": "GPT-5.1-Codex is an AI model provided by vercel.", "family": "gpt", "id": "openai/gpt-5.1-codex", "knowledge": "2024-10", "last_updated": "2025-08-07", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.1-Codex", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "temperature": true, "tool_call": true }, "openai/gpt-5.1-codex-max": { "attachment": true, "cost": { "cache_read": 0.13, "input": 1.25, "output": 10 }, "description": "GPT 5.1 Codex Max is an AI model provided by vercel.", "family": "gpt", "id": "openai/gpt-5.1-codex-max", "knowledge": "2024-10", "last_updated": "2025-08-07", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT 5.1 Codex Max", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "temperature": true, "tool_call": true }, "openai/gpt-5.1-codex-mini": { "attachment": true, "cost": { "cache_read": 0.03, "input": 0.25, "output": 2 }, "description": "GPT-5.1 Codex mini is an AI model provided by vercel.", "family": "gpt", "id": "openai/gpt-5.1-codex-mini", "knowledge": "2024-10", "last_updated": "2025-05-16", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.1 Codex mini", "open_weights": false, "reasoning": true, "release_date": "2025-05-16", "temperature": true, "tool_call": true }, "openai/gpt-5.1-instant": { "attachment": true, "cost": { "cache_read": 0.13, "input": 1.25, "output": 10 }, "description": "GPT-5.1 Instant is an AI model provided by vercel.", "family": "gpt", "id": "openai/gpt-5.1-instant", "knowledge": "2024-10", "last_updated": "2025-08-07", "limit": { "context": 128000, "input": 111616, "output": 16384 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text", "image" ] }, "name": "GPT-5.1 Instant", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "temperature": true, "tool_call": true }, "openai/gpt-5.1-thinking": { "attachment": true, "cost": { "cache_read": 0.13, "input": 1.25, "output": 10 }, "description": "GPT 5.1 Thinking is an AI model provided by vercel.", "family": "gpt", "id": "openai/gpt-5.1-thinking", "knowledge": "2024-10", "last_updated": "2025-08-07", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text", "image" ] }, "name": "GPT 5.1 Thinking", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "temperature": false, "tool_call": true }, "openai/gpt-5.2": { "attachment": true, "cost": { "cache_read": 0.18, "input": 1.75, "output": 14 }, "description": "GPT-5.2 is an AI model provided by vercel.", "family": "gpt", "id": "openai/gpt-5.2", "knowledge": "2024-10", "last_updated": "2025-08-07", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.2", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "temperature": true, "tool_call": true }, "openai/gpt-5.2-chat": { "attachment": true, "cost": { "cache_read": 0.18, "input": 1.75, "output": 14 }, "description": "GPT-5.2 Chat is an AI model provided by vercel.", "family": "gpt", "id": "openai/gpt-5.2-chat", "knowledge": "2024-10", "last_updated": "2025-08-07", "limit": { "context": 128000, "input": 111616, "output": 16384 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.2 Chat", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "temperature": true, "tool_call": true }, "openai/gpt-5.2-codex": { "attachment": true, "cost": { "cache_read": 0.175, "input": 1.75, "output": 14 }, "description": "GPT-5.2-Codex is an AI model provided by vercel.", "family": "gpt-codex", "id": "openai/gpt-5.2-codex", "knowledge": "2024-10", "last_updated": "2025-12", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.2-Codex", "open_weights": false, "reasoning": true, "release_date": "2025-12", "temperature": true, "tool_call": true }, "openai/gpt-5.2-pro": { "attachment": true, "cost": { "input": 21, "output": 168 }, "description": "GPT 5.2 is an AI model provided by vercel.", "family": "gpt", "id": "openai/gpt-5.2-pro", "knowledge": "2024-10", "last_updated": "2025-08-07", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT 5.2 ", "open_weights": false, "reasoning": true, "release_date": "2025-08-07", "temperature": true, "tool_call": true }, "openai/gpt-5.3-chat": { "attachment": true, "cost": { "cache_read": 0.175, "input": 1.75, "output": 14 }, "description": "GPT-5.3 Chat is an AI model provided by vercel.", "family": "gpt", "id": "openai/gpt-5.3-chat", "last_updated": "2026-03-06", "limit": { "context": 128000, "input": 111616, "output": 16384 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.3 Chat", "open_weights": false, "reasoning": true, "release_date": "2026-03-03", "temperature": true, "tool_call": true }, "openai/gpt-5.3-codex": { "attachment": true, "cost": { "cache_read": 0.175, "input": 1.75, "output": 14 }, "description": "GPT 5.3 Codex is an AI model provided by vercel.", "family": "gpt", "id": "openai/gpt-5.3-codex", "last_updated": "2026-02-24", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT 5.3 Codex", "open_weights": false, "reasoning": true, "release_date": "2026-02-24", "temperature": true, "tool_call": true }, "openai/gpt-5.4": { "attachment": true, "cost": { "cache_read": 0.25, "input": 2.5, "output": 15 }, "description": "GPT 5.4 is an AI model provided by vercel.", "family": "gpt", "id": "openai/gpt-5.4", "last_updated": "2026-03-06", "limit": { "context": 1050000, "input": 922000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT 5.4", "open_weights": false, "reasoning": true, "release_date": "2026-03-05", "temperature": true, "tool_call": true }, "openai/gpt-5.4-mini": { "attachment": true, "cost": { "cache_read": 0.075, "input": 0.75, "output": 4.5 }, "description": "GPT 5.4 Mini is an AI model provided by vercel.", "family": "gpt", "id": "openai/gpt-5.4-mini", "last_updated": "2026-03-17", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT 5.4 Mini", "open_weights": false, "reasoning": true, "release_date": "2026-03-17", "temperature": true, "tool_call": true }, "openai/gpt-5.4-nano": { "attachment": true, "cost": { "cache_read": 0.02, "input": 0.19999999999999998, "output": 1.25 }, "description": "GPT 5.4 Nano is an AI model provided by vercel.", "family": "gpt", "id": "openai/gpt-5.4-nano", "last_updated": "2026-03-17", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT 5.4 Nano", "open_weights": false, "reasoning": true, "release_date": "2026-03-17", "temperature": true, "tool_call": true }, "openai/gpt-5.4-pro": { "attachment": true, "cost": { "input": 30, "output": 180 }, "description": "GPT 5.4 Pro is an AI model provided by vercel.", "family": "gpt", "id": "openai/gpt-5.4-pro", "last_updated": "2026-03-06", "limit": { "context": 1050000, "input": 922000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT 5.4 Pro", "open_weights": false, "reasoning": true, "release_date": "2026-03-05", "temperature": true, "tool_call": true }, "openai/gpt-5.5": { "attachment": true, "cost": { "cache_read": 0.5, "input": 5, "output": 30 }, "description": "GPT 5.5 is an AI model provided by vercel.", "family": "gpt", "id": "openai/gpt-5.5", "last_updated": "2026-04-24", "limit": { "context": 1000000, "input": 872000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT 5.5", "open_weights": false, "reasoning": true, "release_date": "2026-04-24", "temperature": true, "tool_call": true }, "openai/gpt-5.5-pro": { "attachment": true, "cost": { "input": 30, "output": 180 }, "description": "GPT 5.5 Pro is an AI model provided by vercel.", "family": "gpt", "id": "openai/gpt-5.5-pro", "last_updated": "2026-04-24", "limit": { "context": 1000000, "input": 872000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT 5.5 Pro", "open_weights": false, "reasoning": true, "release_date": "2026-04-24", "temperature": true, "tool_call": true }, "openai/gpt-oss-120b": { "attachment": false, "cost": { "input": 0.1, "output": 0.5 }, "description": "GPT OSS 120B is an AI model provided by vercel.", "family": "gpt-oss", "id": "openai/gpt-oss-120b", "knowledge": "2024-10", "last_updated": "2025-08-05", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT OSS 120B", "open_weights": true, "reasoning": true, "release_date": "2025-08-05", "temperature": true, "tool_call": true }, "openai/gpt-oss-20b": { "attachment": false, "cost": { "input": 0.07, "output": 0.3 }, "description": "GPT OSS 20B is an AI model provided by vercel.", "family": "gpt-oss", "id": "openai/gpt-oss-20b", "knowledge": "2024-10", "last_updated": "2025-08-05", "limit": { "context": 131072, "input": 98304, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT OSS 20B", "open_weights": true, "reasoning": true, "release_date": "2025-08-05", "temperature": true, "tool_call": true }, "openai/gpt-oss-safeguard-20b": { "attachment": false, "cost": { "cache_read": 0.04, "input": 0.08, "output": 0.3 }, "description": "gpt-oss-safeguard-20b is an AI model provided by vercel.", "family": "gpt-oss", "id": "openai/gpt-oss-safeguard-20b", "knowledge": "2024-10", "last_updated": "2024-12-01", "limit": { "context": 131072, "input": 65536, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "gpt-oss-safeguard-20b", "open_weights": false, "reasoning": true, "release_date": "2024-12-01", "temperature": true, "tool_call": true }, "openai/o1": { "attachment": true, "cost": { "cache_read": 7.5, "input": 15, "output": 60 }, "description": "o1 is an AI model provided by vercel.", "family": "o", "id": "openai/o1", "knowledge": "2023-09", "last_updated": "2024-12-05", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "o1", "open_weights": false, "reasoning": true, "release_date": "2024-12-05", "structured_output": true, "temperature": false, "tool_call": true }, "openai/o3": { "attachment": true, "cost": { "cache_read": 0.5, "input": 2, "output": 8 }, "description": "o3 is an AI model provided by vercel.", "family": "o", "id": "openai/o3", "knowledge": "2024-05", "last_updated": "2025-04-16", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "o3", "open_weights": false, "reasoning": true, "release_date": "2025-04-16", "structured_output": true, "temperature": false, "tool_call": true }, "openai/o3-deep-research": { "attachment": true, "cost": { "cache_read": 2.5, "input": 10, "output": 40 }, "description": "o3-deep-research is an AI model provided by vercel.", "family": "o", "id": "openai/o3-deep-research", "knowledge": "2024-10", "last_updated": "2024-06-26", "limit": { "context": 200000, "input": 100000, "output": 100000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "o3-deep-research", "open_weights": false, "reasoning": true, "release_date": "2024-06-26", "temperature": false, "tool_call": true }, "openai/o3-mini": { "attachment": false, "cost": { "cache_read": 0.55, "input": 1.1, "output": 4.4 }, "description": "o3-mini is an AI model provided by vercel.", "family": "o-mini", "id": "openai/o3-mini", "knowledge": "2024-05", "last_updated": "2025-01-29", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "o3-mini", "open_weights": false, "reasoning": true, "release_date": "2024-12-20", "structured_output": true, "temperature": false, "tool_call": true }, "openai/o3-pro": { "attachment": true, "cost": { "input": 20, "output": 80 }, "description": "o3 Pro is an AI model provided by vercel.", "family": "o-pro", "id": "openai/o3-pro", "knowledge": "2024-10", "last_updated": "2025-04-16", "limit": { "context": 200000, "input": 100000, "output": 100000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "o3 Pro", "open_weights": false, "reasoning": true, "release_date": "2025-04-16", "temperature": false, "tool_call": true }, "openai/o4-mini": { "attachment": true, "cost": { "cache_read": 0.28, "input": 1.1, "output": 4.4 }, "description": "o4-mini is an AI model provided by vercel.", "family": "o-mini", "id": "openai/o4-mini", "knowledge": "2024-05", "last_updated": "2025-04-16", "limit": { "context": 200000, "output": 100000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "o4-mini", "open_weights": false, "reasoning": true, "release_date": "2025-04-16", "structured_output": true, "temperature": false, "tool_call": true }, "openai/text-embedding-3-large": { "attachment": false, "cost": { "input": 0.13, "output": 0 }, "description": "text-embedding-3-large is an AI model provided by vercel.", "family": "text-embedding", "id": "openai/text-embedding-3-large", "last_updated": "2024-01-25", "limit": { "context": 8192, "input": 6656, "output": 1536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "text-embedding-3-large", "open_weights": false, "reasoning": false, "release_date": "2024-01-25", "temperature": false, "tool_call": false }, "openai/text-embedding-3-small": { "attachment": false, "cost": { "input": 0.02, "output": 0 }, "description": "text-embedding-3-small is an AI model provided by vercel.", "family": "text-embedding", "id": "openai/text-embedding-3-small", "last_updated": "2024-01-25", "limit": { "context": 8192, "input": 6656, "output": 1536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "text-embedding-3-small", "open_weights": false, "reasoning": false, "release_date": "2024-01-25", "temperature": false, "tool_call": false }, "openai/text-embedding-ada-002": { "attachment": false, "cost": { "input": 0.1, "output": 0 }, "description": "text-embedding-ada-002 is an AI model provided by vercel.", "family": "text-embedding", "id": "openai/text-embedding-ada-002", "last_updated": "2022-12-15", "limit": { "context": 8192, "input": 6656, "output": 1536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "text-embedding-ada-002", "open_weights": false, "reasoning": false, "release_date": "2022-12-15", "temperature": false, "tool_call": false }, "perplexity/sonar": { "attachment": true, "cost": { "input": 1, "output": 1 }, "description": "Sonar is an AI model provided by vercel.", "family": "sonar", "id": "perplexity/sonar", "knowledge": "2025-02", "last_updated": "2025-02-19", "limit": { "context": 127000, "output": 8000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Sonar", "open_weights": false, "reasoning": false, "release_date": "2025-02-19", "temperature": true, "tool_call": true }, "perplexity/sonar-pro": { "attachment": true, "cost": { "input": 3, "output": 15 }, "description": "Sonar Pro is an AI model provided by vercel.", "family": "sonar-pro", "id": "perplexity/sonar-pro", "knowledge": "2025-09", "last_updated": "2025-02-19", "limit": { "context": 200000, "output": 8000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Sonar Pro", "open_weights": false, "reasoning": false, "release_date": "2025-02-19", "temperature": true, "tool_call": true }, "perplexity/sonar-reasoning": { "attachment": false, "cost": { "input": 1, "output": 5 }, "description": "Sonar Reasoning is an AI model provided by vercel.", "family": "sonar-reasoning", "id": "perplexity/sonar-reasoning", "knowledge": "2025-09", "last_updated": "2025-02-19", "limit": { "context": 127000, "output": 8000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Sonar Reasoning", "open_weights": false, "reasoning": true, "release_date": "2025-02-19", "temperature": true, "tool_call": false }, "perplexity/sonar-reasoning-pro": { "attachment": false, "cost": { "input": 2, "output": 8 }, "description": "Sonar Reasoning Pro is an AI model provided by vercel.", "family": "sonar-reasoning", "id": "perplexity/sonar-reasoning-pro", "knowledge": "2025-09", "last_updated": "2025-02-19", "limit": { "context": 127000, "output": 8000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Sonar Reasoning Pro", "open_weights": false, "reasoning": true, "release_date": "2025-02-19", "temperature": true, "tool_call": false }, "prime-intellect/intellect-3": { "attachment": false, "cost": { "input": 0.2, "output": 1.1 }, "description": "INTELLECT 3 is an AI model provided by vercel.", "family": "intellect", "id": "prime-intellect/intellect-3", "knowledge": "2024-10", "last_updated": "2025-11-26", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "INTELLECT 3", "open_weights": false, "reasoning": true, "release_date": "2025-11-26", "temperature": true, "tool_call": true }, "recraft/recraft-v2": { "attachment": false, "description": "Recraft V2 is an AI model provided by vercel.", "family": "recraft", "id": "recraft/recraft-v2", "last_updated": "2024-03", "limit": { "context": 512, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "name": "Recraft V2", "open_weights": false, "reasoning": false, "release_date": "2024-03", "temperature": false, "tool_call": false }, "recraft/recraft-v3": { "attachment": false, "description": "Recraft V3 is an AI model provided by vercel.", "family": "recraft", "id": "recraft/recraft-v3", "last_updated": "2024-10", "limit": { "context": 512, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "name": "Recraft V3", "open_weights": false, "reasoning": false, "release_date": "2024-10", "temperature": false, "tool_call": false }, "vercel/v0-1.0-md": { "attachment": true, "cost": { "input": 3, "output": 15 }, "description": "v0-1.0-md is an AI model provided by vercel.", "family": "v0", "id": "vercel/v0-1.0-md", "last_updated": "2025-05-22", "limit": { "context": 128000, "output": 32000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "v0-1.0-md", "open_weights": false, "reasoning": true, "release_date": "2025-05-22", "temperature": true, "tool_call": true }, "vercel/v0-1.5-md": { "attachment": true, "cost": { "input": 3, "output": 15 }, "description": "v0-1.5-md is an AI model provided by vercel.", "family": "v0", "id": "vercel/v0-1.5-md", "last_updated": "2025-06-09", "limit": { "context": 128000, "output": 32000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "v0-1.5-md", "open_weights": false, "reasoning": true, "release_date": "2025-06-09", "temperature": true, "tool_call": true }, "voyage/voyage-3-large": { "attachment": false, "cost": { "input": 0.18, "output": 0 }, "description": "voyage-3-large is an AI model provided by vercel.", "family": "voyage", "id": "voyage/voyage-3-large", "last_updated": "2024-09", "limit": { "context": 8192, "output": 1536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "voyage-3-large", "open_weights": false, "reasoning": false, "release_date": "2024-09", "temperature": false, "tool_call": false }, "voyage/voyage-3.5": { "attachment": false, "cost": { "input": 0.06, "output": 0 }, "description": "voyage-3.5 is an AI model provided by vercel.", "family": "voyage", "id": "voyage/voyage-3.5", "last_updated": "2025-05-20", "limit": { "context": 8192, "output": 1536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "voyage-3.5", "open_weights": false, "reasoning": false, "release_date": "2025-05-20", "temperature": false, "tool_call": false }, "voyage/voyage-3.5-lite": { "attachment": false, "cost": { "input": 0.02, "output": 0 }, "description": "voyage-3.5-lite is an AI model provided by vercel.", "family": "voyage", "id": "voyage/voyage-3.5-lite", "last_updated": "2025-05-20", "limit": { "context": 8192, "output": 1536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "voyage-3.5-lite", "open_weights": false, "reasoning": false, "release_date": "2025-05-20", "temperature": false, "tool_call": false }, "voyage/voyage-4": { "attachment": false, "description": "voyage-4 is an AI model provided by vercel.", "family": "voyage", "id": "voyage/voyage-4", "last_updated": "2026-03-06", "limit": { "context": 32000, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "voyage-4", "open_weights": false, "reasoning": false, "release_date": "2026-03-06", "temperature": true, "tool_call": false }, "voyage/voyage-4-large": { "attachment": false, "description": "voyage-4-large is an AI model provided by vercel.", "family": "voyage", "id": "voyage/voyage-4-large", "last_updated": "2026-03-06", "limit": { "context": 32000, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "voyage-4-large", "open_weights": false, "reasoning": false, "release_date": "2026-03-06", "temperature": true, "tool_call": false }, "voyage/voyage-4-lite": { "attachment": false, "description": "voyage-4-lite is an AI model provided by vercel.", "family": "voyage", "id": "voyage/voyage-4-lite", "last_updated": "2026-03-06", "limit": { "context": 32000, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "voyage-4-lite", "open_weights": false, "reasoning": false, "release_date": "2026-03-06", "temperature": true, "tool_call": false }, "voyage/voyage-code-2": { "attachment": false, "cost": { "input": 0.12, "output": 0 }, "description": "voyage-code-2 is an AI model provided by vercel.", "family": "voyage", "id": "voyage/voyage-code-2", "last_updated": "2024-01", "limit": { "context": 8192, "output": 1536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "voyage-code-2", "open_weights": false, "reasoning": false, "release_date": "2024-01", "temperature": false, "tool_call": false }, "voyage/voyage-code-3": { "attachment": false, "cost": { "input": 0.18, "output": 0 }, "description": "voyage-code-3 is an AI model provided by vercel.", "family": "voyage", "id": "voyage/voyage-code-3", "last_updated": "2024-09", "limit": { "context": 8192, "output": 1536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "voyage-code-3", "open_weights": false, "reasoning": false, "release_date": "2024-09", "temperature": false, "tool_call": false }, "voyage/voyage-finance-2": { "attachment": false, "cost": { "input": 0.12, "output": 0 }, "description": "voyage-finance-2 is an AI model provided by vercel.", "family": "voyage", "id": "voyage/voyage-finance-2", "last_updated": "2024-03", "limit": { "context": 8192, "output": 1536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "voyage-finance-2", "open_weights": false, "reasoning": false, "release_date": "2024-03", "temperature": false, "tool_call": false }, "voyage/voyage-law-2": { "attachment": false, "cost": { "input": 0.12, "output": 0 }, "description": "voyage-law-2 is an AI model provided by vercel.", "family": "voyage", "id": "voyage/voyage-law-2", "last_updated": "2024-03", "limit": { "context": 8192, "output": 1536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "voyage-law-2", "open_weights": false, "reasoning": false, "release_date": "2024-03", "temperature": false, "tool_call": false }, "xai/grok-2-vision": { "attachment": true, "cost": { "cache_read": 2, "input": 2, "output": 10 }, "description": "Grok 2 Vision is an AI model provided by vercel.", "family": "grok", "id": "xai/grok-2-vision", "knowledge": "2024-08", "last_updated": "2024-08-20", "limit": { "context": 8192, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 2 Vision", "open_weights": false, "reasoning": false, "release_date": "2024-08-20", "temperature": true, "tool_call": true }, "xai/grok-3": { "attachment": false, "cost": { "cache_read": 0.75, "input": 3, "output": 15 }, "description": "Grok 3 is an AI model provided by vercel.", "family": "grok", "id": "xai/grok-3", "knowledge": "2024-11", "last_updated": "2025-02-17", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok 3", "open_weights": false, "reasoning": false, "release_date": "2025-02-17", "temperature": true, "tool_call": true }, "xai/grok-3-fast": { "attachment": false, "cost": { "cache_read": 1.25, "input": 5, "output": 25 }, "description": "Grok 3 Fast is an AI model provided by vercel.", "family": "grok", "id": "xai/grok-3-fast", "knowledge": "2024-11", "last_updated": "2025-02-17", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok 3 Fast", "open_weights": false, "reasoning": false, "release_date": "2025-02-17", "temperature": true, "tool_call": true }, "xai/grok-3-mini": { "attachment": false, "cost": { "cache_read": 0.075, "input": 0.3, "output": 0.5, "reasoning": 0.5 }, "description": "Grok 3 Mini is an AI model provided by vercel.", "family": "grok", "id": "xai/grok-3-mini", "knowledge": "2024-11", "last_updated": "2025-02-17", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok 3 Mini", "open_weights": false, "reasoning": true, "release_date": "2025-02-17", "temperature": true, "tool_call": true }, "xai/grok-3-mini-fast": { "attachment": false, "cost": { "cache_read": 0.15, "input": 0.6, "output": 4, "reasoning": 4 }, "description": "Grok 3 Mini Fast is an AI model provided by vercel.", "family": "grok", "id": "xai/grok-3-mini-fast", "knowledge": "2024-11", "last_updated": "2025-02-17", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok 3 Mini Fast", "open_weights": false, "reasoning": true, "release_date": "2025-02-17", "temperature": true, "tool_call": true }, "xai/grok-4": { "attachment": false, "cost": { "cache_read": 0.75, "input": 3, "output": 15, "reasoning": 15 }, "description": "Grok 4 is an AI model provided by vercel.", "family": "grok", "id": "xai/grok-4", "knowledge": "2025-07", "last_updated": "2025-07-09", "limit": { "context": 256000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok 4", "open_weights": false, "reasoning": true, "release_date": "2025-07-09", "temperature": true, "tool_call": true }, "xai/grok-4-fast-non-reasoning": { "attachment": true, "cost": { "cache_read": 0.05, "input": 0.2, "output": 0.5 }, "description": "Grok 4 Fast (Non-Reasoning) is an AI model provided by vercel.", "family": "grok", "id": "xai/grok-4-fast-non-reasoning", "knowledge": "2025-07", "last_updated": "2025-09-19", "limit": { "context": 2000000, "output": 30000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 4 Fast (Non-Reasoning)", "open_weights": false, "reasoning": false, "release_date": "2025-09-19", "temperature": true, "tool_call": true }, "xai/grok-4-fast-reasoning": { "attachment": false, "cost": { "cache_read": 0.05, "input": 0.2, "output": 0.5 }, "description": "Grok 4 Fast Reasoning is an AI model provided by vercel.", "family": "grok", "id": "xai/grok-4-fast-reasoning", "knowledge": "2024-10", "last_updated": "2025-07-09", "limit": { "context": 2000000, "output": 256000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok 4 Fast Reasoning", "open_weights": false, "reasoning": true, "release_date": "2025-07-09", "temperature": true, "tool_call": true }, "xai/grok-4.1-fast-non-reasoning": { "attachment": false, "cost": { "cache_read": 0.05, "input": 0.2, "output": 0.5 }, "description": "Grok 4.1 Fast Non-Reasoning is an AI model provided by vercel.", "family": "grok", "id": "xai/grok-4.1-fast-non-reasoning", "knowledge": "2024-10", "last_updated": "2025-07-09", "limit": { "context": 2000000, "output": 30000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok 4.1 Fast Non-Reasoning", "open_weights": false, "reasoning": false, "release_date": "2025-07-09", "temperature": true, "tool_call": true }, "xai/grok-4.1-fast-reasoning": { "attachment": false, "cost": { "cache_read": 0.05, "input": 0.2, "output": 0.5 }, "description": "Grok 4.1 Fast Reasoning is an AI model provided by vercel.", "family": "grok", "id": "xai/grok-4.1-fast-reasoning", "knowledge": "2024-10", "last_updated": "2025-07-09", "limit": { "context": 2000000, "output": 30000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok 4.1 Fast Reasoning", "open_weights": false, "reasoning": true, "release_date": "2025-07-09", "temperature": true, "tool_call": true }, "xai/grok-4.20-multi-agent": { "attachment": false, "cost": { "cache_read": 0.19999999999999998, "input": 2, "output": 6 }, "description": "Grok 4.20 Multi-Agent is an AI model provided by vercel.", "family": "grok", "id": "xai/grok-4.20-multi-agent", "last_updated": "2026-03-23", "limit": { "context": 2000000, "output": 2000000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok 4.20 Multi-Agent", "open_weights": false, "reasoning": true, "release_date": "2026-03-09", "temperature": true, "tool_call": true }, "xai/grok-4.20-multi-agent-beta": { "attachment": false, "cost": { "cache_read": 0.19999999999999998, "input": 2, "output": 6 }, "description": "Grok 4.20 Multi Agent Beta is an AI model provided by vercel.", "family": "grok", "id": "xai/grok-4.20-multi-agent-beta", "last_updated": "2026-03-13", "limit": { "context": 2000000, "output": 2000000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok 4.20 Multi Agent Beta", "open_weights": false, "reasoning": true, "release_date": "2026-03-11", "temperature": true, "tool_call": true }, "xai/grok-4.20-non-reasoning": { "attachment": true, "cost": { "cache_read": 0.19999999999999998, "input": 2, "output": 6 }, "description": "Grok 4.20 Non-Reasoning is an AI model provided by vercel.", "family": "grok", "id": "xai/grok-4.20-non-reasoning", "last_updated": "2026-03-23", "limit": { "context": 2000000, "output": 2000000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Grok 4.20 Non-Reasoning", "open_weights": false, "reasoning": false, "release_date": "2026-03-09", "temperature": true, "tool_call": true }, "xai/grok-4.20-non-reasoning-beta": { "attachment": true, "cost": { "cache_read": 0.19999999999999998, "input": 2, "output": 6 }, "description": "Grok 4.20 Beta Non-Reasoning is an AI model provided by vercel.", "family": "grok", "id": "xai/grok-4.20-non-reasoning-beta", "last_updated": "2026-03-13", "limit": { "context": 2000000, "output": 2000000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Grok 4.20 Beta Non-Reasoning", "open_weights": false, "reasoning": false, "release_date": "2026-03-11", "temperature": true, "tool_call": true }, "xai/grok-4.20-reasoning": { "attachment": true, "cost": { "cache_read": 0.19999999999999998, "input": 2, "output": 6 }, "description": "Grok 4.20 Reasoning is an AI model provided by vercel.", "family": "grok", "id": "xai/grok-4.20-reasoning", "last_updated": "2026-03-23", "limit": { "context": 2000000, "output": 2000000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Grok 4.20 Reasoning", "open_weights": false, "reasoning": true, "release_date": "2026-03-09", "temperature": true, "tool_call": true }, "xai/grok-4.20-reasoning-beta": { "attachment": true, "cost": { "cache_read": 0.19999999999999998, "input": 2, "output": 6 }, "description": "Grok 4.20 Beta Reasoning is an AI model provided by vercel.", "family": "grok", "id": "xai/grok-4.20-reasoning-beta", "last_updated": "2026-03-13", "limit": { "context": 2000000, "output": 2000000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Grok 4.20 Beta Reasoning", "open_weights": false, "reasoning": true, "release_date": "2026-03-11", "temperature": true, "tool_call": true }, "xai/grok-4.3": { "attachment": true, "cost": { "cache_read": 0.19999999999999998, "input": 1.25, "output": 2.5 }, "description": "Grok 4.3 is an AI model provided by vercel.", "family": "grok", "id": "xai/grok-4.3", "last_updated": "2026-05-01", "limit": { "context": 1000000, "output": 1000000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Grok 4.3", "open_weights": false, "reasoning": true, "release_date": "2026-04-30", "temperature": true, "tool_call": true }, "xai/grok-code-fast-1": { "attachment": false, "cost": { "cache_read": 0.02, "input": 0.2, "output": 1.5 }, "description": "Grok Code Fast 1 is an AI model provided by vercel.", "family": "grok", "id": "xai/grok-code-fast-1", "knowledge": "2023-10", "last_updated": "2025-08-28", "limit": { "context": 256000, "output": 10000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok Code Fast 1", "open_weights": false, "reasoning": true, "release_date": "2025-08-28", "temperature": true, "tool_call": true }, "xai/grok-imagine-image": { "attachment": false, "description": "Grok Imagine Image is an AI model provided by vercel.", "family": "grok", "id": "xai/grok-imagine-image", "last_updated": "2026-02-19", "limit": { "context": 0, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "text", "image" ] }, "name": "Grok Imagine Image", "open_weights": false, "reasoning": false, "release_date": "2026-01-28", "temperature": true, "tool_call": false }, "xai/grok-imagine-image-pro": { "attachment": false, "description": "Grok Imagine Image Pro is an AI model provided by vercel.", "family": "grok", "id": "xai/grok-imagine-image-pro", "last_updated": "2026-02-19", "limit": { "context": 0, "output": 0 }, "modalities": { "input": [ "text" ], "output": [ "text", "image" ] }, "name": "Grok Imagine Image Pro", "open_weights": false, "reasoning": false, "release_date": "2026-01-28", "temperature": true, "tool_call": false }, "xiaomi/mimo-v2-flash": { "attachment": false, "cost": { "input": 0.1, "output": 0.29 }, "description": "MiMo V2 Flash is an AI model provided by vercel.", "family": "mimo", "id": "xiaomi/mimo-v2-flash", "knowledge": "2024-10", "last_updated": "2025-12-17", "limit": { "context": 262144, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiMo V2 Flash", "open_weights": false, "reasoning": true, "release_date": "2025-12-17", "temperature": true, "tool_call": true }, "xiaomi/mimo-v2-pro": { "attachment": false, "cost": { "cache_read": 0.19999999999999998, "input": 1, "output": 3 }, "description": "MiMo V2 Pro is an AI model provided by vercel.", "family": "mimo", "id": "xiaomi/mimo-v2-pro", "last_updated": "2026-03-20", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiMo V2 Pro", "open_weights": false, "reasoning": true, "release_date": "2026-03-18", "temperature": true, "tool_call": true }, "xiaomi/mimo-v2.5": { "attachment": true, "cost": { "cache_read": 0.08, "input": 0.39999999999999997, "output": 2 }, "description": "MiMo M2.5 is an AI model provided by vercel.", "family": "mimo-v2.5", "id": "xiaomi/mimo-v2.5", "last_updated": "2026-05-01", "limit": { "context": 1050000, "output": 131100 }, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "name": "MiMo M2.5", "open_weights": false, "reasoning": true, "release_date": "2026-04-22", "temperature": true, "tool_call": true }, "xiaomi/mimo-v2.5-pro": { "attachment": true, "cost": { "cache_read": 0.19999999999999998, "input": 1, "output": 3 }, "description": "MiMo V2.5 Pro is an AI model provided by vercel.", "family": "mimo-v2.5-pro", "id": "xiaomi/mimo-v2.5-pro", "last_updated": "2026-05-01", "limit": { "context": 1050000, "output": 131000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiMo V2.5 Pro", "open_weights": false, "reasoning": true, "release_date": "2026-04-22", "temperature": true, "tool_call": true }, "zai/glm-4.5": { "attachment": false, "cost": { "input": 0.6, "output": 2.2 }, "description": "GLM 4.5 is an AI model provided by vercel.", "family": "glm", "id": "zai/glm-4.5", "interleaved": true, "knowledge": "2025-07", "last_updated": "2025-07-28", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.5", "open_weights": true, "reasoning": true, "release_date": "2025-07-28", "temperature": true, "tool_call": true }, "zai/glm-4.5-air": { "attachment": false, "cost": { "input": 0.2, "output": 1.1 }, "description": "GLM 4.5 Air is an AI model provided by vercel.", "family": "glm-air", "id": "zai/glm-4.5-air", "knowledge": "2025-04", "last_updated": "2025-07-28", "limit": { "context": 128000, "output": 96000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.5 Air", "open_weights": true, "reasoning": true, "release_date": "2025-07-28", "temperature": true, "tool_call": true }, "zai/glm-4.5v": { "attachment": true, "cost": { "input": 0.6, "output": 1.8 }, "description": "GLM 4.5V is an AI model provided by vercel.", "family": "glm", "id": "zai/glm-4.5v", "knowledge": "2025-08", "last_updated": "2025-08-11", "limit": { "context": 66000, "output": 66000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GLM 4.5V", "open_weights": true, "reasoning": true, "release_date": "2025-08-11", "temperature": true, "tool_call": true }, "zai/glm-4.6": { "attachment": false, "cost": { "input": 0.45, "output": 1.8 }, "description": "GLM 4.6 is an AI model provided by vercel.", "family": "glm", "id": "zai/glm-4.6", "interleaved": true, "knowledge": "2025-04", "last_updated": "2025-09-30", "limit": { "context": 200000, "output": 96000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.6", "open_weights": true, "reasoning": true, "release_date": "2025-09-30", "temperature": true, "tool_call": true }, "zai/glm-4.6v": { "attachment": true, "cost": { "cache_read": 0.05, "input": 0.3, "output": 0.9 }, "description": "GLM-4.6V is an AI model provided by vercel.", "family": "glm", "id": "zai/glm-4.6v", "knowledge": "2024-10", "last_updated": "2025-09-30", "limit": { "context": 128000, "output": 24000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GLM-4.6V", "open_weights": false, "reasoning": true, "release_date": "2025-09-30", "temperature": true, "tool_call": true }, "zai/glm-4.6v-flash": { "attachment": true, "description": "GLM-4.6V-Flash is an AI model provided by vercel.", "family": "glm", "id": "zai/glm-4.6v-flash", "knowledge": "2024-10", "last_updated": "2025-09-30", "limit": { "context": 128000, "output": 24000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GLM-4.6V-Flash", "open_weights": false, "reasoning": true, "release_date": "2025-09-30", "temperature": true, "tool_call": true }, "zai/glm-4.7": { "attachment": false, "cost": { "cache_read": 0.08, "input": 0.43, "output": 1.75 }, "description": "GLM 4.7 is an AI model provided by vercel.", "family": "glm", "id": "zai/glm-4.7", "interleaved": true, "knowledge": "2024-10", "last_updated": "2025-12-22", "limit": { "context": 202752, "output": 120000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.7", "open_weights": false, "reasoning": true, "release_date": "2025-12-22", "temperature": true, "tool_call": true }, "zai/glm-4.7-flash": { "attachment": false, "cost": { "input": 0.07, "output": 0.39999999999999997 }, "description": "GLM 4.7 Flash is an AI model provided by vercel.", "family": "glm", "id": "zai/glm-4.7-flash", "last_updated": "2026-03-13", "limit": { "context": 200000, "output": 131000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.7 Flash", "open_weights": false, "reasoning": true, "release_date": "2026-03-13", "temperature": true, "tool_call": true }, "zai/glm-4.7-flashx": { "attachment": false, "cost": { "cache_read": 0.01, "input": 0.06, "output": 0.4 }, "description": "GLM 4.7 FlashX is an AI model provided by vercel.", "family": "glm-flash", "id": "zai/glm-4.7-flashx", "interleaved": true, "knowledge": "2025-01", "last_updated": "2025-01", "limit": { "context": 200000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.7 FlashX", "open_weights": true, "reasoning": true, "release_date": "2025-01", "temperature": true, "tool_call": true }, "zai/glm-5": { "attachment": false, "cost": { "cache_read": 0.2, "input": 1, "output": 3.2 }, "description": "GLM-5 is an AI model provided by vercel.", "family": "glm", "id": "zai/glm-5", "last_updated": "2026-02-19", "limit": { "context": 202800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5", "open_weights": true, "reasoning": true, "release_date": "2026-02-12", "temperature": true, "tool_call": true }, "zai/glm-5-turbo": { "attachment": false, "cost": { "cache_read": 0.24, "input": 1.2, "output": 4 }, "description": "GLM 5 Turbo is an AI model provided by vercel.", "family": "glm", "id": "zai/glm-5-turbo", "last_updated": "2026-03-17", "limit": { "context": 202800, "output": 131100 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 5 Turbo", "open_weights": false, "reasoning": true, "release_date": "2026-03-15", "temperature": true, "tool_call": true }, "zai/glm-5.1": { "attachment": true, "cost": { "cache_read": 0.26, "input": 1.4, "output": 4.4 }, "description": "GLM 5.1 is an AI model provided by vercel.", "family": "glm", "id": "zai/glm-5.1", "last_updated": "2026-04-16", "limit": { "context": 202752, "output": 202752 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GLM 5.1", "open_weights": false, "reasoning": true, "release_date": "2026-04-07", "temperature": true, "tool_call": true }, "zai/glm-5v-turbo": { "attachment": true, "cost": { "cache_read": 0.24, "input": 1.2, "output": 4 }, "description": "GLM 5V Turbo is an AI model provided by vercel.", "family": "glm", "id": "zai/glm-5v-turbo", "last_updated": "2026-04-03", "limit": { "context": 200000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GLM 5V Turbo", "open_weights": false, "reasoning": true, "release_date": "2026-04-01", "temperature": true, "tool_call": true } }, "name": "Vercel AI Gateway", "npm": "@ai-sdk/gateway" }, "vivgrid": { "api": "https://api.vivgrid.com/v1", "doc": "https://docs.vivgrid.com/models", "env": [ "VIVGRID_API_KEY" ], "iconURL": "https://models.dev/logos/vivgrid.svg", "id": "vivgrid", "models": { "deepseek-v3.2": { "attachment": false, "cost": { "input": 0.28, "output": 0.42 }, "description": "DeepSeek-V3.2 is an AI model provided by vivgrid.", "family": "deepseek", "id": "deepseek-v3.2", "knowledge": "2024-07", "last_updated": "2025-12-01", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek-V3.2", "open_weights": true, "provider": { "npm": "@ai-sdk/openai-compatible" }, "reasoning": true, "release_date": "2025-12-01", "temperature": true, "tool_call": true }, "deepseek-v4-pro": { "attachment": false, "cost": { "cache_read": 0.145, "input": 1.74, "output": 3.48 }, "description": "DeepSeek V4 Pro is an AI model provided by vivgrid.", "family": "deepseek-thinking", "id": "deepseek-v4-pro", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-05", "last_updated": "2026-04-24", "limit": { "context": 1000000, "output": 384000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V4 Pro", "open_weights": true, "provider": { "npm": "@ai-sdk/openai-compatible" }, "reasoning": true, "release_date": "2026-04-24", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-3.1-flash-lite-preview": { "attachment": true, "cost": { "cache_read": 0.025, "cache_write": 1, "input": 0.25, "output": 1.5 }, "description": "Gemini 3.1 Flash Lite Preview is an AI model provided by vivgrid.", "family": "gemini-flash-lite", "id": "gemini-3.1-flash-lite-preview", "knowledge": "2025-01", "last_updated": "2026-03-03", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "name": "Gemini 3.1 Flash Lite Preview", "open_weights": false, "provider": { "npm": "@ai-sdk/openai-compatible" }, "reasoning": true, "release_date": "2026-03-03", "structured_output": true, "temperature": true, "tool_call": true }, "gemini-3.1-pro-preview": { "attachment": true, "cost": { "cache_read": 0.2, "context_over_200k": { "cache_read": 0.4, "input": 4, "output": 18 }, "input": 2, "output": 12, "tiers": [ { "cache_read": 0.4, "input": 4, "output": 18, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Gemini 3.1 Pro Preview is an AI model provided by vivgrid.", "family": "gemini-pro", "id": "gemini-3.1-pro-preview", "knowledge": "2025-01", "last_updated": "2026-02-19", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "name": "Gemini 3.1 Pro Preview", "open_weights": false, "provider": { "npm": "@ai-sdk/openai-compatible" }, "reasoning": true, "release_date": "2026-02-19", "structured_output": true, "temperature": true, "tool_call": true }, "gpt-5-mini": { "attachment": true, "cost": { "cache_read": 0.03, "input": 0.25, "output": 2 }, "description": "GPT-5 Mini is an AI model provided by vivgrid.", "family": "gpt-mini", "id": "gpt-5-mini", "knowledge": "2024-05-30", "last_updated": "2025-08-07", "limit": { "context": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5 Mini", "open_weights": false, "provider": { "npm": "@ai-sdk/openai-compatible" }, "reasoning": true, "release_date": "2025-08-07", "temperature": false, "tool_call": true }, "gpt-5.1-codex": { "attachment": false, "cost": { "cache_read": 0.125, "input": 1.25, "output": 10 }, "description": "GPT-5.1 Codex is an AI model provided by vivgrid.", "family": "gpt-codex", "id": "gpt-5.1-codex", "knowledge": "2024-09-30", "last_updated": "2025-11-13", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.1 Codex", "open_weights": false, "reasoning": true, "release_date": "2025-11-13", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.1-codex-max": { "attachment": false, "cost": { "cache_read": 0.125, "input": 1.25, "output": 10 }, "description": "GPT-5.1 Codex Max is an AI model provided by vivgrid.", "family": "gpt-codex", "id": "gpt-5.1-codex-max", "knowledge": "2024-09-30", "last_updated": "2025-11-13", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.1 Codex Max", "open_weights": false, "reasoning": true, "release_date": "2025-11-13", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.2-codex": { "attachment": false, "cost": { "cache_read": 0.175, "input": 1.75, "output": 14 }, "description": "GPT-5.2 Codex is an AI model provided by vivgrid.", "family": "gpt-codex", "id": "gpt-5.2-codex", "knowledge": "2025-08-31", "last_updated": "2026-01-14", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.2 Codex", "open_weights": false, "reasoning": true, "release_date": "2026-01-14", "temperature": false, "tool_call": true }, "gpt-5.3-codex": { "attachment": false, "cost": { "cache_read": 0.175, "input": 1.75, "output": 14 }, "description": "GPT-5.3 Codex is an AI model provided by vivgrid.", "family": "gpt-codex", "id": "gpt-5.3-codex", "knowledge": "2025-08-31", "last_updated": "2026-02-24", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.3 Codex", "open_weights": false, "reasoning": true, "release_date": "2026-02-24", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.4": { "attachment": true, "cost": { "cache_read": 0.25, "input": 2.5, "output": 15 }, "description": "GPT-5.4 is an AI model provided by vivgrid.", "family": "gpt", "id": "gpt-5.4", "knowledge": "2025-08-31", "last_updated": "2026-03-05", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.4", "open_weights": false, "provider": { "npm": "@ai-sdk/openai-compatible" }, "reasoning": true, "release_date": "2026-03-05", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.4-mini": { "attachment": true, "cost": { "cache_read": 0.075, "input": 0.75, "output": 4.5 }, "description": "GPT-5.4 Mini is an AI model provided by vivgrid.", "family": "gpt-mini", "id": "gpt-5.4-mini", "knowledge": "2025-08-31", "last_updated": "2026-03-17", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.4 Mini", "open_weights": false, "provider": { "npm": "@ai-sdk/openai-compatible" }, "reasoning": true, "release_date": "2026-03-17", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.4-nano": { "attachment": true, "cost": { "cache_read": 0.02, "input": 0.2, "output": 1.25 }, "description": "GPT-5.4 Nano is an AI model provided by vivgrid.", "family": "gpt-nano", "id": "gpt-5.4-nano", "knowledge": "2025-08-31", "last_updated": "2026-03-17", "limit": { "context": 400000, "input": 272000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.4 Nano", "open_weights": false, "provider": { "npm": "@ai-sdk/openai-compatible" }, "reasoning": true, "release_date": "2026-03-17", "structured_output": true, "temperature": false, "tool_call": true }, "gpt-5.5": { "attachment": true, "cost": { "cache_read": 0.5, "context_over_200k": { "cache_read": 1, "input": 10, "output": 45 }, "input": 5, "output": 30, "tiers": [ { "cache_read": 1, "input": 10, "output": 45, "tier": { "size": 272000, "type": "context" } } ] }, "description": "GPT-5.5 is an AI model provided by vivgrid.", "family": "gpt", "id": "gpt-5.5", "knowledge": "2025-12-01", "last_updated": "2026-04-23", "limit": { "context": 1050000, "input": 922000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.5", "open_weights": false, "provider": { "npm": "@ai-sdk/openai-compatible" }, "reasoning": true, "release_date": "2026-04-23", "structured_output": true, "temperature": false, "tool_call": true } }, "name": "Vivgrid", "npm": "@ai-sdk/openai" }, "vultr": { "api": "https://api.vultrinference.com/v1", "doc": "https://api.vultrinference.com/", "env": [ "VULTR_API_KEY" ], "iconURL": "https://models.dev/logos/vultr.svg", "id": "vultr", "models": { "DeepSeek-V3.2": { "attachment": false, "cost": { "input": 0.55, "output": 1.65 }, "description": "DeepSeek V3.2 is an AI model provided by vultr.", "family": "deepseek", "id": "DeepSeek-V3.2", "knowledge": "2024-07", "last_updated": "2025-12-01", "limit": { "context": 127000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3.2", "open_weights": true, "reasoning": false, "release_date": "2025-12-01", "temperature": true, "tool_call": true }, "GLM-5-FP8": { "attachment": false, "cost": { "input": 0.85, "output": 3.1 }, "description": "GLM 5 FP8 is an AI model provided by vultr.", "family": "glm", "id": "GLM-5-FP8", "knowledge": "2025-05", "last_updated": "2026-02-11", "limit": { "context": 200000, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 5 FP8", "open_weights": true, "reasoning": false, "release_date": "2026-02-11", "temperature": true, "tool_call": true }, "Kimi-K2.5": { "attachment": false, "cost": { "input": 0.55, "output": 2.75 }, "description": "Kimi K2 Instruct is an AI model provided by vultr.", "family": "kimi", "id": "Kimi-K2.5", "knowledge": "2024-04", "last_updated": "2026-01-27", "limit": { "context": 254000, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 Instruct", "open_weights": true, "reasoning": false, "release_date": "2026-01-27", "temperature": true, "tool_call": true }, "MiniMax-M2.5": { "attachment": false, "cost": { "input": 0.3, "output": 1.2 }, "description": "MiniMax M2.5 is an AI model provided by vultr.", "family": "minimax", "id": "MiniMax-M2.5", "knowledge": "2024-09", "last_updated": "2025-02-11", "limit": { "context": 194000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M2.5", "open_weights": true, "reasoning": false, "release_date": "2025-02-11", "temperature": true, "tool_call": true }, "gpt-oss-120b": { "attachment": false, "cost": { "input": 0.15, "output": 0.6 }, "description": "GPT OSS 120B is an AI model provided by vultr.", "family": "gpt-oss", "id": "gpt-oss-120b", "knowledge": "2024-06", "last_updated": "2025-08-05", "limit": { "context": 129000, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT OSS 120B", "open_weights": true, "reasoning": false, "release_date": "2025-08-05", "temperature": true, "tool_call": true } }, "name": "Vultr", "npm": "@ai-sdk/openai-compatible" }, "wafer.ai": { "api": "https://pass.wafer.ai/v1", "doc": "https://docs.wafer.ai/wafer-pass", "env": [ "WAFER_API_KEY" ], "iconURL": "https://models.dev/logos/wafer.ai.svg", "id": "wafer.ai", "models": { "GLM-5.1": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "GLM-5.1 is an AI model provided by wafer.ai.", "family": "glm", "id": "GLM-5.1", "knowledge": "2025-04", "last_updated": "2026-04-07", "limit": { "context": 202752, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5.1", "open_weights": true, "reasoning": true, "release_date": "2026-04-07", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen3.5-397B-A17B": { "attachment": true, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "Qwen3.5 397B A17B is an AI model provided by wafer.ai.", "family": "qwen", "id": "Qwen3.5-397B-A17B", "knowledge": "2025-04", "last_updated": "2026-02-16", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Qwen3.5 397B A17B", "open_weights": true, "reasoning": true, "release_date": "2026-02-16", "structured_output": true, "temperature": true, "tool_call": true } }, "name": "Wafer", "npm": "@ai-sdk/openai-compatible" }, "wandb": { "api": "https://api.inference.wandb.ai/v1", "doc": "https://docs.wandb.ai/guides/integrations/inference/", "env": [ "WANDB_API_KEY" ], "iconURL": "https://models.dev/logos/wandb.svg", "id": "wandb", "lobeIcon": "WeightsBiases", "models": { "MiniMaxAI/MiniMax-M2.5": { "attachment": false, "cost": { "input": 0.3, "output": 1.2 }, "description": "MiniMax M2.5 is an AI model provided by wandb.", "family": "minimax", "id": "MiniMaxAI/MiniMax-M2.5", "last_updated": "2026-03-12", "limit": { "context": 196608, "output": 196608 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M2.5", "open_weights": true, "reasoning": false, "release_date": "2026-02-12", "structured_output": true, "temperature": true, "tool_call": true }, "OpenPipe/Qwen3-14B-Instruct": { "attachment": false, "cost": { "input": 0.05, "output": 0.22 }, "description": "OpenPipe Qwen3 14B Instruct is an AI model provided by wandb.", "family": "qwen", "id": "OpenPipe/Qwen3-14B-Instruct", "last_updated": "2026-03-12", "limit": { "context": 32768, "output": 32768 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "OpenPipe Qwen3 14B Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-04-29", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-235B-A22B-Instruct-2507": { "attachment": false, "cost": { "input": 0.1, "output": 0.1 }, "description": "Qwen3 235B A22B Instruct 2507 is an AI model provided by wandb.", "family": "qwen", "id": "Qwen/Qwen3-235B-A22B-Instruct-2507", "knowledge": "2025-04", "last_updated": "2026-03-12", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 235B A22B Instruct 2507", "open_weights": true, "reasoning": false, "release_date": "2025-04-28", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-235B-A22B-Thinking-2507": { "attachment": false, "cost": { "input": 0.1, "output": 0.1 }, "description": "Qwen3-235B-A22B-Thinking-2507 is an AI model provided by wandb.", "family": "qwen", "id": "Qwen/Qwen3-235B-A22B-Thinking-2507", "knowledge": "2025-04", "last_updated": "2026-03-12", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3-235B-A22B-Thinking-2507", "open_weights": true, "reasoning": true, "release_date": "2025-07-25", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-30B-A3B-Instruct-2507": { "attachment": false, "cost": { "input": 0.1, "output": 0.3 }, "description": "Qwen3 30B A3B Instruct 2507 is an AI model provided by wandb.", "family": "qwen", "id": "Qwen/Qwen3-30B-A3B-Instruct-2507", "last_updated": "2026-03-12", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3 30B A3B Instruct 2507", "open_weights": true, "reasoning": false, "release_date": "2025-07-29", "structured_output": true, "temperature": true, "tool_call": true }, "Qwen/Qwen3-Coder-480B-A35B-Instruct": { "attachment": false, "cost": { "input": 1, "output": 1.5 }, "description": "Qwen3-Coder-480B-A35B-Instruct is an AI model provided by wandb.", "family": "qwen", "id": "Qwen/Qwen3-Coder-480B-A35B-Instruct", "knowledge": "2025-04", "last_updated": "2026-03-12", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3-Coder-480B-A35B-Instruct", "open_weights": true, "reasoning": false, "release_date": "2025-07-23", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek-ai/DeepSeek-V3.1": { "attachment": false, "cost": { "input": 0.55, "output": 1.65 }, "description": "DeepSeek V3.1 is an AI model provided by wandb.", "family": "deepseek", "id": "deepseek-ai/DeepSeek-V3.1", "last_updated": "2026-03-12", "limit": { "context": 161000, "output": 161000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3.1", "open_weights": true, "reasoning": false, "release_date": "2025-08-21", "structured_output": true, "temperature": true, "tool_call": true }, "meta-llama/Llama-3.1-70B-Instruct": { "attachment": false, "cost": { "input": 0.8, "output": 0.8 }, "description": "Llama 3.1 70B is an AI model provided by wandb.", "family": "llama", "id": "meta-llama/Llama-3.1-70B-Instruct", "last_updated": "2026-03-12", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama 3.1 70B", "open_weights": true, "reasoning": false, "release_date": "2024-07-23", "structured_output": true, "temperature": true, "tool_call": true }, "meta-llama/Llama-3.1-8B-Instruct": { "attachment": false, "cost": { "input": 0.22, "output": 0.22 }, "description": "Meta-Llama-3.1-8B-Instruct is an AI model provided by wandb.", "family": "llama", "id": "meta-llama/Llama-3.1-8B-Instruct", "knowledge": "2023-12", "last_updated": "2026-03-12", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Meta-Llama-3.1-8B-Instruct", "open_weights": true, "reasoning": true, "release_date": "2024-07-23", "structured_output": true, "temperature": true, "tool_call": true }, "meta-llama/Llama-3.3-70B-Instruct": { "attachment": false, "cost": { "input": 0.71, "output": 0.71 }, "description": "Llama-3.3-70B-Instruct is an AI model provided by wandb.", "family": "llama", "id": "meta-llama/Llama-3.3-70B-Instruct", "knowledge": "2023-12", "last_updated": "2026-03-12", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Llama-3.3-70B-Instruct", "open_weights": true, "reasoning": true, "release_date": "2024-12-06", "structured_output": true, "temperature": true, "tool_call": true }, "meta-llama/Llama-4-Scout-17B-16E-Instruct": { "attachment": false, "cost": { "input": 0.17, "output": 0.66 }, "description": "Llama 4 Scout 17B 16E Instruct is an AI model provided by wandb.", "family": "llama", "id": "meta-llama/Llama-4-Scout-17B-16E-Instruct", "knowledge": "2024-12", "last_updated": "2026-03-12", "limit": { "context": 64000, "output": 64000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Llama 4 Scout 17B 16E Instruct", "open_weights": true, "reasoning": true, "release_date": "2025-01-31", "structured_output": true, "temperature": true, "tool_call": true }, "microsoft/Phi-4-mini-instruct": { "attachment": false, "cost": { "input": 0.08, "output": 0.35 }, "description": "Phi-4-mini-instruct is an AI model provided by wandb.", "family": "phi", "id": "microsoft/Phi-4-mini-instruct", "knowledge": "2023-10", "last_updated": "2026-03-12", "limit": { "context": 128000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Phi-4-mini-instruct", "open_weights": true, "reasoning": true, "release_date": "2024-12-11", "structured_output": true, "temperature": true, "tool_call": true }, "moonshotai/Kimi-K2.5": { "attachment": true, "cost": { "input": 0.5, "output": 2.85 }, "description": "Kimi K2.5 is an AI model provided by wandb.", "family": "kimi", "id": "moonshotai/Kimi-K2.5", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-03-12", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Kimi K2.5", "open_weights": true, "reasoning": true, "release_date": "2026-01-27", "structured_output": true, "temperature": true, "tool_call": true }, "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8": { "attachment": false, "cost": { "input": 0.2, "output": 0.8 }, "description": "NVIDIA Nemotron 3 Super 120B is an AI model provided by wandb.", "family": "nemotron", "id": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8", "last_updated": "2026-03-12", "limit": { "context": 262144, "output": 262144 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "NVIDIA Nemotron 3 Super 120B", "open_weights": true, "reasoning": false, "release_date": "2026-03-11", "structured_output": true, "temperature": true, "tool_call": true }, "openai/gpt-oss-120b": { "attachment": false, "cost": { "input": 0.15, "output": 0.6 }, "description": "gpt-oss-120b is an AI model provided by wandb.", "family": "gpt-oss", "id": "openai/gpt-oss-120b", "last_updated": "2026-03-12", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "gpt-oss-120b", "open_weights": false, "reasoning": false, "release_date": "2025-08-05", "structured_output": true, "temperature": true, "tool_call": true }, "openai/gpt-oss-20b": { "attachment": false, "cost": { "input": 0.05, "output": 0.2 }, "description": "gpt-oss-20b is an AI model provided by wandb.", "family": "gpt-oss", "id": "openai/gpt-oss-20b", "last_updated": "2026-03-12", "limit": { "context": 131072, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "gpt-oss-20b", "open_weights": false, "reasoning": false, "release_date": "2025-08-05", "structured_output": true, "temperature": true, "tool_call": true }, "zai-org/GLM-5-FP8": { "attachment": false, "cost": { "input": 1, "output": 3.2 }, "description": "GLM 5 is an AI model provided by wandb.", "family": "glm", "id": "zai-org/GLM-5-FP8", "last_updated": "2026-03-12", "limit": { "context": 200000, "output": 200000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 5", "open_weights": true, "reasoning": false, "release_date": "2026-02-11", "structured_output": true, "temperature": true, "tool_call": true }, "zai-org/GLM-5.1": { "attachment": false, "cost": { "cache_read": 0.26, "cache_write": 0, "input": 1.4, "output": 4.4 }, "description": "GLM-5.1 is an AI model provided by wandb.", "family": "glm", "id": "zai-org/GLM-5.1", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-03-27", "limit": { "context": 200000, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5.1", "open_weights": false, "reasoning": true, "release_date": "2026-03-27", "structured_output": true, "temperature": true, "tool_call": true } }, "name": "Weights & Biases", "npm": "@ai-sdk/openai-compatible" }, "xai": { "doc": "https://docs.x.ai/docs/models", "env": [ "XAI_API_KEY" ], "iconURL": "https://models.dev/logos/xai.svg", "id": "xai", "lobeIcon": "XAI.Color", "models": { "grok-2": { "attachment": false, "cost": { "cache_read": 2, "input": 2, "output": 10 }, "description": "Grok 2 is an AI model provided by xai.", "family": "grok", "id": "grok-2", "knowledge": "2024-08", "last_updated": "2024-08-20", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok 2", "open_weights": false, "reasoning": false, "release_date": "2024-08-20", "temperature": true, "tool_call": true }, "grok-2-1212": { "attachment": false, "cost": { "cache_read": 2, "input": 2, "output": 10 }, "description": "Grok 2 (1212) is an AI model provided by xai.", "family": "grok", "id": "grok-2-1212", "knowledge": "2024-08", "last_updated": "2024-12-12", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok 2 (1212)", "open_weights": false, "reasoning": false, "release_date": "2024-12-12", "temperature": true, "tool_call": true }, "grok-2-latest": { "attachment": false, "cost": { "cache_read": 2, "input": 2, "output": 10 }, "description": "Grok 2 Latest is an AI model provided by xai.", "family": "grok", "id": "grok-2-latest", "knowledge": "2024-08", "last_updated": "2024-12-12", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok 2 Latest", "open_weights": false, "reasoning": false, "release_date": "2024-08-20", "temperature": true, "tool_call": true }, "grok-2-vision": { "attachment": true, "cost": { "cache_read": 2, "input": 2, "output": 10 }, "description": "Grok 2 Vision is an AI model provided by xai.", "family": "grok", "id": "grok-2-vision", "knowledge": "2024-08", "last_updated": "2024-08-20", "limit": { "context": 8192, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 2 Vision", "open_weights": false, "reasoning": false, "release_date": "2024-08-20", "temperature": true, "tool_call": true }, "grok-2-vision-1212": { "attachment": true, "cost": { "cache_read": 2, "input": 2, "output": 10 }, "description": "Grok 2 Vision (1212) is an AI model provided by xai.", "family": "grok", "id": "grok-2-vision-1212", "knowledge": "2024-08", "last_updated": "2024-12-12", "limit": { "context": 8192, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 2 Vision (1212)", "open_weights": false, "reasoning": false, "release_date": "2024-08-20", "temperature": true, "tool_call": true }, "grok-2-vision-latest": { "attachment": true, "cost": { "cache_read": 2, "input": 2, "output": 10 }, "description": "Grok 2 Vision Latest is an AI model provided by xai.", "family": "grok", "id": "grok-2-vision-latest", "knowledge": "2024-08", "last_updated": "2024-12-12", "limit": { "context": 8192, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 2 Vision Latest", "open_weights": false, "reasoning": false, "release_date": "2024-08-20", "temperature": true, "tool_call": true }, "grok-3": { "attachment": false, "cost": { "cache_read": 0.75, "input": 3, "output": 15 }, "description": "Grok 3 is an AI model provided by xai.", "family": "grok", "id": "grok-3", "knowledge": "2024-11", "last_updated": "2025-02-17", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok 3", "open_weights": false, "reasoning": false, "release_date": "2025-02-17", "temperature": true, "tool_call": true }, "grok-3-fast": { "attachment": false, "cost": { "cache_read": 1.25, "input": 5, "output": 25 }, "description": "Grok 3 Fast is an AI model provided by xai.", "family": "grok", "id": "grok-3-fast", "knowledge": "2024-11", "last_updated": "2025-02-17", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok 3 Fast", "open_weights": false, "reasoning": false, "release_date": "2025-02-17", "temperature": true, "tool_call": true }, "grok-3-fast-latest": { "attachment": false, "cost": { "cache_read": 1.25, "input": 5, "output": 25 }, "description": "Grok 3 Fast Latest is an AI model provided by xai.", "family": "grok", "id": "grok-3-fast-latest", "knowledge": "2024-11", "last_updated": "2025-02-17", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok 3 Fast Latest", "open_weights": false, "reasoning": false, "release_date": "2025-02-17", "temperature": true, "tool_call": true }, "grok-3-latest": { "attachment": false, "cost": { "cache_read": 0.75, "input": 3, "output": 15 }, "description": "Grok 3 Latest is an AI model provided by xai.", "family": "grok", "id": "grok-3-latest", "knowledge": "2024-11", "last_updated": "2025-02-17", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok 3 Latest", "open_weights": false, "reasoning": false, "release_date": "2025-02-17", "temperature": true, "tool_call": true }, "grok-3-mini": { "attachment": false, "cost": { "cache_read": 0.075, "input": 0.3, "output": 0.5, "reasoning": 0.5 }, "description": "Grok 3 Mini is an AI model provided by xai.", "family": "grok", "id": "grok-3-mini", "knowledge": "2024-11", "last_updated": "2025-02-17", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok 3 Mini", "open_weights": false, "reasoning": true, "release_date": "2025-02-17", "temperature": true, "tool_call": true }, "grok-3-mini-fast": { "attachment": false, "cost": { "cache_read": 0.15, "input": 0.6, "output": 4, "reasoning": 4 }, "description": "Grok 3 Mini Fast is an AI model provided by xai.", "family": "grok", "id": "grok-3-mini-fast", "knowledge": "2024-11", "last_updated": "2025-02-17", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok 3 Mini Fast", "open_weights": false, "reasoning": true, "release_date": "2025-02-17", "temperature": true, "tool_call": true }, "grok-3-mini-fast-latest": { "attachment": false, "cost": { "cache_read": 0.15, "input": 0.6, "output": 4, "reasoning": 4 }, "description": "Grok 3 Mini Fast Latest is an AI model provided by xai.", "family": "grok", "id": "grok-3-mini-fast-latest", "knowledge": "2024-11", "last_updated": "2025-02-17", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok 3 Mini Fast Latest", "open_weights": false, "reasoning": true, "release_date": "2025-02-17", "temperature": true, "tool_call": true }, "grok-3-mini-latest": { "attachment": false, "cost": { "cache_read": 0.075, "input": 0.3, "output": 0.5, "reasoning": 0.5 }, "description": "Grok 3 Mini Latest is an AI model provided by xai.", "family": "grok", "id": "grok-3-mini-latest", "knowledge": "2024-11", "last_updated": "2025-02-17", "limit": { "context": 131072, "output": 8192 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok 3 Mini Latest", "open_weights": false, "reasoning": true, "release_date": "2025-02-17", "temperature": true, "tool_call": true }, "grok-4": { "attachment": false, "cost": { "cache_read": 0.75, "input": 3, "output": 15, "reasoning": 15 }, "description": "Grok 4 is an AI model provided by xai.", "family": "grok", "id": "grok-4", "knowledge": "2025-07", "last_updated": "2025-07-09", "limit": { "context": 256000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok 4", "open_weights": false, "reasoning": true, "release_date": "2025-07-09", "temperature": true, "tool_call": true }, "grok-4-1-fast": { "attachment": true, "cost": { "cache_read": 0.05, "input": 0.2, "output": 0.5 }, "description": "Grok 4.1 Fast is an AI model provided by xai.", "family": "grok", "id": "grok-4-1-fast", "knowledge": "2025-07", "last_updated": "2025-11-19", "limit": { "context": 2000000, "output": 30000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 4.1 Fast", "open_weights": false, "reasoning": true, "release_date": "2025-11-19", "temperature": true, "tool_call": true }, "grok-4-1-fast-non-reasoning": { "attachment": true, "cost": { "cache_read": 0.05, "input": 0.2, "output": 0.5 }, "description": "Grok 4.1 Fast (Non-Reasoning) is an AI model provided by xai.", "family": "grok", "id": "grok-4-1-fast-non-reasoning", "knowledge": "2025-07", "last_updated": "2025-11-19", "limit": { "context": 2000000, "output": 30000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 4.1 Fast (Non-Reasoning)", "open_weights": false, "reasoning": false, "release_date": "2025-11-19", "temperature": true, "tool_call": true }, "grok-4-fast": { "attachment": true, "cost": { "cache_read": 0.05, "input": 0.2, "output": 0.5 }, "description": "Grok 4 Fast is an AI model provided by xai.", "family": "grok", "id": "grok-4-fast", "knowledge": "2025-07", "last_updated": "2025-09-19", "limit": { "context": 2000000, "output": 30000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 4 Fast", "open_weights": false, "reasoning": true, "release_date": "2025-09-19", "temperature": true, "tool_call": true }, "grok-4-fast-non-reasoning": { "attachment": true, "cost": { "cache_read": 0.05, "input": 0.2, "output": 0.5 }, "description": "Grok 4 Fast (Non-Reasoning) is an AI model provided by xai.", "family": "grok", "id": "grok-4-fast-non-reasoning", "knowledge": "2025-07", "last_updated": "2025-09-19", "limit": { "context": 2000000, "output": 30000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 4 Fast (Non-Reasoning)", "open_weights": false, "reasoning": false, "release_date": "2025-09-19", "temperature": true, "tool_call": true }, "grok-4.20-0309-non-reasoning": { "attachment": true, "cost": { "cache_read": 0.2, "context_over_200k": { "cache_read": 0.4, "input": 4, "output": 12 }, "input": 2, "output": 6, "tiers": [ { "cache_read": 0.4, "input": 4, "output": 12, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Grok 4.20 (Non-Reasoning) is an AI model provided by xai.", "family": "grok", "id": "grok-4.20-0309-non-reasoning", "last_updated": "2026-03-09", "limit": { "context": 2000000, "output": 30000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 4.20 (Non-Reasoning)", "open_weights": false, "reasoning": false, "release_date": "2026-03-09", "temperature": true, "tool_call": true }, "grok-4.20-0309-reasoning": { "attachment": true, "cost": { "cache_read": 0.2, "context_over_200k": { "cache_read": 0.4, "input": 4, "output": 12 }, "input": 2, "output": 6, "tiers": [ { "cache_read": 0.4, "input": 4, "output": 12, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Grok 4.20 (Reasoning) is an AI model provided by xai.", "family": "grok", "id": "grok-4.20-0309-reasoning", "last_updated": "2026-03-09", "limit": { "context": 2000000, "output": 30000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 4.20 (Reasoning)", "open_weights": false, "reasoning": true, "release_date": "2026-03-09", "temperature": true, "tool_call": true }, "grok-4.20-multi-agent-0309": { "attachment": true, "cost": { "cache_read": 0.2, "context_over_200k": { "cache_read": 0.4, "input": 4, "output": 12 }, "input": 2, "output": 6, "tiers": [ { "cache_read": 0.4, "input": 4, "output": 12, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Grok 4.20 Multi-Agent is an AI model provided by xai.", "family": "grok", "id": "grok-4.20-multi-agent-0309", "last_updated": "2026-03-09", "limit": { "context": 2000000, "output": 30000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 4.20 Multi-Agent", "open_weights": false, "reasoning": true, "release_date": "2026-03-09", "temperature": true, "tool_call": false }, "grok-4.3": { "attachment": true, "cost": { "cache_read": 0.2, "context_over_200k": { "cache_read": 0.4, "input": 2.5, "output": 5 }, "input": 1.25, "output": 2.5, "tiers": [ { "cache_read": 0.4, "input": 2.5, "output": 5, "tier": { "size": 200000, "type": "context" } } ] }, "description": "Grok 4.3 is an AI model provided by xai.", "family": "grok", "id": "grok-4.3", "last_updated": "2026-05-01", "limit": { "context": 1000000, "output": 30000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 4.3", "open_weights": false, "reasoning": true, "release_date": "2026-05-01", "temperature": true, "tool_call": true }, "grok-beta": { "attachment": false, "cost": { "cache_read": 5, "input": 5, "output": 15 }, "description": "Grok Beta is an AI model provided by xai.", "family": "grok-beta", "id": "grok-beta", "knowledge": "2024-08", "last_updated": "2024-11-01", "limit": { "context": 131072, "output": 4096 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok Beta", "open_weights": false, "reasoning": false, "release_date": "2024-11-01", "temperature": true, "tool_call": true }, "grok-code-fast-1": { "attachment": false, "cost": { "cache_read": 0.02, "input": 0.2, "output": 1.5 }, "description": "Grok Code Fast 1 is an AI model provided by xai.", "family": "grok", "id": "grok-code-fast-1", "knowledge": "2023-10", "last_updated": "2025-08-28", "limit": { "context": 256000, "output": 10000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok Code Fast 1", "open_weights": false, "reasoning": true, "release_date": "2025-08-28", "temperature": true, "tool_call": true }, "grok-vision-beta": { "attachment": true, "cost": { "cache_read": 5, "input": 5, "output": 15 }, "description": "Grok Vision Beta is an AI model provided by xai.", "family": "grok-vision", "id": "grok-vision-beta", "knowledge": "2024-08", "last_updated": "2024-11-01", "limit": { "context": 8192, "output": 4096 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok Vision Beta", "open_weights": false, "reasoning": false, "release_date": "2024-11-01", "temperature": true, "tool_call": true } }, "name": "xAI", "npm": "@ai-sdk/xai" }, "xiaomi": { "api": "https://api.xiaomimimo.com/v1", "doc": "https://platform.xiaomimimo.com/#/docs", "env": [ "XIAOMI_API_KEY" ], "iconURL": "https://models.dev/logos/xiaomi.svg", "id": "xiaomi", "models": { "mimo-v2-flash": { "attachment": false, "cost": { "cache_read": 0.01, "input": 0.1, "output": 0.3 }, "description": "MiMo-V2-Flash is an AI model provided by xiaomi.", "family": "mimo", "id": "mimo-v2-flash", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-12-01", "last_updated": "2026-02-04", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiMo-V2-Flash", "open_weights": true, "reasoning": true, "release_date": "2025-12-16", "temperature": true, "tool_call": true }, "mimo-v2-omni": { "attachment": true, "cost": { "cache_read": 0.08, "input": 0.4, "output": 2 }, "description": "MiMo-V2-Omni is an AI model provided by xiaomi.", "family": "mimo", "id": "mimo-v2-omni", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-12", "last_updated": "2026-03-18", "limit": { "context": 262144, "output": 131072 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "MiMo-V2-Omni", "open_weights": false, "reasoning": true, "release_date": "2026-03-18", "temperature": true, "tool_call": true }, "mimo-v2-pro": { "attachment": false, "cost": { "cache_read": 0.2, "context_over_200k": { "cache_read": 0.4, "input": 2, "output": 6 }, "input": 1, "output": 3, "tiers": [ { "cache_read": 0.4, "input": 2, "output": 6, "tier": { "size": 256000, "type": "context" } } ] }, "description": "MiMo-V2-Pro is an AI model provided by xiaomi.", "family": "mimo", "id": "mimo-v2-pro", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-12", "last_updated": "2026-03-18", "limit": { "context": 1048576, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiMo-V2-Pro", "open_weights": false, "reasoning": true, "release_date": "2026-03-18", "temperature": true, "tool_call": true }, "mimo-v2.5": { "attachment": true, "cost": { "cache_read": 0.08, "context_over_200k": { "cache_read": 0.16, "input": 0.8, "output": 4 }, "input": 0.4, "output": 2, "tiers": [ { "cache_read": 0.16, "input": 0.8, "output": 4, "tier": { "size": 256000, "type": "context" } } ] }, "description": "MiMo-V2.5 is an AI model provided by xiaomi.", "family": "mimo", "id": "mimo-v2.5", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-12", "last_updated": "2026-04-22", "limit": { "context": 1048576, "output": 131072 }, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "name": "MiMo-V2.5", "open_weights": true, "reasoning": true, "release_date": "2026-04-22", "temperature": true, "tool_call": true }, "mimo-v2.5-pro": { "attachment": false, "cost": { "cache_read": 0.2, "context_over_200k": { "cache_read": 0.4, "input": 2, "output": 6 }, "input": 1, "output": 3, "tiers": [ { "cache_read": 0.4, "input": 2, "output": 6, "tier": { "size": 256000, "type": "context" } } ] }, "description": "MiMo-V2.5-Pro is an AI model provided by xiaomi.", "family": "mimo", "id": "mimo-v2.5-pro", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-12", "last_updated": "2026-04-22", "limit": { "context": 1048576, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiMo-V2.5-Pro", "open_weights": true, "reasoning": true, "release_date": "2026-04-22", "temperature": true, "tool_call": true } }, "name": "Xiaomi", "npm": "@ai-sdk/openai-compatible" }, "xiaomi-token-plan-ams": { "api": "https://token-plan-ams.xiaomimimo.com/v1", "doc": "https://platform.xiaomimimo.com/#/docs", "env": [ "XIAOMI_API_KEY" ], "iconURL": "https://models.dev/logos/xiaomi-token-plan-ams.svg", "id": "xiaomi-token-plan-ams", "models": { "mimo-v2-flash": { "attachment": false, "cost": { "cache_read": 0, "input": 0, "output": 0 }, "description": "MiMo-V2-Flash is an AI model provided by xiaomi-token-plan-ams.", "family": "mimo", "id": "mimo-v2-flash", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-12-01", "last_updated": "2026-02-04", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiMo-V2-Flash", "open_weights": true, "reasoning": true, "release_date": "2025-12-16", "temperature": true, "tool_call": true }, "mimo-v2-omni": { "attachment": true, "cost": { "cache_read": 0, "input": 0, "output": 0 }, "description": "MiMo-V2-Omni is an AI model provided by xiaomi-token-plan-ams.", "family": "mimo", "id": "mimo-v2-omni", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-12", "last_updated": "2026-03-18", "limit": { "context": 262144, "output": 131072 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "MiMo-V2-Omni", "open_weights": false, "reasoning": true, "release_date": "2026-03-18", "temperature": true, "tool_call": true }, "mimo-v2-pro": { "attachment": false, "cost": { "cache_read": 0, "input": 0, "output": 0 }, "description": "MiMo-V2-Pro is an AI model provided by xiaomi-token-plan-ams.", "family": "mimo", "id": "mimo-v2-pro", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-12", "last_updated": "2026-03-18", "limit": { "context": 1048576, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiMo-V2-Pro", "open_weights": false, "reasoning": true, "release_date": "2026-03-18", "temperature": true, "tool_call": true }, "mimo-v2-tts": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "MiMo-V2-TTS is an AI model provided by xiaomi-token-plan-ams.", "family": "mimo", "id": "mimo-v2-tts", "last_updated": "2026-03-18", "limit": { "context": 8192, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "name": "MiMo-V2-TTS", "open_weights": true, "reasoning": false, "release_date": "2026-03-18", "tool_call": false }, "mimo-v2.5": { "attachment": true, "cost": { "cache_read": 0, "input": 0, "output": 0 }, "description": "MiMo-V2.5 is an AI model provided by xiaomi-token-plan-ams.", "family": "mimo", "id": "mimo-v2.5", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-12", "last_updated": "2026-04-22", "limit": { "context": 1048576, "output": 131072 }, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "name": "MiMo-V2.5", "open_weights": true, "reasoning": true, "release_date": "2026-04-22", "temperature": true, "tool_call": true }, "mimo-v2.5-pro": { "attachment": false, "cost": { "cache_read": 0, "input": 0, "output": 0 }, "description": "MiMo-V2.5-Pro is an AI model provided by xiaomi-token-plan-ams.", "family": "mimo", "id": "mimo-v2.5-pro", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-12", "last_updated": "2026-04-22", "limit": { "context": 1048576, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiMo-V2.5-Pro", "open_weights": true, "reasoning": true, "release_date": "2026-04-22", "temperature": true, "tool_call": true } }, "name": "Xiaomi Token Plan (Europe)", "npm": "@ai-sdk/openai-compatible" }, "xiaomi-token-plan-cn": { "api": "https://token-plan-cn.xiaomimimo.com/v1", "doc": "https://platform.xiaomimimo.com/#/docs", "env": [ "XIAOMI_API_KEY" ], "iconURL": "https://models.dev/logos/xiaomi-token-plan-cn.svg", "id": "xiaomi-token-plan-cn", "models": { "mimo-v2-flash": { "attachment": false, "cost": { "cache_read": 0, "input": 0, "output": 0 }, "description": "MiMo-V2-Flash is an AI model provided by xiaomi-token-plan-cn.", "family": "mimo", "id": "mimo-v2-flash", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-12-01", "last_updated": "2026-02-04", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiMo-V2-Flash", "open_weights": true, "reasoning": true, "release_date": "2025-12-16", "temperature": true, "tool_call": true }, "mimo-v2-omni": { "attachment": true, "cost": { "cache_read": 0, "input": 0, "output": 0 }, "description": "MiMo-V2-Omni is an AI model provided by xiaomi-token-plan-cn.", "family": "mimo", "id": "mimo-v2-omni", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-12", "last_updated": "2026-03-18", "limit": { "context": 262144, "output": 131072 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "MiMo-V2-Omni", "open_weights": false, "reasoning": true, "release_date": "2026-03-18", "temperature": true, "tool_call": true }, "mimo-v2-pro": { "attachment": false, "cost": { "cache_read": 0, "input": 0, "output": 0 }, "description": "MiMo-V2-Pro is an AI model provided by xiaomi-token-plan-cn.", "family": "mimo", "id": "mimo-v2-pro", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-12", "last_updated": "2026-03-18", "limit": { "context": 1048576, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiMo-V2-Pro", "open_weights": false, "reasoning": true, "release_date": "2026-03-18", "temperature": true, "tool_call": true }, "mimo-v2-tts": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "MiMo-V2-TTS is an AI model provided by xiaomi-token-plan-cn.", "family": "mimo", "id": "mimo-v2-tts", "last_updated": "2026-03-18", "limit": { "context": 8192, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "name": "MiMo-V2-TTS", "open_weights": true, "reasoning": false, "release_date": "2026-03-18", "tool_call": false }, "mimo-v2.5": { "attachment": true, "cost": { "cache_read": 0, "input": 0, "output": 0 }, "description": "MiMo-V2.5 is an AI model provided by xiaomi-token-plan-cn.", "family": "mimo", "id": "mimo-v2.5", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-12", "last_updated": "2026-04-22", "limit": { "context": 1048576, "output": 131072 }, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "name": "MiMo-V2.5", "open_weights": true, "reasoning": true, "release_date": "2026-04-22", "temperature": true, "tool_call": true }, "mimo-v2.5-pro": { "attachment": false, "cost": { "cache_read": 0, "input": 0, "output": 0 }, "description": "MiMo-V2.5-Pro is an AI model provided by xiaomi-token-plan-cn.", "family": "mimo", "id": "mimo-v2.5-pro", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-12", "last_updated": "2026-04-22", "limit": { "context": 1048576, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiMo-V2.5-Pro", "open_weights": true, "reasoning": true, "release_date": "2026-04-22", "temperature": true, "tool_call": true } }, "name": "Xiaomi Token Plan (China)", "npm": "@ai-sdk/openai-compatible" }, "xiaomi-token-plan-sgp": { "api": "https://token-plan-sgp.xiaomimimo.com/v1", "doc": "https://platform.xiaomimimo.com/#/docs", "env": [ "XIAOMI_API_KEY" ], "iconURL": "https://models.dev/logos/xiaomi-token-plan-sgp.svg", "id": "xiaomi-token-plan-sgp", "models": { "mimo-v2-flash": { "attachment": false, "cost": { "cache_read": 0, "input": 0, "output": 0 }, "description": "MiMo-V2-Flash is an AI model provided by xiaomi-token-plan-sgp.", "family": "mimo", "id": "mimo-v2-flash", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-12-01", "last_updated": "2026-02-04", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiMo-V2-Flash", "open_weights": true, "reasoning": true, "release_date": "2025-12-16", "temperature": true, "tool_call": true }, "mimo-v2-omni": { "attachment": true, "cost": { "cache_read": 0, "input": 0, "output": 0 }, "description": "MiMo-V2-Omni is an AI model provided by xiaomi-token-plan-sgp.", "family": "mimo", "id": "mimo-v2-omni", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-12", "last_updated": "2026-03-18", "limit": { "context": 262144, "output": 131072 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "MiMo-V2-Omni", "open_weights": false, "reasoning": true, "release_date": "2026-03-18", "temperature": true, "tool_call": true }, "mimo-v2-pro": { "attachment": false, "cost": { "cache_read": 0, "input": 0, "output": 0 }, "description": "MiMo-V2-Pro is an AI model provided by xiaomi-token-plan-sgp.", "family": "mimo", "id": "mimo-v2-pro", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-12", "last_updated": "2026-03-18", "limit": { "context": 1048576, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiMo-V2-Pro", "open_weights": false, "reasoning": true, "release_date": "2026-03-18", "temperature": true, "tool_call": true }, "mimo-v2-tts": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "MiMo-V2-TTS is an AI model provided by xiaomi-token-plan-sgp.", "family": "mimo", "id": "mimo-v2-tts", "last_updated": "2026-03-18", "limit": { "context": 8192, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "name": "MiMo-V2-TTS", "open_weights": true, "reasoning": false, "release_date": "2026-03-18", "tool_call": false }, "mimo-v2.5": { "attachment": true, "cost": { "cache_read": 0, "input": 0, "output": 0 }, "description": "MiMo-V2.5 is an AI model provided by xiaomi-token-plan-sgp.", "family": "mimo", "id": "mimo-v2.5", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-12", "last_updated": "2026-04-22", "limit": { "context": 1048576, "output": 131072 }, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "name": "MiMo-V2.5", "open_weights": true, "reasoning": true, "release_date": "2026-04-22", "temperature": true, "tool_call": true }, "mimo-v2.5-pro": { "attachment": false, "cost": { "cache_read": 0, "input": 0, "output": 0 }, "description": "MiMo-V2.5-Pro is an AI model provided by xiaomi-token-plan-sgp.", "family": "mimo", "id": "mimo-v2.5-pro", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-12", "last_updated": "2026-04-22", "limit": { "context": 1048576, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiMo-V2.5-Pro", "open_weights": true, "reasoning": true, "release_date": "2026-04-22", "temperature": true, "tool_call": true } }, "name": "Xiaomi Token Plan (Singapore)", "npm": "@ai-sdk/openai-compatible" }, "xpersona": { "api": "https://xpersona.co/v1", "doc": "https://xpersona.co/docs", "env": [ "XPERSONA_API_KEY" ], "iconURL": "https://models.dev/logos/xpersona.svg", "id": "xpersona", "models": { "xpersona-frieren-coder": { "attachment": false, "cost": { "cache_read": 0.15, "input": 1.5, "output": 6, "reasoning": 6 }, "description": "Xpersona Frieren Coder is an AI model provided by xpersona.", "id": "xpersona-frieren-coder", "knowledge": "2025-08-31", "last_updated": "2026-05-13", "limit": { "context": 128000, "output": 16384 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Xpersona Frieren Coder", "open_weights": false, "reasoning": true, "release_date": "2026-05-01", "structured_output": true, "temperature": false, "tool_call": true } }, "name": "Xpersona", "npm": "@ai-sdk/openai-compatible" }, "zai": { "api": "https://api.z.ai/api/paas/v4", "doc": "https://docs.z.ai/guides/overview/pricing", "env": [ "ZHIPU_API_KEY" ], "iconURL": "https://models.dev/logos/zai.svg", "id": "zai", "lobeIcon": "ZAI", "models": { "glm-4.5": { "attachment": false, "cost": { "cache_read": 0.11, "cache_write": 0, "input": 0.6, "output": 2.2 }, "description": "GLM-4.5 is an AI model provided by zai.", "family": "glm", "id": "glm-4.5", "knowledge": "2025-04", "last_updated": "2025-07-28", "limit": { "context": 131072, "output": 98304 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.5", "open_weights": true, "reasoning": true, "release_date": "2025-07-28", "temperature": true, "tool_call": true }, "glm-4.5-air": { "attachment": false, "cost": { "cache_read": 0.03, "cache_write": 0, "input": 0.2, "output": 1.1 }, "description": "GLM-4.5-Air is an AI model provided by zai.", "family": "glm-air", "id": "glm-4.5-air", "knowledge": "2025-04", "last_updated": "2025-07-28", "limit": { "context": 131072, "output": 98304 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.5-Air", "open_weights": true, "reasoning": true, "release_date": "2025-07-28", "temperature": true, "tool_call": true }, "glm-4.5-flash": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "GLM-4.5-Flash is an AI model provided by zai.", "family": "glm-flash", "id": "glm-4.5-flash", "knowledge": "2025-04", "last_updated": "2025-07-28", "limit": { "context": 131072, "output": 98304 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.5-Flash", "open_weights": true, "reasoning": true, "release_date": "2025-07-28", "temperature": true, "tool_call": true }, "glm-4.5v": { "attachment": true, "cost": { "input": 0.6, "output": 1.8 }, "description": "GLM-4.5V is an AI model provided by zai.", "family": "glm", "id": "glm-4.5v", "knowledge": "2025-04", "last_updated": "2025-08-11", "limit": { "context": 64000, "output": 16384 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "GLM-4.5V", "open_weights": true, "reasoning": true, "release_date": "2025-08-11", "temperature": true, "tool_call": true }, "glm-4.6": { "attachment": false, "cost": { "cache_read": 0.11, "cache_write": 0, "input": 0.6, "output": 2.2 }, "description": "GLM-4.6 is an AI model provided by zai.", "family": "glm", "id": "glm-4.6", "knowledge": "2025-04", "last_updated": "2025-09-30", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.6", "open_weights": true, "reasoning": true, "release_date": "2025-09-30", "temperature": true, "tool_call": true }, "glm-4.6v": { "attachment": true, "cost": { "input": 0.3, "output": 0.9 }, "description": "GLM-4.6V is an AI model provided by zai.", "family": "glm", "id": "glm-4.6v", "knowledge": "2025-04", "last_updated": "2025-12-08", "limit": { "context": 128000, "output": 32768 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "GLM-4.6V", "open_weights": true, "reasoning": true, "release_date": "2025-12-08", "temperature": true, "tool_call": true }, "glm-4.7": { "attachment": false, "cost": { "cache_read": 0.11, "cache_write": 0, "input": 0.6, "output": 2.2 }, "description": "GLM-4.7 is an AI model provided by zai.", "family": "glm", "id": "glm-4.7", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-04", "last_updated": "2025-12-22", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.7", "open_weights": true, "reasoning": true, "release_date": "2025-12-22", "temperature": true, "tool_call": true }, "glm-4.7-flash": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "GLM-4.7-Flash is an AI model provided by zai.", "family": "glm-flash", "id": "glm-4.7-flash", "knowledge": "2025-04", "last_updated": "2026-01-19", "limit": { "context": 200000, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.7-Flash", "open_weights": true, "reasoning": true, "release_date": "2026-01-19", "temperature": true, "tool_call": true }, "glm-4.7-flashx": { "attachment": false, "cost": { "cache_read": 0.01, "cache_write": 0, "input": 0.07, "output": 0.4 }, "description": "GLM-4.7-FlashX is an AI model provided by zai.", "family": "glm-flash", "id": "glm-4.7-flashx", "knowledge": "2025-04", "last_updated": "2026-01-19", "limit": { "context": 200000, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.7-FlashX", "open_weights": true, "reasoning": true, "release_date": "2026-01-19", "temperature": true, "tool_call": true }, "glm-5": { "attachment": false, "cost": { "cache_read": 0.2, "cache_write": 0, "input": 1, "output": 3.2 }, "description": "GLM-5 is an AI model provided by zai.", "family": "glm", "id": "glm-5", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-02-11", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5", "open_weights": true, "reasoning": true, "release_date": "2026-02-11", "temperature": true, "tool_call": true }, "glm-5-turbo": { "attachment": false, "cost": { "cache_read": 0.24, "cache_write": 0, "input": 1.2, "output": 4 }, "description": "GLM-5-Turbo is an AI model provided by zai.", "family": "glm", "id": "glm-5-turbo", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-03-16", "limit": { "context": 200000, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5-Turbo", "open_weights": false, "reasoning": true, "release_date": "2026-03-16", "structured_output": true, "temperature": true, "tool_call": true }, "glm-5.1": { "attachment": false, "cost": { "cache_read": 0.26, "cache_write": 0, "input": 1.4, "output": 4.4 }, "description": "GLM-5.1 is an AI model provided by zai.", "family": "glm", "id": "glm-5.1", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-03-27", "limit": { "context": 200000, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5.1", "open_weights": false, "reasoning": true, "release_date": "2026-03-27", "structured_output": true, "temperature": true, "tool_call": true }, "glm-5v-turbo": { "attachment": true, "cost": { "cache_read": 0.24, "cache_write": 0, "input": 1.2, "output": 4 }, "description": "GLM-5V-Turbo is an AI model provided by zai.", "family": "glm", "id": "glm-5v-turbo", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-01", "limit": { "context": 200000, "output": 131072 }, "modalities": { "input": [ "text", "image", "video", "pdf" ], "output": [ "text" ] }, "name": "GLM-5V-Turbo", "open_weights": false, "reasoning": true, "release_date": "2026-04-01", "temperature": true, "tool_call": true } }, "name": "Z.AI", "npm": "@ai-sdk/openai-compatible" }, "zai-coding-plan": { "api": "https://api.z.ai/api/coding/paas/v4", "doc": "https://docs.z.ai/devpack/overview", "env": [ "ZHIPU_API_KEY" ], "iconURL": "https://models.dev/logos/zai-coding-plan.svg", "id": "zai-coding-plan", "models": { "glm-4.5-air": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "GLM-4.5-Air is an AI model provided by zai-coding-plan.", "family": "glm-air", "id": "glm-4.5-air", "knowledge": "2025-04", "last_updated": "2025-07-28", "limit": { "context": 131072, "output": 98304 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.5-Air", "open_weights": true, "reasoning": true, "release_date": "2025-07-28", "temperature": true, "tool_call": true }, "glm-4.7": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "GLM-4.7 is an AI model provided by zai-coding-plan.", "family": "glm", "id": "glm-4.7", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-04", "last_updated": "2025-12-22", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.7", "open_weights": true, "reasoning": true, "release_date": "2025-12-22", "temperature": true, "tool_call": true }, "glm-5-turbo": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "GLM-5-Turbo is an AI model provided by zai-coding-plan.", "family": "glm", "id": "glm-5-turbo", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-03-16", "limit": { "context": 200000, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5-Turbo", "open_weights": false, "reasoning": true, "release_date": "2026-03-16", "structured_output": true, "temperature": true, "tool_call": true }, "glm-5.1": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "GLM-5.1 is an AI model provided by zai-coding-plan.", "family": "glm", "id": "glm-5.1", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-03-27", "limit": { "context": 200000, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5.1", "open_weights": false, "reasoning": true, "release_date": "2026-03-27", "structured_output": true, "temperature": true, "tool_call": true }, "glm-5v-turbo": { "attachment": true, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "GLM-5V-Turbo is an AI model provided by zai-coding-plan.", "family": "glm", "id": "glm-5v-turbo", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-01", "limit": { "context": 200000, "output": 131072 }, "modalities": { "input": [ "text", "image", "video", "pdf" ], "output": [ "text" ] }, "name": "GLM-5V-Turbo", "open_weights": false, "reasoning": true, "release_date": "2026-04-01", "temperature": true, "tool_call": true } }, "name": "Z.AI Coding Plan", "npm": "@ai-sdk/openai-compatible" }, "zenmux": { "api": "https://zenmux.ai/api/v1", "doc": "https://docs.zenmux.ai", "env": [ "ZENMUX_API_KEY" ], "iconURL": "https://models.dev/logos/zenmux.svg", "id": "zenmux", "models": { "anthropic/claude-3.5-haiku": { "attachment": true, "cost": { "cache_read": 0.08, "cache_write": 1, "input": 0.8, "output": 4 }, "description": "Claude 3.5 Haiku is an AI model provided by zenmux.", "id": "anthropic/claude-3.5-haiku", "knowledge": "2025-01-01", "last_updated": "2024-11-04", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Claude 3.5 Haiku", "open_weights": false, "provider": { "api": "https://zenmux.ai/api/anthropic/v1", "npm": "@ai-sdk/anthropic" }, "reasoning": false, "release_date": "2024-11-04", "temperature": true, "tool_call": true }, "anthropic/claude-3.7-sonnet": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude 3.7 Sonnet is an AI model provided by zenmux.", "id": "anthropic/claude-3.7-sonnet", "knowledge": "2025-01-01", "last_updated": "2025-02-24", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude 3.7 Sonnet", "open_weights": false, "provider": { "api": "https://zenmux.ai/api/anthropic/v1", "npm": "@ai-sdk/anthropic" }, "reasoning": true, "release_date": "2025-02-24", "temperature": true, "tool_call": true }, "anthropic/claude-haiku-4.5": { "attachment": true, "cost": { "cache_read": 0.1, "cache_write": 1.25, "input": 1, "output": 5 }, "description": "Claude Haiku 4.5 is an AI model provided by zenmux.", "id": "anthropic/claude-haiku-4.5", "knowledge": "2025-01-01", "last_updated": "2025-10-15", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "name": "Claude Haiku 4.5", "open_weights": false, "provider": { "api": "https://zenmux.ai/api/anthropic/v1", "npm": "@ai-sdk/anthropic" }, "reasoning": false, "release_date": "2025-10-15", "temperature": true, "tool_call": true }, "anthropic/claude-opus-4": { "attachment": true, "cost": { "cache_read": 1.5, "cache_write": 18.75, "input": 15, "output": 75 }, "description": "Claude Opus 4 is an AI model provided by zenmux.", "id": "anthropic/claude-opus-4", "knowledge": "2025-01-01", "last_updated": "2025-05-22", "limit": { "context": 200000, "output": 32000 }, "modalities": { "input": [ "image", "text", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4", "open_weights": false, "provider": { "api": "https://zenmux.ai/api/anthropic/v1", "npm": "@ai-sdk/anthropic" }, "reasoning": true, "release_date": "2025-05-22", "temperature": true, "tool_call": true }, "anthropic/claude-opus-4.1": { "attachment": true, "cost": { "cache_read": 1.5, "cache_write": 18.75, "input": 15, "output": 75 }, "description": "Claude Opus 4.1 is an AI model provided by zenmux.", "id": "anthropic/claude-opus-4.1", "knowledge": "2025-01-01", "last_updated": "2025-08-05", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "image", "text", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.1", "open_weights": false, "provider": { "api": "https://zenmux.ai/api/anthropic/v1", "npm": "@ai-sdk/anthropic" }, "reasoning": true, "release_date": "2025-08-05", "temperature": true, "tool_call": true }, "anthropic/claude-opus-4.5": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "input": 5, "output": 25 }, "description": "Claude Opus 4.5 is an AI model provided by zenmux.", "id": "anthropic/claude-opus-4.5", "knowledge": "2025-01-01", "last_updated": "2025-11-24", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "pdf", "image", "text" ], "output": [ "text" ] }, "name": "Claude Opus 4.5", "open_weights": false, "provider": { "api": "https://zenmux.ai/api/anthropic/v1", "npm": "@ai-sdk/anthropic" }, "reasoning": true, "release_date": "2025-11-24", "temperature": true, "tool_call": true }, "anthropic/claude-opus-4.6": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "input": 5, "output": 25 }, "description": "Claude Opus 4.6 is an AI model provided by zenmux.", "id": "anthropic/claude-opus-4.6", "knowledge": "2025-05-31", "last_updated": "2026-02-06", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "name": "Claude Opus 4.6", "open_weights": false, "provider": { "api": "https://zenmux.ai/api/anthropic/v1", "npm": "@ai-sdk/anthropic" }, "reasoning": true, "release_date": "2026-02-06", "temperature": true, "tool_call": true }, "anthropic/claude-opus-4.7": { "attachment": true, "cost": { "cache_read": 0.5, "cache_write": 6.25, "input": 5, "output": 25 }, "description": "Claude Opus 4.7 is an AI model provided by zenmux.", "id": "anthropic/claude-opus-4.7", "knowledge": "2026-01-31", "last_updated": "2026-04-16", "limit": { "context": 1000000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Opus 4.7", "open_weights": false, "provider": { "api": "https://zenmux.ai/api/anthropic/v1", "npm": "@ai-sdk/anthropic" }, "reasoning": true, "release_date": "2026-04-16", "temperature": false, "tool_call": true }, "anthropic/claude-sonnet-4": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 4 is an AI model provided by zenmux.", "id": "anthropic/claude-sonnet-4", "knowledge": "2025-01-01", "last_updated": "2025-05-22", "limit": { "context": 1000000, "output": 64000 }, "modalities": { "input": [ "image", "text", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4", "open_weights": false, "provider": { "api": "https://zenmux.ai/api/anthropic/v1", "npm": "@ai-sdk/anthropic" }, "reasoning": true, "release_date": "2025-05-22", "temperature": true, "tool_call": true }, "anthropic/claude-sonnet-4.5": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 4.5 is an AI model provided by zenmux.", "id": "anthropic/claude-sonnet-4.5", "knowledge": "2025-01-01", "last_updated": "2025-09-29", "limit": { "context": 1000000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.5", "open_weights": false, "provider": { "api": "https://zenmux.ai/api/anthropic/v1", "npm": "@ai-sdk/anthropic" }, "reasoning": true, "release_date": "2025-09-29", "temperature": true, "tool_call": true }, "anthropic/claude-sonnet-4.6": { "attachment": true, "cost": { "cache_read": 0.3, "cache_write": 3.75, "input": 3, "output": 15 }, "description": "Claude Sonnet 4.6 is an AI model provided by zenmux.", "id": "anthropic/claude-sonnet-4.6", "knowledge": "2025-08-31", "last_updated": "2026-02-18", "limit": { "context": 1000000, "output": 64000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Claude Sonnet 4.6", "open_weights": false, "provider": { "api": "https://zenmux.ai/api/anthropic/v1", "npm": "@ai-sdk/anthropic" }, "reasoning": true, "release_date": "2026-02-18", "temperature": true, "tool_call": true }, "baidu/ernie-5.0-thinking-preview": { "attachment": true, "cost": { "input": 0.84, "output": 3.37 }, "description": "ERNIE 5.0 is an AI model provided by zenmux.", "id": "baidu/ernie-5.0-thinking-preview", "knowledge": "2025-01-01", "last_updated": "2026-01-22", "limit": { "context": 128000, "output": 64000 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "ERNIE 5.0", "open_weights": false, "reasoning": true, "release_date": "2026-01-22", "temperature": true, "tool_call": true }, "deepseek/deepseek-chat": { "attachment": false, "cost": { "cache_read": 0.03, "input": 0.28, "output": 0.42 }, "description": "DeepSeek-V3.2 (Non-thinking Mode) is an AI model provided by zenmux.", "id": "deepseek/deepseek-chat", "knowledge": "2025-01-01", "last_updated": "2025-12-01", "limit": { "context": 128000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek-V3.2 (Non-thinking Mode)", "open_weights": false, "reasoning": false, "release_date": "2025-12-01", "temperature": true, "tool_call": true }, "deepseek/deepseek-v3.2": { "attachment": false, "cost": { "input": 0.28, "output": 0.43 }, "description": "DeepSeek V3.2 is an AI model provided by zenmux.", "id": "deepseek/deepseek-v3.2", "knowledge": "2025-01-01", "last_updated": "2025-12-05", "limit": { "context": 128000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V3.2", "open_weights": false, "reasoning": true, "release_date": "2025-12-05", "temperature": true, "tool_call": true }, "deepseek/deepseek-v3.2-exp": { "attachment": false, "cost": { "input": 0.22, "output": 0.33 }, "description": "DeepSeek-V3.2-Exp is an AI model provided by zenmux.", "id": "deepseek/deepseek-v3.2-exp", "knowledge": "2025-01-01", "last_updated": "2025-09-29", "limit": { "context": 163000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek-V3.2-Exp", "open_weights": false, "reasoning": true, "release_date": "2025-09-29", "temperature": true, "tool_call": true }, "deepseek/deepseek-v4-flash": { "attachment": false, "cost": { "cache_read": 0.028, "input": 0.14, "output": 0.28 }, "description": "DeepSeek V4 Flash is an AI model provided by zenmux.", "family": "deepseek-flash", "id": "deepseek/deepseek-v4-flash", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-05", "last_updated": "2026-04-24", "limit": { "context": 1000000, "output": 384000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V4 Flash", "open_weights": true, "reasoning": true, "release_date": "2026-04-24", "structured_output": true, "temperature": true, "tool_call": true }, "deepseek/deepseek-v4-pro": { "attachment": false, "cost": { "cache_read": 0.145, "input": 1.74, "output": 3.48 }, "description": "DeepSeek V4 Pro is an AI model provided by zenmux.", "family": "deepseek-thinking", "id": "deepseek/deepseek-v4-pro", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-05", "last_updated": "2026-04-24", "limit": { "context": 1000000, "output": 384000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "DeepSeek V4 Pro", "open_weights": true, "reasoning": true, "release_date": "2026-04-24", "structured_output": true, "temperature": true, "tool_call": true }, "google/gemini-2.5-flash": { "attachment": true, "cost": { "cache_read": 0.07, "cache_write": 1, "input": 0.3, "output": 2.5 }, "description": "Gemini 2.5 Flash is an AI model provided by zenmux.", "id": "google/gemini-2.5-flash", "knowledge": "2025-01-01", "last_updated": "2025-06-17", "limit": { "context": 1048000, "output": 64000 }, "modalities": { "input": [ "pdf", "image", "text", "audio" ], "output": [ "text" ] }, "name": "Gemini 2.5 Flash", "open_weights": false, "reasoning": true, "release_date": "2025-06-17", "temperature": true, "tool_call": true }, "google/gemini-2.5-flash-lite": { "attachment": true, "cost": { "cache_read": 0.03, "cache_write": 1, "input": 0.1, "output": 0.4 }, "description": "Gemini 2.5 Flash Lite is an AI model provided by zenmux.", "id": "google/gemini-2.5-flash-lite", "knowledge": "2025-01-01", "last_updated": "2025-07-22", "limit": { "context": 1048000, "output": 64000 }, "modalities": { "input": [ "pdf", "image", "text", "audio" ], "output": [ "text" ] }, "name": "Gemini 2.5 Flash Lite", "open_weights": false, "reasoning": false, "release_date": "2025-07-22", "temperature": true, "tool_call": true }, "google/gemini-2.5-pro": { "attachment": true, "cost": { "cache_read": 0.31, "cache_write": 4.5, "input": 1.25, "output": 10 }, "description": "Gemini 2.5 Pro is an AI model provided by zenmux.", "id": "google/gemini-2.5-pro", "knowledge": "2025-01-01", "last_updated": "2025-06-17", "limit": { "context": 1048000, "output": 64000 }, "modalities": { "input": [ "pdf", "image", "text", "audio", "video" ], "output": [ "text" ] }, "name": "Gemini 2.5 Pro", "open_weights": false, "reasoning": true, "release_date": "2025-06-17", "temperature": true, "tool_call": true }, "google/gemini-3-flash-preview": { "attachment": true, "cost": { "cache_read": 0.05, "cache_write": 1, "input": 0.5, "output": 3 }, "description": "Gemini 3 Flash Preview is an AI model provided by zenmux.", "id": "google/gemini-3-flash-preview", "knowledge": "2025-01-01", "last_updated": "2025-12-17", "limit": { "context": 1048000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf", "audio" ], "output": [ "text" ] }, "name": "Gemini 3 Flash Preview", "open_weights": false, "reasoning": true, "release_date": "2025-12-17", "temperature": true, "tool_call": true }, "google/gemini-3.1-flash-lite-preview": { "attachment": true, "cost": { "input": 0.25, "output": 1.5 }, "description": "Gemini 3.1 Flash Lite Preview is an AI model provided by zenmux.", "id": "google/gemini-3.1-flash-lite-preview", "last_updated": "2025-03-20", "limit": { "context": 1050000, "output": 65530 }, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "name": "Gemini 3.1 Flash Lite Preview", "open_weights": false, "reasoning": false, "release_date": "2025-03-20", "temperature": true, "tool_call": true }, "google/gemini-3.1-pro-preview": { "attachment": true, "cost": { "cache_read": 0.2, "cache_write": 4.5, "input": 2, "output": 12 }, "description": "Gemini 3.1 Pro Preview is an AI model provided by zenmux.", "id": "google/gemini-3.1-pro-preview", "knowledge": "2026-02-19", "last_updated": "2026-02-19", "limit": { "context": 1048000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf", "audio", "video" ], "output": [ "text" ] }, "name": "Gemini 3.1 Pro Preview", "open_weights": false, "reasoning": true, "release_date": "2026-02-19", "temperature": true, "tool_call": true }, "inclusionai/ling-1t": { "attachment": false, "cost": { "cache_read": 0.11, "input": 0.56, "output": 2.24 }, "description": "Ling-1T is an AI model provided by zenmux.", "id": "inclusionai/ling-1t", "knowledge": "2025-01-01", "last_updated": "2025-10-09", "limit": { "context": 128000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Ling-1T", "open_weights": false, "reasoning": false, "release_date": "2025-10-09", "temperature": true, "tool_call": true }, "inclusionai/ring-1t": { "attachment": false, "cost": { "cache_read": 0.11, "input": 0.56, "output": 2.24 }, "description": "Ring-1T is an AI model provided by zenmux.", "id": "inclusionai/ring-1t", "knowledge": "2025-01-01", "last_updated": "2025-10-12", "limit": { "context": 128000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Ring-1T", "open_weights": false, "reasoning": true, "release_date": "2025-10-12", "temperature": true, "tool_call": true }, "kuaishou/kat-coder-pro-v2": { "attachment": false, "cost": { "cache_read": 0.06, "input": 0.3, "output": 1.2 }, "description": "KAT-Coder-Pro-V2 is an AI model provided by zenmux.", "id": "kuaishou/kat-coder-pro-v2", "last_updated": "2026-03-30", "limit": { "context": 256000, "output": 80000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "KAT-Coder-Pro-V2", "open_weights": false, "reasoning": false, "release_date": "2026-03-30", "temperature": true, "tool_call": true }, "minimax/minimax-m2": { "attachment": false, "cost": { "cache_read": 0.03, "cache_write": 0.38, "input": 0.3, "output": 1.2 }, "description": "MiniMax M2 is an AI model provided by zenmux.", "id": "minimax/minimax-m2", "knowledge": "2025-01-01", "last_updated": "2025-10-27", "limit": { "context": 204000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M2", "open_weights": false, "provider": { "api": "https://zenmux.ai/api/anthropic/v1", "npm": "@ai-sdk/anthropic" }, "reasoning": true, "release_date": "2025-10-27", "temperature": true, "tool_call": true }, "minimax/minimax-m2.1": { "attachment": false, "cost": { "cache_read": 0.03, "cache_write": 0.38, "input": 0.3, "output": 1.2 }, "description": "MiniMax M2.1 is an AI model provided by zenmux.", "id": "minimax/minimax-m2.1", "knowledge": "2025-01-01", "last_updated": "2025-12-22", "limit": { "context": 204000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M2.1", "open_weights": false, "provider": { "api": "https://zenmux.ai/api/anthropic/v1", "npm": "@ai-sdk/anthropic" }, "reasoning": true, "release_date": "2025-12-22", "temperature": true, "tool_call": true }, "minimax/minimax-m2.5": { "attachment": false, "cost": { "cache_read": 0.03, "cache_write": 0.375, "input": 0.3, "output": 1.2 }, "description": "MiniMax M2.5 is an AI model provided by zenmux.", "id": "minimax/minimax-m2.5", "knowledge": "2025-01-01", "last_updated": "2026-02-13", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M2.5", "open_weights": false, "provider": { "api": "https://zenmux.ai/api/anthropic/v1", "npm": "@ai-sdk/anthropic" }, "reasoning": true, "release_date": "2026-02-13", "temperature": true, "tool_call": true }, "minimax/minimax-m2.5-lightning": { "attachment": false, "cost": { "cache_read": 0.06, "cache_write": 0.75, "input": 0.6, "output": 4.8 }, "description": "MiniMax M2.5 highspeed is an AI model provided by zenmux.", "id": "minimax/minimax-m2.5-lightning", "knowledge": "2025-01-01", "last_updated": "2026-02-13", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M2.5 highspeed", "open_weights": false, "provider": { "api": "https://zenmux.ai/api/anthropic/v1", "npm": "@ai-sdk/anthropic" }, "reasoning": true, "release_date": "2026-02-13", "temperature": true, "tool_call": true }, "minimax/minimax-m2.7": { "attachment": true, "cost": { "input": 0.3055, "output": 1.2219 }, "description": "MiniMax M2.7 is an AI model provided by zenmux.", "id": "minimax/minimax-m2.7", "knowledge": "2025-01-01", "last_updated": "2026-03-20", "limit": { "context": 204800, "output": 131070 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M2.7", "open_weights": false, "provider": { "api": "https://zenmux.ai/api/anthropic/v1", "npm": "@ai-sdk/anthropic" }, "reasoning": true, "release_date": "2026-03-20", "temperature": true, "tool_call": true }, "minimax/minimax-m2.7-highspeed": { "attachment": true, "cost": { "input": 0.611, "output": 2.4439 }, "description": "MiniMax M2.7 highspeed is an AI model provided by zenmux.", "id": "minimax/minimax-m2.7-highspeed", "knowledge": "2025-01-01", "last_updated": "2026-03-20", "limit": { "context": 204800, "output": 131070 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiniMax M2.7 highspeed", "open_weights": false, "provider": { "api": "https://zenmux.ai/api/anthropic/v1", "npm": "@ai-sdk/anthropic" }, "reasoning": true, "release_date": "2026-03-20", "temperature": true, "tool_call": true }, "moonshotai/kimi-k2-0905": { "attachment": false, "cost": { "cache_read": 0.15, "input": 0.6, "output": 2.5 }, "description": "Kimi K2 0905 is an AI model provided by zenmux.", "id": "moonshotai/kimi-k2-0905", "knowledge": "2025-01-01", "last_updated": "2025-09-04", "limit": { "context": 262000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 0905", "open_weights": false, "reasoning": false, "release_date": "2025-09-04", "temperature": true, "tool_call": true }, "moonshotai/kimi-k2-thinking": { "attachment": false, "cost": { "cache_read": 0.15, "input": 0.6, "output": 2.5 }, "description": "Kimi K2 Thinking is an AI model provided by zenmux.", "id": "moonshotai/kimi-k2-thinking", "knowledge": "2025-01-01", "last_updated": "2025-11-06", "limit": { "context": 262000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 Thinking", "open_weights": false, "reasoning": true, "release_date": "2025-11-06", "temperature": true, "tool_call": true }, "moonshotai/kimi-k2-thinking-turbo": { "attachment": false, "cost": { "cache_read": 0.15, "input": 1.15, "output": 8 }, "description": "Kimi K2 Thinking Turbo is an AI model provided by zenmux.", "id": "moonshotai/kimi-k2-thinking-turbo", "knowledge": "2025-01-01", "last_updated": "2025-11-06", "limit": { "context": 262000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Kimi K2 Thinking Turbo", "open_weights": false, "reasoning": true, "release_date": "2025-11-06", "temperature": true, "tool_call": true }, "moonshotai/kimi-k2.5": { "attachment": true, "cost": { "cache_read": 0.1, "input": 0.58, "output": 3.02 }, "description": "Kimi K2.5 is an AI model provided by zenmux.", "id": "moonshotai/kimi-k2.5", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-01-01", "last_updated": "2026-01-27", "limit": { "context": 262000, "output": 64000 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Kimi K2.5", "open_weights": false, "reasoning": true, "release_date": "2026-01-27", "temperature": false, "tool_call": true }, "moonshotai/kimi-k2.6": { "attachment": true, "cost": { "cache_read": 0.16, "input": 0.95, "output": 4 }, "description": "Kimi K2.6 is an AI model provided by zenmux.", "id": "moonshotai/kimi-k2.6", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-01-01", "last_updated": "2026-04-20", "limit": { "context": 262140, "output": 262140 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Kimi K2.6", "open_weights": true, "reasoning": true, "release_date": "2026-04-20", "temperature": false, "tool_call": true }, "openai/gpt-5": { "attachment": true, "cost": { "cache_read": 0.12, "input": 1.25, "output": 10 }, "description": "GPT-5 is an AI model provided by zenmux.", "id": "openai/gpt-5", "knowledge": "2025-01-01", "last_updated": "2025-08-07", "limit": { "context": 400000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5", "open_weights": false, "provider": { "api": "https://zenmux.ai/api/v1", "npm": "@ai-sdk/openai" }, "reasoning": true, "release_date": "2025-08-07", "temperature": true, "tool_call": true }, "openai/gpt-5-codex": { "attachment": true, "cost": { "cache_read": 0.12, "input": 1.25, "output": 10 }, "description": "GPT-5 Codex is an AI model provided by zenmux.", "id": "openai/gpt-5-codex", "knowledge": "2025-01-01", "last_updated": "2025-09-23", "limit": { "context": 400000, "output": 64000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5 Codex", "open_weights": false, "provider": { "api": "https://zenmux.ai/api/v1", "npm": "@ai-sdk/openai" }, "reasoning": true, "release_date": "2025-09-23", "temperature": true, "tool_call": true }, "openai/gpt-5.1": { "attachment": true, "cost": { "cache_read": 0.12, "input": 1.25, "output": 10 }, "description": "GPT-5.1 is an AI model provided by zenmux.", "id": "openai/gpt-5.1", "knowledge": "2025-01-01", "last_updated": "2025-11-13", "limit": { "context": 400000, "output": 64000 }, "modalities": { "input": [ "image", "text", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.1", "open_weights": false, "provider": { "api": "https://zenmux.ai/api/v1", "npm": "@ai-sdk/openai" }, "reasoning": true, "release_date": "2025-11-13", "temperature": true, "tool_call": true }, "openai/gpt-5.1-chat": { "attachment": true, "cost": { "cache_read": 0.12, "input": 1.25, "output": 10 }, "description": "GPT-5.1 Chat is an AI model provided by zenmux.", "id": "openai/gpt-5.1-chat", "knowledge": "2025-01-01", "last_updated": "2025-11-13", "limit": { "context": 128000, "output": 64000 }, "modalities": { "input": [ "pdf", "image", "text" ], "output": [ "text" ] }, "name": "GPT-5.1 Chat", "open_weights": false, "provider": { "api": "https://zenmux.ai/api/v1", "npm": "@ai-sdk/openai" }, "reasoning": false, "release_date": "2025-11-13", "temperature": true, "tool_call": true }, "openai/gpt-5.1-codex": { "attachment": true, "cost": { "cache_read": 0.12, "input": 1.25, "output": 10 }, "description": "GPT-5.1-Codex is an AI model provided by zenmux.", "id": "openai/gpt-5.1-codex", "knowledge": "2025-01-01", "last_updated": "2025-11-13", "limit": { "context": 400000, "output": 64000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.1-Codex", "open_weights": false, "provider": { "api": "https://zenmux.ai/api/v1", "npm": "@ai-sdk/openai" }, "reasoning": true, "release_date": "2025-11-13", "temperature": true, "tool_call": true }, "openai/gpt-5.1-codex-mini": { "attachment": true, "cost": { "cache_read": 0.03, "input": 0.25, "output": 2 }, "description": "GPT-5.1-Codex-Mini is an AI model provided by zenmux.", "id": "openai/gpt-5.1-codex-mini", "knowledge": "2025-01-01", "last_updated": "2025-11-13", "limit": { "context": 400000, "output": 64000 }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "name": "GPT-5.1-Codex-Mini", "open_weights": false, "provider": { "api": "https://zenmux.ai/api/v1", "npm": "@ai-sdk/openai" }, "reasoning": true, "release_date": "2025-11-13", "temperature": true, "tool_call": true }, "openai/gpt-5.2": { "attachment": true, "cost": { "cache_read": 0.17, "input": 1.75, "output": 14 }, "description": "GPT-5.2 is an AI model provided by zenmux.", "id": "openai/gpt-5.2", "knowledge": "2025-01-01", "last_updated": "2025-12-11", "limit": { "context": 400000, "output": 64000 }, "modalities": { "input": [ "image", "text", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.2", "open_weights": false, "provider": { "api": "https://zenmux.ai/api/v1", "npm": "@ai-sdk/openai" }, "reasoning": true, "release_date": "2025-12-11", "temperature": false, "tool_call": true }, "openai/gpt-5.2-codex": { "attachment": true, "cost": { "cache_read": 0.17, "input": 1.75, "output": 14 }, "description": "GPT-5.2-Codex is an AI model provided by zenmux.", "id": "openai/gpt-5.2-codex", "knowledge": "2025-01-01", "last_updated": "2026-01-15", "limit": { "context": 400000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.2-Codex", "open_weights": false, "provider": { "api": "https://zenmux.ai/api/v1", "npm": "@ai-sdk/openai" }, "reasoning": true, "release_date": "2026-01-15", "temperature": false, "tool_call": true }, "openai/gpt-5.2-pro": { "attachment": true, "cost": { "input": 21, "output": 168 }, "description": "GPT-5.2-Pro is an AI model provided by zenmux.", "id": "openai/gpt-5.2-pro", "knowledge": "2025-08-31", "last_updated": "2025-12-11", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.2-Pro", "open_weights": false, "provider": { "api": "https://zenmux.ai/api/v1", "npm": "@ai-sdk/openai" }, "reasoning": true, "release_date": "2025-12-11", "temperature": false, "tool_call": true }, "openai/gpt-5.3-chat": { "attachment": true, "cost": { "input": 1.75, "output": 14 }, "description": "GPT-5.3 Chat is an AI model provided by zenmux.", "id": "openai/gpt-5.3-chat", "knowledge": "2025-08-31", "last_updated": "2026-03-20", "limit": { "context": 128000, "output": 16380 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT-5.3 Chat", "open_weights": false, "provider": { "api": "https://zenmux.ai/api/v1", "npm": "@ai-sdk/openai" }, "reasoning": false, "release_date": "2026-03-20", "temperature": true, "tool_call": true }, "openai/gpt-5.3-codex": { "attachment": true, "cost": { "input": 1.75, "output": 14 }, "description": "GPT-5.3 Codex is an AI model provided by zenmux.", "id": "openai/gpt-5.3-codex", "knowledge": "2025-08-31", "last_updated": "2026-03-20", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT-5.3 Codex", "open_weights": false, "provider": { "api": "https://zenmux.ai/api/v1", "npm": "@ai-sdk/openai" }, "reasoning": true, "release_date": "2026-03-20", "temperature": true, "tool_call": true }, "openai/gpt-5.4": { "attachment": true, "cost": { "input": 3.75, "output": 18.75 }, "description": "GPT-5.4 is an AI model provided by zenmux.", "id": "openai/gpt-5.4", "knowledge": "2025-08-31", "last_updated": "2026-03-20", "limit": { "context": 1050000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.4", "open_weights": false, "provider": { "api": "https://zenmux.ai/api/v1", "npm": "@ai-sdk/openai" }, "reasoning": true, "release_date": "2026-03-20", "temperature": true, "tool_call": true }, "openai/gpt-5.4-mini": { "attachment": true, "cost": { "input": 0.75, "output": 4.5 }, "description": "GPT-5.4 Mini is an AI model provided by zenmux.", "id": "openai/gpt-5.4-mini", "knowledge": "2025-08-31", "last_updated": "2026-03-20", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT-5.4 Mini", "open_weights": false, "provider": { "api": "https://zenmux.ai/api/v1", "npm": "@ai-sdk/openai" }, "reasoning": false, "release_date": "2026-03-20", "temperature": true, "tool_call": true }, "openai/gpt-5.4-nano": { "attachment": false, "cost": { "input": 0.2, "output": 1.25 }, "description": "GPT-5.4 Nano is an AI model provided by zenmux.", "id": "openai/gpt-5.4-nano", "knowledge": "2025-08-31", "last_updated": "2026-03-20", "limit": { "context": 400000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GPT-5.4 Nano", "open_weights": false, "provider": { "api": "https://zenmux.ai/api/v1", "npm": "@ai-sdk/openai" }, "reasoning": false, "release_date": "2026-03-20", "temperature": true, "tool_call": true }, "openai/gpt-5.4-pro": { "attachment": true, "cost": { "input": 45, "output": 225 }, "description": "GPT-5.4 Pro is an AI model provided by zenmux.", "id": "openai/gpt-5.4-pro", "knowledge": "2025-08-31", "last_updated": "2026-03-20", "limit": { "context": 1050000, "output": 128000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "GPT-5.4 Pro", "open_weights": false, "provider": { "api": "https://zenmux.ai/api/v1", "npm": "@ai-sdk/openai" }, "reasoning": true, "release_date": "2026-03-20", "temperature": true, "tool_call": true }, "openai/gpt-5.5": { "attachment": true, "cost": { "cache_read": 0.5, "context_over_200k": { "cache_read": 1, "input": 10, "output": 45 }, "input": 5, "output": 30, "tiers": [ { "cache_read": 1, "input": 10, "output": 45, "tier": { "size": 272000, "type": "context" } } ] }, "description": "GPT-5.5 is an AI model provided by zenmux.", "experimental": { "modes": { "fast": { "cost": { "cache_read": 1.25, "input": 12.5, "output": 75 }, "provider": { "body": { "service_tier": "priority" } } } } }, "family": "gpt", "id": "openai/gpt-5.5", "knowledge": "2025-12-01", "last_updated": "2026-04-23", "limit": { "context": 1050000, "input": 922000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.5", "open_weights": false, "reasoning": true, "release_date": "2026-04-23", "structured_output": true, "temperature": false, "tool_call": true }, "openai/gpt-5.5-pro": { "attachment": true, "cost": { "context_over_200k": { "input": 60, "output": 270 }, "input": 30, "output": 180, "tiers": [ { "input": 60, "output": 270, "tier": { "size": 272000, "type": "context" } } ] }, "description": "GPT-5.5 Pro is an AI model provided by zenmux.", "family": "gpt-pro", "id": "openai/gpt-5.5-pro", "knowledge": "2025-12-01", "last_updated": "2026-04-23", "limit": { "context": 1050000, "input": 922000, "output": 128000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "name": "GPT-5.5 Pro", "open_weights": false, "reasoning": true, "release_date": "2026-04-23", "structured_output": true, "temperature": false, "tool_call": true }, "qwen/qwen3-coder-plus": { "attachment": false, "cost": { "cache_read": 0.1, "cache_write": 1.25, "input": 1, "output": 5 }, "description": "Qwen3-Coder-Plus is an AI model provided by zenmux.", "id": "qwen/qwen3-coder-plus", "knowledge": "2025-01-01", "last_updated": "2025-07-23", "limit": { "context": 1000000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3-Coder-Plus", "open_weights": false, "reasoning": false, "release_date": "2025-07-23", "temperature": true, "tool_call": true }, "qwen/qwen3-max": { "attachment": false, "cost": { "input": 1.2, "output": 6 }, "description": "Qwen3-Max-Thinking is an AI model provided by zenmux.", "id": "qwen/qwen3-max", "knowledge": "2025-01-01", "last_updated": "2026-01-23", "limit": { "context": 256000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3-Max-Thinking", "open_weights": false, "reasoning": true, "release_date": "2026-01-23", "temperature": true, "tool_call": true }, "qwen/qwen3.5-flash": { "attachment": true, "cost": { "input": 0.1, "output": 0.4 }, "description": "Qwen3.5 Flash is an AI model provided by zenmux.", "id": "qwen/qwen3.5-flash", "knowledge": "2025-01-01", "last_updated": "2026-03-20", "limit": { "context": 1020000, "output": 1020000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen3.5 Flash", "open_weights": false, "reasoning": false, "release_date": "2026-03-20", "temperature": true, "tool_call": true }, "qwen/qwen3.5-plus": { "attachment": true, "cost": { "input": 0.8, "output": 4.8 }, "description": "Qwen3.5 Plus is an AI model provided by zenmux.", "id": "qwen/qwen3.5-plus", "knowledge": "2025-01-01", "last_updated": "2026-03-20", "limit": { "context": 1000000, "output": 64000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Qwen3.5 Plus", "open_weights": false, "reasoning": true, "release_date": "2026-03-20", "temperature": true, "tool_call": true }, "qwen/qwen3.6-plus": { "attachment": false, "cost": { "cache_read": 0.05, "cache_write": 0.625, "context_over_200k": { "cache_read": 0.2, "cache_write": 2.5, "input": 2, "output": 6 }, "input": 0.5, "output": 3, "tiers": [ { "cache_read": 0.2, "cache_write": 2.5, "input": 2, "output": 6, "tier": { "size": 256000, "type": "context" } } ] }, "description": "Qwen3.6-Plus is an AI model provided by zenmux.", "id": "qwen/qwen3.6-plus", "last_updated": "2026-03-30", "limit": { "context": 1000000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Qwen3.6-Plus", "open_weights": false, "reasoning": true, "release_date": "2026-03-30", "temperature": true, "tool_call": true }, "sapiens-ai/agnes-1.5-lite": { "attachment": true, "cost": { "input": 0.12, "output": 0.6 }, "description": "Agnes 1.5 Lite is an AI model provided by zenmux.", "id": "sapiens-ai/agnes-1.5-lite", "last_updated": "2026-03-26", "limit": { "context": 256000, "output": 256000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Agnes 1.5 Lite", "open_weights": false, "reasoning": false, "release_date": "2026-03-26", "temperature": true, "tool_call": true }, "sapiens-ai/agnes-1.5-pro": { "attachment": false, "cost": { "input": 0.16, "output": 0.8 }, "description": "Agnes 1.5 Pro is an AI model provided by zenmux.", "id": "sapiens-ai/agnes-1.5-pro", "last_updated": "2026-03-21", "limit": { "context": 256000, "output": 256000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Agnes 1.5 Pro", "open_weights": false, "reasoning": true, "release_date": "2026-03-21", "temperature": true, "tool_call": true }, "stepfun/step-3": { "attachment": true, "cost": { "input": 0.21, "output": 0.57 }, "description": "Step-3 is an AI model provided by zenmux.", "id": "stepfun/step-3", "knowledge": "2025-01-01", "last_updated": "2025-07-31", "limit": { "context": 65536, "output": 64000 }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "name": "Step-3", "open_weights": false, "reasoning": true, "release_date": "2025-07-31", "temperature": true, "tool_call": true }, "stepfun/step-3.5-flash": { "attachment": false, "cost": { "input": 0.1, "output": 0.3 }, "description": "Step 3.5 Flash is an AI model provided by zenmux.", "id": "stepfun/step-3.5-flash", "knowledge": "2025-01-01", "last_updated": "2026-02-02", "limit": { "context": 256000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Step 3.5 Flash", "open_weights": false, "reasoning": false, "release_date": "2026-02-02", "temperature": true, "tool_call": true }, "stepfun/step-3.5-flash-free": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "Step 3.5 Flash (Free) is an AI model provided by zenmux.", "id": "stepfun/step-3.5-flash-free", "knowledge": "2025-01-01", "last_updated": "2026-02-02", "limit": { "context": 256000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Step 3.5 Flash (Free)", "open_weights": false, "reasoning": true, "release_date": "2026-02-02", "temperature": true, "tool_call": true }, "tencent/hy3-preview": { "attachment": false, "cost": { "cache_read": 0.058, "cache_write": 0, "input": 0.172, "output": 0.572 }, "description": "Hy3 preview is an AI model provided by zenmux.", "family": "Hy", "id": "tencent/hy3-preview", "last_updated": "2026-04-20", "limit": { "context": 256000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Hy3 preview", "open_weights": true, "reasoning": true, "release_date": "2026-04-20", "temperature": true, "tool_call": true }, "volcengine/doubao-seed-1.8": { "attachment": true, "cost": { "cache_read": 0.02, "cache_write": 0.0024, "input": 0.11, "output": 0.28 }, "description": "Doubao-Seed-1.8 is an AI model provided by zenmux.", "id": "volcengine/doubao-seed-1.8", "knowledge": "2025-01-01", "last_updated": "2025-12-18", "limit": { "context": 256000, "output": 64000 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Doubao-Seed-1.8", "open_weights": false, "reasoning": true, "release_date": "2025-12-18", "temperature": true, "tool_call": true }, "volcengine/doubao-seed-2.0-code": { "attachment": true, "cost": { "input": 0.9, "output": 4.48 }, "description": "Doubao Seed 2.0 Code is an AI model provided by zenmux.", "id": "volcengine/doubao-seed-2.0-code", "knowledge": "2025-01-01", "last_updated": "2026-03-20", "limit": { "context": 256000, "output": 32000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Doubao Seed 2.0 Code", "open_weights": false, "reasoning": false, "release_date": "2026-03-20", "temperature": true, "tool_call": true }, "volcengine/doubao-seed-2.0-lite": { "attachment": true, "cost": { "cache_read": 0.02, "cache_write": 0.0024, "input": 0.09, "output": 0.51 }, "description": "Doubao-Seed-2.0-lite is an AI model provided by zenmux.", "id": "volcengine/doubao-seed-2.0-lite", "knowledge": "2026-02-14", "last_updated": "2026-02-14", "limit": { "context": 256000, "output": 64000 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Doubao-Seed-2.0-lite", "open_weights": false, "reasoning": true, "release_date": "2026-02-14", "temperature": true, "tool_call": true }, "volcengine/doubao-seed-2.0-mini": { "attachment": true, "cost": { "cache_read": 0.01, "cache_write": 0.0024, "input": 0.03, "output": 0.28 }, "description": "Doubao-Seed-2.0-mini is an AI model provided by zenmux.", "id": "volcengine/doubao-seed-2.0-mini", "knowledge": "2026-02-14", "last_updated": "2026-02-14", "limit": { "context": 256000, "output": 64000 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Doubao-Seed-2.0-mini", "open_weights": false, "reasoning": true, "release_date": "2026-02-14", "temperature": true, "tool_call": true }, "volcengine/doubao-seed-2.0-pro": { "attachment": true, "cost": { "cache_read": 0.09, "cache_write": 0.0024, "input": 0.45, "output": 2.24 }, "description": "Doubao-Seed-2.0-pro is an AI model provided by zenmux.", "id": "volcengine/doubao-seed-2.0-pro", "knowledge": "2026-02-14", "last_updated": "2026-02-14", "limit": { "context": 256000, "output": 64000 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Doubao-Seed-2.0-pro", "open_weights": false, "reasoning": true, "release_date": "2026-02-14", "temperature": true, "tool_call": true }, "volcengine/doubao-seed-code": { "attachment": true, "cost": { "cache_read": 0.03, "input": 0.17, "output": 1.12 }, "description": "Doubao-Seed-Code is an AI model provided by zenmux.", "id": "volcengine/doubao-seed-code", "knowledge": "2025-01-01", "last_updated": "2025-11-11", "limit": { "context": 256000, "output": 64000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Doubao-Seed-Code", "open_weights": false, "reasoning": true, "release_date": "2025-11-11", "temperature": true, "tool_call": true }, "x-ai/grok-4": { "attachment": true, "cost": { "cache_read": 0.75, "input": 3, "output": 15 }, "description": "Grok 4 is an AI model provided by zenmux.", "id": "x-ai/grok-4", "knowledge": "2025-01-01", "last_updated": "2025-07-09", "limit": { "context": 256000, "output": 64000 }, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "name": "Grok 4", "open_weights": false, "reasoning": true, "release_date": "2025-07-09", "temperature": true, "tool_call": true }, "x-ai/grok-4-fast": { "attachment": true, "cost": { "cache_read": 0.05, "input": 0.2, "output": 0.5 }, "description": "Grok 4 Fast is an AI model provided by zenmux.", "id": "x-ai/grok-4-fast", "knowledge": "2025-01-01", "last_updated": "2025-09-19", "limit": { "context": 2000000, "output": 64000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 4 Fast", "open_weights": false, "reasoning": true, "release_date": "2025-09-19", "temperature": true, "tool_call": true }, "x-ai/grok-4.1-fast": { "attachment": true, "cost": { "cache_read": 0.05, "input": 0.2, "output": 0.5 }, "description": "Grok 4.1 Fast is an AI model provided by zenmux.", "id": "x-ai/grok-4.1-fast", "knowledge": "2025-01-01", "last_updated": "2025-11-20", "limit": { "context": 2000000, "output": 64000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 4.1 Fast", "open_weights": false, "reasoning": true, "release_date": "2025-11-20", "temperature": true, "tool_call": true }, "x-ai/grok-4.1-fast-non-reasoning": { "attachment": true, "cost": { "cache_read": 0.05, "input": 0.2, "output": 0.5 }, "description": "Grok 4.1 Fast Non Reasoning is an AI model provided by zenmux.", "id": "x-ai/grok-4.1-fast-non-reasoning", "knowledge": "2025-01-01", "last_updated": "2025-11-20", "limit": { "context": 2000000, "output": 64000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "name": "Grok 4.1 Fast Non Reasoning", "open_weights": false, "reasoning": false, "release_date": "2025-11-20", "temperature": true, "tool_call": true }, "x-ai/grok-4.2-fast": { "attachment": true, "cost": { "input": 3, "output": 9 }, "description": "Grok 4.2 Fast is an AI model provided by zenmux.", "id": "x-ai/grok-4.2-fast", "knowledge": "2025-08-31", "last_updated": "2026-03-20", "limit": { "context": 2000000, "output": 30000 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Grok 4.2 Fast", "open_weights": false, "reasoning": true, "release_date": "2026-03-20", "temperature": true, "tool_call": true }, "x-ai/grok-4.2-fast-non-reasoning": { "attachment": true, "cost": { "input": 3, "output": 9 }, "description": "Grok 4.2 Fast Non Reasoning is an AI model provided by zenmux.", "id": "x-ai/grok-4.2-fast-non-reasoning", "knowledge": "2025-08-31", "last_updated": "2026-03-20", "limit": { "context": 2000000, "output": 30000 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "Grok 4.2 Fast Non Reasoning", "open_weights": false, "reasoning": false, "release_date": "2026-03-20", "temperature": true, "tool_call": true }, "x-ai/grok-code-fast-1": { "attachment": false, "cost": { "cache_read": 0.02, "input": 0.2, "output": 1.5 }, "description": "Grok Code Fast 1 is an AI model provided by zenmux.", "id": "x-ai/grok-code-fast-1", "knowledge": "2025-01-01", "last_updated": "2025-08-26", "limit": { "context": 256000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "Grok Code Fast 1", "open_weights": false, "reasoning": true, "release_date": "2025-08-26", "temperature": true, "tool_call": true }, "xiaomi/mimo-v2-flash": { "attachment": false, "cost": { "cache_read": 0.01, "input": 0.1, "output": 0.3 }, "description": "MiMo-V2-Flash is an AI model provided by zenmux.", "family": "mimo", "id": "xiaomi/mimo-v2-flash", "knowledge": "2024-12-01", "last_updated": "2026-02-04", "limit": { "context": 262144, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiMo-V2-Flash", "open_weights": true, "reasoning": true, "release_date": "2025-12-16", "temperature": true, "tool_call": true }, "xiaomi/mimo-v2-omni": { "attachment": true, "cost": { "cache_read": 0.08, "input": 0.4, "output": 2 }, "description": "MiMo V2 Omni is an AI model provided by zenmux.", "family": "mimo", "id": "xiaomi/mimo-v2-omni", "knowledge": "2024-12", "last_updated": "2026-03-18", "limit": { "context": 265000, "output": 265000 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "name": "MiMo V2 Omni", "open_weights": false, "reasoning": true, "release_date": "2026-03-18", "temperature": true, "tool_call": true }, "xiaomi/mimo-v2-pro": { "attachment": false, "cost": { "cache_read": 0.2, "context_over_200k": { "cache_read": 0.4, "input": 2, "output": 6 }, "input": 1, "output": 3, "tiers": [ { "cache_read": 0.4, "input": 2, "output": 6, "tier": { "size": 256000, "type": "context" } } ] }, "description": "MiMo V2 Pro is an AI model provided by zenmux.", "family": "mimo", "id": "xiaomi/mimo-v2-pro", "knowledge": "2024-12", "last_updated": "2026-03-18", "limit": { "context": 1000000, "output": 256000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiMo V2 Pro", "open_weights": false, "reasoning": true, "release_date": "2026-03-18", "temperature": true, "tool_call": true }, "xiaomi/mimo-v2.5": { "attachment": true, "cost": { "cache_read": 0.08, "context_over_200k": { "cache_read": 0.16, "input": 0.8, "output": 4 }, "input": 0.4, "output": 2, "tiers": [ { "cache_read": 0.16, "input": 0.8, "output": 4, "tier": { "size": 256000, "type": "context" } } ] }, "description": "MiMo-V2.5 is an AI model provided by zenmux.", "family": "mimo", "id": "xiaomi/mimo-v2.5", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-12", "last_updated": "2026-04-22", "limit": { "context": 1048576, "output": 131072 }, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "name": "MiMo-V2.5", "open_weights": true, "reasoning": true, "release_date": "2026-04-22", "temperature": true, "tool_call": true }, "xiaomi/mimo-v2.5-pro": { "attachment": false, "cost": { "cache_read": 0.2, "context_over_200k": { "cache_read": 0.4, "input": 2, "output": 6 }, "input": 1, "output": 3, "tiers": [ { "cache_read": 0.4, "input": 2, "output": 6, "tier": { "size": 256000, "type": "context" } } ] }, "description": "MiMo-V2.5-Pro is an AI model provided by zenmux.", "family": "mimo", "id": "xiaomi/mimo-v2.5-pro", "interleaved": { "field": "reasoning_content" }, "knowledge": "2024-12", "last_updated": "2026-04-22", "limit": { "context": 1048576, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "MiMo-V2.5-Pro", "open_weights": true, "reasoning": true, "release_date": "2026-04-22", "temperature": true, "tool_call": true }, "z-ai/glm-4.5": { "attachment": false, "cost": { "cache_read": 0.07, "input": 0.35, "output": 1.54 }, "description": "GLM 4.5 is an AI model provided by zenmux.", "id": "z-ai/glm-4.5", "knowledge": "2025-01-01", "last_updated": "2025-07-25", "limit": { "context": 128000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.5", "open_weights": false, "reasoning": true, "release_date": "2025-07-25", "temperature": true, "tool_call": true }, "z-ai/glm-4.5-air": { "attachment": false, "cost": { "cache_read": 0.02, "input": 0.11, "output": 0.56 }, "description": "GLM 4.5 Air is an AI model provided by zenmux.", "id": "z-ai/glm-4.5-air", "knowledge": "2025-01-01", "last_updated": "2025-07-25", "limit": { "context": 128000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.5 Air", "open_weights": false, "reasoning": true, "release_date": "2025-07-25", "temperature": true, "tool_call": true }, "z-ai/glm-4.6": { "attachment": false, "cost": { "cache_read": 0.07, "input": 0.35, "output": 1.54 }, "description": "GLM 4.6 is an AI model provided by zenmux.", "id": "z-ai/glm-4.6", "knowledge": "2025-01-01", "last_updated": "2025-09-30", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.6", "open_weights": false, "reasoning": true, "release_date": "2025-09-30", "temperature": true, "tool_call": true }, "z-ai/glm-4.6v": { "attachment": true, "cost": { "cache_read": 0.03, "input": 0.14, "output": 0.42 }, "description": "GLM 4.6V is an AI model provided by zenmux.", "id": "z-ai/glm-4.6v", "knowledge": "2025-01-01", "last_updated": "2025-12-08", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "GLM 4.6V", "open_weights": false, "reasoning": true, "release_date": "2025-12-08", "temperature": true, "tool_call": true }, "z-ai/glm-4.6v-flash": { "attachment": true, "cost": { "cache_read": 0.0043, "input": 0.02, "output": 0.21 }, "description": "GLM 4.6V FlashX is an AI model provided by zenmux.", "id": "z-ai/glm-4.6v-flash", "knowledge": "2025-01-01", "last_updated": "2025-12-08", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "GLM 4.6V FlashX", "open_weights": false, "reasoning": true, "release_date": "2025-12-08", "temperature": true, "tool_call": true }, "z-ai/glm-4.6v-flash-free": { "attachment": true, "cost": { "input": 0, "output": 0 }, "description": "GLM 4.6V Flash (Free) is an AI model provided by zenmux.", "id": "z-ai/glm-4.6v-flash-free", "knowledge": "2025-01-01", "last_updated": "2025-12-08", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "GLM 4.6V Flash (Free)", "open_weights": false, "reasoning": true, "release_date": "2025-12-08", "temperature": true, "tool_call": true }, "z-ai/glm-4.7": { "attachment": false, "cost": { "cache_read": 0.06, "input": 0.28, "output": 1.14 }, "description": "GLM 4.7 is an AI model provided by zenmux.", "id": "z-ai/glm-4.7", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-01-01", "last_updated": "2025-12-23", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.7", "open_weights": false, "reasoning": true, "release_date": "2025-12-23", "temperature": true, "tool_call": true }, "z-ai/glm-4.7-flash-free": { "attachment": false, "cost": { "input": 0, "output": 0 }, "description": "GLM 4.7 Flash (Free) is an AI model provided by zenmux.", "id": "z-ai/glm-4.7-flash-free", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-01-01", "last_updated": "2026-01-19", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.7 Flash (Free)", "open_weights": false, "reasoning": true, "release_date": "2026-01-19", "temperature": true, "tool_call": true }, "z-ai/glm-4.7-flashx": { "attachment": false, "cost": { "cache_read": 0.01, "input": 0.07, "output": 0.42 }, "description": "GLM 4.7 FlashX is an AI model provided by zenmux.", "id": "z-ai/glm-4.7-flashx", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-01-01", "last_updated": "2026-01-19", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 4.7 FlashX", "open_weights": false, "reasoning": true, "release_date": "2026-01-19", "temperature": true, "tool_call": true }, "z-ai/glm-5": { "attachment": false, "cost": { "cache_read": 0.14, "input": 0.58, "output": 2.6 }, "description": "GLM 5 is an AI model provided by zenmux.", "id": "z-ai/glm-5", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-01-01", "last_updated": "2026-02-12", "limit": { "context": 200000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 5", "open_weights": true, "reasoning": true, "release_date": "2026-02-12", "temperature": true, "tool_call": true }, "z-ai/glm-5-turbo": { "attachment": true, "cost": { "input": 0.88, "output": 3.48 }, "description": "GLM 5 Turbo is an AI model provided by zenmux.", "id": "z-ai/glm-5-turbo", "knowledge": "2025-01-01", "last_updated": "2026-03-20", "limit": { "context": 200000, "output": 128000 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM 5 Turbo", "open_weights": false, "reasoning": true, "release_date": "2026-03-20", "temperature": true, "tool_call": true }, "z-ai/glm-5.1": { "attachment": false, "cost": { "cache_read": 0.1903, "input": 0.8781, "output": 3.5126 }, "description": "GLM-5.1 is an AI model provided by zenmux.", "id": "z-ai/glm-5.1", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-03", "limit": { "context": 200000, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5.1", "open_weights": false, "reasoning": true, "release_date": "2026-04-03", "structured_output": true, "temperature": true, "tool_call": true }, "z-ai/glm-5v-turbo": { "attachment": true, "cost": { "cache_read": 0.1743, "input": 0.726, "output": 3.1946 }, "description": "GLM 5V Turbo is an AI model provided by zenmux.", "id": "z-ai/glm-5v-turbo", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-01", "limit": { "context": 200000, "output": 128000 }, "modalities": { "input": [ "text", "image", "video", "pdf" ], "output": [ "text" ] }, "name": "GLM 5V Turbo", "open_weights": false, "reasoning": true, "release_date": "2026-04-01", "temperature": true, "tool_call": true } }, "name": "ZenMux", "npm": "@ai-sdk/openai-compatible" }, "zhipuai": { "api": "https://open.bigmodel.cn/api/paas/v4", "doc": "https://docs.z.ai/guides/overview/pricing", "env": [ "ZHIPU_API_KEY" ], "iconURL": "https://models.dev/logos/zhipuai.svg", "id": "zhipuai", "lobeIcon": "Zhipu.Color", "models": { "glm-4.5": { "attachment": false, "cost": { "cache_read": 0.11, "cache_write": 0, "input": 0.6, "output": 2.2 }, "description": "GLM-4.5 is an AI model provided by zhipuai.", "family": "glm", "id": "glm-4.5", "knowledge": "2025-04", "last_updated": "2025-07-28", "limit": { "context": 131072, "output": 98304 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.5", "open_weights": true, "reasoning": true, "release_date": "2025-07-28", "temperature": true, "tool_call": true }, "glm-4.5-air": { "attachment": false, "cost": { "cache_read": 0.03, "cache_write": 0, "input": 0.2, "output": 1.1 }, "description": "GLM-4.5-Air is an AI model provided by zhipuai.", "family": "glm-air", "id": "glm-4.5-air", "knowledge": "2025-04", "last_updated": "2025-07-28", "limit": { "context": 131072, "output": 98304 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.5-Air", "open_weights": true, "reasoning": true, "release_date": "2025-07-28", "temperature": true, "tool_call": true }, "glm-4.5-flash": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "GLM-4.5-Flash is an AI model provided by zhipuai.", "family": "glm-flash", "id": "glm-4.5-flash", "knowledge": "2025-04", "last_updated": "2025-07-28", "limit": { "context": 131072, "output": 98304 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.5-Flash", "open_weights": true, "reasoning": true, "release_date": "2025-07-28", "temperature": true, "tool_call": true }, "glm-4.5v": { "attachment": true, "cost": { "input": 0.6, "output": 1.8 }, "description": "GLM-4.5V is an AI model provided by zhipuai.", "family": "glm", "id": "glm-4.5v", "knowledge": "2025-04", "last_updated": "2025-08-11", "limit": { "context": 64000, "output": 16384 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "GLM-4.5V", "open_weights": true, "reasoning": true, "release_date": "2025-08-11", "temperature": true, "tool_call": true }, "glm-4.6": { "attachment": false, "cost": { "cache_read": 0.11, "cache_write": 0, "input": 0.6, "output": 2.2 }, "description": "GLM-4.6 is an AI model provided by zhipuai.", "family": "glm", "id": "glm-4.6", "knowledge": "2025-04", "last_updated": "2025-09-30", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.6", "open_weights": true, "reasoning": true, "release_date": "2025-09-30", "temperature": true, "tool_call": true }, "glm-4.6v": { "attachment": true, "cost": { "input": 0.3, "output": 0.9 }, "description": "GLM-4.6V is an AI model provided by zhipuai.", "family": "glm", "id": "glm-4.6v", "knowledge": "2025-04", "last_updated": "2025-12-08", "limit": { "context": 128000, "output": 32768 }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "name": "GLM-4.6V", "open_weights": true, "reasoning": true, "release_date": "2025-12-08", "temperature": true, "tool_call": true }, "glm-4.7": { "attachment": false, "cost": { "cache_read": 0.11, "cache_write": 0, "input": 0.6, "output": 2.2 }, "description": "GLM-4.7 is an AI model provided by zhipuai.", "family": "glm", "id": "glm-4.7", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-04", "last_updated": "2025-12-22", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.7", "open_weights": true, "reasoning": true, "release_date": "2025-12-22", "temperature": true, "tool_call": true }, "glm-4.7-flash": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "GLM-4.7-Flash is an AI model provided by zhipuai.", "family": "glm-flash", "id": "glm-4.7-flash", "knowledge": "2025-04", "last_updated": "2026-01-19", "limit": { "context": 200000, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.7-Flash", "open_weights": true, "reasoning": true, "release_date": "2026-01-19", "temperature": true, "tool_call": true }, "glm-4.7-flashx": { "attachment": false, "cost": { "cache_read": 0.01, "cache_write": 0, "input": 0.07, "output": 0.4 }, "description": "GLM-4.7-FlashX is an AI model provided by zhipuai.", "family": "glm-flash", "id": "glm-4.7-flashx", "knowledge": "2025-04", "last_updated": "2026-01-19", "limit": { "context": 200000, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.7-FlashX", "open_weights": true, "reasoning": true, "release_date": "2026-01-19", "temperature": true, "tool_call": true }, "glm-5": { "attachment": false, "cost": { "cache_read": 0.2, "cache_write": 0, "input": 1, "output": 3.2 }, "description": "GLM-5 is an AI model provided by zhipuai.", "family": "glm", "id": "glm-5", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-02-11", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5", "open_weights": true, "reasoning": true, "release_date": "2026-02-11", "temperature": true, "tool_call": true }, "glm-5.1": { "attachment": false, "cost": { "cache_read": 1.3, "cache_write": 0, "input": 6, "output": 24 }, "description": "GLM-5.1 is an AI model provided by zhipuai.", "family": "glm", "id": "glm-5.1", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-03-27", "limit": { "context": 200000, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5.1", "open_weights": false, "reasoning": true, "release_date": "2026-03-27", "structured_output": true, "temperature": true, "tool_call": true }, "glm-5v-turbo": { "attachment": true, "cost": { "cache_read": 1.2, "cache_write": 0, "input": 5, "output": 22 }, "description": "GLM-5V-Turbo is an AI model provided by zhipuai.", "family": "glm", "id": "glm-5v-turbo", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-01", "limit": { "context": 200000, "output": 131072 }, "modalities": { "input": [ "text", "image", "video", "pdf" ], "output": [ "text" ] }, "name": "GLM-5V-Turbo", "open_weights": false, "reasoning": true, "release_date": "2026-04-01", "temperature": true, "tool_call": true } }, "name": "Zhipu AI", "npm": "@ai-sdk/openai-compatible" }, "zhipuai-coding-plan": { "api": "https://open.bigmodel.cn/api/coding/paas/v4", "doc": "https://docs.bigmodel.cn/cn/coding-plan/overview", "env": [ "ZHIPU_API_KEY" ], "iconURL": "https://models.dev/logos/zhipuai-coding-plan.svg", "id": "zhipuai-coding-plan", "models": { "glm-4.5-air": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "GLM-4.5-Air is an AI model provided by zhipuai-coding-plan.", "family": "glm-air", "id": "glm-4.5-air", "knowledge": "2025-04", "last_updated": "2025-07-28", "limit": { "context": 131072, "output": 98304 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.5-Air", "open_weights": true, "reasoning": true, "release_date": "2025-07-28", "temperature": true, "tool_call": true }, "glm-4.7": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "GLM-4.7 is an AI model provided by zhipuai-coding-plan.", "family": "glm", "id": "glm-4.7", "interleaved": { "field": "reasoning_content" }, "knowledge": "2025-04", "last_updated": "2025-12-22", "limit": { "context": 204800, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-4.7", "open_weights": true, "reasoning": true, "release_date": "2025-12-22", "temperature": true, "tool_call": true }, "glm-5-turbo": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "GLM-5-Turbo is an AI model provided by zhipuai-coding-plan.", "family": "glm", "id": "glm-5-turbo", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-03-16", "limit": { "context": 200000, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5-Turbo", "open_weights": false, "reasoning": true, "release_date": "2026-03-16", "structured_output": true, "temperature": true, "tool_call": true }, "glm-5.1": { "attachment": false, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "GLM-5.1 is an AI model provided by zhipuai-coding-plan.", "family": "glm", "id": "glm-5.1", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-03-27", "limit": { "context": 200000, "output": 131072 }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "name": "GLM-5.1", "open_weights": false, "reasoning": true, "release_date": "2026-03-27", "structured_output": true, "temperature": true, "tool_call": true }, "glm-5v-turbo": { "attachment": true, "cost": { "cache_read": 0, "cache_write": 0, "input": 0, "output": 0 }, "description": "GLM-5V-Turbo is an AI model provided by zhipuai-coding-plan.", "family": "glm", "id": "glm-5v-turbo", "interleaved": { "field": "reasoning_content" }, "last_updated": "2026-04-01", "limit": { "context": 200000, "output": 131072 }, "modalities": { "input": [ "text", "image", "video", "pdf" ], "output": [ "text" ] }, "name": "GLM-5V-Turbo", "open_weights": false, "reasoning": true, "release_date": "2026-04-01", "temperature": true, "tool_call": true } }, "name": "Zhipu AI Coding Plan", "npm": "@ai-sdk/openai-compatible" } }