{
  "api": "https://open.bigmodel.cn/api/paas/v4",
  "billing": {
    "priority": 10
  },
  "currency": "CNY",
  "doc": "https://docs.bigmodel.cn/cn/guide/start/pricing",
  "env": [
    "ZHIPU_API_KEY"
  ],
  "iconURL": "https://models.dev/logos/zhipuai.svg",
  "id": "zhipuai",
  "lobeIcon": "Zhipu.Color",
  "models": {
    "glm-4.5": {
      "attachment": false,
      "canonical_model_id": "zhipuai/glm-4.5",
      "cost": {
        "cache_read": 0.11,
        "cache_write": 0,
        "input": 0.6,
        "output": 2.2
      },
      "description": "Hybrid-reasoning GLM release that made the 4.5 line broadly useful",
      "family": "glm",
      "id": "glm-4.5",
      "interleaved": {
        "field": "reasoning_content"
      },
      "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,
      "reasoning_options": [
        {
          "type": "toggle"
        }
      ],
      "release_date": "2025-07-28",
      "temperature": true,
      "tool_call": true
    },
    "glm-4.5-air": {
      "attachment": false,
      "canonical_model_id": "zhipuai/glm-4.5-air",
      "cost": {
        "cache_read": 0.16,
        "cache_write": 0,
        "currency": "CNY",
        "input": 0.8,
        "output": 6,
        "tiers": [
          {
            "cache_read": 0.24,
            "input": 1.2,
            "output": 8,
            "tier": {
              "size": 32000,
              "type": "context"
            }
          }
        ]
      },
      "description": "Lighter GLM-4.5 variant for fast coding assistance and cheaper agents",
      "family": "glm-air",
      "id": "glm-4.5-air",
      "interleaved": {
        "field": "reasoning_content"
      },
      "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,
      "reasoning_options": [
        {
          "type": "toggle"
        }
      ],
      "release_date": "2025-07-28",
      "temperature": true,
      "tool_call": true
    },
    "glm-4.5-flash": {
      "attachment": false,
      "canonical_model_id": "zhipuai/glm-4.5-flash",
      "cost": {
        "cache_read": 0,
        "cache_write": 0,
        "currency": "CNY",
        "input": 0,
        "output": 0
      },
      "description": "Efficient GLM model for fast reasoning, coding, and agent workflows",
      "family": "glm-flash",
      "id": "glm-4.5-flash",
      "interleaved": {
        "field": "reasoning_content"
      },
      "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": false,
      "reasoning": true,
      "reasoning_options": [
        {
          "type": "toggle"
        }
      ],
      "release_date": "2025-07-28",
      "temperature": true,
      "tool_call": true
    },
    "glm-4.5v": {
      "attachment": true,
      "canonical_model_id": "zhipuai/glm-4.5v",
      "cost": {
        "cache_read": 0.4,
        "cache_write": 0,
        "currency": "CNY",
        "input": 2,
        "output": 6,
        "tiers": [
          {
            "cache_read": 0.8,
            "input": 4,
            "output": 12,
            "tier": {
              "size": 32000,
              "type": "context"
            }
          }
        ]
      },
      "description": "GLM vision model for visual reasoning, documents, and multimodal agents",
      "family": "glm",
      "id": "glm-4.5v",
      "interleaved": {
        "field": "reasoning_content"
      },
      "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,
      "reasoning_options": [
        {
          "type": "toggle"
        }
      ],
      "release_date": "2025-08-11",
      "temperature": true,
      "tool_call": true
    },
    "glm-4.6": {
      "attachment": false,
      "canonical_model_id": "zhipuai/glm-4.6",
      "cost": {
        "cache_read": 0.11,
        "cache_write": 0,
        "input": 0.6,
        "output": 2.2
      },
      "description": "Late GLM-4 workhorse for coding agents, reasoning, and structured tasks",
      "family": "glm",
      "id": "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,
      "reasoning_options": [
        {
          "type": "toggle"
        }
      ],
      "release_date": "2025-09-30",
      "temperature": true,
      "tool_call": true
    },
    "glm-4.6v": {
      "attachment": true,
      "canonical_model_id": "zhipuai/glm-4.6v",
      "cost": {
        "cache_read": 0.2,
        "cache_write": 0,
        "currency": "CNY",
        "input": 1,
        "output": 3,
        "tiers": [
          {
            "cache_read": 0.4,
            "input": 2,
            "output": 6,
            "tier": {
              "size": 32000,
              "type": "context"
            }
          }
        ]
      },
      "description": "GLM vision model for visual reasoning, documents, and multimodal agents",
      "family": "glm",
      "id": "glm-4.6v",
      "interleaved": {
        "field": "reasoning_content"
      },
      "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,
      "reasoning_options": [
        {
          "type": "toggle"
        }
      ],
      "release_date": "2025-12-08",
      "temperature": true,
      "tool_call": true
    },
    "glm-4.6v-flash": {
      "attachment": true,
      "canonical_model_id": "zhipuai/glm-4.6v-flash",
      "cost": {
        "cache_read": 0,
        "cache_write": 0,
        "input": 0,
        "output": 0
      },
      "description": "Lightweight GLM vision model for visual reasoning, documents, and multimodal agents",
      "family": "glm-flash",
      "id": "glm-4.6v-flash",
      "interleaved": {
        "field": "reasoning_content"
      },
      "last_updated": "2025-12-08",
      "limit": {
        "context": 128000,
        "output": 32768
      },
      "modalities": {
        "input": [
          "text",
          "image",
          "video"
        ],
        "output": [
          "text"
        ]
      },
      "name": "GLM-4.6V-Flash",
      "open_weights": true,
      "reasoning": true,
      "reasoning_options": [
        {
          "type": "toggle"
        }
      ],
      "release_date": "2025-12-08",
      "temperature": true,
      "tool_call": true
    },
    "glm-4.7": {
      "attachment": false,
      "canonical_model_id": "zhipuai/glm-4.7",
      "cost": {
        "cache_read": 0.6,
        "cache_write": 0,
        "currency": "CNY",
        "input": 3,
        "output": 14,
        "tiers": [
          {
            "cache_read": 0.8,
            "input": 4,
            "output": 16,
            "tier": {
              "size": 32000,
              "type": "context"
            }
          }
        ]
      },
      "description": "Mature GLM model for dependable coding, reasoning, and structured agent tasks",
      "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,
      "reasoning_options": [
        {
          "type": "toggle"
        }
      ],
      "release_date": "2025-12-22",
      "temperature": true,
      "tool_call": true
    },
    "glm-4.7-flash": {
      "attachment": false,
      "canonical_model_id": "zhipuai/glm-4.7-flash",
      "cost": {
        "cache_read": 0,
        "cache_write": 0,
        "currency": "CNY",
        "input": 0,
        "output": 0
      },
      "description": "Budget GLM lane for fast coding help, routing, and everyday automation",
      "family": "glm-flash",
      "id": "glm-4.7-flash",
      "interleaved": {
        "field": "reasoning_content"
      },
      "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,
      "reasoning_options": [
        {
          "type": "toggle"
        }
      ],
      "release_date": "2026-01-19",
      "temperature": true,
      "tool_call": true
    },
    "glm-4.7-flashx": {
      "attachment": false,
      "canonical_model_id": "zhipuai/glm-4.7-flashx",
      "cost": {
        "cache_read": 0.1,
        "cache_write": 0,
        "currency": "CNY",
        "input": 0.5,
        "output": 3
      },
      "description": "Efficient GLM model for fast reasoning, coding, and agent workflows",
      "family": "glm-flash",
      "id": "glm-4.7-flashx",
      "interleaved": {
        "field": "reasoning_content"
      },
      "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,
      "reasoning_options": [
        {
          "type": "toggle"
        }
      ],
      "release_date": "2026-01-19",
      "temperature": true,
      "tool_call": true
    },
    "glm-5": {
      "attachment": false,
      "canonical_model_id": "zhipuai/glm-5",
      "cost": {
        "cache_read": 1,
        "cache_write": 0,
        "currency": "CNY",
        "input": 4,
        "output": 18,
        "tiers": [
          {
            "cache_read": 1.5,
            "input": 6,
            "output": 22,
            "tier": {
              "size": 32000,
              "type": "context"
            }
          }
        ]
      },
      "description": "General GLM flagship for coding, analysis, and tool-heavy engineering workflows",
      "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,
      "reasoning_options": [
        {
          "type": "toggle"
        }
      ],
      "release_date": "2026-02-12",
      "temperature": true,
      "tool_call": true
    },
    "glm-5.1": {
      "attachment": false,
      "canonical_model_id": "zhipuai/glm-5.1",
      "cost": {
        "cache_read": 1.3,
        "cache_write": 0,
        "currency": "CNY",
        "input": 6,
        "output": 24,
        "tiers": [
          {
            "cache_read": 2,
            "input": 8,
            "output": 28,
            "tier": {
              "size": 32000,
              "type": "context"
            }
          }
        ]
      },
      "description": "Strong GLM coding model for agentic engineering, terminals, and repository generation",
      "family": "glm",
      "id": "glm-5.1",
      "interleaved": {
        "field": "reasoning_content"
      },
      "last_updated": "2026-04-07",
      "limit": {
        "context": 200000,
        "output": 131072
      },
      "modalities": {
        "input": [
          "text"
        ],
        "output": [
          "text"
        ]
      },
      "name": "GLM-5.1",
      "open_weights": true,
      "reasoning": true,
      "reasoning_options": [
        {
          "type": "toggle"
        }
      ],
      "release_date": "2026-04-07",
      "structured_output": true,
      "temperature": true,
      "tool_call": true
    },
    "glm-5.2": {
      "attachment": false,
      "canonical_model_id": "zhipuai/glm-5.2",
      "cost": {
        "cache_read": 2,
        "cache_write": 0,
        "currency": "CNY",
        "input": 8,
        "output": 28
      },
      "description": "Open flagship GLM for long-horizon coding agents and million-token context work",
      "family": "glm",
      "id": "glm-5.2",
      "interleaved": {
        "field": "reasoning_content"
      },
      "last_updated": "2026-06-13",
      "limit": {
        "context": 1000000,
        "output": 131072
      },
      "modalities": {
        "input": [
          "text"
        ],
        "output": [
          "text"
        ]
      },
      "name": "GLM-5.2",
      "open_weights": true,
      "reasoning": true,
      "reasoning_options": [
        {
          "type": "toggle"
        },
        {
          "type": "effort",
          "values": [
            "high",
            "max"
          ]
        }
      ],
      "release_date": "2026-06-13",
      "structured_output": true,
      "temperature": true,
      "tool_call": true
    },
    "glm-5.3": {
      "attachment": false,
      "canonical_model_id": "zhipuai/glm-5.3",
      "cost": {
        "cache_read": 2,
        "cache_write": 0,
        "currency": "CNY",
        "input": 8,
        "output": 28
      },
      "description": "Flagship GLM model for long-horizon coding, agents, and complex project delivery",
      "family": "glm",
      "id": "glm-5.3",
      "interleaved": {
        "field": "reasoning_content"
      },
      "last_updated": "2026-08-14",
      "limit": {
        "context": 1000000,
        "output": 131072
      },
      "modalities": {
        "input": [
          "text"
        ],
        "output": [
          "text"
        ]
      },
      "name": "GLM-5.3",
      "open_weights": true,
      "reasoning": true,
      "reasoning_options": [
        {
          "type": "effort",
          "values": [
            "low",
            "high",
            "max"
          ]
        }
      ],
      "release_date": "2026-08-14",
      "structured_output": true,
      "temperature": true,
      "tool_call": true
    },
    "glm-5.3-flash": {
      "attachment": true,
      "canonical_model_id": "zhipuai/glm-5.3-flash",
      "cost": {
        "cache_read": 0.23,
        "cache_write": 0,
        "currency": "CNY",
        "input": 0.8,
        "output": 2.8
      },
      "description": "Native multimodal GLM model for efficient coding and long-horizon agent tasks",
      "family": "glm-flash",
      "id": "glm-5.3-flash",
      "interleaved": {
        "field": "reasoning_content"
      },
      "last_updated": "2026-08-26",
      "limit": {
        "context": 1000000,
        "output": 131072
      },
      "modalities": {
        "input": [
          "text",
          "image",
          "video",
          "pdf"
        ],
        "output": [
          "text"
        ]
      },
      "name": "GLM-5.3-Flash",
      "open_weights": true,
      "reasoning": true,
      "reasoning_options": [
        {
          "type": "effort",
          "values": [
            "low",
            "high",
            "max"
          ]
        }
      ],
      "release_date": "2026-08-26",
      "structured_output": true,
      "temperature": true,
      "tool_call": true
    },
    "glm-5.3-flashx": {
      "attachment": true,
      "canonical_model_id": "zhipuai/glm-5.3-flash",
      "cost": {
        "cache_read": 0.57,
        "cache_write": 0,
        "currency": "CNY",
        "input": 2,
        "output": 7
      },
      "description": "High-speed GLM-5.3-Flash serving option for coding and agent workflows",
      "family": "glm-flash",
      "id": "glm-5.3-flashx",
      "interleaved": {
        "field": "reasoning_content"
      },
      "last_updated": "2026-09-18",
      "limit": {
        "context": 1000000,
        "output": 131072
      },
      "modalities": {
        "input": [
          "text",
          "image",
          "video",
          "pdf"
        ],
        "output": [
          "text"
        ]
      },
      "name": "GLM-5.3-FlashX",
      "open_weights": true,
      "reasoning": true,
      "reasoning_options": [
        {
          "type": "effort",
          "values": [
            "low",
            "high",
            "max"
          ]
        }
      ],
      "release_date": "2026-09-18",
      "structured_output": true,
      "temperature": true,
      "tool_call": true
    },
    "glm-5v-turbo": {
      "attachment": true,
      "canonical_model_id": "zhipuai/glm-5v-turbo",
      "cost": {
        "cache_read": 1.2,
        "cache_write": 0,
        "currency": "CNY",
        "input": 5,
        "output": 22,
        "tiers": [
          {
            "cache_read": 1.8,
            "input": 7,
            "output": 26,
            "tier": {
              "size": 32000,
              "type": "context"
            }
          }
        ]
      },
      "description": "Fast GLM vision model for screenshots, documents, and multimodal agent tasks",
      "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,
      "reasoning_options": [
        {
          "type": "toggle"
        }
      ],
      "release_date": "2026-04-01",
      "temperature": true,
      "tool_call": true
    }
  },
  "name": "Zhipu AI",
  "npm": "@ai-sdk/openai-compatible"
}