{
  "api": "https://api.stepfun.com/v1",
  "billing": {
    "priority": 10
  },
  "currency": "CNY",
  "doc": "https://platform.stepfun.com/docs/zh/overview/concept",
  "env": [
    "STEPFUN_API_KEY"
  ],
  "iconURL": "https://models.dev/logos/stepfun.svg",
  "id": "stepfun",
  "lobeIcon": "Stepfun",
  "models": {
    "step-3.5-flash": {
      "attachment": false,
      "canonical_model_id": "stepfun/step-3.5-flash",
      "cost": {
        "cache_read": 0.14,
        "currency": "CNY",
        "input": 0.7,
        "output": 2.1
      },
      "description": "StepFun flash lane for quick multimodal reasoning and coding assistance",
      "family": "step",
      "id": "step-3.5-flash",
      "interleaved": {
        "field": "reasoning_content"
      },
      "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,
      "reasoning_options": [
        {
          "type": "effort",
          "values": [
            "low",
            "high"
          ]
        }
      ],
      "release_date": "2026-01-29",
      "structured_output": true,
      "temperature": true,
      "tool_call": true
    },
    "step-3.5-flash-2603": {
      "attachment": false,
      "canonical_model_id": "stepfun/step-3.5-flash-2603",
      "cost": {
        "cache_read": 0.14,
        "currency": "CNY",
        "input": 0.7,
        "output": 2.1
      },
      "description": "StepFun flash model for efficient multimodal reasoning, coding, and tool use",
      "family": "step",
      "id": "step-3.5-flash-2603",
      "interleaved": {
        "field": "reasoning_content"
      },
      "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,
      "reasoning_options": [
        {
          "type": "effort",
          "values": [
            "low",
            "high"
          ]
        }
      ],
      "release_date": "2026-04-02",
      "structured_output": true,
      "temperature": true,
      "tool_call": true
    },
    "step-3.7-flash": {
      "attachment": true,
      "canonical_model_id": "stepfun/step-3.7-flash",
      "cost": {
        "cache_read": 0.27,
        "currency": "CNY",
        "input": 1.35,
        "output": 8.1
      },
      "description": "Newer StepFun flash model for faster agents, coding, and multimodal prompts",
      "id": "step-3.7-flash",
      "interleaved": {
        "field": "reasoning_content"
      },
      "knowledge": "2026-03-01",
      "last_updated": "2026-05-29",
      "limit": {
        "context": 256000,
        "input": 256000,
        "output": 256000
      },
      "modalities": {
        "input": [
          "text",
          "image",
          "video"
        ],
        "output": [
          "text"
        ]
      },
      "name": "Step 3.7 Flash",
      "open_weights": true,
      "reasoning": true,
      "reasoning_options": [
        {
          "type": "effort",
          "values": [
            "low",
            "medium",
            "high"
          ]
        }
      ],
      "release_date": "2026-05-29",
      "structured_output": true,
      "temperature": true,
      "tool_call": true
    },
    "step-5-preview": {
      "attachment": true,
      "canonical_model_id": "stepfun/step-5-preview",
      "cost": {
        "cache_read": 0.10461,
        "input": 1.04613,
        "output": 2.98895
      },
      "description": "StepFun's next-generation flagship base model for coding and professional knowledge work, with native text, image, and video input and a 1M-token context window",
      "id": "step-5-preview",
      "interleaved": {
        "field": "reasoning_content"
      },
      "last_updated": "2026-09-20",
      "limit": {
        "context": 1000000,
        "input": 1000000,
        "output": 65536
      },
      "modalities": {
        "input": [
          "text",
          "image",
          "video"
        ],
        "output": [
          "text"
        ]
      },
      "name": "Step 5 Preview",
      "open_weights": true,
      "reasoning": true,
      "reasoning_options": [
        {
          "type": "effort",
          "values": [
            "low",
            "medium",
            "high"
          ]
        }
      ],
      "release_date": "2026-09-16",
      "structured_output": true,
      "temperature": true,
      "tool_call": true
    },
    "step-tts-2": {
      "attachment": false,
      "description": "Speech generation model for controllable voice, narration, and audio delivery",
      "family": "step",
      "id": "step-tts-2",
      "last_updated": "2026-07-02",
      "limit": {
        "context": 0,
        "output": 0
      },
      "modalities": {
        "input": [
          "text"
        ],
        "output": [
          "audio"
        ]
      },
      "name": "Step TTS 2",
      "open_weights": false,
      "provider": {
        "npm": "@ai-sdk/openai"
      },
      "reasoning": false,
      "release_date": "2026-03-01",
      "temperature": false,
      "tool_call": false,
      "type": "speech"
    },
    "stepaudio-2.5-asr": {
      "attachment": true,
      "description": "Speech transcription model for accurate audio-to-text and captioning workflows",
      "family": "step",
      "id": "stepaudio-2.5-asr",
      "last_updated": "2026-07-02",
      "limit": {
        "context": 0,
        "output": 0
      },
      "modalities": {
        "input": [
          "audio"
        ],
        "output": [
          "text"
        ]
      },
      "name": "StepAudio 2.5 ASR",
      "open_weights": false,
      "provider": {
        "npm": "@ai-sdk/openai"
      },
      "reasoning": false,
      "release_date": "2026-04-24",
      "temperature": false,
      "tool_call": false,
      "type": "transcription"
    },
    "stepaudio-2.5-tts": {
      "attachment": false,
      "description": "Speech generation model for controllable voice, narration, and audio delivery",
      "family": "step",
      "id": "stepaudio-2.5-tts",
      "last_updated": "2026-07-02",
      "limit": {
        "context": 0,
        "output": 0
      },
      "modalities": {
        "input": [
          "text"
        ],
        "output": [
          "audio"
        ]
      },
      "name": "StepAudio 2.5 TTS",
      "open_weights": false,
      "provider": {
        "npm": "@ai-sdk/openai"
      },
      "reasoning": false,
      "release_date": "2026-04-16",
      "temperature": false,
      "tool_call": false,
      "type": "speech"
    }
  },
  "name": "StepFun (China)",
  "npm": "@ai-sdk/openai-compatible"
}