{
  "source": "build",
  "runtime_observed": false,
  "catalog_hash": "db92ce3432f6314799e250adecab22e083f0629676ccd878f11940f75eea2026",
  "items": [
    {
      "id": "gemma4-12b",
      "kind": "llm",
      "summary": "Smaller and faster. Good for short chat, extraction and image questions.",
      "tags": [
        "chat",
        "coding",
        "聊天",
        "文本"
      ],
      "protocols": [
        {
          "id": "chat",
          "method": "POST",
          "path": "/v1/chat/completions",
          "content_type": "application/json",
          "modes": [
            "json",
            "sse"
          ],
          "schema_scope": "supported_subset",
          "input_schema": {
            "type": "object",
            "properties": {
              "model": {
                "const": "gemma4-12b"
              },
              "messages": {
                "type": "array",
                "minItems": 1,
                "items": {
                  "type": "object"
                }
              },
              "stream": {
                "type": "boolean"
              },
              "max_tokens": {
                "type": "integer",
                "minimum": 1
              }
            },
            "required": [
              "model",
              "messages"
            ],
            "additionalProperties": true
          },
          "constraints": [
            "Follow the selected protocol. This schema documents a subset, not all engine parameters.",
            "Images must be inline data URLs or base64; remote image URLs are refused."
          ],
          "example": {
            "model": "gemma4-12b",
            "messages": [
              {
                "role": "user",
                "content": "Say hello."
              }
            ],
            "max_tokens": 32
          }
        },
        {
          "id": "completions",
          "method": "POST",
          "path": "/v1/completions",
          "content_type": "application/json",
          "modes": [
            "json",
            "sse"
          ],
          "schema_scope": "supported_subset",
          "input_schema": {
            "type": "object",
            "properties": {
              "model": {
                "const": "gemma4-12b"
              },
              "prompt": {
                "type": [
                  "string",
                  "array"
                ]
              },
              "stream": {
                "type": "boolean"
              },
              "max_tokens": {
                "type": "integer",
                "minimum": 1
              }
            },
            "required": [
              "model",
              "prompt"
            ],
            "additionalProperties": true
          },
          "constraints": [
            "Follow the selected protocol. This schema documents a subset, not all engine parameters.",
            "Images must be inline data URLs or base64; remote image URLs are refused."
          ],
          "example": {
            "model": "gemma4-12b",
            "prompt": "Say hello.",
            "max_tokens": 32
          }
        },
        {
          "id": "responses",
          "method": "POST",
          "path": "/v1/responses",
          "content_type": "application/json",
          "modes": [
            "json",
            "sse"
          ],
          "schema_scope": "supported_subset",
          "input_schema": {
            "type": "object",
            "properties": {
              "model": {
                "const": "gemma4-12b"
              },
              "input": {
                "type": [
                  "string",
                  "array"
                ]
              },
              "stream": {
                "type": "boolean"
              },
              "max_tokens": {
                "type": "integer",
                "minimum": 1
              }
            },
            "required": [
              "model",
              "input"
            ],
            "additionalProperties": true
          },
          "constraints": [
            "Follow the selected protocol. This schema documents a subset, not all engine parameters.",
            "Images must be inline data URLs or base64; remote image URLs are refused."
          ],
          "example": {
            "model": "gemma4-12b",
            "input": "Say hello.",
            "max_output_tokens": 32
          }
        },
        {
          "id": "messages",
          "method": "POST",
          "path": "/v1/messages",
          "content_type": "application/json",
          "modes": [
            "json",
            "sse"
          ],
          "schema_scope": "supported_subset",
          "input_schema": {
            "type": "object",
            "properties": {
              "model": {
                "const": "gemma4-12b"
              },
              "messages": {
                "type": "array",
                "minItems": 1,
                "items": {
                  "type": "object"
                }
              },
              "stream": {
                "type": "boolean"
              },
              "max_tokens": {
                "type": "integer",
                "minimum": 1
              }
            },
            "required": [
              "model",
              "messages",
              "max_tokens"
            ],
            "additionalProperties": true
          },
          "constraints": [
            "Follow the selected protocol. This schema documents a subset, not all engine parameters.",
            "Images must be inline data URLs or base64; remote image URLs are refused."
          ],
          "example": {
            "model": "gemma4-12b",
            "messages": [
              {
                "role": "user",
                "content": "Say hello."
              }
            ],
            "max_tokens": 32
          }
        }
      ],
      "guaranteed": {
        "max_images": 16,
        "remote_images": false
      },
      "documented": {
        "context_tokens": 131072,
        "context_runtime_verified": false,
        "features": [
          "Tool calls",
          "Streaming",
          "Prompt caching",
          "JSON mode and structured output"
        ],
        "limitations": [
          "Up to 16 images per request, inline only (data URL or base64)."
        ]
      },
      "billing": {
        "meter": "tokens",
        "quota_basis": "uncached_input_plus_output",
        "pricing": {
          "status": "quote_required"
        }
      },
      "external_limits": null,
      "schema_version": 1,
      "publication": "public",
      "next": [
        {
          "method": "POST",
          "path": "/v1/chat/completions",
          "content_type": "application/json",
          "body": {
            "model": "gemma4-12b",
            "messages": [
              {
                "role": "user",
                "content": "Say hello."
              }
            ],
            "max_tokens": 32
          }
        },
        {
          "method": "POST",
          "path": "/v1/completions",
          "content_type": "application/json",
          "body": {
            "model": "gemma4-12b",
            "prompt": "Say hello.",
            "max_tokens": 32
          }
        },
        {
          "method": "POST",
          "path": "/v1/responses",
          "content_type": "application/json",
          "body": {
            "model": "gemma4-12b",
            "input": "Say hello.",
            "max_output_tokens": 32
          }
        },
        {
          "method": "POST",
          "path": "/v1/messages",
          "content_type": "application/json",
          "body": {
            "model": "gemma4-12b",
            "messages": [
              {
                "role": "user",
                "content": "Say hello."
              }
            ],
            "max_tokens": 32
          }
        }
      ],
      "contract_hash": "a867515abd7d712d3e2f71cd260494ac0afe5b2dbc66c96168a10af98deb2520"
    },
    {
      "id": "gemma4-12b-direct",
      "kind": "llm",
      "summary": "Gemma 4 12B with an adapter that declines fewer requests.",
      "tags": [
        "chat",
        "coding",
        "聊天",
        "文本"
      ],
      "protocols": [
        {
          "id": "chat",
          "method": "POST",
          "path": "/v1/chat/completions",
          "content_type": "application/json",
          "modes": [
            "json",
            "sse"
          ],
          "schema_scope": "supported_subset",
          "input_schema": {
            "type": "object",
            "properties": {
              "model": {
                "const": "gemma4-12b-direct"
              },
              "messages": {
                "type": "array",
                "minItems": 1,
                "items": {
                  "type": "object"
                }
              },
              "stream": {
                "type": "boolean"
              },
              "max_tokens": {
                "type": "integer",
                "minimum": 1
              }
            },
            "required": [
              "model",
              "messages"
            ],
            "additionalProperties": true
          },
          "constraints": [
            "Follow the selected protocol. This schema documents a subset, not all engine parameters.",
            "Images must be inline data URLs or base64; remote image URLs are refused."
          ],
          "example": {
            "model": "gemma4-12b-direct",
            "messages": [
              {
                "role": "user",
                "content": "Say hello."
              }
            ],
            "max_tokens": 32
          }
        },
        {
          "id": "completions",
          "method": "POST",
          "path": "/v1/completions",
          "content_type": "application/json",
          "modes": [
            "json",
            "sse"
          ],
          "schema_scope": "supported_subset",
          "input_schema": {
            "type": "object",
            "properties": {
              "model": {
                "const": "gemma4-12b-direct"
              },
              "prompt": {
                "type": [
                  "string",
                  "array"
                ]
              },
              "stream": {
                "type": "boolean"
              },
              "max_tokens": {
                "type": "integer",
                "minimum": 1
              }
            },
            "required": [
              "model",
              "prompt"
            ],
            "additionalProperties": true
          },
          "constraints": [
            "Follow the selected protocol. This schema documents a subset, not all engine parameters.",
            "Images must be inline data URLs or base64; remote image URLs are refused."
          ],
          "example": {
            "model": "gemma4-12b-direct",
            "prompt": "Say hello.",
            "max_tokens": 32
          }
        },
        {
          "id": "responses",
          "method": "POST",
          "path": "/v1/responses",
          "content_type": "application/json",
          "modes": [
            "json",
            "sse"
          ],
          "schema_scope": "supported_subset",
          "input_schema": {
            "type": "object",
            "properties": {
              "model": {
                "const": "gemma4-12b-direct"
              },
              "input": {
                "type": [
                  "string",
                  "array"
                ]
              },
              "stream": {
                "type": "boolean"
              },
              "max_tokens": {
                "type": "integer",
                "minimum": 1
              }
            },
            "required": [
              "model",
              "input"
            ],
            "additionalProperties": true
          },
          "constraints": [
            "Follow the selected protocol. This schema documents a subset, not all engine parameters.",
            "Images must be inline data URLs or base64; remote image URLs are refused."
          ],
          "example": {
            "model": "gemma4-12b-direct",
            "input": "Say hello.",
            "max_output_tokens": 32
          }
        },
        {
          "id": "messages",
          "method": "POST",
          "path": "/v1/messages",
          "content_type": "application/json",
          "modes": [
            "json",
            "sse"
          ],
          "schema_scope": "supported_subset",
          "input_schema": {
            "type": "object",
            "properties": {
              "model": {
                "const": "gemma4-12b-direct"
              },
              "messages": {
                "type": "array",
                "minItems": 1,
                "items": {
                  "type": "object"
                }
              },
              "stream": {
                "type": "boolean"
              },
              "max_tokens": {
                "type": "integer",
                "minimum": 1
              }
            },
            "required": [
              "model",
              "messages",
              "max_tokens"
            ],
            "additionalProperties": true
          },
          "constraints": [
            "Follow the selected protocol. This schema documents a subset, not all engine parameters.",
            "Images must be inline data URLs or base64; remote image URLs are refused."
          ],
          "example": {
            "model": "gemma4-12b-direct",
            "messages": [
              {
                "role": "user",
                "content": "Say hello."
              }
            ],
            "max_tokens": 32
          }
        }
      ],
      "guaranteed": {
        "max_images": 16,
        "remote_images": false
      },
      "documented": {
        "context_tokens": 131072,
        "context_runtime_verified": false,
        "features": [
          "Tool calls",
          "Streaming",
          "Prompt caching",
          "JSON mode and structured output"
        ],
        "limitations": [
          "Up to 16 images per request, inline only (data URL or base64).",
          "You are responsible for what you ask it to write."
        ]
      },
      "billing": {
        "meter": "tokens",
        "quota_basis": "uncached_input_plus_output",
        "pricing": {
          "status": "quote_required"
        }
      },
      "external_limits": null,
      "schema_version": 1,
      "publication": "public",
      "next": [
        {
          "method": "POST",
          "path": "/v1/chat/completions",
          "content_type": "application/json",
          "body": {
            "model": "gemma4-12b-direct",
            "messages": [
              {
                "role": "user",
                "content": "Say hello."
              }
            ],
            "max_tokens": 32
          }
        },
        {
          "method": "POST",
          "path": "/v1/completions",
          "content_type": "application/json",
          "body": {
            "model": "gemma4-12b-direct",
            "prompt": "Say hello.",
            "max_tokens": 32
          }
        },
        {
          "method": "POST",
          "path": "/v1/responses",
          "content_type": "application/json",
          "body": {
            "model": "gemma4-12b-direct",
            "input": "Say hello.",
            "max_output_tokens": 32
          }
        },
        {
          "method": "POST",
          "path": "/v1/messages",
          "content_type": "application/json",
          "body": {
            "model": "gemma4-12b-direct",
            "messages": [
              {
                "role": "user",
                "content": "Say hello."
              }
            ],
            "max_tokens": 32
          }
        }
      ],
      "contract_hash": "da686f843ffb2b181a40169d622228f91d36d7d53c747917bd1ad91dc6364a1a"
    },
    {
      "id": "qwen3.8-27b",
      "kind": "llm",
      "summary": "General chat, coding agents and tool use. Our default model.",
      "tags": [
        "chat",
        "coding",
        "聊天",
        "文本"
      ],
      "protocols": [
        {
          "id": "chat",
          "method": "POST",
          "path": "/v1/chat/completions",
          "content_type": "application/json",
          "modes": [
            "json",
            "sse"
          ],
          "schema_scope": "supported_subset",
          "input_schema": {
            "type": "object",
            "properties": {
              "model": {
                "const": "qwen3.8-27b"
              },
              "messages": {
                "type": "array",
                "minItems": 1,
                "items": {
                  "type": "object"
                }
              },
              "stream": {
                "type": "boolean"
              },
              "max_tokens": {
                "type": "integer",
                "minimum": 1
              }
            },
            "required": [
              "model",
              "messages"
            ],
            "additionalProperties": true
          },
          "constraints": [
            "Follow the selected protocol. This schema documents a subset, not all engine parameters.",
            "Images must be inline data URLs or base64; remote image URLs are refused."
          ],
          "example": {
            "model": "qwen3.8-27b",
            "messages": [
              {
                "role": "user",
                "content": "Say hello."
              }
            ],
            "max_tokens": 32
          }
        },
        {
          "id": "completions",
          "method": "POST",
          "path": "/v1/completions",
          "content_type": "application/json",
          "modes": [
            "json",
            "sse"
          ],
          "schema_scope": "supported_subset",
          "input_schema": {
            "type": "object",
            "properties": {
              "model": {
                "const": "qwen3.8-27b"
              },
              "prompt": {
                "type": [
                  "string",
                  "array"
                ]
              },
              "stream": {
                "type": "boolean"
              },
              "max_tokens": {
                "type": "integer",
                "minimum": 1
              }
            },
            "required": [
              "model",
              "prompt"
            ],
            "additionalProperties": true
          },
          "constraints": [
            "Follow the selected protocol. This schema documents a subset, not all engine parameters.",
            "Images must be inline data URLs or base64; remote image URLs are refused."
          ],
          "example": {
            "model": "qwen3.8-27b",
            "prompt": "Say hello.",
            "max_tokens": 32
          }
        },
        {
          "id": "responses",
          "method": "POST",
          "path": "/v1/responses",
          "content_type": "application/json",
          "modes": [
            "json",
            "sse"
          ],
          "schema_scope": "supported_subset",
          "input_schema": {
            "type": "object",
            "properties": {
              "model": {
                "const": "qwen3.8-27b"
              },
              "input": {
                "type": [
                  "string",
                  "array"
                ]
              },
              "stream": {
                "type": "boolean"
              },
              "max_tokens": {
                "type": "integer",
                "minimum": 1
              }
            },
            "required": [
              "model",
              "input"
            ],
            "additionalProperties": true
          },
          "constraints": [
            "Follow the selected protocol. This schema documents a subset, not all engine parameters.",
            "Images must be inline data URLs or base64; remote image URLs are refused."
          ],
          "example": {
            "model": "qwen3.8-27b",
            "input": "Say hello.",
            "max_output_tokens": 32
          }
        },
        {
          "id": "messages",
          "method": "POST",
          "path": "/v1/messages",
          "content_type": "application/json",
          "modes": [
            "json",
            "sse"
          ],
          "schema_scope": "supported_subset",
          "input_schema": {
            "type": "object",
            "properties": {
              "model": {
                "const": "qwen3.8-27b"
              },
              "messages": {
                "type": "array",
                "minItems": 1,
                "items": {
                  "type": "object"
                }
              },
              "stream": {
                "type": "boolean"
              },
              "max_tokens": {
                "type": "integer",
                "minimum": 1
              }
            },
            "required": [
              "model",
              "messages",
              "max_tokens"
            ],
            "additionalProperties": true
          },
          "constraints": [
            "Follow the selected protocol. This schema documents a subset, not all engine parameters.",
            "Images must be inline data URLs or base64; remote image URLs are refused."
          ],
          "example": {
            "model": "qwen3.8-27b",
            "messages": [
              {
                "role": "user",
                "content": "Say hello."
              }
            ],
            "max_tokens": 32
          }
        }
      ],
      "guaranteed": {
        "max_images": 16,
        "remote_images": false
      },
      "documented": {
        "context_tokens": 131072,
        "context_runtime_verified": false,
        "features": [
          "Tool calls",
          "Streaming",
          "Prompt caching",
          "JSON mode and structured output",
          "Thinking off by default; turn it on with chat_template_kwargs.enable_thinking or reasoning_effort"
        ],
        "limitations": [
          "Up to 16 images per request, inline only (data URL or base64)."
        ]
      },
      "billing": {
        "meter": "tokens",
        "quota_basis": "uncached_input_plus_output",
        "pricing": {
          "status": "quote_required"
        }
      },
      "external_limits": null,
      "schema_version": 1,
      "publication": "public",
      "next": [
        {
          "method": "POST",
          "path": "/v1/chat/completions",
          "content_type": "application/json",
          "body": {
            "model": "qwen3.8-27b",
            "messages": [
              {
                "role": "user",
                "content": "Say hello."
              }
            ],
            "max_tokens": 32
          }
        },
        {
          "method": "POST",
          "path": "/v1/completions",
          "content_type": "application/json",
          "body": {
            "model": "qwen3.8-27b",
            "prompt": "Say hello.",
            "max_tokens": 32
          }
        },
        {
          "method": "POST",
          "path": "/v1/responses",
          "content_type": "application/json",
          "body": {
            "model": "qwen3.8-27b",
            "input": "Say hello.",
            "max_output_tokens": 32
          }
        },
        {
          "method": "POST",
          "path": "/v1/messages",
          "content_type": "application/json",
          "body": {
            "model": "qwen3.8-27b",
            "messages": [
              {
                "role": "user",
                "content": "Say hello."
              }
            ],
            "max_tokens": 32
          }
        }
      ],
      "contract_hash": "2c35ff9e4fefd385e1228e2e58d4dd45d22f45541acdea07e81d81f6c530d6bc"
    },
    {
      "id": "qwen3.8-27b-cute",
      "kind": "llm",
      "summary": "The direct model with a casual, short, emoji-friendly chat persona.",
      "tags": [
        "chat",
        "coding",
        "聊天",
        "文本",
        "陪聊"
      ],
      "protocols": [
        {
          "id": "chat",
          "method": "POST",
          "path": "/v1/chat/completions",
          "content_type": "application/json",
          "modes": [
            "json",
            "sse"
          ],
          "schema_scope": "supported_subset",
          "input_schema": {
            "type": "object",
            "properties": {
              "model": {
                "const": "qwen3.8-27b-cute"
              },
              "messages": {
                "type": "array",
                "minItems": 1,
                "items": {
                  "type": "object"
                }
              },
              "stream": {
                "type": "boolean"
              },
              "max_tokens": {
                "type": "integer",
                "minimum": 1
              }
            },
            "required": [
              "model",
              "messages"
            ],
            "additionalProperties": true
          },
          "constraints": [
            "Follow the selected protocol. This schema documents a subset, not all engine parameters.",
            "Images must be inline data URLs or base64; remote image URLs are refused."
          ],
          "example": {
            "model": "qwen3.8-27b-cute",
            "messages": [
              {
                "role": "user",
                "content": "Say hello."
              }
            ],
            "max_tokens": 32
          }
        },
        {
          "id": "completions",
          "method": "POST",
          "path": "/v1/completions",
          "content_type": "application/json",
          "modes": [
            "json",
            "sse"
          ],
          "schema_scope": "supported_subset",
          "input_schema": {
            "type": "object",
            "properties": {
              "model": {
                "const": "qwen3.8-27b-cute"
              },
              "prompt": {
                "type": [
                  "string",
                  "array"
                ]
              },
              "stream": {
                "type": "boolean"
              },
              "max_tokens": {
                "type": "integer",
                "minimum": 1
              }
            },
            "required": [
              "model",
              "prompt"
            ],
            "additionalProperties": true
          },
          "constraints": [
            "Follow the selected protocol. This schema documents a subset, not all engine parameters.",
            "Images must be inline data URLs or base64; remote image URLs are refused."
          ],
          "example": {
            "model": "qwen3.8-27b-cute",
            "prompt": "Say hello.",
            "max_tokens": 32
          }
        },
        {
          "id": "responses",
          "method": "POST",
          "path": "/v1/responses",
          "content_type": "application/json",
          "modes": [
            "json",
            "sse"
          ],
          "schema_scope": "supported_subset",
          "input_schema": {
            "type": "object",
            "properties": {
              "model": {
                "const": "qwen3.8-27b-cute"
              },
              "input": {
                "type": [
                  "string",
                  "array"
                ]
              },
              "stream": {
                "type": "boolean"
              },
              "max_tokens": {
                "type": "integer",
                "minimum": 1
              }
            },
            "required": [
              "model",
              "input"
            ],
            "additionalProperties": true
          },
          "constraints": [
            "Follow the selected protocol. This schema documents a subset, not all engine parameters.",
            "Images must be inline data URLs or base64; remote image URLs are refused."
          ],
          "example": {
            "model": "qwen3.8-27b-cute",
            "input": "Say hello.",
            "max_output_tokens": 32
          }
        },
        {
          "id": "messages",
          "method": "POST",
          "path": "/v1/messages",
          "content_type": "application/json",
          "modes": [
            "json",
            "sse"
          ],
          "schema_scope": "supported_subset",
          "input_schema": {
            "type": "object",
            "properties": {
              "model": {
                "const": "qwen3.8-27b-cute"
              },
              "messages": {
                "type": "array",
                "minItems": 1,
                "items": {
                  "type": "object"
                }
              },
              "stream": {
                "type": "boolean"
              },
              "max_tokens": {
                "type": "integer",
                "minimum": 1
              }
            },
            "required": [
              "model",
              "messages",
              "max_tokens"
            ],
            "additionalProperties": true
          },
          "constraints": [
            "Follow the selected protocol. This schema documents a subset, not all engine parameters.",
            "Images must be inline data URLs or base64; remote image URLs are refused."
          ],
          "example": {
            "model": "qwen3.8-27b-cute",
            "messages": [
              {
                "role": "user",
                "content": "Say hello."
              }
            ],
            "max_tokens": 32
          }
        }
      ],
      "guaranteed": {
        "max_images": 16,
        "remote_images": false
      },
      "documented": {
        "context_tokens": 131072,
        "context_runtime_verified": false,
        "features": [
          "Streaming",
          "Prompt caching"
        ],
        "limitations": [
          "Not for strict-format output such as JSON or classification.",
          "Up to 16 images per request, inline only (data URL or base64)."
        ]
      },
      "billing": {
        "meter": "tokens",
        "quota_basis": "uncached_input_plus_output",
        "pricing": {
          "status": "quote_required"
        }
      },
      "external_limits": null,
      "schema_version": 1,
      "publication": "public",
      "next": [
        {
          "method": "POST",
          "path": "/v1/chat/completions",
          "content_type": "application/json",
          "body": {
            "model": "qwen3.8-27b-cute",
            "messages": [
              {
                "role": "user",
                "content": "Say hello."
              }
            ],
            "max_tokens": 32
          }
        },
        {
          "method": "POST",
          "path": "/v1/completions",
          "content_type": "application/json",
          "body": {
            "model": "qwen3.8-27b-cute",
            "prompt": "Say hello.",
            "max_tokens": 32
          }
        },
        {
          "method": "POST",
          "path": "/v1/responses",
          "content_type": "application/json",
          "body": {
            "model": "qwen3.8-27b-cute",
            "input": "Say hello.",
            "max_output_tokens": 32
          }
        },
        {
          "method": "POST",
          "path": "/v1/messages",
          "content_type": "application/json",
          "body": {
            "model": "qwen3.8-27b-cute",
            "messages": [
              {
                "role": "user",
                "content": "Say hello."
              }
            ],
            "max_tokens": 32
          }
        }
      ],
      "contract_hash": "ad6e199d194bf6a634568d6964aa2016916e03bc91e300804058ae40b868dfef"
    },
    {
      "id": "qwen3.8-27b-direct",
      "kind": "llm",
      "summary": "Qwen3.8 27B with an adapter that declines fewer requests.",
      "tags": [
        "chat",
        "coding",
        "聊天",
        "文本"
      ],
      "protocols": [
        {
          "id": "chat",
          "method": "POST",
          "path": "/v1/chat/completions",
          "content_type": "application/json",
          "modes": [
            "json",
            "sse"
          ],
          "schema_scope": "supported_subset",
          "input_schema": {
            "type": "object",
            "properties": {
              "model": {
                "const": "qwen3.8-27b-direct"
              },
              "messages": {
                "type": "array",
                "minItems": 1,
                "items": {
                  "type": "object"
                }
              },
              "stream": {
                "type": "boolean"
              },
              "max_tokens": {
                "type": "integer",
                "minimum": 1
              }
            },
            "required": [
              "model",
              "messages"
            ],
            "additionalProperties": true
          },
          "constraints": [
            "Follow the selected protocol. This schema documents a subset, not all engine parameters.",
            "Images must be inline data URLs or base64; remote image URLs are refused."
          ],
          "example": {
            "model": "qwen3.8-27b-direct",
            "messages": [
              {
                "role": "user",
                "content": "Say hello."
              }
            ],
            "max_tokens": 32
          }
        },
        {
          "id": "completions",
          "method": "POST",
          "path": "/v1/completions",
          "content_type": "application/json",
          "modes": [
            "json",
            "sse"
          ],
          "schema_scope": "supported_subset",
          "input_schema": {
            "type": "object",
            "properties": {
              "model": {
                "const": "qwen3.8-27b-direct"
              },
              "prompt": {
                "type": [
                  "string",
                  "array"
                ]
              },
              "stream": {
                "type": "boolean"
              },
              "max_tokens": {
                "type": "integer",
                "minimum": 1
              }
            },
            "required": [
              "model",
              "prompt"
            ],
            "additionalProperties": true
          },
          "constraints": [
            "Follow the selected protocol. This schema documents a subset, not all engine parameters.",
            "Images must be inline data URLs or base64; remote image URLs are refused."
          ],
          "example": {
            "model": "qwen3.8-27b-direct",
            "prompt": "Say hello.",
            "max_tokens": 32
          }
        },
        {
          "id": "responses",
          "method": "POST",
          "path": "/v1/responses",
          "content_type": "application/json",
          "modes": [
            "json",
            "sse"
          ],
          "schema_scope": "supported_subset",
          "input_schema": {
            "type": "object",
            "properties": {
              "model": {
                "const": "qwen3.8-27b-direct"
              },
              "input": {
                "type": [
                  "string",
                  "array"
                ]
              },
              "stream": {
                "type": "boolean"
              },
              "max_tokens": {
                "type": "integer",
                "minimum": 1
              }
            },
            "required": [
              "model",
              "input"
            ],
            "additionalProperties": true
          },
          "constraints": [
            "Follow the selected protocol. This schema documents a subset, not all engine parameters.",
            "Images must be inline data URLs or base64; remote image URLs are refused."
          ],
          "example": {
            "model": "qwen3.8-27b-direct",
            "input": "Say hello.",
            "max_output_tokens": 32
          }
        },
        {
          "id": "messages",
          "method": "POST",
          "path": "/v1/messages",
          "content_type": "application/json",
          "modes": [
            "json",
            "sse"
          ],
          "schema_scope": "supported_subset",
          "input_schema": {
            "type": "object",
            "properties": {
              "model": {
                "const": "qwen3.8-27b-direct"
              },
              "messages": {
                "type": "array",
                "minItems": 1,
                "items": {
                  "type": "object"
                }
              },
              "stream": {
                "type": "boolean"
              },
              "max_tokens": {
                "type": "integer",
                "minimum": 1
              }
            },
            "required": [
              "model",
              "messages",
              "max_tokens"
            ],
            "additionalProperties": true
          },
          "constraints": [
            "Follow the selected protocol. This schema documents a subset, not all engine parameters.",
            "Images must be inline data URLs or base64; remote image URLs are refused."
          ],
          "example": {
            "model": "qwen3.8-27b-direct",
            "messages": [
              {
                "role": "user",
                "content": "Say hello."
              }
            ],
            "max_tokens": 32
          }
        }
      ],
      "guaranteed": {
        "max_images": 16,
        "remote_images": false
      },
      "documented": {
        "context_tokens": 131072,
        "context_runtime_verified": false,
        "features": [
          "Tool calls",
          "Streaming",
          "Prompt caching",
          "JSON mode and structured output",
          "Thinking off by default; turn it on with chat_template_kwargs.enable_thinking or reasoning_effort"
        ],
        "limitations": [
          "Up to 16 images per request, inline only (data URL or base64).",
          "You are responsible for what you ask it to write."
        ]
      },
      "billing": {
        "meter": "tokens",
        "quota_basis": "uncached_input_plus_output",
        "pricing": {
          "status": "quote_required"
        }
      },
      "external_limits": null,
      "schema_version": 1,
      "publication": "public",
      "next": [
        {
          "method": "POST",
          "path": "/v1/chat/completions",
          "content_type": "application/json",
          "body": {
            "model": "qwen3.8-27b-direct",
            "messages": [
              {
                "role": "user",
                "content": "Say hello."
              }
            ],
            "max_tokens": 32
          }
        },
        {
          "method": "POST",
          "path": "/v1/completions",
          "content_type": "application/json",
          "body": {
            "model": "qwen3.8-27b-direct",
            "prompt": "Say hello.",
            "max_tokens": 32
          }
        },
        {
          "method": "POST",
          "path": "/v1/responses",
          "content_type": "application/json",
          "body": {
            "model": "qwen3.8-27b-direct",
            "input": "Say hello.",
            "max_output_tokens": 32
          }
        },
        {
          "method": "POST",
          "path": "/v1/messages",
          "content_type": "application/json",
          "body": {
            "model": "qwen3.8-27b-direct",
            "messages": [
              {
                "role": "user",
                "content": "Say hello."
              }
            ],
            "max_tokens": 32
          }
        }
      ],
      "contract_hash": "35e8fbce6d44bf7687cb9c8eba6cd0f0443f929fc76f88bf344abfe8855a39a9"
    },
    {
      "id": "sensevoice-small",
      "kind": "asr",
      "summary": "Transcribe short WAV recordings to text.",
      "tags": [
        "audio",
        "transcription",
        "语音识别",
        "转写"
      ],
      "protocols": [
        {
          "id": "transcription",
          "method": "POST",
          "path": "/v1/audio/transcriptions",
          "content_type": "multipart/form-data",
          "modes": [
            "json",
            "verbose_json",
            "text"
          ],
          "schema_scope": "complete_fields",
          "input_schema": {
            "type": "object",
            "properties": {
              "model": {
                "const": "sensevoice-small"
              },
              "file": {
                "type": "string",
                "format": "binary"
              },
              "language": {
                "type": "string",
                "maxLength": 16
              },
              "response_format": {
                "enum": [
                  "json",
                  "verbose_json",
                  "text"
                ]
              },
              "temperature": {
                "description": "Accepted and ignored by the engine."
              }
            },
            "required": [
              "model",
              "file"
            ],
            "additionalProperties": false
          },
          "constraints": [
            "Upload a non-empty WAV: PCM16 or float32, 1–2 channels, 8–48 kHz.",
            "The file example names a local upload; do not send that name as a text form field."
          ],
          "example": {
            "model": "sensevoice-small",
            "file": "@sample.wav",
            "response_format": "verbose_json"
          }
        }
      ],
      "guaranteed": {
        "max_audio_ms": 30000,
        "max_request_bytes": 26214400,
        "encodings": [
          "pcm16",
          "float32"
        ],
        "channels": [
          1,
          2
        ],
        "sample_rate_hz": [
          8000,
          48000
        ]
      },
      "documented": {
        "guide": "https://tokenflow.dev/speech",
        "limits": [
          "No speaker diarization; convert other formats to WAV first."
        ]
      },
      "billing": {
        "meter": "audio_ms",
        "minimum_billed_units": 10000,
        "measured": "audio_duration_ms",
        "pricing": {
          "meter": "audio_ms",
          "usd_per_hour": 0.054,
          "unit": "audio_hour",
          "status": "open",
          "currency": "USD",
          "checked_at": "2026-11-18",
          "settlement": "customer_agreement"
        }
      },
      "external_limits": {
        "concurrency": {
          "perTenant": 2,
          "external": 3,
          "retryAfterS": 2
        },
        "default_monthly": {
          "limit": 36000000,
          "unit": "audio_ms"
        },
        "quota_is_not_free_credit": true
      },
      "schema_version": 1,
      "publication": "public",
      "next": [
        {
          "method": "POST",
          "path": "/v1/audio/transcriptions",
          "content_type": "multipart/form-data",
          "body": {
            "model": "sensevoice-small",
            "file": "@sample.wav",
            "response_format": "verbose_json"
          }
        }
      ],
      "contract_hash": "5e30a3f6cc9ae65c75b2681a84a483271d90b9c9c499fb8f0e1f873ba5042ec2"
    },
    {
      "id": "tokenflow-tts-1",
      "kind": "tts",
      "summary": "Generate speech from text using preset or described voices.",
      "tags": [
        "audio",
        "synthesis",
        "语音合成",
        "朗读"
      ],
      "protocols": [
        {
          "id": "speech",
          "method": "POST",
          "path": "/v1/audio/speech",
          "content_type": "application/json",
          "modes": [
            "mp3",
            "opus",
            "aac",
            "flac",
            "wav",
            "pcm",
            "stream_pcm",
            "stream_opus"
          ],
          "schema_scope": "complete_fields",
          "input_schema": {
            "type": "object",
            "properties": {
              "model": {
                "const": "tokenflow-tts-1"
              },
              "input": {
                "type": "string",
                "minLength": 1,
                "maxLength": 4000
              },
              "voice": {
                "type": "string",
                "enum": [
                  "zh-female-calm",
                  "zh-male-warm",
                  "en-female-clear",
                  "zh-sunwukong",
                  "en-female-warm-us",
                  "en-female-sweet-us",
                  "en-female-mature-us",
                  "en-female-southern-us",
                  "en-female-bedtime-us",
                  "en-female-soft-uk",
                  "en-female-posh-uk",
                  "en-female-lilt-ie",
                  "en-female-bright-au",
                  "en-female-mellow-au"
                ]
              },
              "instructions": {
                "type": "string",
                "minLength": 1,
                "maxLength": 200,
                "pattern": "^[^()（）]+$"
              },
              "response_format": {
                "enum": [
                  "mp3",
                  "opus",
                  "aac",
                  "flac",
                  "wav",
                  "pcm"
                ],
                "default": "mp3"
              },
              "stream": {
                "type": "boolean"
              },
              "seed": {
                "type": "integer",
                "minimum": 0,
                "maximum": 2147483647
              },
              "speed": {
                "type": "number",
                "minimum": 0.75,
                "maximum": 1.5,
                "default": 1
              }
            },
            "required": [
              "model",
              "input"
            ],
            "additionalProperties": false,
            "not": {
              "required": [
                "voice",
                "instructions"
              ]
            },
            "allOf": [
              {
                "if": {
                  "properties": {
                    "stream": {
                      "const": true
                    }
                  },
                  "required": [
                    "stream"
                  ]
                },
                "then": {
                  "properties": {
                    "response_format": {
                      "enum": [
                        "pcm",
                        "opus"
                      ]
                    }
                  }
                }
              }
            ]
          },
          "constraints": [
            "Input and instructions must contain non-whitespace text.",
            "Choose voice or instructions, never both. Instructions cannot contain parentheses.",
            "Formats as OpenAI names them: mp3 (default), opus, aac, flac, wav, pcm. pcm is 24 kHz 16-bit little-endian mono, streamed or not. Streaming takes pcm (default) or opus.",
            "Every audio response names its origin in the x-aigc-label header; mp3, aac, opus, flac and wav also carry it in the file. Keep it when you store or pass audio on.",
            "No cloning from your own recordings. Disclose AI speech and preserve origin metadata."
          ],
          "example": {
            "model": "tokenflow-tts-1",
            "input": "你好，欢迎使用语音服务。",
            "voice": "zh-female-calm"
          }
        }
      ],
      "guaranteed": {
        "max_input_characters": 4000,
        "max_instructions_characters": 200,
        "max_request_bytes": 65536,
        "voices": [
          "zh-female-calm",
          "zh-male-warm",
          "en-female-clear",
          "zh-sunwukong",
          "en-female-warm-us",
          "en-female-sweet-us",
          "en-female-mature-us",
          "en-female-southern-us",
          "en-female-bedtime-us",
          "en-female-soft-uk",
          "en-female-posh-uk",
          "en-female-lilt-ie",
          "en-female-bright-au",
          "en-female-mellow-au"
        ]
      },
      "documented": {
        "guide": "https://tokenflow.dev/speech",
        "limits": [
          "Text-based voice design; no cloning from your own audio."
        ]
      },
      "billing": {
        "meter": "tts_audio_ms",
        "minimum_billed_units": 1000,
        "measured": "delivered_audio_ms",
        "pricing": {
          "meter": "tts_audio_ms",
          "usd_per_hour": 1,
          "unit": "audio_hour",
          "status": "open",
          "currency": "USD",
          "checked_at": "2026-11-18",
          "settlement": "customer_agreement"
        }
      },
      "external_limits": {
        "concurrency": {
          "perTenant": 4,
          "external": 8,
          "retryAfterS": 5
        },
        "default_monthly": {
          "limit": 72000000,
          "unit": "tts_audio_ms"
        },
        "quota_is_not_free_credit": true
      },
      "schema_version": 1,
      "publication": "public",
      "next": [
        {
          "method": "POST",
          "path": "/v1/audio/speech",
          "content_type": "application/json",
          "body": {
            "model": "tokenflow-tts-1",
            "input": "你好，欢迎使用语音服务。",
            "voice": "zh-female-calm"
          }
        }
      ],
      "contract_hash": "b3cca7f750e7aada5b50c26de627245762875ba118bfb7d94a5949b11467ca9e"
    }
  ]
}
