{
  "openapi": "3.1.0",
  "info": {
    "title": "KosCompute API",
    "description": "OpenAI-compatible REST API with Responses and Anthropic Messages compatibility. The advertised surface is generated from the classified public contract. Capabilities are model-dependent; query GET /v1/models before using optional features.",
    "version": "2026-08-17T12:48:31+00:00",
    "contact": {
      "email": "api@koscompute.com"
    }
  },
  "servers": [
    {
      "url": "https://api.koscompute.com/v1",
      "description": "Production API"
    }
  ],
  "paths": {
    "/models": {
      "get": {
        "tags": [
          "Models"
        ],
        "summary": "List available models",
        "description": "Returns publicly available models with capabilities, pricing, and metadata. No authentication required.",
        "operationId": "listModels",
        "responses": {
          "200": {
            "description": "Successful response",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ListModelsResponse"
                }
              }
            }
          }
        },
        "security": []
      }
    },
    "/chat/completions": {
      "post": {
        "tags": [
          "Chat Completions"
        ],
        "summary": "Create a chat completion",
        "description": "Creates a model response for the given chat conversation. Supports vision image_url inputs, reasoning, tool calling, and structured outputs when declared by the model. Vision processor limits are model-specific. Compatible with OpenAI's chat completions API.",
        "operationId": "createChatCompletion",
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/ChatCompletionRequest"
              }
            }
          }
        },
        "responses": {
          "200": {
            "description": "Successful response",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ChatCompletionResponse"
                }
              }
            }
          },
          "400": {
            "$ref": "#/components/responses/BadRequest"
          },
          "401": {
            "$ref": "#/components/responses/Unauthorized"
          },
          "403": {
            "$ref": "#/components/responses/Forbidden"
          },
          "404": {
            "$ref": "#/components/responses/NotFound"
          },
          "413": {
            "$ref": "#/components/responses/RequestTooLarge"
          },
          "429": {
            "$ref": "#/components/responses/RateLimit"
          },
          "502": {
            "$ref": "#/components/responses/BadGateway"
          },
          "503": {
            "$ref": "#/components/responses/ServiceUnavailable"
          },
          "504": {
            "$ref": "#/components/responses/GatewayTimeout"
          },
          "500": {
            "$ref": "#/components/responses/InternalServerError"
          }
        },
        "security": [
          {
            "BearerAuth": []
          }
        ]
      }
    },
    "/responses": {
      "post": {
        "tags": [
          "Responses"
        ],
        "summary": "Create a response",
        "description": "Stateless, zero-data-retention Responses API compatibility for text generation. Supports message input, streaming SSE, local function tools, structured text formats, and model-dependent reasoning controls. store=true and non-null previous_response_id are rejected; clients must resend conversation context in input.",
        "operationId": "createResponse",
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/CreateResponseRequest"
              }
            }
          }
        },
        "responses": {
          "200": {
            "description": "Completed JSON response or a canonical Responses SSE stream when stream=true",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ResponseObject"
                }
              },
              "text/event-stream": {
                "schema": {
                  "type": "string"
                }
              }
            }
          },
          "400": {
            "$ref": "#/components/responses/BadRequest"
          },
          "401": {
            "$ref": "#/components/responses/Unauthorized"
          },
          "403": {
            "$ref": "#/components/responses/Forbidden"
          },
          "404": {
            "$ref": "#/components/responses/NotFound"
          },
          "413": {
            "$ref": "#/components/responses/RequestTooLarge"
          },
          "429": {
            "$ref": "#/components/responses/RateLimit"
          },
          "500": {
            "$ref": "#/components/responses/InternalServerError"
          },
          "502": {
            "$ref": "#/components/responses/BadGateway"
          },
          "503": {
            "$ref": "#/components/responses/ServiceUnavailable"
          },
          "504": {
            "$ref": "#/components/responses/GatewayTimeout"
          }
        },
        "security": [
          {
            "BearerAuth": []
          }
        ]
      }
    },
    "/messages": {
      "post": {
        "tags": [
          "Messages"
        ],
        "summary": "Create a message (Anthropic Messages compatibility)",
        "description": "Anthropic Messages API compatibility endpoint. Accepts Anthropic-format requests and returns Anthropic-format responses. Supports tools, system prompts, and streaming. Authenticate with either Authorization: Bearer or x-api-key header.",
        "operationId": "createMessage",
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/AnthropicMessageRequest"
              }
            }
          }
        },
        "responses": {
          "200": {
            "description": "Successful response",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/AnthropicMessageResponse"
                }
              }
            }
          },
          "400": {
            "$ref": "#/components/responses/BadRequest"
          },
          "401": {
            "$ref": "#/components/responses/Unauthorized"
          },
          "403": {
            "$ref": "#/components/responses/Forbidden"
          },
          "404": {
            "$ref": "#/components/responses/NotFound"
          },
          "413": {
            "$ref": "#/components/responses/RequestTooLarge"
          },
          "429": {
            "$ref": "#/components/responses/RateLimit"
          },
          "500": {
            "$ref": "#/components/responses/InternalServerError"
          },
          "529": {
            "description": "Anthropic-compatible provider unavailable or upstream failure",
            "headers": {
              "Retry-After": {
                "schema": {
                  "type": "integer"
                }
              }
            },
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/AnthropicError"
                }
              }
            }
          }
        },
        "security": [
          {
            "BearerAuth": []
          }
        ]
      }
    },
    "/audio/transcriptions": {
      "post": {
        "tags": [
          "Audio"
        ],
        "summary": "Transcribe audio to text",
        "description": "Transcribes audio to text using speech-to-text models. Accepts audio files via multipart form upload. Available models: openai/whisper-large-v3, openai/whisper-large-v3-turbo",
        "operationId": "createTranscription",
        "requestBody": {
          "required": true,
          "content": {
            "multipart/form-data": {
              "schema": {
                "$ref": "#/components/schemas/AudioTranscriptionRequest"
              }
            }
          }
        },
        "responses": {
          "200": {
            "description": "Transcription result",
            "content": {
              "application/json": {
                "schema": {
                  "type": "object"
                }
              },
              "text/plain": {
                "schema": {
                  "type": "string"
                }
              },
              "text/srt": {
                "schema": {
                  "type": "string"
                }
              },
              "text/vtt": {
                "schema": {
                  "type": "string"
                }
              }
            }
          },
          "400": {
            "$ref": "#/components/responses/BadRequest"
          },
          "401": {
            "$ref": "#/components/responses/Unauthorized"
          },
          "403": {
            "$ref": "#/components/responses/Forbidden"
          },
          "404": {
            "$ref": "#/components/responses/NotFound"
          },
          "413": {
            "$ref": "#/components/responses/RequestTooLarge"
          },
          "429": {
            "$ref": "#/components/responses/RateLimit"
          },
          "502": {
            "$ref": "#/components/responses/BadGateway"
          },
          "503": {
            "$ref": "#/components/responses/ServiceUnavailable"
          },
          "504": {
            "$ref": "#/components/responses/GatewayTimeout"
          },
          "500": {
            "$ref": "#/components/responses/InternalServerError"
          }
        },
        "security": [
          {
            "BearerAuth": []
          }
        ]
      }
    },
    "/audio/speech": {
      "post": {
        "tags": [
          "Audio"
        ],
        "summary": "Synthesize speech from text",
        "description": "Converts text to speech. Returns audio binary. Available models: kosmik/tts-kokoro-quality, kosmik/tts-piper-fast",
        "operationId": "createSpeech",
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/AudioSpeechRequest"
              }
            }
          }
        },
        "responses": {
          "200": {
            "description": "Audio binary response",
            "content": {
              "audio/wav": {
                "schema": {
                  "type": "string",
                  "format": "binary"
                }
              }
            }
          },
          "400": {
            "$ref": "#/components/responses/BadRequest"
          },
          "401": {
            "$ref": "#/components/responses/Unauthorized"
          },
          "403": {
            "$ref": "#/components/responses/Forbidden"
          },
          "404": {
            "$ref": "#/components/responses/NotFound"
          },
          "413": {
            "$ref": "#/components/responses/RequestTooLarge"
          },
          "429": {
            "$ref": "#/components/responses/RateLimit"
          },
          "502": {
            "$ref": "#/components/responses/BadGateway"
          },
          "503": {
            "$ref": "#/components/responses/ServiceUnavailable"
          },
          "504": {
            "$ref": "#/components/responses/GatewayTimeout"
          },
          "500": {
            "$ref": "#/components/responses/InternalServerError"
          }
        },
        "security": [
          {
            "BearerAuth": []
          }
        ]
      }
    },
    "/health": {
      "get": {
        "tags": [
          "Health"
        ],
        "summary": "Health check",
        "description": "Returns service status. No authentication required.",
        "operationId": "healthCheck",
        "servers": [
          {
            "url": "https://api.koscompute.com",
            "description": "Production host"
          }
        ],
        "responses": {
          "200": {
            "description": "Service healthy",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/HealthResponse"
                }
              }
            }
          }
        },
        "security": []
      }
    },
    "/": {
      "head": {
        "tags": [
          "Health"
        ],
        "summary": "Probe the API host",
        "description": "Returns 204 with no response body. No authentication required.",
        "operationId": "probeApiHost",
        "servers": [
          {
            "url": "https://api.koscompute.com",
            "description": "Production host"
          }
        ],
        "responses": {
          "204": {
            "description": "API host is reachable"
          }
        },
        "security": []
      }
    }
  },
  "components": {
    "securitySchemes": {
      "BearerAuth": {
        "type": "http",
        "scheme": "bearer",
        "bearerFormat": "API-Key"
      }
    },
    "schemas": {
      "Error": {
        "type": "object",
        "properties": {
          "error": {
            "type": "object",
            "properties": {
              "message": {
                "type": "string",
                "description": "Human-readable error message"
              },
              "type": {
                "type": "string",
                "description": "Error category: invalid_request_error, authentication_error, etc."
              },
              "code": {
                "type": "string",
                "description": "Machine-readable error code"
              },
              "param": {
                "type": [
                  "string",
                  "null"
                ],
                "description": "Parameter that triggered the error"
              },
              "metadata": {
                "type": "object",
                "description": "Retry and capacity details. A vision-capacity 429 includes retry_after plus modality, state, active_requests, total_concurrency, and available_concurrency."
              }
            },
            "required": [
              "message",
              "type"
            ]
          }
        },
        "required": [
          "error"
        ]
      },
      "Model": {
        "type": "object",
        "properties": {
          "id": {
            "type": "string"
          },
          "object": {
            "type": "string",
            "enum": [
              "model"
            ]
          },
          "created": {
            "type": "integer"
          },
          "owned_by": {
            "type": "string"
          },
          "name": {
            "type": "string"
          },
          "kind": {
            "type": "string",
            "enum": [
              "chat",
              "audio-transcription",
              "audio-speech",
              "image",
              "image-edit",
              "embedding",
              "rerank"
            ]
          },
          "task": {
            "type": "string"
          },
          "supported_endpoints": {
            "type": "array",
            "items": {
              "type": "string"
            }
          },
          "input_modalities": {
            "type": "array",
            "items": {
              "type": "string"
            }
          },
          "output_modalities": {
            "type": "array",
            "items": {
              "type": "string"
            }
          },
          "context_length": {
            "type": "integer"
          },
          "modality_context_lengths": {
            "type": "object",
            "description": "Context limits by input modality when they differ.",
            "additionalProperties": {
              "type": "integer",
              "minimum": 0
            }
          },
          "max_output_length": {
            "type": "integer"
          },
          "capacity_tpm": {
            "type": "integer",
            "description": "Published approximate token capacity per minute"
          },
          "capacity": {
            "type": "object",
            "description": "Sanitized live admission capacity at response time",
            "properties": {
              "available_concurrency": {
                "type": "integer",
                "minimum": 0
              },
              "total_concurrency": {
                "type": "integer",
                "minimum": 0
              },
              "active_requests": {
                "type": "integer",
                "minimum": 0
              },
              "utilization_percent": {
                "type": "number",
                "minimum": 0,
                "maximum": 100
              },
              "unit": {
                "type": "string",
                "enum": [
                  "concurrent_requests"
                ]
              },
              "updated_at": {
                "type": "integer",
                "description": "Unix timestamp"
              },
              "modalities": {
                "type": "object",
                "description": "Live concurrency split by text and vision pools.",
                "additionalProperties": {
                  "type": "object",
                  "properties": {
                    "available_concurrency": {
                      "type": "integer",
                      "minimum": 0
                    },
                    "total_concurrency": {
                      "type": "integer",
                      "minimum": 0
                    },
                    "active_requests": {
                      "type": "integer",
                      "minimum": 0
                    },
                    "utilization_percent": {
                      "type": "number",
                      "minimum": 0,
                      "maximum": 100
                    }
                  }
                }
              }
            },
            "required": [
              "available_concurrency",
              "total_concurrency",
              "active_requests",
              "utilization_percent",
              "unit",
              "updated_at"
            ]
          },
          "vision": {
            "type": "object",
            "description": "Public vision limits and normalization policy.",
            "properties": {
              "max_image_edge": {
                "type": "integer",
                "description": "Recommended maximum client-side longest edge."
              },
              "max_pixels": {
                "type": "integer",
                "description": "Enforced multimodal processor pixel budget."
              },
              "max_tokens": {
                "type": "integer",
                "description": "Maximum generated tokens for a vision request."
              },
              "context_length": {
                "type": "integer",
                "description": "Vision backend context limit."
              },
              "retry_after_seconds": {
                "type": "integer",
                "description": "Normal retry delay when vision capacity is full."
              }
            }
          },
          "pricing": {
            "type": "object"
          },
          "supported_features": {
            "type": "array",
            "items": {
              "type": "string"
            }
          },
          "is_ready": {
            "type": "boolean"
          }
        }
      },
      "ListModelsResponse": {
        "type": "object",
        "properties": {
          "object": {
            "type": "string",
            "enum": [
              "list"
            ]
          },
          "data": {
            "type": "array",
            "items": {
              "$ref": "#/components/schemas/Model"
            }
          }
        },
        "required": [
          "object",
          "data"
        ]
      },
      "ChatContentPart": {
        "oneOf": [
          {
            "type": "object",
            "properties": {
              "type": {
                "type": "string",
                "enum": [
                  "text"
                ]
              },
              "text": {
                "type": "string"
              }
            },
            "required": [
              "type",
              "text"
            ]
          },
          {
            "type": "object",
            "description": "Vision input. Supports HTTPS URLs and JPEG, PNG, or WebP data URLs. Processor pixel and edge guidance is model-specific and published by GET /v1/models.",
            "properties": {
              "type": {
                "type": "string",
                "enum": [
                  "image_url"
                ]
              },
              "image_url": {
                "oneOf": [
                  {
                    "type": "string",
                    "format": "uri"
                  },
                  {
                    "type": "object",
                    "properties": {
                      "url": {
                        "type": "string"
                      },
                      "detail": {
                        "type": "string",
                        "enum": [
                          "auto",
                          "low",
                          "high"
                        ]
                      }
                    },
                    "required": [
                      "url"
                    ]
                  }
                ]
              }
            },
            "required": [
              "type",
              "image_url"
            ]
          }
        ]
      },
      "ChatMessage": {
        "type": "object",
        "properties": {
          "role": {
            "type": "string",
            "enum": [
              "system",
              "developer",
              "user",
              "assistant",
              "tool"
            ]
          },
          "content": {
            "oneOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              },
              {
                "type": "array",
                "items": {
                  "$ref": "#/components/schemas/ChatContentPart"
                }
              }
            ]
          },
          "name": {
            "type": "string"
          },
          "tool_call_id": {
            "type": "string"
          },
          "tool_calls": {
            "type": "array",
            "items": {
              "$ref": "#/components/schemas/ToolCall"
            }
          }
        },
        "required": [
          "role"
        ]
      },
      "ToolCall": {
        "type": "object",
        "properties": {
          "id": {
            "type": "string"
          },
          "type": {
            "type": "string",
            "enum": [
              "function"
            ]
          },
          "function": {
            "type": "object",
            "properties": {
              "name": {
                "type": "string"
              },
              "arguments": {
                "type": "string"
              }
            },
            "required": [
              "name",
              "arguments"
            ]
          }
        },
        "required": [
          "id",
          "type",
          "function"
        ]
      },
      "ToolDefinition": {
        "type": "object",
        "properties": {
          "type": {
            "type": "string",
            "enum": [
              "function"
            ]
          },
          "function": {
            "type": "object",
            "properties": {
              "name": {
                "type": "string"
              },
              "description": {
                "type": "string"
              },
              "parameters": {
                "type": "object"
              },
              "strict": {
                "type": "boolean"
              }
            },
            "required": [
              "name"
            ]
          }
        },
        "required": [
          "type",
          "function"
        ]
      },
      "ResponseFormat": {
        "oneOf": [
          {
            "type": "object",
            "properties": {
              "type": {
                "enum": [
                  "text"
                ]
              }
            },
            "required": [
              "type"
            ]
          },
          {
            "type": "object",
            "properties": {
              "type": {
                "enum": [
                  "json_object"
                ]
              }
            },
            "required": [
              "type"
            ]
          },
          {
            "type": "object",
            "properties": {
              "type": {
                "enum": [
                  "json_schema"
                ]
              },
              "json_schema": {
                "type": "object"
              }
            },
            "required": [
              "type",
              "json_schema"
            ]
          }
        ]
      },
      "ChatCompletionRequest": {
        "type": "object",
        "properties": {
          "model": {
            "type": "string",
            "description": "Canonical model ID from GET /v1/models"
          },
          "messages": {
            "type": "array",
            "items": {
              "$ref": "#/components/schemas/ChatMessage"
            },
            "minItems": 1
          },
          "temperature": {
            "type": "number",
            "minimum": 0,
            "maximum": 2
          },
          "top_p": {
            "type": "number",
            "minimum": 0,
            "maximum": 1
          },
          "top_k": {
            "type": "integer",
            "minimum": 0
          },
          "min_p": {
            "type": "number",
            "minimum": 0,
            "maximum": 1
          },
          "frequency_penalty": {
            "type": "number",
            "minimum": -2,
            "maximum": 2
          },
          "presence_penalty": {
            "type": "number",
            "minimum": -2,
            "maximum": 2
          },
          "repetition_penalty": {
            "type": "number",
            "minimum": 0.1,
            "maximum": 2
          },
          "max_tokens": {
            "type": "integer",
            "minimum": 0,
            "description": "Legacy alias for max_completion_tokens. It limits all completion tokens, including reasoning. If both fields are present, their values must match."
          },
          "max_completion_tokens": {
            "type": "integer",
            "minimum": 0,
            "description": "Hard maximum for all completion tokens, including reasoning and visible output."
          },
          "stop": {
            "oneOf": [
              {
                "type": "string"
              },
              {
                "type": "array",
                "items": {
                  "type": "string"
                }
              }
            ]
          },
          "seed": {
            "type": "integer"
          },
          "logit_bias": {
            "type": "object"
          },
          "logprobs": {
            "type": "boolean"
          },
          "top_logprobs": {
            "type": "integer"
          },
          "stream": {
            "type": "boolean"
          },
          "stream_options": {
            "type": "object",
            "properties": {
              "include_usage": {
                "type": "boolean"
              }
            }
          },
          "response_format": {
            "$ref": "#/components/schemas/ResponseFormat"
          },
          "tools": {
            "type": "array",
            "items": {
              "$ref": "#/components/schemas/ToolDefinition"
            }
          },
          "tool_choice": {
            "oneOf": [
              {
                "type": "string",
                "enum": [
                  "auto",
                  "required",
                  "none"
                ]
              },
              {
                "type": "object"
              }
            ]
          },
          "reasoning": {
            "type": "object",
            "description": "Reasoning controls. The reasoning sub-budget never increases max_completion_tokens.",
            "properties": {
              "enabled": {
                "type": "boolean"
              },
              "effort": {
                "type": "string",
                "enum": [
                  "none",
                  "low",
                  "medium",
                  "high",
                  "xhigh"
                ]
              },
              "max_tokens": {
                "type": "integer",
                "minimum": 0,
                "description": "Reasoning sub-budget bounded by the total completion limit."
              },
              "exclude": {
                "type": "boolean",
                "description": "Exclude reasoning from response (still used internally)"
              }
            }
          },
          "reasoning_effort": {
            "type": "string",
            "enum": [
              "none",
              "low",
              "medium",
              "high",
              "xhigh"
            ],
            "description": "Top-level alias for reasoning.effort. Model-specific canonical effort sets are published per-model in GET /v1/models (model_info.supported_reasoning_efforts)."
          },
          "include_reasoning": {
            "type": "boolean"
          },
          "user": {
            "type": "string"
          }
        },
        "required": [
          "model",
          "messages"
        ]
      },
      "Usage": {
        "type": "object",
        "properties": {
          "prompt_tokens": {
            "type": "integer"
          },
          "completion_tokens": {
            "type": "integer"
          },
          "completion_tokens_details": {
            "type": "object",
            "properties": {
              "reasoning_tokens": {
                "type": "integer"
              },
              "visible_tokens": {
                "type": "integer"
              }
            }
          },
          "total_tokens": {
            "type": "integer"
          },
          "reasoning_tokens": {
            "type": "integer"
          },
          "cache_read_tokens": {
            "type": "integer"
          }
        }
      },
      "ChatCompletionChoice": {
        "type": "object",
        "properties": {
          "index": {
            "type": "integer"
          },
          "message": {
            "$ref": "#/components/schemas/ChatMessage"
          },
          "finish_reason": {
            "description": "length means the total completion budget was exhausted, including during reasoning; stop means normal completion.",
            "type": [
              "string",
              "null"
            ],
            "enum": [
              "stop",
              "length",
              "tool_calls",
              "content_filter",
              "reasoning",
              null
            ]
          }
        }
      },
      "ChatCompletionResponse": {
        "type": "object",
        "properties": {
          "id": {
            "type": "string"
          },
          "object": {
            "type": "string"
          },
          "created": {
            "type": "integer"
          },
          "model": {
            "type": "string"
          },
          "choices": {
            "type": "array",
            "items": {
              "$ref": "#/components/schemas/ChatCompletionChoice"
            }
          },
          "usage": {
            "$ref": "#/components/schemas/Usage"
          }
        }
      },
      "ResponsesContentPart": {
        "type": "object",
        "properties": {
          "type": {
            "type": "string",
            "enum": [
              "input_text",
              "output_text"
            ]
          },
          "text": {
            "type": "string"
          }
        },
        "required": [
          "type",
          "text"
        ]
      },
      "ResponsesInputItem": {
        "oneOf": [
          {
            "type": "object",
            "properties": {
              "type": {
                "type": "string",
                "enum": [
                  "message"
                ]
              },
              "role": {
                "type": "string",
                "enum": [
                  "system",
                  "developer",
                  "user",
                  "assistant"
                ]
              },
              "content": {
                "oneOf": [
                  {
                    "type": "string"
                  },
                  {
                    "type": "array",
                    "items": {
                      "$ref": "#/components/schemas/ResponsesContentPart"
                    }
                  }
                ]
              }
            },
            "required": [
              "role",
              "content"
            ]
          },
          {
            "type": "object",
            "properties": {
              "type": {
                "type": "string",
                "enum": [
                  "function_call"
                ]
              },
              "call_id": {
                "type": "string"
              },
              "name": {
                "type": "string"
              },
              "arguments": {
                "type": "string",
                "description": "JSON-encoded arguments"
              }
            },
            "required": [
              "type",
              "call_id",
              "name",
              "arguments"
            ]
          },
          {
            "type": "object",
            "properties": {
              "type": {
                "type": "string",
                "enum": [
                  "function_call_output"
                ]
              },
              "call_id": {
                "type": "string"
              },
              "output": {
                "type": "string"
              }
            },
            "required": [
              "type",
              "call_id",
              "output"
            ]
          }
        ]
      },
      "ResponsesFunctionTool": {
        "type": "object",
        "description": "A local function declaration. The nested Chat Completions-compatible function shape is also accepted.",
        "properties": {
          "type": {
            "type": "string",
            "enum": [
              "function"
            ]
          },
          "name": {
            "type": "string"
          },
          "description": {
            "type": "string"
          },
          "parameters": {
            "type": "object"
          },
          "strict": {
            "type": "boolean"
          },
          "function": {
            "type": "object"
          }
        },
        "required": [
          "type"
        ]
      },
      "CreateResponseRequest": {
        "type": "object",
        "additionalProperties": false,
        "properties": {
          "model": {
            "type": "string",
            "description": "Public model ID returned by GET /models"
          },
          "input": {
            "oneOf": [
              {
                "type": "string"
              },
              {
                "type": "array",
                "minItems": 1,
                "items": {
                  "$ref": "#/components/schemas/ResponsesInputItem"
                }
              }
            ]
          },
          "stream": {
            "type": "boolean",
            "default": false
          },
          "temperature": {
            "type": "number",
            "minimum": 0,
            "maximum": 2
          },
          "top_p": {
            "type": "number",
            "exclusiveMinimum": 0,
            "maximum": 1
          },
          "max_output_tokens": {
            "type": "integer",
            "minimum": 1
          },
          "tools": {
            "type": "array",
            "maxItems": 128,
            "items": {
              "$ref": "#/components/schemas/ResponsesFunctionTool"
            }
          },
          "tool_choice": {
            "oneOf": [
              {
                "type": "string",
                "enum": [
                  "auto",
                  "required",
                  "none"
                ]
              },
              {
                "type": "object"
              }
            ]
          },
          "parallel_tool_calls": {
            "type": "boolean"
          },
          "text": {
            "type": "object",
            "properties": {
              "format": {
                "type": "object"
              }
            }
          },
          "reasoning": {
            "type": "object",
            "description": "Model-dependent reasoning controls; public reasoning text is not exposed."
          },
          "metadata": {
            "type": "object"
          },
          "store": {
            "type": "boolean",
            "enum": [
              false
            ],
            "default": false
          },
          "previous_response_id": {
            "type": "null"
          },
          "prompt_cache_key": {
            "type": "null"
          }
        },
        "required": [
          "model",
          "input"
        ]
      },
      "ResponsesUsage": {
        "type": "object",
        "properties": {
          "input_tokens": {
            "type": "integer"
          },
          "input_tokens_details": {
            "type": "object",
            "properties": {
              "cached_tokens": {
                "type": "integer"
              }
            }
          },
          "output_tokens": {
            "type": "integer"
          },
          "output_tokens_details": {
            "type": "object",
            "properties": {
              "reasoning_tokens": {
                "type": "integer"
              }
            }
          },
          "total_tokens": {
            "type": "integer"
          }
        },
        "required": [
          "input_tokens",
          "output_tokens",
          "total_tokens"
        ]
      },
      "ResponseObject": {
        "type": "object",
        "properties": {
          "id": {
            "type": "string",
            "pattern": "^resp_"
          },
          "object": {
            "type": "string",
            "enum": [
              "response"
            ]
          },
          "created_at": {
            "type": "integer"
          },
          "status": {
            "type": "string",
            "enum": [
              "completed",
              "incomplete",
              "in_progress"
            ]
          },
          "error": {
            "type": [
              "object",
              "null"
            ]
          },
          "incomplete_details": {
            "type": [
              "object",
              "null"
            ]
          },
          "model": {
            "type": "string"
          },
          "output": {
            "type": "array",
            "items": {
              "type": "object"
            }
          },
          "parallel_tool_calls": {
            "type": "boolean"
          },
          "previous_response_id": {
            "type": "null"
          },
          "metadata": {
            "type": "object"
          },
          "usage": {
            "oneOf": [
              {
                "$ref": "#/components/schemas/ResponsesUsage"
              },
              {
                "type": "null"
              }
            ]
          }
        },
        "required": [
          "id",
          "object",
          "created_at",
          "status",
          "model",
          "output"
        ]
      },
      "AudioTranscriptionRequest": {
        "type": "object",
        "properties": {
          "file": {
            "type": "string",
            "format": "binary",
            "description": "Audio file (multipart)"
          },
          "model": {
            "type": "string"
          },
          "language": {
            "type": "string"
          },
          "response_format": {
            "type": "string",
            "enum": [
              "json",
              "text",
              "srt",
              "verbose_json",
              "vtt"
            ]
          },
          "temperature": {
            "type": "number"
          },
          "timestamp_granularities": {
            "type": "array",
            "items": {
              "type": "string",
              "enum": [
                "word",
                "segment"
              ]
            }
          }
        },
        "required": [
          "file",
          "model"
        ]
      },
      "AudioSpeechRequest": {
        "type": "object",
        "properties": {
          "model": {
            "type": "string"
          },
          "input": {
            "type": "string",
            "description": "Text to synthesize"
          },
          "voice": {
            "type": "string",
            "description": "Voice identifier"
          },
          "response_format": {
            "type": "string",
            "enum": [
              "wav",
              "mp3",
              "flac",
              "opus",
              "pcm"
            ],
            "default": "wav"
          },
          "speed": {
            "type": "number",
            "default": 1.0
          }
        },
        "required": [
          "model",
          "input"
        ]
      },
      "AnthropicMessageRequest": {
        "type": "object",
        "properties": {
          "model": {
            "type": "string"
          },
          "messages": {
            "type": "array",
            "items": {
              "type": "object",
              "properties": {
                "role": {
                  "type": "string",
                  "enum": [
                    "user",
                    "assistant"
                  ]
                },
                "content": {
                  "oneOf": [
                    {
                      "type": "string"
                    },
                    {
                      "type": "array",
                      "items": {
                        "type": "object"
                      }
                    }
                  ]
                }
              },
              "required": [
                "role",
                "content"
              ]
            }
          },
          "max_tokens": {
            "type": "integer"
          },
          "system": {
            "oneOf": [
              {
                "type": "string"
              },
              {
                "type": "array",
                "items": {
                  "type": "object"
                }
              }
            ]
          },
          "temperature": {
            "type": "number"
          },
          "top_p": {
            "type": "number"
          },
          "top_k": {
            "type": "integer"
          },
          "stop_sequences": {
            "type": "array",
            "items": {
              "type": "string"
            }
          },
          "tools": {
            "type": "array"
          },
          "tool_choice": {
            "type": "object"
          },
          "metadata": {
            "type": "object"
          }
        },
        "required": [
          "model",
          "messages",
          "max_tokens"
        ]
      },
      "AnthropicMessageResponse": {
        "type": "object",
        "properties": {
          "id": {
            "type": "string"
          },
          "type": {
            "type": "string",
            "enum": [
              "message"
            ]
          },
          "role": {
            "type": "string",
            "enum": [
              "assistant"
            ]
          },
          "content": {
            "type": "array",
            "items": {
              "type": "object"
            }
          },
          "model": {
            "type": "string"
          },
          "stop_reason": {
            "type": [
              "string",
              "null"
            ]
          },
          "stop_sequence": {
            "type": [
              "string",
              "null"
            ]
          },
          "usage": {
            "type": "object",
            "properties": {
              "input_tokens": {
                "type": "integer"
              },
              "output_tokens": {
                "type": "integer"
              }
            }
          }
        }
      },
      "AnthropicError": {
        "type": "object",
        "properties": {
          "type": {
            "type": "string",
            "enum": [
              "error"
            ]
          },
          "error": {
            "type": "object",
            "properties": {
              "type": {
                "type": "string",
                "enum": [
                  "invalid_request_error",
                  "authentication_error",
                  "permission_error",
                  "not_found_error",
                  "request_too_large",
                  "rate_limit_error",
                  "api_error",
                  "overloaded_error"
                ]
              },
              "message": {
                "type": "string"
              }
            },
            "required": [
              "type",
              "message"
            ]
          }
        },
        "required": [
          "type",
          "error"
        ]
      },
      "HealthResponse": {
        "type": "object",
        "properties": {
          "status": {
            "type": "string",
            "enum": [
              "ok"
            ]
          }
        }
      }
    },
    "responses": {
      "BadRequest": {
        "description": "Bad request — invalid parameters or payload",
        "content": {
          "application/json": {
            "schema": {
              "$ref": "#/components/schemas/Error"
            }
          }
        }
      },
      "Unauthorized": {
        "description": "Invalid or missing API key",
        "content": {
          "application/json": {
            "schema": {
              "$ref": "#/components/schemas/Error"
            }
          }
        }
      },
      "Forbidden": {
        "description": "Model not allowed for this API key",
        "content": {
          "application/json": {
            "schema": {
              "$ref": "#/components/schemas/Error"
            }
          }
        }
      },
      "RateLimit": {
        "description": "Rate limit or admission capacity is full. The message states when to retry; vision saturation also reports active/total vision concurrency.",
        "headers": {
          "Retry-After": {
            "description": "Seconds to wait before retrying",
            "schema": {
              "type": "integer"
            }
          }
        },
        "content": {
          "application/json": {
            "schema": {
              "$ref": "#/components/schemas/Error"
            }
          }
        }
      },
      "InternalServerError": {
        "description": "Internal server error",
        "content": {
          "application/json": {
            "schema": {
              "$ref": "#/components/schemas/Error"
            }
          }
        }
      },
      "NotFound": {
        "description": "Public model not found",
        "content": {
          "application/json": {
            "schema": {
              "$ref": "#/components/schemas/Error"
            }
          }
        }
      },
      "RequestTooLarge": {
        "description": "Request body exceeds the limit",
        "content": {
          "application/json": {
            "schema": {
              "$ref": "#/components/schemas/Error"
            }
          }
        }
      },
      "BadGateway": {
        "description": "Invalid or failed upstream response",
        "content": {
          "application/json": {
            "schema": {
              "$ref": "#/components/schemas/Error"
            }
          }
        }
      },
      "ServiceUnavailable": {
        "description": "No healthy route",
        "headers": {
          "Retry-After": {
            "schema": {
              "type": "integer"
            }
          }
        },
        "content": {
          "application/json": {
            "schema": {
              "$ref": "#/components/schemas/Error"
            }
          }
        }
      },
      "GatewayTimeout": {
        "description": "Backend generation timeout",
        "headers": {
          "Retry-After": {
            "schema": {
              "type": "integer"
            }
          }
        },
        "content": {
          "application/json": {
            "schema": {
              "$ref": "#/components/schemas/Error"
            }
          }
        }
      }
    }
  },
  "security": [
    {
      "BearerAuth": []
    }
  ],
  "tags": [
    {
      "name": "Models",
      "description": "Model catalog"
    },
    {
      "name": "Chat Completions",
      "description": "OpenAI-compatible chat completions"
    },
    {
      "name": "Responses",
      "description": "OpenAI Responses API compatibility for stateless text generation"
    },
    {
      "name": "Messages",
      "description": "Anthropic Messages compatibility"
    },
    {
      "name": "Audio",
      "description": "Speech recognition and synthesis"
    },
    {
      "name": "Health",
      "description": "Service health check"
    }
  ]
}