{
  "openapi": "3.0.0",
  "info": {
    "title": "Baseten Responses",
    "version": "1.0.0",
    "description": "OpenAI Responses-compatible API for Baseten Model APIs. Requests are stateless: send the full conversation as `input` on every call."
  },
  "paths": {
    "/v1/responses": {
      "post": {
        "summary": "Create a response",
        "description": "Creates a model response from an input string or a list of input items. Requests are stateless: Baseten stores no response, so send prior turns back as input rather than referring to an earlier response.",
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "type": "object",
                "properties": {
                  "model": {
                    "type": "string",
                    "description": "Model slug, such as `zai-org/GLM-5.3`."
                  },
                  "input": {
                    "description": "A prompt string, or the full conversation as input items. Include prior user messages, all response output items, and a function_call_output for each application function call.",
                    "oneOf": [
                      {
                        "type": "string"
                      },
                      {
                        "type": "array",
                        "items": {
                          "oneOf": [
                            {
                              "$ref": "#/components/schemas/InputMessage"
                            },
                            {
                              "$ref": "#/components/schemas/ReasoningItem"
                            },
                            {
                              "$ref": "#/components/schemas/FunctionCall"
                            },
                            {
                              "$ref": "#/components/schemas/FunctionCallOutput"
                            }
                          ]
                        }
                      }
                    ]
                  },
                  "instructions": {
                    "type": "string",
                    "description": "System-level instructions for the request."
                  },
                  "max_output_tokens": {
                    "type": "integer",
                    "minimum": 1,
                    "description": "Upper bound on generated tokens, including reasoning tokens."
                  },
                  "temperature": {
                    "type": "number",
                    "format": "float",
                    "default": 1,
                    "minimum": 0,
                    "maximum": 2,
                    "description": "Sampling temperature, from 0 to 2."
                  },
                  "top_p": {
                    "type": "number",
                    "format": "float",
                    "default": 1,
                    "minimum": 0,
                    "maximum": 1,
                    "description": "Nucleus sampling threshold, from 0 to 1."
                  },
                  "stream": {
                    "type": "boolean",
                    "default": false,
                    "description": "Stream server-sent events instead of returning one JSON object."
                  },
                  "tools": {
                    "type": "array",
                    "description": "Function tools the model can call.",
                    "items": {
                      "type": "object",
                      "properties": {
                        "type": {
                          "type": "string",
                          "enum": [
                            "function"
                          ]
                        },
                        "name": {
                          "type": "string"
                        },
                        "description": {
                          "type": "string"
                        },
                        "parameters": {
                          "type": "object",
                          "description": "JSON Schema for the function arguments."
                        }
                      },
                      "required": [
                        "type",
                        "name",
                        "parameters"
                      ]
                    }
                  },
                  "tool_choice": {
                    "description": "Whether the model calls a tool. `auto` lets the model decide, `required` forces a call, `none` forbids one.",
                    "oneOf": [
                      {
                        "type": "string",
                        "enum": [
                          "auto",
                          "required",
                          "none"
                        ]
                      },
                      {
                        "type": "object",
                        "properties": {
                          "type": {
                            "type": "string",
                            "enum": [
                              "function"
                            ]
                          },
                          "name": {
                            "type": "string"
                          }
                        },
                        "required": [
                          "type",
                          "name"
                        ]
                      }
                    ]
                  },
                  "parallel_tool_calls": {
                    "type": "boolean",
                    "default": true,
                    "description": "Lets the model emit more than one function call in a response."
                  },
                  "text": {
                    "type": "object",
                    "description": "Output format for the message text.",
                    "properties": {
                      "format": {
                        "oneOf": [
                          {
                            "type": "object",
                            "properties": {
                              "type": {
                                "type": "string",
                                "enum": [
                                  "text"
                                ]
                              }
                            },
                            "required": [
                              "type"
                            ]
                          },
                          {
                            "type": "object",
                            "properties": {
                              "type": {
                                "type": "string",
                                "enum": [
                                  "json_schema"
                                ]
                              },
                              "name": {
                                "type": "string"
                              },
                              "schema": {
                                "type": "object"
                              },
                              "strict": {
                                "type": "boolean"
                              }
                            },
                            "required": [
                              "type",
                              "name",
                              "schema"
                            ]
                          }
                        ]
                      }
                    }
                  },
                  "reasoning": {
                    "type": "object",
                    "description": "Reasoning settings for models that expose them.",
                    "properties": {
                      "effort": {
                        "type": "string",
                        "enum": [
                          "minimal",
                          "low",
                          "medium",
                          "high"
                        ]
                      }
                    }
                  },
                  "metadata": {
                    "type": "object",
                    "description": "Up to 16 key-value pairs, echoed back on the response.",
                    "additionalProperties": {
                      "type": "string"
                    }
                  },
                  "truncation": {
                    "type": "string",
                    "enum": [
                      "auto",
                      "disabled"
                    ],
                    "default": "disabled",
                    "description": "`auto` or `disabled`."
                  }
                },
                "required": [
                  "model",
                  "input"
                ]
              }
            }
          }
        },
        "responses": {
          "200": {
            "description": "A response, which can be completed, incomplete, or failed; or a server-sent event stream when stream is true. Inspect the outcome before using the output.",
            "content": {
              "application/json": {
                "schema": {
                  "type": "object",
                  "properties": {
                    "id": {
                      "type": "string",
                      "description": "Response identifier, prefixed `resp_`."
                    },
                    "object": {
                      "type": "string",
                      "enum": [
                        "response"
                      ]
                    },
                    "created_at": {
                      "type": "integer"
                    },
                    "completed_at": {
                      "type": "integer",
                      "nullable": true
                    },
                    "status": {
                      "type": "string",
                      "enum": [
                        "completed",
                        "incomplete",
                        "failed",
                        "in_progress"
                      ]
                    },
                    "model": {
                      "type": "string"
                    },
                    "output": {
                      "type": "array",
                      "description": "Output items in the order the model produced them.",
                      "items": {
                        "oneOf": [
                          {
                            "type": "object",
                            "properties": {
                              "type": {
                                "type": "string",
                                "enum": [
                                  "message"
                                ]
                              },
                              "id": {
                                "type": "string"
                              },
                              "status": {
                                "type": "string"
                              },
                              "role": {
                                "type": "string",
                                "enum": [
                                  "assistant"
                                ]
                              },
                              "content": {
                                "type": "array",
                                "items": {
                                  "type": "object",
                                  "properties": {
                                    "type": {
                                      "type": "string",
                                      "enum": [
                                        "output_text"
                                      ]
                                    },
                                    "text": {
                                      "type": "string"
                                    },
                                    "annotations": {
                                      "type": "array",
                                      "items": {
                                        "type": "object"
                                      }
                                    }
                                  },
                                  "required": [
                                    "type",
                                    "text"
                                  ]
                                }
                              }
                            },
                            "required": [
                              "type",
                              "id",
                              "role",
                              "content"
                            ]
                          },
                          {
                            "type": "object",
                            "properties": {
                              "type": {
                                "type": "string",
                                "enum": [
                                  "reasoning"
                                ]
                              },
                              "id": {
                                "type": "string"
                              },
                              "summary": {
                                "type": "array",
                                "items": {
                                  "type": "object"
                                }
                              },
                              "content": {
                                "type": "array",
                                "items": {
                                  "type": "object",
                                  "properties": {
                                    "type": {
                                      "type": "string",
                                      "enum": [
                                        "reasoning_text"
                                      ]
                                    },
                                    "text": {
                                      "type": "string"
                                    }
                                  },
                                  "required": [
                                    "type",
                                    "text"
                                  ]
                                }
                              }
                            },
                            "required": [
                              "type",
                              "id"
                            ]
                          },
                          {
                            "type": "object",
                            "properties": {
                              "type": {
                                "type": "string",
                                "enum": [
                                  "function_call"
                                ]
                              },
                              "id": {
                                "type": "string"
                              },
                              "call_id": {
                                "type": "string"
                              },
                              "name": {
                                "type": "string"
                              },
                              "arguments": {
                                "type": "string",
                                "description": "The function arguments, encoded as a JSON string."
                              }
                            },
                            "required": [
                              "type",
                              "id",
                              "call_id",
                              "name",
                              "arguments"
                            ]
                          }
                        ]
                      }
                    },
                    "usage": {
                      "type": "object",
                      "nullable": true,
                      "properties": {
                        "input_tokens": {
                          "type": "integer"
                        },
                        "input_tokens_details": {
                          "type": "object",
                          "properties": {
                            "cached_tokens": {
                              "type": "integer"
                            },
                            "cache_write_tokens": {
                              "type": "integer"
                            }
                          }
                        },
                        "output_tokens": {
                          "type": "integer"
                        },
                        "output_tokens_details": {
                          "type": "object",
                          "properties": {
                            "reasoning_tokens": {
                              "type": "integer"
                            }
                          }
                        },
                        "total_tokens": {
                          "type": "integer"
                        }
                      }
                    },
                    "incomplete_details": {
                      "type": "object",
                      "nullable": true,
                      "properties": {
                        "reason": {
                          "type": "string",
                          "description": "Why generation stopped early, such as `max_output_tokens`."
                        }
                      }
                    },
                    "error": {
                      "type": "object",
                      "nullable": true
                    },
                    "metadata": {
                      "type": "object",
                      "additionalProperties": {
                        "type": "string"
                      }
                    },
                    "instructions": {
                      "type": "string",
                      "nullable": true
                    },
                    "max_output_tokens": {
                      "type": "integer",
                      "nullable": true
                    },
                    "parallel_tool_calls": {
                      "type": "boolean"
                    },
                    "temperature": {
                      "type": "number",
                      "format": "float"
                    },
                    "top_p": {
                      "type": "number",
                      "format": "float"
                    },
                    "tool_choice": {
                      "type": "string"
                    },
                    "tools": {
                      "type": "array",
                      "items": {
                        "type": "object"
                      }
                    },
                    "truncation": {
                      "type": "string"
                    },
                    "service_tier": {
                      "type": "string"
                    },
                    "text": {
                      "type": "object"
                    },
                    "reasoning": {
                      "type": "object",
                      "nullable": true
                    }
                  },
                  "required": [
                    "id",
                    "object",
                    "created_at",
                    "status",
                    "model",
                    "output"
                  ]
                }
              },
              "text/event-stream": {
                "schema": {
                  "type": "string",
                  "description": "Server-sent events. Each event carries a `type`, a `sequence_number`, and a payload, starting with `response.created` and ending with `response.completed`, `response.incomplete`, or `response.failed`."
                }
              }
            }
          },
          "400": {
            "description": "The request was rejected.",
            "content": {
              "application/json": {
                "schema": {
                  "type": "object"
                }
              }
            }
          }
        }
      }
    }
  },
  "servers": [
    {
      "url": "https://inference.baseten.co",
      "description": "Baseten Model APIs"
    }
  ],
  "security": [
    {
      "BearerAuth": []
    }
  ],
  "components": {
    "securitySchemes": {
      "BearerAuth": {
        "type": "http",
        "scheme": "bearer",
        "description": "A Baseten API key."
      }
    },
    "schemas": {
      "InputMessage": {
        "type": "object",
        "properties": {
          "role": {
            "type": "string",
            "enum": [
              "user",
              "assistant",
              "system",
              "developer"
            ]
          },
          "content": {
            "oneOf": [
              {
                "type": "string"
              },
              {
                "type": "array",
                "items": {
                  "type": "object",
                  "properties": {
                    "type": {
                      "type": "string",
                      "enum": [
                        "input_text",
                        "output_text"
                      ]
                    },
                    "text": {
                      "type": "string"
                    }
                  },
                  "required": [
                    "type",
                    "text"
                  ]
                }
              }
            ]
          },
          "type": {
            "type": "string",
            "enum": [
              "message"
            ]
          }
        },
        "required": [
          "role",
          "content"
        ]
      },
      "ReasoningItem": {
        "type": "object",
        "properties": {
          "type": {
            "type": "string",
            "enum": [
              "reasoning"
            ]
          },
          "id": {
            "type": "string"
          },
          "summary": {
            "type": "array",
            "items": {
              "type": "object"
            }
          },
          "content": {
            "type": "array",
            "items": {
              "type": "object",
              "properties": {
                "type": {
                  "type": "string",
                  "enum": [
                    "reasoning_text"
                  ]
                },
                "text": {
                  "type": "string"
                }
              },
              "required": [
                "type",
                "text"
              ]
            }
          }
        },
        "required": [
          "type",
          "id"
        ]
      },
      "FunctionCall": {
        "type": "object",
        "properties": {
          "type": {
            "type": "string",
            "enum": [
              "function_call"
            ]
          },
          "id": {
            "type": "string"
          },
          "call_id": {
            "type": "string"
          },
          "name": {
            "type": "string"
          },
          "arguments": {
            "type": "string",
            "description": "The function arguments, encoded as a JSON string."
          }
        },
        "required": [
          "type",
          "call_id",
          "name",
          "arguments"
        ]
      },
      "FunctionCallOutput": {
        "type": "object",
        "description": "The result of an application function call. Match call_id to the function_call item and encode the result as a string.",
        "properties": {
          "type": {
            "type": "string",
            "enum": [
              "function_call_output"
            ]
          },
          "call_id": {
            "type": "string"
          },
          "output": {
            "type": "string"
          }
        },
        "required": [
          "type",
          "call_id",
          "output"
        ]
      }
    }
  }
}