CreateChatCompletionRequest

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "#/components/schemas/CreateChatCompletionRequest",
  "title": "CreateChatCompletionRequest",
  "type": "object",
  "required": [
    "model",
    "messages"
  ],
  "properties": {
    "model": {
      "type": "string",
      "description": "ID of the model to use (e.g., gpt-4o, gpt-4-turbo, gpt-3.5-turbo)",
      "examples": [
        "gpt-4o"
      ]
    },
    "messages": {
      "type": "array",
      "description": "A list of messages comprising the conversation so far",
      "items": {
        "$ref": "#/components/schemas/ChatMessage"
      }
    },
    "temperature": {
      "type": "number",
      "minimum": 0,
      "maximum": 2,
      "default": 1,
      "description": "Sampling temperature between 0 and 2"
    },
    "top_p": {
      "type": "number",
      "minimum": 0,
      "maximum": 1,
      "default": 1,
      "description": "Nucleus sampling parameter"
    },
    "n": {
      "type": "integer",
      "minimum": 1,
      "default": 1,
      "description": "Number of chat completion choices to generate"
    },
    "stream": {
      "type": "boolean",
      "default": false,
      "description": "Whether to stream partial message deltas"
    },
    "stop": {
      "oneOf": [
        {
          "type": "string"
        },
        {
          "type": "array",
          "items": {
            "type": "string"
          }
        }
      ],
      "description": "Up to 4 sequences where the API will stop generating"
    },
    "max_tokens": {
      "type": "integer",
      "description": "Maximum number of tokens to generate in the completion"
    },
    "max_completion_tokens": {
      "type": "integer",
      "description": "Upper bound for tokens generated in the completion including reasoning tokens"
    },
    "presence_penalty": {
      "type": "number",
      "minimum": -2,
      "maximum": 2,
      "default": 0,
      "description": "Penalize new tokens based on presence in text so far"
    },
    "frequency_penalty": {
      "type": "number",
      "minimum": -2,
      "maximum": 2,
      "default": 0,
      "description": "Penalize new tokens based on frequency in text so far"
    },
    "logit_bias": {
      "type": "object",
      "additionalProperties": {
        "type": "number"
      },
      "description": "Modify the likelihood of specified tokens appearing"
    },
    "user": {
      "type": "string",
      "description": "A unique identifier representing your end-user"
    },
    "tools": {
      "type": "array",
      "items": {
        "$ref": "#/components/schemas/Tool"
      },
      "description": "A list of tools the model may call"
    },
    "tool_choice": {
      "oneOf": [
        {
          "type": "string",
          "enum": [
            "none",
            "auto",
            "required"
          ]
        },
        {
          "type": "object",
          "properties": {
            "type": {
              "type": "string",
              "enum": [
                "function"
              ]
            },
            "function": {
              "type": "object",
              "properties": {
                "name": {
                  "type": "string"
                }
              }
            }
          }
        }
      ],
      "description": "Controls which tool is called by the model"
    },
    "response_format": {
      "type": "object",
      "properties": {
        "type": {
          "type": "string",
          "enum": [
            "text",
            "json_object",
            "json_schema"
          ]
        }
      },
      "description": "Specifies the format that the model must output"
    },
    "seed": {
      "type": "integer",
      "description": "Deterministic sampling seed for reproducible outputs"
    }
  }
}