ChatCompletionRequest

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "#/components/schemas/ChatCompletionRequest",
  "title": "ChatCompletionRequest",
  "type": "object",
  "required": [
    "model",
    "messages"
  ],
  "properties": {
    "model": {
      "type": "string",
      "description": "ID of the model to use. You can use the Models API to see all available models.",
      "example": "mistral-large-latest"
    },
    "messages": {
      "type": "array",
      "description": "A list of messages comprising the conversation so far. Each message has a role and content.",
      "items": {
        "$ref": "#/components/schemas/ChatMessage"
      }
    },
    "temperature": {
      "type": "number",
      "description": "Sampling temperature between 0.0 and 1.5. Higher values like 0.7 produce more random output, while lower values like 0.2 produce more focused and deterministic output.",
      "minimum": 0.0,
      "maximum": 1.5,
      "default": 0.7
    },
    "top_p": {
      "type": "number",
      "description": "Nucleus sampling parameter. The model considers tokens with top_p probability mass. A value of 0.1 means only the top 10% of tokens are considered.",
      "minimum": 0.0,
      "maximum": 1.0,
      "default": 1.0
    },
    "max_tokens": {
      "type": "integer",
      "description": "The maximum number of tokens to generate in the chat completion. The total token count of the prompt plus max_tokens cannot exceed the model's context length.",
      "minimum": 1
    },
    "stream": {
      "type": "boolean",
      "description": "Whether to stream back partial progress as server-sent events. If true, tokens are sent as data-only events as they become available, terminated by a data: [DONE] message.",
      "default": false
    },
    "stop": {
      "oneOf": [
        {
          "type": "string"
        },
        {
          "type": "array",
          "items": {
            "type": "string"
          }
        }
      ],
      "description": "Stop generation if this token is detected, or if one of these tokens is detected when providing an array."
    },
    "random_seed": {
      "type": "integer",
      "description": "The seed to use for random sampling. If set, different calls will generate deterministic results."
    },
    "response_format": {
      "type": "object",
      "description": "An object specifying the format that the model must output. Setting to json_object enables JSON mode.",
      "properties": {
        "type": {
          "type": "string",
          "enum": [
            "text",
            "json_object"
          ],
          "description": "The format type. Use json_object to enable JSON mode."
        }
      }
    },
    "tools": {
      "type": "array",
      "description": "A list of tools the model may call. Currently only functions are supported as a tool.",
      "items": {
        "$ref": "#/components/schemas/Tool"
      }
    },
    "tool_choice": {
      "type": "string",
      "description": "Controls which tool is called by the model. Can be auto, none, any, or required.",
      "enum": [
        "auto",
        "none",
        "any",
        "required"
      ]
    },
    "presence_penalty": {
      "type": "number",
      "description": "Penalizes repetition of words or phrases. A higher value encourages the model to use a wider variety of words and phrases.",
      "minimum": -2.0,
      "maximum": 2.0,
      "default": 0.0
    },
    "frequency_penalty": {
      "type": "number",
      "description": "Penalizes repetition based on frequency in the generated text. A higher value discourages repeating frequently used words.",
      "minimum": -2.0,
      "maximum": 2.0,
      "default": 0.0
    },
    "safe_prompt": {
      "type": "boolean",
      "description": "Whether to inject a safety prompt before all conversations.",
      "default": false
    }
  }
}