Body Required

• model string Required

  The ID of the model to use for chat completion.

• messages array[object] Required

  A list of messages comprising the conversation so far.

  Hide messages attributes Show messages attributes object

  • role string Required

    The role of the message author.

    Values are system, user, assistant, or tool.

  • content string | null | array[object] Required

    The content of the message. Can be a string, an array of content parts, or null for function messages.

    One of:

    string-1 string | null array-2 array[object] | null

    Hide attributes Show attributes object

    • type string Required

      Values are text or image_url.

    • text string
    • image_url object
      Hide image_url attributes Show image_url attributes object

      • url string Required
      • detail string

        Values are auto, low, or high. Default value is auto.

  • name string

    The name of the author of this message. May be omitted in most cases.

  • tool_call_id string

    Tool call ID if this message is a tool response.

  • tool_calls array[object]

    A list of tool calls made by the assistant.

    Hide tool_calls attributes Show tool_calls attributes object

    • id string Required

      The ID of the tool call.

    • type string Required

      The type of the tool call. Currently, only 'function' is supported.

      Value is function.

    • function object Required
      Hide function attributes Show function attributes object

      • name string Required

        The name of the function to call.

      • arguments string Required

        The arguments to be passed to the function, represented as a JSON string.

  • function_call object

    The function call made by the assistant. Deprecated: use tool_calls instead.

    Hide function_call attributes Show function_call attributes object

    • name string Required
    • arguments string Required
• temperature number

  What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.

  Minimum value is 0, maximum value is 2. Default value is 1.0.

• top_p number

  An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.

  Minimum value is 0, maximum value is 1. Default value is 1.0.

• n integer

  How many chat completion choices to generate for each input message.

  Minimum value is 1. Default value is 1.

• stream boolean

  If set, partial message deltas will be sent, like in ChatGPT. Tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a data: [DONE] message.

  Default value is false.

• max_tokens integer

  The maximum number of tokens to generate in the chat completion.

  Minimum value is 1.

• presence_penalty number

  Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.

  Minimum value is -2, maximum value is 2. Default value is 0.

• frequency_penalty number

  Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.

  Minimum value is -2, maximum value is 2. Default value is 0.

• logit_bias object

  Modify the likelihood of specified tokens appearing in the completion.

  Hide logit_bias attribute Show logit_bias attribute object

  • * number Additional properties

    Modify the likelihood of specified tokens appearing in the completion.

• user string

  A unique identifier representing your end-user, which can help the API to monitor and detect abuse.

• tools array[object]

  A list of tools the model may call. Currently, only functions are supported as a tool.

  Hide tools attributes Show tools attributes object

  • type string Required

    The type of tool. Currently, only 'function' is supported.

    Value is function.

  • function object Required
    Hide function attributes Show function attributes object

    • name string Required

      The name of the function to be called.

    • parameters object Required

      The parameters the function accepts, described as a JSON Schema object.

    • description string

      A description of what the function does.

• tool_choice string | object

  Controls how the model uses tools.

  One of:

  string-1 string object-2 object

  Controls how the model uses tools. 'auto' allows the model to use tools when appropriate, 'none' disables tool usage.

  Values are auto or none.

  Specifies a particular function to be called.

  Hide attributes Show attributes

  • type string Required

    Value is function.

  • function object Required
    Hide function attribute Show function attribute object

    • name string Required