CreateChatCompletionStreamRequestBody

Request parameters for creating a chat completion. Based on the OpenAI Chat Completions API.

Example Usage

import { CreateChatCompletionStreamRequestBody } from "@meetkai/mka1/models/operations";

let value: CreateChatCompletionStreamRequestBody = {
  model: "Golf",
  messages: [
    {
      role: "developer",
      content: [],
    },
  ],
};

Fields

Field	Type	Required	Description
model	string	✔️	ID of the model to use. You can use provider:model format (e.g., 'anthropic:claude-3-5-sonnet-20241022') or just the model name with a default provider.
messages	operations.CreateChatCompletionStreamMessages[]	✔️	A list of messages comprising the conversation so far. At least one message is required.
tools	operations.CreateChatCompletionStreamTools[]	➖	A list of tools the model may call. Use this to provide function definitions the model can invoke.
toolChoice	any	➖	Controls which (if any) tool is called by the model. 'none' means the model will not call any tool. 'auto' means the model can pick. 'required' forces a tool call.
stream	boolean	➖	If set, partial message deltas will be sent as server-sent events. Note: This field is ignored by the streaming endpoint, used only by OpenAI-compatible client endpoints.
n	number	➖	How many chat completion choices to generate for each input message. Default is 1.
maxTokens	number	➖	The maximum number of tokens that can be generated in the chat completion. The total length of input tokens and generated tokens is limited by the model's context length.
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.
topP	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.
frequencyPenalty	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.
presencePenalty	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.
seed	number	➖	If specified, the system will make a best effort to sample deterministically. Determinism is not guaranteed, but the same seed should typically return similar results.
stop	operations.CreateChatCompletionStreamStop	➖	Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.
responseFormat	operations.CreateChatCompletionStreamResponseFormat	➖	An object specifying the format that the model must output. Setting to { 'type': 'json_object' } enables JSON mode.
logprobs	operations.CreateChatCompletionStreamLogprobs	➖	Include the log probabilities on the most likely output tokens. If true, returns the log probabilities of each output token.
user	string	➖	A unique identifier representing your end-user, which can help monitor and detect abuse. Also used for usage tracking and analytics.
streamOptions	operations.CreateChatCompletionStreamStreamOptions	➖	Options for streaming response. Only set this when you set stream: true.
parallelToolCalls	boolean	➖	Whether to enable parallel function calling during tool use.
reasoningEffort	operations.CreateChatCompletionStreamReasoningEffort	➖	Constrains effort on reasoning for reasoning models. Lower effort results in faster responses and fewer reasoning tokens. Supported values: 'minimal', 'low', 'medium', 'high'. Note: gpt-5-pro only supports 'high'.