Provider routing override. Use a source key such as openai, openrouter, xai, google, alibaba, minimax, moonshot, baidu, or togetherai to run that provider with no fallback; auto (default) uses the full fallback chain. Case-insensitive.

An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens.

The maximum number of tokens that can be generated in the chat completion. This value can be used to control costs for text generated via API.

If set to True, the model response data will be streamed to the client as it is generated using server-sent events.

Enable provider compatibility normalization for tool function JSON schemas.

Whether to enable parallel function calling during tool use.

What sampling temperature to use. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or top_p but not both.

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. We generally recommend altering this or temperature but not both.

Specifies whether to use the thinking mode.

The maximum reasoning length, effective only when enable_thinking is set to true.

A unique identifier for the chat completion.

The object type.

The Unix timestamp (in seconds) of when the chat completion was created.

The model used for the chat completion.