xAI Responses API response body.
interface XAIResponseWhether to process the response asynchronously in the background. Note: Unsupported.
The Unix timestamp (in seconds) for the response creation time.
Debug output information (when available).
Unique ID of the response.
Details about why the response is incomplete (if status is "incomplete").
Max number of tokens that can be generated. Includes both output and reasoning tokens.
Model name used to generate the response.
The object type of this resource. Always set to response.
The response generated by the model.
Whether to allow the model to run parallel tool calls.
The ID of the previous response from the model.
Reasoning configuration used for the response.
Status of the response.
Whether to store the input message(s) and response.
Sampling temperature used (between 0 and 2).
Settings for customizing a text response.
Controls which tool is called by the model.
A list of tools the model may call. Maximum of 128 tools.
Nucleus sampling probability mass used.
Token usage information.
Unique identifier representing your end-user. Used for monitoring and abuse detection.