Create a response
Create a model response using the OpenAI Responses API shape. Use this endpoint when you want input items, function-call output items, server-side tools, structured text output, response storage, or Responses-style streaming events.
Set reasoning.effort to default, none, minimal, low, medium, high, xhigh, or max, or omit it for the model default. Some models also support numeric reasoning effort. Check the model’s Mixlayer documentation page for supported values and ranges. Models reject unsupported efforts; see Reasoning for model-specific mappings.
Set stream to true to receive typed server-sent events; the stream ends with data: [DONE].
Authentication
Request
Metadata stored with the response when store is true.
Prompt-cache key echoed on the response object.
End-user or session identifier echoed on the response object.
Store the response for later use with previous_response_id.
If true, return Responses Server-Sent Events. Defaults to false.
Function and hosted web-search tools available to the model.
Restricts sampling to the highest-probability tokens.
Response
A complete response or a stream of typed response events, selected by the request’s stream field
Whether background processing was requested, always false.
Object type, always response.
Generated message, reasoning, and function-call items.
Processing tier, always default.
Response status: in_progress, completed, or incomplete.
Input truncation policy, always disabled.
Response-level error details, when generation fails.
Prompt-cache key supplied with the request.
End-user or session identifier supplied with the request.