OpenAI Responses
Use this endpoint when your client requires OpenAI’s Responses API wire
protocol, such as Codex with wire_api = "responses".
This endpoint is intended for GPT-series LinkModel chat models. The
request body, supported model values, streaming flag, and optional tool
fields are defined in the schema below.
Official protocol reference: OpenAI Responses API.
Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Body
Text input or Responses API input items.
"Reply with exactly one word: pong"
Optional system or developer instructions.
Maximum number of output tokens to generate.
1024
If true, stream typed Responses API events over SSE.
Optional reasoning controls, such as { "effort": "none" }. Support can vary by selected model and provider.
Optional text output controls.
Sampling temperature.
0 <= x <= 21
Nucleus sampling parameter.
0 <= x <= 11
Optional previous response ID for multi-turn clients that use response chaining. Support can vary by selected model and provider.
Whether the response should be stored when supported by the provider. Support can vary by selected model and provider.
Optional metadata attached to the response. Support can vary by selected model and provider.
Optional Responses API tools. Support can vary by selected model and provider.
Tool selection strategy. Support can vary by selected model and provider.
auto, none