Create Model Response (Control Reasoning Effort)

POST

/v1/responses

• Control reasoning length for reasoning models via reasoning.effort (minimal / low / medium / high)
• Compatible with the OpenAI Responses API create response endpoint
• Some models (e.g. o3-pro, codex-mini-latest) only support the Response format
• Official docs: Create a model response

Authorizations

bearer

Type

HTTP (bearer)

Request Body

application/json

object

ID of the model to use. See the model endpoint compatibility table for which models work with the Responses API.

object[]

Required

Text, image, and other inputs for the model to generate a response.

object

Description of the chain-of-thought the reasoning model uses when generating a reply.