Create response (OpenAI Responses API)
Creates a response using OpenAI Responses API format. Supports streaming via SSE.
Async inference: Send x-bf-async: true to submit the request as a background job and receive a job ID immediately. Poll with x-bf-async-id: <job-id> to retrieve the result. When the job is still processing, the response status will not be completed. When completed, the full response with output_text will be returned. See Async Inference for details.
Note: This endpoint also works without the /v1 prefix (e.g., /openai/responses).
Headers
Set to true to submit this request as an async job. Returns immediately with a job ID. Not compatible with streaming.
Poll for results of a previously submitted async job by providing the job ID returned from the initial async request.
Override the default result TTL in seconds. Results expire after this duration from completion time.
Request body
Example request
{
"model": "gpt-4"
}Response
Successful response