Source: Background mode (OpenAI guide)

OpenAI's guide to running long Responses API calls asynchronously with background: true, polling, cancellation and resumable streaming.

Contents
  • What: official API documentation page
  • Publisher: OpenAI
  • Date: living document; read 2026-11-14
  • Original: Background mode

Summary

How to start long-running reasoning or agentic responses without holding a connection open, then poll, cancel or resume streaming.

Key claims

  • background: true runs the response asynchronously; poll GET while status is queued or in_progress; other statuses are terminal.
  • POST /responses/{id}/cancel stops it and is idempotent.
  • With background and stream both true, track each event’s sequence_number; after a drop, resume with stream=true and starting_after.
  • Time to first token is higher than for synchronous calls.
  • Background mode stores response data temporarily even with store=false; for ZDR projects it is kept for about 10 minutes.

Feeds

OpenAI Responses API

Suggest changes →