Background completion windows
OpenAI added two-hour and eight-hour background completion windows to the Responses API in public beta, with token rates 30% and 40% below Standard.
Developers can now choose a two-hour or eight-hour window for background requests in the Responses API. Model token rates are 30% lower than Standard for the two-hour window and 40% lower for the eight-hour window. The changelog lists gpt-6.2-astra, gpt-6.2-sol, gpt-6.1-terra and gpt-6-luna as supported.
- Date
- Tuesday 17 November 2026
- Lab
- OpenAI
- Kind
- feature
- Access
- closed API
- Price
- 30% lower than Standard (two-hour), 40% lower than Standard (eight-hour)
Figures
| Measure | Value | Measured by |
|---|---|---|
| Discount vs Standard, two-hour window | 30% model token rates | company |
| Discount vs Standard, eight-hour window | 40% model token rates | company |
The feature is in public beta. Details are in OpenAI's background mode guide.
Sources
This record was checked against its sources on 17 November 2026. How we check