Skip to main content

News · AI

OpenAI adds two-hour and eight-hour background completion windows to Responses API

OpenAI gave developers using the Responses API a choice of two-hour or eight-hour background completion windows on Nov 17, 2026; the eight-hour window has a 40% lower token rate.

1 min read Source: developers.openai.com

What changed: OpenAI added a two-hour and an eight-hour background completion window option to the Responses API public beta. Model token rates are 30% lower than Standard for the two-hour window and 40% lower for the eight-hour window.

Who is affected

The source says this applies to OpenAI API customers using the background completion feature of the Responses API; no specific industry or country limitation is stated.

What it means for your business

For businesses using the OpenAI API, this means choosing the eight-hour window for long-running background requests gets a lower token rate.

What to do

If you use background completion in the Responses API, pick the window length (two or eight hours) that fits your workflow and compare the token rate difference.

When it takes effect

The source gives no separate effective date; the feature was announced and made available in the Responses API public beta on November 17, 2026.

Source: https://developers.openai.com/api/docs/changelog#2026-11-17

Related reading

First conversation

Tell us what you want to do, and we will work out together where to start.

In the first call we talk through your business, where things stand and what matters most. We say plainly which parts make sense for us to take on and which you should run yourself.

Cookie preferences

We use measurement and advertising tools (Google Analytics, Microsoft Clarity, Google Ads, Meta Pixel) to improve the site and measure the results of our ads, only with your consent. Necessary records are always on. Details in our cookie policy.