OpenAI introduces cheaper background completion windows in the Responses API
OpenAI has introduced background completion windows in the Responses API in public beta: the two-hour window is 30% cheaper and the eight-hour window is 40% cheaper than the standard tariff, in exchange for higher response latency.
OpenAI has introduced a new option in the Responses API called background completion windows, available in public beta. Developers can choose between a two-hour and an eight-hour window for processing a request, with the company stating that the token rates for the model are lower than the standard Standard tariff — by 30% for the two-hour window and by 40% for the eight-hour window.
The feature is available for the gpt-6.2-astra, gpt-6.2-sol, gpt-6.1-terra, and gpt-6-luna models via the v1/responses interface. The lower price comes in exchange for higher response latency, meaning it is intended for tasks where an immediate reaction is not necessary.
Why it matters
For developers and companies that process batch or non-interactive tasks via the API (e.g., analyses, content generation without the need for an immediate reply), this is a direct way to reduce token costs by tens of percent in exchange for tolerating a longer response time on the order of hours.
Two audiences, two different impacts
What this means
For individuals
Developers working with the Responses API get a cheaper option for batch or non-interactive tasks, but must expect a response time on the order of hours instead of an immediate reply.
For a business
Companies that process large-volume or non-urgent requests via the Responses API can reduce token costs by 30% (two-hour window) or 40% (eight-hour window) compared to the standard rate, if they accept a longer response time.
DevelopmentCheck the original
Event sources
clearly official source · 1 publisher, 0 independent. We count feeds from the same owner only once.