OpenAI Rolls Out Background Mode: Long Tasks Can Run for 8 Hours, Tokens Up to 40% Cheaper
Nov 20, 19:32
November 20 — According to OpenAI's developer documentation, OpenAI has added a "completion window" option to the Responses API background mode. When the 2h or 8h window is selected, the model's token rate is 30% and 40% lower than Standard respectively; the default soonest window offers no discount. The feature is currently in public beta on GPT-6.2 Astra, GPT-6.2 Sol, GPT-6.1 Terra and GPT-6 Luna. The documentation also discloses that, starting with GPT-6.2 Astra and Sol, new models no longer offer Flex processing. The discounted windows require Standard processing, do not support streaming output, and share rate limits with the Batch API. Subsequent requests that use the same continuation_id receive a higher queue priority.