What happened
OpenAI Developers says setting `completion_window` to `2h` costs 30% less per token than Standard, while `8h` costs 40% less. It also advises setting a continuation ID when sending notes and reusing it in follow-up requests to get higher queue priority. The post links to the Background API guide.
Why it matters
Using a continuation ID on follow-up requests raises their queue priority, while choosing a longer completion window lowers the per-token price compared with Standard.
Set “completion_window” to “2h” for 30% less per token than Standard, or “8h” for 40% less.
Set a continuation ID when you send the notes and reuse it on follow-up requests to give them higher queue priority.
2 reports
The story so far
OpenAI Developers introduced completion_window settings for their Background API, allowing users to reduce costs by scheduling response times. Users can set the completion_window parameter to "2h" for 30% less per token than Standard pricing, or "8h" to save 40% per token. These settings provide the API an extended window to process inputs, such as generating a morning brief from meeting notes submitted the previous evening. Additionally, OpenAI Developers advises users to include a "continuation ID" when submitting initial notes and to reuse that same identifier on subsequent follow-up requests to receive higher queue priority.
