Here’s one example: send your meeting notes before you log off and ask for a morning brief.
Set "completion_window" to "8h" to give the API an eight-hour window for the first response.
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.
How the story developed · 2
View full event- 11/19 07:39 (UTC+8)
Here’s one example: send your meeting notes before you log off and ask for a morning brief. Set "completion_window" to "8h" to give the API an eight-hour window for the first response. This report
- 11/19 07:39 (UTC+8)OpenAI Shares Background API Settings for Lower Per-Token PricesOpenAI Developers · X
