Peaked at #1 Now #1
OpenAI launches 12-hour prompt caching
OpenAI launches 12-hour prompt caching in its API; logged-in Codex and Work users keep caches forever with no penalty.
Key points
- OpenAI now offers 12-hour prompt caching in the API, and the 30-minute default can be kept or mixed with 12h in one request, with 12h for shared instructions and 30 minutes for newer conversation content.
- For logged-in users across Codex & Work, cache is kept forever with no penalty for returning to an old conversation or resuming after a few hours, and hitting the cache is guaranteed.
Key points and the reaction summary are written by AI from the posts on this page. Check the original post. How we use AI
Original post
Day 16/
You can now cache for 12h in the API and for logged in users across Codex & Work we keep cache forever and you don’t have any penalty for coming back to an old conversation or resuming after a few hours and are now guaranteed to hit the cache.Quoting @OpenAIDevs: You can now choose 12-hour prompt caching in the API.
Persistent agents, like dots, reuse context throughout the day.
You can keep shared instructions, tools, and context cached longer and pay the lower cached-input rate, even when requests are hours apart.
What others are saying
2 more-
Theo - t3.gg @theo 2,065
Theo shares that API caching lasts 12h while logged-in Codex and Work users keep cache forever with no penalty, calling it the biggest ship in 28 days.
View on X -
OpenAI Devs announced 12-hour prompt caching in the API, letting persistent agents reuse context at cached-input rates.
View on X
Top replies on X
Sign in to see 1 top replies from X
From @OpenAIDevs and others. Spam removed, with English and Chinese translations.
Discussion 0
Sign up Sign in to join the discussion
No comments yet. Start the conversation.