OpenAI API supports 12-hour prompt caching; caches are retained long-term for logged-in Codex and Work users
The OpenAI developer account announced that the API can now opt into 12-hour prompt caching, so shared instructions, tools, and context can stay cached longer, and even when requests are hours apart they are billed at the lower cached-input rate. Tibo added that for logged-in Codex and Work users, caches are retained indefinitely, so returning to an old conversation or continuing hours later incurs no extra cost and cache hits are guaranteed.
Why read this
AI score 52
The original text explains that API prompt caching is extended to 12 hours and sets out the difference in cache retention for logged-in Codex and Work users, to help assess cost changes for long-running agents.
Topics
View original postYou 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.
View original
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.
Body
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.