API adds 12-hour prompt caching; logged-in Codex and Work users can keep reusing conversation cachesMachine translation

Automatically verified and published · Generated and evidence-checked automatically; not reviewed by a human.

AI introduction

API users can now choose 12-hour prompt caching, allowing requests hours apart to use the lower cached-input rate. The post also says caches are kept indefinitely for logged-in Codex and Work users, with a guaranteed cache hit when they return to an old conversation.

Original post · Original

The article text is unavailable in this language; an existing version is shown.

Tibo@thsottiaux

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.

QuoteOpenAI Developers@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.

View this post on X ↗

09:10 · 2026-10-21 · UTC+8

Found an error? Send a correction