OpenAI keeps Codex cache forever, API cache gets 12 hours

Resuming an old conversation after a few hours carries no penalty for logged-in Codex and Work users, OpenAI said on Day 16 of its 28-day Codex sprint. It keeps their cache forever, and they’re guaranteed to hit it.
API developers get a 12-hour cache. Caching stores the already processed part of a prompt, so a repeated system prompt or document doesn’t get processed again from scratch.
The change builds on OpenAI’s September 22 caching update for GPT-6, which cut cached input token costs by up to 90%.
Up next
Claude’s auto mode skips connector “Always ask” settings
Claude’s auto mode read a user’s Fastmail inbox through a connector set to “Always ask for permission,” and Anthropic called it expected behavior. Would you keep an email connector on in auto mode, or remove it?
Related stories
- GPT-6 caching update cuts cached input costs by up to 90%
- OpenAI says its Codex app should eat 60% less disk space
- OpenAI’s Decisions API exits beta at 400 questions a call
- Your ChatGPT Plus plan can now pay for other apps’ AI
- Code strings point to a $50 production plan for OpenAI’s API
- Token costs drop out of Replit’s new Free Mode
Comments
No comments yet. Be the first.
Join the conversation
Sign in to leave a comment. It appears after moderation.

