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
OpenAI ships an official CLI for its REST API
Three shells, Bash, zsh and fish, get image picker Tab shortcuts saved quietly the first time you run OpenAI’s official CLI for its API. The README points to an opt-out. Has a CLI ever edited your shell setup without asking you first?
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
- 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
- Jev answers in 195 ms, OpenAI Decisions in 208 ms
Comments
No comments yet. Be the first.
Join the conversation
Sign in to leave a comment. It appears after moderation.