Ability to set prompt_cache_retention
Resolved 💬 2 comments Opened Nov 15, 2025 by EmpowerZ Closed Jan 14, 2026
💡 Likely answer: A maintainer (etraut-openai, contributor)
responded on this thread — see the highlighted reply below.
What feature would you like to see?
GPT-5.1 models (including gpt-5.1-codex) support extended retention by setting prompt_cache_retention: "24h". Otherwise the cache is short-lived. From what I see there is no way to set this parameter in codex.
Additional information
_No response_
2 Comments
This feature request hasn't seen many upvotes or activity in a couple of months, so I'm going to close it.
Less important now that there's only one option moving forward:
<img width="893" height="237" alt="Image" src="https://github.com/user-attachments/assets/9db23389-6c3d-4301-a6db-57f184b76739" />