Codex is literally unusable, i always got prompt_cache_retention is not supported on this model
Open 💬 1 comment Opened Aug 19, 2026 by rasyidrafi
💡 Likely answer: A maintainer (github-actions[bot], contributor)
responded on this thread — see the highlighted reply below.
What issue are you seeing?
Always got this everytime sending message,
Error: OpenAI API error (400): {"message":"prompt_cache_retention is not supported on this
model","type":"invalid_request_error","param":"prompt_cache_retention","code":"invalid_parameter"}
Using pi harness with chatgpt subs, using gpt-5.6-luna max
it just start happening today, yesterday seems fine
What steps can reproduce the bug?
use codex like normal, this happen whenever use codex or pi
What is the expected behavior?
should continue to work without throwing those errors
Additional information
_No response_
1 Comment
Potential duplicates detected. Please review them and close your issue if it is a duplicate.
Powered by Codex Action