Every startup gives "Approaching rate limits", actually limits are ways off
Resolved 💬 3 comments Opened Nov 21, 2025 by il13h Closed Dec 3, 2025
💡 Likely answer: A maintainer (github-actions[bot], contributor)
responded on this thread — see the highlighted reply below.
What version of Codex is running?
codex-cli 0.63.0
What subscription do you have?
Plus
Which model were you using?
gpt-5.1-codex-max
What platform is your computer?
Linux 6.6.87.2-microsoft-standard-WSL2 x86_64 unknown
What issue are you seeing?
Every time I start Codex with "codex resume", it gives me the "Approaching rate limits" prompt and suggests I change to mini model. This happens regardless how many tokens I have available in my plan. I just choose to continue with current model and everything then works fine. Surely something is just gone askew in my installation but I don't know how to find out what. Problem happened also on previous versions, I believe it started 1-2 weeks ago.
What steps can reproduce the bug?
- Run "codex resume" to start Codex in my environment
- Get the unnecessary prompt
What is the expected behavior?
Expected behavior is not to get the prompt suggesting model change, since it is not correct in my situation.
Additional information
_No response_
3 Comments
Potential duplicates detected. Please review them and close your issue if it is a duplicate.
Powered by Codex Action
Put this in your config.toml:
Thanks for reporting. I'm going to close this issue in favor of #7354, which is the same underlying problem.