Selected model is at capacity. Please try a different model.
Resolved 💬 5 comments Opened Apr 25, 2026 by smileBeda Closed Apr 25, 2026
💡 Likely answer: A maintainer (github-actions[bot], contributor)
responded on this thread — see the highlighted reply below.
What version of Codex CLI is running?
0.125.0
What subscription do you have?
PLUS PRO
Which model were you using?
5.5
What platform is your computer?
macOS
What terminal emulator and version are you using (if applicable)?
terminal, tmux
What issue are you seeing?
Many users are getting Selected model is at capacity. Please try a different model. and similar results.
We are pro users with priority access.
What steps can reproduce the bug?
Uploaded thread: 019dc564-1e9c-74f0-821b-7f047b0cf4ee
What is the expected behavior?
No interruptions.
Reset wen?
Additional information
Thanks.
5 Comments
Potential duplicates detected. Please review them and close your issue if it is a duplicate.
Powered by Codex Action
OK yes, https://github.com/openai/codex/issues/19446 is a duplicate.
me too
<img width="1004" height="564" alt="Image" src="https://github.com/user-attachments/assets/a21fd4af-bc26-41b0-bfad-566102f56145" />
<img width="394" height="367" alt="Image" src="https://github.com/user-attachments/assets/57960a66-20c0-488e-bb36-9442de52e90d" />
Seeing the same issue on Codex CLI with
gpt-5.5.gpt-5.5Selected model is at capacity. Please try a different model.minutes ago
gpt-5.4allowed the session to continueThis appears to be an active capacity problem rather than an isolated local issue.
Adding a fresh report with one more symptom here: https://github.com/openai/codex/issues/27149
In our case, after switching models to recover from the capacity error, the session often comes back showing only around 60-70% context left.