Selected model is at capacity. Please try a different model.
What version of the Codex App are you using (From “About Codex” dialog)?
Version 26.623.61825
What subscription do you have?
Plus
What platform is your computer?
Darwin 25.6.0 arm64 arm
What issue are you seeing?
The 5.5 High model cannot be used because every task immediately fails with the following error:
"Selected model is at capacity. Please try a different model."
The issue has persisted for about one hour.
I have already restarted the Codex app, but the problem remains.
Expected behavior:
The task should either start normally, be queued until capacity is available, or automatically fall back to another compatible model.
Actual behavior:
The task fails immediately and cannot be started using the 5.5 High model.
What steps can reproduce the bug?
- Open the Codex app.
- Select the 5.5 High model.
- Start any task (the prompt does not matter).
- The task immediately fails with the message:
"Selected model is at capacity. Please try a different model."
The issue has persisted for about one hour and still occurs after restarting the Codex app.
What is the expected behavior?
The selected model should accept the task and start processing it normally.
If the model is temporarily at capacity, the app should queue the request, clearly indicate that capacity is temporarily unavailable, or automatically offer a compatible fallback model instead of immediately failing.
Additional information
The issue started while my weekly usage was approximately:
- Session usage: 5h
- Weekly usage: 45%
- Overall weekly limit: 75%
The error appeared even though I had not reached my usage limit. Restarting the Codex app did not resolve the issue.
8 Comments
Potential duplicates detected. Please review them and close your issue if it is a duplicate.
Powered by Codex Action
same here， it's too bad
same here 😬
same here... keep trying continue...
same problem
ja, same here...
same problem
I would like to add one more observation that may or may not be related.
Since yesterday, I have noticed what appears to be unusually fast Codex usage depletion, although I do not have objective measurements to confirm it.
I also saw the recent OpenAI status update stating:
“We have identified that some reports of Codex usage limits depleting faster than expected are related to our abuse and fraud prevention systems incorrectly rate limiting certain accounts.”
I cannot confirm that my account is affected by the same issue, but the timing seems to coincide with when I started experiencing both the capacity errors and the apparent increase in usage consumption.
I hope this additional context may help with the investigation.