The following prompt pops up frequently, making the subscription almost unusable.Selected model is at capacity. Please try a different model.
Open 💬 10 comments Opened Aug 10, 2026 by NAXXcode
What version of the Codex App are you using (From “About Codex” dialog)?
latest
What subscription do you have?
pro20x
What platform is your computer?
win11
What issue are you seeing?
The following prompt pops up frequently, making the subscription almost unusable.Selected model is at capacity. Please try a different model.
I tried switching the model but it didn't work.
What steps can reproduce the bug?
I have been getting this prompt constantly in my conversations over the past hour, and I can't use it properly at all.
What is the expected behavior?
codex should be working
Additional information
No response
10 Comments
Same issue for me (Pro 20x).
+1 pro 20x
我使用 5.6 sol fast会被限流。 把fast关了就可以了
Same issue for me (Pro 20x)，It is not possible to succeed using any of the 5.6 models.
yep,My 5.6 models is also unavailable, while 5.4 and 5.5 are functional.
Me too，I hope OpenAI fixes this immediately; it significantly impacts the user experience.
Same issue here. It's completely unusable right now – it breaks after just a few sentences.
Sol and Terra are both affected. Switching models does not resolve the issue.
same here, especially for terra and luna :(
Title:
Codex repeatedly reports "Selected model is at capacity"
during approximately 04:30–05:50 ICT (UTC+7)
Environment:
Issue:
I repeatedly encounter:
"Selected model is at capacity.
Please try a different model."
This appears to happen repeatedly around 04:30–05:50
Vietnam time (ICT / UTC+7).
Outside this period, the same model normally works.
The error can occur while an existing session is actively
working and I still have remaining usage/quota.
Frequency:
[example: 4 out of 5 days]
Expected:
The selected model should remain available, or Codex should
automatically retry/fail over when temporary model capacity
is unavailable.
Actual:
The request fails with "Selected model is at capacity."