Repository navigation
Selected model is at capacity. Please try a different model Please take this seriously and provide a clear solution. #46079
Description
What version of the Codex App are you using (From “About Codex” dialog)?
26.908.70816
What subscription do you have?
pro20x
What platform is your computer?
macos Darwin 25.6.0 arm64 arm
What issue are you seeing?
It happens every time on my account. "Selected model is at capacity. Please try a different model." i changed every model ,it show the same issue. Feedback ID:01a0aa1e-ac3f-7711-b510-cca09d99847f
What steps can reproduce the bug?
Feedback ID:01a0aa1e-ac3f-7711-b510-cca09d99847f
What is the expected behavior?
Feedback ID:01a0aa1e-ac3f-7711-b510-cca09d99847f
Additional information
I've been using GPT for a long time, and only recently started noticing what feels like a real drop in quality or intelligence.
I've always trusted you guys to provide the level of service and quality users should be able to expect. I also genuinely believe that better
collaboration between people and Al can help us do better work and, in some small way, make the world a better place.
So, if there's any chance you can press the 'back to normal effort/model' button on your side, I'd be incredibly grateful."
Activity
github-actions commentedon Sep 17, 2026
Potential duplicates detected. Please review them and close your issue if it is a duplicate.
Powered by Codex Action
GaryLBQ commentedon Sep 17, 2026
Too many days! Fuck!
austindtranz-cloud commentedon Sep 17, 2026
I am also encountering the “Selected model is at capacity. Please try a different model.” error in ChatGPT Work/Codex on Windows. My main subscription is Pro 20x, and I also pay for a second Pro subscription to maintain continuity on client projects.
These interruptions are affecting real development work and contractual deadlines. I want to continue using OpenAI, but it is becoming difficult to plan work around access that I cannot reliably depend on.
I am reporting the same visible error, not claiming that I have reproduced the original author's exact environment, failure frequency or underlying cause. In particular, I cannot establish from my current evidence whether my capacity failures occurred while quota was still available or whether they share a cause with my separate usage problem.
I have documented the early exhaustion of my weekly allowance separately in #41220 (comment) and have an ongoing Support case with screenshots and a detailed follow-up. That is my own related report, not an additional independent user.
Please investigate the affected accounts and clarify what this error represents, rather than leaving users to guess whether it is service capacity, quota or another access problem. If failed or retried work consumed allowance incorrectly, please restore it. I would also appreciate consideration of a temporary weekly reset or goodwill allowance while the problems are investigated. I understand that a quota reset alone would not necessarily fix a capacity error.
Account identifiers and supporting evidence can be shared privately through Support.
ccccmmmz commentedon Sep 17, 2026
Please expedite this—it has already been three days. Is there no anomaly monitoring? As paying subscribers, are our experiences simply being ignored?
lixiang4543 commentedon Sep 17, 2026
Selected model is at capacity. Please try a different model.
The reason is that after switching to the GPT6 model, this error occurred, causing all models to become unavailable. Before this switch, everything was working fine.I suspect that they have planted spies in the GPT6 model.