You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Selected model is at capacity. Please try a different model. #46172
What version of the Codex App are you using (From “About Codex” dialog)?
latest version
What subscription do you have?
chatgpt plus
What platform is your computer?
windows 11
What issue are you seeing?
I am currently using the desktop application CodeX. I have tried every model and also tested the page, but the error persists; yet the problem remains the same. I have also tried restarting or logging in again, but the issue persists. No matter how I change the model or restart and log in, the same error keeps occurring. Even using my reset card didn't work. This has seriously affected my usage. As a paying user, I shouldn't have to endure such an experience.
What steps can reproduce the bug?
After starting Codex in Windows, simply selecting a model to create a conversation will result in this response. This phenomenon began this afternoon.
I would like to know how long it will take to fix this problem. I can provide relevant information to assist in the investigation of this damn issue.🤯🤯🤯
Just now, I suddenly got better and my response speed increased as well. This left me unsure whether it was temporary or had been fixed; but my token was quickly depleted, yet I did nothing.
Just now, I suddenly got better and my response speed increased as well. This left me unsure whether it was temporary or had been fixed; but my token was quickly depleted, yet I did nothing.
OK, I've confirmed it. This is just a temporary solution. I really have no idea when this damn problem will be resolved.
I am a Plus subscription user. Why do I keep getting the prompt "The selected model is at capacity. Please try a different model"? I learned from X that this is a risk control measure, but my job requirements force me to use a VPN and may cause my IP to change back and forth; but I am a Plus member, and this shouldn't happen to me.
@tibo-openai Damn Tibo, what on earth is he up to? This problem has persisted for a long time and still hasn't been resolved? It is still happening continuously.
@tibo-openai Damn Tibo, what on earth is he up to? This problem has persisted for a long time and still hasn't been resolved? It is still happening continuously.
Is not the server load, is all about shadow banning and specting that people do nothing, I redunded this scam @tibo-openai
Paying since o1 and got shadow banned, my co worker account works just fine both on x20 plan.
Since I submitted this issue, I spent approximately two weeks dealing with it. The problem occurred indirectly during the second week. After that, I was back to normal. This might be a wrong judgment in risk control. I submit such feedback every time this issue occurs through the Codex. During the feedback process, all types have been selected. I'm going to close this issue.
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
Banishglory commentedon Sep 17, 2026
I would like to know how long it will take to fix this problem. I can provide relevant information to assist in the investigation of this damn issue.🤯🤯🤯
emvia commentedon Sep 17, 2026
same here. all models keeps showing : Selected model is at capacity. Please try a different model.
Banishglory commentedon Sep 17, 2026
I don't know what the authorities are doing? When I came to raise the issue today, I found that there were already so many issues.
lengmouling commentedon Sep 17, 2026
我也遇到同样的问题,今天一天都无法进行开发工作
Banishglory commentedon Sep 17, 2026
那就好好休养吧
lengmouling commentedon Sep 17, 2026
Banishglory commentedon Sep 17, 2026
Just now, I suddenly got better and my response speed increased as well. This left me unsure whether it was temporary or had been fixed; but my token was quickly depleted, yet I did nothing.
Banishglory commentedon Sep 17, 2026
OK, I've confirmed it. This is just a temporary solution. I really have no idea when this damn problem will be resolved.
lixiang4543 commentedon Sep 17, 2026
Selected model is at capacity. Please try a different model.
Banishglory commentedon Sep 17, 2026
I am a Plus subscription user. Why do I keep getting the prompt "The selected model is at capacity. Please try a different model"? I learned from X that this is a risk control measure, but my job requirements force me to use a VPN and may cause my IP to change back and forth; but I am a Plus member, and this shouldn't happen to me.
Banishglory commentedon Sep 17, 2026
@jif-oai @codex
xionghaizhi commentedon Sep 21, 2026
Banishglory commentedon Sep 21, 2026
@tibo-openai It has been going on from September 17th until today. What are you doing?Should we just ignore so many feedback issues?
carlfm01 commentedon Sep 22, 2026
Terra, Sol and Astra all down, any solution?
Imacx-maria commentedon Sep 22, 2026
Same problem here. Its completly unsusable for the past 3 days. Either with Sol or Astra. Happens frequently
Banishglory commentedon Sep 24, 2026
@tibo-openai Damn Tibo, what on earth is he up to? This problem has persisted for a long time and still hasn't been resolved? It is still happening continuously.
carlfm01 commentedon Sep 24, 2026
Is not the server load, is all about shadow banning and specting that people do nothing, I redunded this scam @tibo-openai
Paying since o1 and got shadow banned, my co worker account works just fine both on x20 plan.
carlfm01 commentedon Sep 24, 2026
qiuyang1995 commentedon Sep 27, 2026
Banishglory commentedon Oct 13, 2026
Since I submitted this issue, I spent approximately two weeks dealing with it. The problem occurred indirectly during the second week. After that, I was back to normal. This might be a wrong judgment in risk control. I submit such feedback every time this issue occurs through the Codex. During the feedback process, all types have been selected. I'm going to close this issue.