Repository navigation
Selected model is at capacity. Please try a different model #46980
Description
What version of the Codex App are you using (From “About Codex” dialog)?
26.915.4065.0
What subscription do you have?
ChatGPT $200 Pro (20x)
What platform is your computer?
Microsoft Windows NT 10.0.26200.0 x64
What issue are you seeing?
For the last 30hrs I have been continuously getting this error 'Selected model is at capacity. Please try a different model' while using any model Astra or Luna for example) and when the Astra is working, it is completely degraded and requires babysitting and continuous correcting. And because of all of this it has wasted 35% of my weekly usage as when it does work it is wasting tokens on redoing work and on context etc. This is completely unacceptable product / service for what I pay for the subscription. Please finally fix this and provide some banked resets as compensation.
What steps can reproduce the bug?
Feedback ID: 01a0c1ea-017d-79f3-b133-1008d144c9d2
What is the expected behavior?
That Astra works as it has been designed to
Additional information
No response
Activity
github-actions commentedon Sep 21, 2026
Potential duplicates detected. Please review them and close your issue if it is a duplicate.
Powered by Codex Action
igortadicbre commentedon Sep 21, 2026
Same problem! igtcoder@gmail.com x20 Pro.
zmny11ezmqc9n commentedon Sep 21, 2026
Same problem!
Banishglory commentedon Sep 22, 2026
same problem！🤯🤯🤯🤯🤯🤯🤯🤯🤯🤯🤯🤯🤯🤯🤯🤯🤯🤯🤯🤯🤯
What the hell is the point of paying for Plus if you're just going to tell me to 'switch models' every single day? Fix your shit, OpenAI. This is a joke.
Difficulty-in-naming commentedon Sep 22, 2026
Same problem!
yangchaoNJ commentedon Sep 23, 2026
Same problem! Pro 20x.
qiuyang1995 commentedon Sep 26, 2026
Same problem! Pro 20x.
HaoTechGuy commentedon Sep 29, 2026
Selected model is at capacity. Please try a different model.
Same problem! Pro 20x. zhanhao.leo@foxmail.com
pietertal commentedon Oct 5, 2026
■ Selected model is at capacity. Please try a different model. GPT6 Luna medium. Plus
Im4lish commentedon Oct 8, 2026
same problem on 20X
MUKEKANN commentedon Oct 12, 2026
Same problem!
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.
shupiange commentedon Oct 21, 2026
same problem 1460249683@qq.com