Repository navigation
Multiple GPT-5 / GPT-6 models return "Selected model is at capacity" #43375
Description
Description
Codex repeatedly returns the following error across multiple models:
Selected model is at capacity. Please try a different model.
This does not appear to be limited to a single model. I observed the issue when switching between multiple GPT-5 and GPT-6 models, including GPT-6 Astra and GPT-5.6 variants.
Actual behavior
Requests fail with:
Selected model is at capacity. Please try a different model.
Switching between available GPT-5 / GPT-6 models often results in the same error.
Retrying does not reliably recover the request.
Expected behavior
If one model is temporarily unavailable, Codex should route the request to another available backend or provide more detailed information about the failure source.
It would be helpful to distinguish between:
- individual model capacity
- account-level throttling
- regional capacity
- backend serving/routing failures
Reproduction
- Open Codex.
- Select GPT-6 Astra or GPT-5.6.
- Submit a normal coding task.
- Receive
Selected model is at capacity. - Switch to another GPT-5/GPT-6 model.
- The same error can occur again.
Additional information
The problem affects multiple models at the same time, suggesting this may be related to Codex backend capacity or request routing rather than one specific model being unavailable.
A request ID or more detailed diagnostic information in the UI would help users report these incidents.
Date observed
2026-09-07
Activity
github-actions commentedon Sep 7, 2026
Potential duplicates detected. Please review them and close your issue if it is a duplicate.
Powered by Codex Action
zjie0723 commentedon Sep 7, 2026
mark.
MMortise commentedon Sep 7, 2026
菲区？
LiangDazhu commentedon Sep 7, 2026
Singapore
zjie0723 commentedon Sep 7, 2026
MMortise commentedon Sep 7, 2026
zjie0723 commentedon Sep 7, 2026
LiangDazhu commentedon Sep 7, 2026
查了一圈下来。 只有部分用户有这个问题。。。。看上去不是平台算力问题， 就是针对账号进行了区别控制
MMortise commentedon Sep 7, 2026
就是被标记了，MEXC？
zjie0723 commentedon Sep 7, 2026
meowameowameow commentedon Sep 7, 2026
Same problem
medetasi commentedon Sep 7, 2026
Same problem
BadrikKWORK commentedon Sep 8, 2026
Тоже самое и как решать это?
опен аи вообще в курсе?
3 remaining items
duyleekun commentedon Sep 10, 2026
tarik02 commentedon Sep 10, 2026
82962bc9-24b3-4ad3-b497-5d209b8bd554
xwchris commentedon Sep 10, 2026
+1
bkrescaperaseuse commentedon Sep 10, 2026
Same. Codex is unusable atm
cooltzy commentedon Sep 11, 2026
same
TensorDog commentedon Sep 14, 2026
same
felix-xqs commentedon Sep 15, 2026
same
hao0oah commentedon Sep 15, 2026
same problem
Jeazun commentedon Sep 15, 2026
same problem
TJKkking commentedon Sep 16, 2026
SAME
maksymilan commentedon Sep 16, 2026
Q14 commentedon Sep 18, 2026
away0730 commentedon Oct 12, 2026
Still down as of October 12, 2026 — GPT-6 Astra and GPT-6.1 Sol both unusable
Adding another data point to this thread. As of today (October 12, 2026), I am still experiencing the same capacity errors described in the original report.
Both GPT-6 Astra and the newer GPT-6.1 Sol are affected for me. I keep hitting “Selected model is at capacity” across the CLI and the web version. Switching between models doesn’t help — the error follows regardless of which one I pick, which matches what others have already noted in this thread.
It’s been over a month since the original reports on Sep 8, and the issue appears to be ongoing. Is there any official update on when this will be resolved?
a18711010997 commentedon Oct 12, 2026
一样的情况
ppy-web commentedon Oct 12, 2026
same problem 😭😭😭