[Pro][Windows] Multiple Codex models repeatedly fail with "Selected model is at capacity" / server_overloaded #45376

Activity

1. github-actions

   added

   bugSomething isn't workingSomething isn't working

   windows-osIssues related to Codex on Windows systemsIssues related to Codex on Windows systems

   rate-limitsIssues related to rate limits, quotas, and token usage reportingIssues related to rate limits, quotas, and token usage reporting

   on Sep 14, 2026
2. github-actions commented on Sep 14, 2026

   

   github-actionsbot

   on Sep 14, 2026 – with GitHub Actions

   Contributor

   More actions

   Potential duplicates detected. Please review them and close your issue if it is a duplicate.

   • [Windows][Codex Desktop][Pro] All models fail with "Selected model is at capacity" (server_overloaded) #44516
   • I have 100% quota available but cannot use the AI. This issue has persisted for a whole week. Every time I attempt to use it, I get the message: Selected model is at capacity. Please try a different model. #45368
   • Selected model is at capacity. Please try a different model. #44541
   • Repeated ⚠ Selected model is at capacity. Please try a different model. #44497
   • [Bug] Intermittent "Selected model is at capacity" errors in Codex Desktop (all models) on ChatGPT Pro #44531

   Powered by Codex Action
3. xini444915666-ctrl commented on Sep 29, 2026

   

   xini444915666-ctrl

   on Sep 29, 2026

   More actions

   I am experiencing the same issue on Windows with a ChatGPT Pro 20x subscription.

   The problem started around Sep 22, 2026 and is still occurring on Sep 29.

   The error is:

   Selected model is at capacity. Please try a different model.

   In my recent use it occurs on virtually every Codex task, often multiple times during the same task.

   I extracted 60 distinct affected turns from local Codex session logs across 12 source log files. All 60 records contain:

   codex_error_info: server_overloaded

   Local selected_model values in those records:

   • gpt-6-astra: 46
   • gpt-5.6-sol: 5
   • gpt-6-sol: 1
   • unknown: 8

   I submitted an affected session through Codex /feedback with diagnostic logs included.

   Feedback ID:
   01a0eb8b-243f-7bd1-83d4-1a8de7299c2b

   OpenAI Help Center repeatedly returns the Model/Feature Access limitation template and immediately closes the support case, so I have not been able to obtain an individual technical review.

   Please correlate this Feedback ID with server-side diagnostics if possible.