⚠ Selected model is at capacity. Please try a different model. #44478

Activity

1. LimyTax

   added

   appIssues related to the Codex desktop appIssues related to the Codex desktop app

   on Sep 10, 2026
2. 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 10, 2026
3. github-actions commented on Sep 10, 2026

   

   github-actionsBot

   on Sep 10, 2026 – with GitHub Actions

   Contributor

   More actions

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

   • Selected model is at capacity. Please try a different model. #43322
   • 20x pro: Selected model is at capacity. Please try a different model. #44396
   • Selected model is at capacity. Please try a different model. #44395
   • Codex Desktop completely unusable for one week - all models show "Selected model is at capacity" on Pro 20x plan #43752
   • "I keep getting the 'model at capacity' error. I've tried switching to different models but they're all full. Is the service actually working? This is extremely frustrating and the user experience is very poor #43455

   Powered by Codex Action
4. tarik02 commented on Sep 10, 2026

   

   tarik02

   on Sep 10, 2026

   More actions

   82962bc9-24b3-4ad3-b497-5d209b8bd554
5. fzd461894954-sketch commented on Sep 10, 2026

   

   fzd461894954-sketch

   on Sep 10, 2026 – with ChatGPT Codex Connector

   More actions

   I can reproduce this on ChatGPT Pro with Codex CLI 0.153.4.

   On 2026-09-10 (Asia/Shanghai), GPT-6 Astra/Ultra, GPT-5.6 Terra (xhigh), Luna (low), and Sol (low) all returned:
   “Selected model is at capacity. Please try a different model.”

   Local records show at least 41 server_overloaded failures from 09:35 to 12:52. Codex usage was 0%, with no rate-limit or spend-cap trigger. OpenAI Help Center support has escalated my case to a human agent.
6. fzd461894954-sketch commented on Sep 10, 2026

   

   fzd461894954-sketch

   on Sep 10, 2026 – with ChatGPT Codex Connector

   More actions

   Update: status.openai.com marked the related ChatGPT incident resolved at 22:28 (Asia/Shanghai), but GPT-5.6 Sol (xhigh) still returned the capacity error and GPT-6 Astra (Ultra) continued retrying without a response. Only GPT-5.3 Codex Spark (low) succeeded. This suggests the Codex primary model pool was not fully recovered even after the status incident was marked resolved. The Help Center case remains escalated to human support.