Third concurrent Codex desktop chat fails with HTTP 429 #54017

Activity

1. github-actions

   added

   bugSomething isn't workingSomething isn't working

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

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

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

   

   github-actionsbot

   on Oct 14, 2026 – with GitHub Actions

   Contributor

   More actions

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

   • [CLI][WSL] Repeated retry-exhausted HTTP 429 with only 3 active sessions and 69% allowance remaining #54010
   • Windows Codex Desktop: HTTP 429 across multiple tasks while ~70% of weekly allowance remains #53978
   • [Windows][Pro] Critical Codex performance degradation, stalled agents and repeated HTTP 429 errors #54004

   Powered by Codex Action
3. khuyendev commented on Oct 15, 2026

   

   khuyendev

   on Oct 15, 2026

   More actions

   Hello OpenAI Support Team,

   I'm a ChatGPT Pro subscriber ($200/month), and I'd like to report a significant regression in Codex performance and reliability that started around October 11, 2026.

   I'm experiencing these issues while using the official Codex application, primarily with GPT-6.1 Sol.

   Issues observed:

   1. Frequent HTTP 429 errors: Requests are being rejected with "Too Many Requests" or model capacity errors, even when my subscription usage allowance has not been exhausted.
   2. Significantly slower responses: GPT-6.1 Sol now takes noticeably longer to generate responses. Even ordinary chat requests can take an unusually long time to complete.
   3. Concurrent request failures: Previously, I could run approximately 20 concurrent GPT-6.1 Sol Fast Mode requests reliably. Since October 11, running multiple requests has become increasingly unreliable.
   4. Overall performance regression: The same workloads that previously completed quickly and consistently now experience prolonged delays, retries, and request failures.

   I've found numerous similar reports from other ChatGPT Pro subscribers on the official Codex GitHub repository:

   • Codex Completely Unusable Since October 11 — All Models Permanently Fail With Capacity / 429 Errors #54221
   • Third concurrent Codex desktop chat fails with HTTP 429 #54017
   • [Windows] Codex Desktop: repeated "Selected model is at capacity" (server_is_overloaded, NO_MORE_RETRY) with weekly usage at 1% - 171 failed turns over 3 days #53594
   • Frequent “Selected model is at capacity” errors on Pro 20x, especially with concurrent Codex sessions #52397

   Could you please investigate and clarify the following?

   1. Has OpenAI recently changed or reduced the concurrency limits for ChatGPT Pro accounts?
   2. Are there new restrictions on simultaneous requests using GPT-6.1 Sol Fast Mode?
   3. Is there an ongoing backend capacity, throttling, or performance issue affecting Codex since October 11?
   4. What are the officially supported concurrent request limits for ChatGPT Pro subscribers?
   5. When can affected users expect normal response speeds and reliability to be restored?

   As a paying Pro subscriber, reliable performance and predictable concurrency limits are important for my development workflow.

   The combination of frequent 429 errors and substantially slower response times is significantly affecting my productivity.

   I would appreciate a technical investigation rather than a generic rate-limit explanation, especially given the number of similar reports from other subscribers.

   Thank you for your assistance. I can provide diagnostic logs, request IDs, and timestamps if needed.

   Best regards