Codex on Windows: all 7 models return 503 'at capacity' for 25+ hours with 94% quota left
kriouerlia · ghdev · 2026-10-13
A Windows 10 22H2 user reports Codex Desktop failing on all 7 available models (gpt-6.1-sol, gpt-6-astra, gpt-6-sol, gpt-6-luna, gpt-5.6-) since 2026-10-12, with "Selected model is at capacity" and HTTP 503 persisting 25+ hours.
- Log-based quantification from /.codex/logs2.sqlite: 59 "at capacity" errors, 25 HTTP 503s, 17 pre-sampling compact failures; the last hour shows 23 server-side rejections and zero client timeouts or transport errors.
- The account is ChatGPT Pro with response headers showing 94% quota remaining — ruling out quota and local/network issues and pointing to a server-side capacity/routing fault. Corroborates issues #52812 and #53407.
- Environment: Codex Desktop 26.930.4958.0, bundled codex-cli 0.160.0.
More from Models
- OpenAI's Decisions API hits GA: near real-time routing up to 10x faster than GPT-6 Luna — OpenAIDevs · 2026-10-23
- DeepLearning.AI weekly: GPT-6.1 hits 97.9% byte parity on COBOL migration — DeepLearningAI · 2026-10-23
- Marker's lite mode scores 75.1 vs 42.3 for Azure Read on OmniParseBench — VikParuchuri · 2026-10-23
- Datalab launches lite OCR at $0.50 per 1,000 pages, 20-30x cheaper than Azure, Google and AWS layout APIs — VikParuchuri · 2026-10-23
- LiveNerf's 29-day data finds no nerfing of Claude Opus 5.5 — TheOnlyVibemaster · 2026-10-23
- PHP Foundation reveals Anthropic's Claude cyber model scanned PHP, validated with OpenAI's Daybreak Red — saibharadwaj · 2026-10-23