Codex Pro 5x users hit 'model at capacity' errors all afternoon, GitHub issue shows
Secretmakewomenwomen · ghdev · 2026-09-17
A GitHub issue on openai/codex reports that a Pro 5x subscriber on macOS running the latest Codex App gets a "Selected model is at capacity. Please try a different model" error on every task run, blocking work for an entire afternoon. The user criticizes paying for a high-tier subscription with no availability and suggests OpenAI learn from Claude. The issue carries bug and rate-limits labels and has 7 comments so far.
More from Models
- Qwen 3.8 Omni Flash Surfaces with Continuous Video/Audio Understanding and Custom Harness — Mr_Moonsilver · 2026-09-18
- Encoders and decoders are the same thing, and decoders have been doing classification for years — HanchungLee · 2026-09-18
- Sakana AI Launches Fugu Max, a Multi-Agent Orchestrator Routing Tasks to Leanest Capable Models — tkasasagi · 2026-09-18
- Prediction: Every Future LLM Will Ship With a Native 'Jev Mode' — multimodalart · 2026-09-18
- Why don't LLM labs compete on personality? Users value it over raw capability — dioscuri · 2026-09-18
- Fine-tuned 4B model as a decision scorer with temperature-scaled confidence — Gradio · 2026-09-18