Codex Pro user blocked on all models despite full quota, suspected risk-control flag
LiuliKyin · ghdev · 2026-10-21
A Codex Pro subscriber reports that since October 21, every model (GPT-6.1, gpt-6-astra, GPT-6, GPT-5.6, etc.) returns "Selected model is at capacity" across Web, desktop app, and CLI — despite the account having full quota.
- Timeline: the account had an unauthorized MFA binding security incident, resolved October 19; it worked fine on Oct 19-20, then the error appeared suddenly at 8:30 AM on Oct 21
- Key detail: the error spans all models and all interfaces, so it's clearly not a single-model capacity issue
- The user suspects an account-level restriction or a risk-control false flag, possibly tied to the earlier compromise or a flagged IP
Codex version 0.163.0; the issue has 10 comments.
More from coding & agent
- Decisions API hits GA as agents automate cloud video editing via feedback loops — dkundel · 2026-10-23
- A curated library of 50+ free AI agent resources: videos, repos, one Google Doc — ifioknkem · 2026-10-23
- The 'best free AI agent resource library on the internet,' in one Google Doc — ifioknkem · 2026-10-23
- Vercel adds no-account deploys: drag and drop a file to get a live URL — steren · 2026-10-23
- Dev runs 5 Claude Code sessions that coordinate via MCP Agent Mail to root his network cameras — doodlestein · 2026-10-23
- Vercel ships 'vercel deploy --temporary' for ephemeral agent-built deployments — cramforce · 2026-10-23