OpenAI Codex usage limits are tied to your ChatGPT plan and split into a rolling 5-hour window and a separate weekly window. OpenAI publishes estimated local-message ranges for Plus by model, and frames Pro as 5x–20x more usage than Plus — but exact weekly allowances are not published. Check /status or the official usage page for your actual current numbers.
| Plan | 5-Hour Window | Weekly Window | Token Ceiling | Ceiling Behavior | Source |
|---|---|---|---|---|---|
| Free | Not published by OpenAI | Not published by OpenAI | Not published by OpenAI | Paused until reset; may fall back to a lower-capability model | Not published |
| Plus ($20/mo) | Est. 15–280 local messages / 5h (model-dependent) | Not published by OpenAI | Not published by OpenAI | Prompts pause until reset, credits, or a paid instant reset | Official (estimate) |
| Pro ($200/mo) | 5x–20x more usage than Plus | Not published by OpenAI | Not published by OpenAI | Prompts pause until reset, credits, or a paid instant reset | Official |
| Business / Enterprise | Custom / seat-pooled (contract-specific) | Custom / seat-pooled (contract-specific) | Contract agreement | Admin visibility; behavior varies by contract | Official |
How This Table Is Sourced
Rows marked Official reflect what OpenAI documents directly, and Official (estimate) reflects OpenAI's own published estimate ranges — these are estimates, not guaranteed caps, and actual usage varies. Rows marked Not published mean OpenAI has not disclosed a specific number for that cell — we don't estimate or invent one. For your own account, /status and the official ChatGPT usage page remain the authoritative source. Source: chatgpt.com/codex/pricing.
Subscribed to ChatGPT Plus? Read the breakdown of ChatGPT Plus Codex limits.
Considering the $200/month tier? See our guide to ChatGPT Pro Codex limits.
Need to know exact recovery timing? Read when your Codex usage resets.
Encountering throttled sessions? Review why am I rate limited and what happens now.