Quick answer
Codex documents pro 20× local-message range as 200–40,000 messages per 5 hours, depending on model. The lower end corresponds to GPT-5.6 Sol and the upper range to GPT-5.6 Luna.
Verified Aug 22, 2026Official source
Current limits
| Constraint | Current value | Scope | Verified source |
|---|---|---|---|
| Pro 20× local-message rangeThe lower end corresponds to GPT-5.6 Sol and the upper range to GPT-5.6 Luna. | 200–40,000 messages per 5 hours, depending on model | ChatGPT Pro 20× | OpenAIAug 22, 2026 |
Why does this limit matter?
Capacity planning still needs the exact model because the plan multiplier alone does not predict messages.
This value is scoped to ChatGPT Pro 20×; a different plan, runtime, model, endpoint, region, or account can produce a different effective constraint.
What should you check?
- Use the usage dashboard for plan totals and /status for the active CLI session.
- Confirm the exact plan, model, runtime, endpoint, region, and account that serve the failing workload.
- Record the observed value, response headers or configuration, timestamp, and source without logging secrets.
Important caveats
- The published numbers are ranges and additional weekly limits may apply.
- Treat the official source and live account configuration as authoritative if they differ from this verified snapshot.
HyperObserve reports the documented platform constraint. Your application, SDK, gateway, provider, region, or account can impose a lower effective limit.
Related