Quick answer
Codex documents pro 20× local-message range as 100–40,000 messages per 5 hours, depending on model. The Pro 20× column ranges from 100–900 for GPT-6 Astra and 200–2,000 for GPT-5.6 Sol to 5,000–40,000 for GPT-5.6 Luna.
Verified Sep 17, 2026Official source
Current limits
| Constraint | Current value | Scope | Verified source |
|---|---|---|---|
| Pro 20× local-message rangeThe Pro 20× column ranges from 100–900 for GPT-6 Astra and 200–2,000 for GPT-5.6 Sol to 5,000–40,000 for GPT-5.6 Luna. | 100–40,000 messages per 5 hours, depending on model | ChatGPT Pro 20× | OpenAISep 17, 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