Quick answer
Codex documents plus local-message range as 10–2,000 messages per 5 hours, depending on model. The official table ranges from 10–100 for GPT-5.6 Sol to 250–2,000 for GPT-5.6 Luna.
Verified Aug 22, 2026Official source
Current limits
| Constraint | Current value | Scope | Verified source |
|---|---|---|---|
| Plus local-message rangeThe official table ranges from 10–100 for GPT-5.6 Sol to 250–2,000 for GPT-5.6 Luna. | 10–2,000 messages per 5 hours, depending on model | ChatGPT Plus | OpenAIAug 22, 2026 |
Why does this limit matter?
Model choice changes effective message capacity by far more than a single plan-wide headline would suggest.
This value is scoped to ChatGPT Plus; a different plan, runtime, model, endpoint, region, or account can produce a different effective constraint.
What should you check?
- Open the usage dashboard or run /status in an active Codex 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
- Local messages and cloud chats share a five-hour window, 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