Verified history
OpenAI lowered the bottom of the Codex plus message range
The pricing page's local-messages-per-five-hour table now starts at a lower per-model figure because GPT-6 Astra was added at the low end; the top of the range is unchanged. Detection date recorded; no effective date published.
Teams standardising on the newest model get fewer local messages per window than the older lower bound suggested.
OpenAI lowered the bottom of the Codex pro 5x message range
The pricing page's local-messages-per-five-hour table now starts at a lower per-model figure because GPT-6 Astra was added at the low end; the top of the range is unchanged. Detection date recorded; no effective date published.
Teams standardising on the newest model get fewer local messages per window than the older lower bound suggested.
OpenAI lowered the bottom of the Codex pro 20x message range
The pricing page's local-messages-per-five-hour table now starts at a lower per-model figure because GPT-6 Astra was added at the low end; the top of the range is unchanged. Detection date recorded; no effective date published.
Teams standardising on the newest model get fewer local messages per window than the older lower bound suggested.
Current monitored baseline
HyperObserve currently monitors 4 scoped observations for Codex. The baseline covers Plus local-message range, Pro 5× local-message range, Pro 20× local-message range, post-allowance continuation. Each value retains its plan, product, endpoint, region, account, or runtime qualifier so a future change can be compared against the correct scope.
| Constraint | Current value | Scope | Verified source |
|---|---|---|---|
| Plus local-message rangeThe official Plus column ranges from 5–45 for GPT-6 Astra and 10–100 for GPT-5.6 Sol to 250–2,000 for GPT-5.6 Luna. | 5–2,000 messages per 5 hours, depending on model | ChatGPT Plus | OpenAISep 17, 2026 |
| Pro 5× local-message rangeThe Pro 5× column ranges from 25–225 for GPT-6 Astra and 50–500 for GPT-5.6 Sol to 1,250–10,000 for GPT-5.6 Luna. | 25–10,000 messages per 5 hours, depending on model | ChatGPT Pro 5× | OpenAISep 17, 2026 |
| 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 |
| post-allowance continuationPlus and Pro can purchase credits, while API-key chats use standard API billing. | Additional credits or API-key usage | Plan dependent | OpenAISep 17, 2026 |
Tracked constraints and impact
Local message allowances, five-hour windows, credits, and plan-dependent agent usage. A change is recorded only when it alters a constraint developers can act on, such as capacity planning, request shaping, model selection, deployment configuration, storage design, retry behavior, or account budgeting.
Codex Plus Local Message Limits
Codex Plus Local Message Limits, verified against Codex's official documentation with scope, implementation impact, caveats, and a direct check.
Codex Pro 5× Local Message Limits
Codex Pro 5× Local Message Limits, verified against Codex's official documentation with scope, implementation impact, caveats, and a direct check.
Codex Pro 20× Local Message Limits
Codex Pro 20× Local Message Limits, verified against Codex's official documentation with scope, implementation impact, caveats, and a direct check.
Codex Credits & Usage After Plan Limits
Codex Credits & Usage After Plan Limits, verified against Codex's official documentation with scope, implementation impact, caveats, and a direct check.
How a change is verified
- Compare the current first-party statement with the previously stored observation, including the exact plan, model, runtime, endpoint, region, and account scope.
- Separate a true product change from documentation clarification, temporary capacity, configurable account state, or a limit that applies to a different execution path.
- Preserve the old and new values, official source, effective date when disclosed, detection date, and practical impact. If those elements cannot be supported, no historical event is published.
Official sources monitored
These first-party documents support the current Codex baseline. HyperObserve links directly to them so you can confirm the live wording before making a production decision.
Plan tables, five-hour windows, credits, and usage checks