Quick answer
Claude documents plan capacity as Free: limited; Pro: standard; Max: 5× or 20× Pro. Capacity is plan-relative rather than a universal message count and varies with workload.
Verified Aug 22, 2026Official source
Current limits
| Constraint | Current value | Scope | Verified source |
|---|---|---|---|
| plan capacityCapacity is plan-relative rather than a universal message count and varies with workload. | Free: limited; Pro: standard; Max: 5× or 20× Pro | Personal plans | AnthropicAug 22, 2026 |
Why does this limit matter?
Long conversations, attachments, model choice, and tool use consume the allowance at different rates.
This value is scoped to Personal plans; a different plan, runtime, model, endpoint, region, or account can produce a different effective constraint.
What should you check?
- Open the Claude plan and usage screens for the account that is sending messages.
- 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 5× and 20× labels describe capacity relative to Pro, not a guaranteed number of identical prompts.
- 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