Quick answer
GitHub Copilot documents monthly premium requests as Legacy annual Pro: 300; Pro+: 1,500 per month. Other plans receive monthly GitHub AI Credits instead: Pro 1,500, Pro+ 7,000, Max 20,000, where one credit equals $0.01.
Verified Sep 17, 2026Official source
Current limits
| Constraint | Current value | Scope | Verified source |
|---|---|---|---|
| monthly premium requestsOther plans receive monthly GitHub AI Credits instead: Pro 1,500, Pro+ 7,000, Max 20,000, where one credit equals $0.01. | Legacy annual Pro: 300; Pro+: 1,500 per month | Annual Pro/Pro+ on legacy request-based billing (after 2026-06-01) | GitHubSep 17, 2026 |
Why does this limit matter?
A prompt can consume more than one premium request when its feature or model has a multiplier.
This value is scoped to Annual Pro/Pro+ on legacy request-based billing (after 2026-06-01); a different plan, runtime, model, endpoint, region, or account can produce a different effective constraint.
What should you check?
- Open Copilot usage and entitlements and match the current billing model and plan.
- 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
- GitHub labels the request-based scheme legacy; usage-based accounts should read the AI Credits documentation rather than this allowance.
- 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