Quick answer
GitHub Copilot documents code review multiplier as 13 premium requests per review. Under usage-based billing, code review is charged in AI credits by tokens plus GitHub Actions minutes rather than a fixed multiplier.
Verified Sep 17, 2026Official source
Current limits
| Constraint | Current value | Scope | Verified source |
|---|---|---|---|
| code review multiplierUnder usage-based billing, code review is charged in AI credits by tokens plus GitHub Actions minutes rather than a fixed multiplier. | 13 premium requests per review | Legacy annual Pro/Pro+ plans | GitHubSep 17, 2026 |
Why does this limit matter?
Automated or frequent reviews can consume the monthly allowance much faster than one-request chat prompts.
This value is scoped to Legacy annual Pro/Pro+ plans; a different plan, runtime, model, endpoint, region, or account can produce a different effective constraint.
What should you check?
- Count scheduled and manual reviews separately from chat prompts in usage reports.
- 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
- Other features and model selections use their own multipliers.
- 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