Quick answer
Gemini documents compute-based usage as Refreshes every 5 hours until a weekly limit is reached. Prompt complexity, model, feature, thinking level, and chat length affect consumption.
Verified Aug 22, 2026Official source
Current limits
| Constraint | Current value | Scope | Verified source |
|---|---|---|---|
| compute-based usagePrompt complexity, model, feature, thinking level, and chat length affect consumption. | Refreshes every 5 hours until a weekly limit is reached | Personal accounts | GoogleAug 22, 2026 |
Why does this limit matter?
A simple prompt count cannot represent usage when advanced reasoning and media features consume more compute.
This value is scoped to Personal accounts; a different plan, runtime, model, endpoint, region, or account can produce a different effective constraint.
What should you check?
- Open Settings → Usage Limits to see proximity to the limit and the displayed refresh time.
- 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
- Google may change limits due to testing, capacity, availability, or increased activity.
- 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