Quick answer
Gemini documents consumer context window as 32K free; 128K AI Plus; 1M AI Pro and Ultra. Google describes this as the content Gemini Apps can consider together.
Verified Aug 22, 2026Official source
Current limits
| Constraint | Current value | Scope | Verified source |
|---|---|---|---|
| consumer context windowGoogle describes this as the content Gemini Apps can consider together. | 32K free; 128K AI Plus; 1M AI Pro and Ultra | Personal Google AI plans | GoogleAug 22, 2026 |
Why does this limit matter?
Large file and code workflows can lose relevant connections when the combined chat exceeds the active plan window.
This value is scoped to Personal Google AI plans; a different plan, runtime, model, endpoint, region, or account can produce a different effective constraint.
What should you check?
- Open Gemini Settings → Usage Limits and confirm the active subscription before budgeting files.
- 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
- Deep Think has a separate documented context window and product limits can change with availability.
- 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