Quick answer
Mistral API documents current model context range as 128K or 256K tokens for documented current models. Input and output tokens together count toward the model context window.
Verified Aug 22, 2026Official source
Current limits
| Constraint | Current value | Scope | Verified source |
|---|---|---|---|
| current model context rangeInput and output tokens together count toward the model context window. | 128K or 256K tokens for documented current models | Model specific | Mistral AIAug 22, 2026 |
Why does this limit matter?
Reserving no output space can turn an otherwise valid input into a 400 response.
This value is scoped to Model specific; a different plan, runtime, model, endpoint, region, or account can produce a different effective constraint.
What should you check?
- Match the deployed model ID to the limitations table and reserve max_tokens.
- 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 model cards are the authoritative current list and may add models with different windows.
- 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