Quick answer
Mistral API documents admin limit visibility as RPS plus per-model TPM and monthly token limits. An admin API key is required to read organization rate and spend contexts.
Verified Aug 22, 2026Official source
Current limits
| Constraint | Current value | Scope | Verified source |
|---|---|---|---|
| admin limit visibilityAn admin API key is required to read organization rate and spend contexts. | RPS plus per-model TPM and monthly token limits | Admin API beta | Mistral AIAug 22, 2026 |
Why does this limit matter?
Reading live limits avoids embedding example values that do not belong to the current organization.
This value is scoped to Admin API beta; a different plan, runtime, model, endpoint, region, or account can produce a different effective constraint.
What should you check?
- Call GET /v1/admin/rate-limit with an admin key and store only non-secret limit metadata.
- 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 endpoint is marked beta and its schema can evolve.
- 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