Writer · Rate Limits

Writer Rate Limits

Writer enforces RPM (requests per minute) and TPM (tokens per minute) on the AI Studio Platform API, with limits tied to the customer's contract and configured per organization and per model. The exact per-tier limits are not publicly disclosed and are pending reconciliation.

3 Limits Throttle: 429
AILLMEnterpriseContent GenerationPalmyraRate LimitingQuotasThrottling

Limits

Requests Per Minute (RPM) organization
requests
see provider documentation
Per-model RPM, varies by contract and model. Pending reconciliation.
Tokens Per Minute (TPM) organization
tokens
see provider documentation
Per-model TPM, varies by contract and model. Pending reconciliation.
Concurrent Requests organization
concurrent
see provider documentation
Concurrency cap per model. Pending reconciliation.

Policies

Tiered Limits
Higher limits unlocked through Enterprise contract size.
Backoff Strategy
Clients should implement exponential backoff with jitter and honor Retry-After.

Sources