Patronus AI · Rate Limits

Patronus Rate Limits

Patronus AI applies per-API-key rate limits and tier-based monthly quotas. Specific RPS thresholds are not publicly documented; the API returns 429 on overage.

Patronus Rate Limits is the machine-readable rate-limit profile for Patronus AI on the APIs.io network, conforming to the API Commons Rate Limits specification.

It captures 2 rate-limit definitions, measuring requests and calls.

The profile also includes 2 backoff/retry policies defined and response codes documented for throttled.

Tagged areas include AI Evaluation, GenAI, Guardrails, Hallucination Detection, and LLM.

2 Limits Throttle: 429
AI EvaluationGenAIGuardrailsHallucination DetectionLLMAgentsRate LimitingQuotasThrottling

Limits

Per API key account
requests
see provider documentation
Throttled with 429 on overage.
Monthly evaluator calls account
calls
tier-defined
Each tier has a monthly quota.

Policies

Backoff Strategy
Honor 429 with exponential backoff.
Caching
Cache evaluator results when scoring identical inputs.

Sources