Galileo · Rate Limits

Galileo Ai Rate Limits

Galileo applies per-API-key rate limits and per-tier monthly trace/evaluation quotas. Specific RPS thresholds are not publicly documented on the docs landing page; the API returns 429 on overage. Coordinate with Galileo support for higher limits.

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

It captures 2 rate-limit definitions, measuring requests and traces+evals.

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

Tagged areas include AI Evaluation, Observability, GenAI, Guardrails, and Agentic AI.

2 Limits Throttle: 429
AI EvaluationObservabilityGenAIGuardrailsAgentic AILLMRate LimitingQuotasThrottling

Limits

Per API key account
requests
see provider documentation
Throttled with 429 on overage.
Monthly quota account
traces+evals
tier-defined
Each plan tier has a monthly trace/eval allowance.

Policies

Backoff Strategy
Honor 429/Retry-After with exponential backoff.
Sampling
Sample traces in production to stay within tier quota.

Sources