Keywords AI · Rate Limits

Keywordsai Rate Limits

Keywords AI authenticates all API calls with a Bearer API key and enforces account-level rate limits on the gateway and data endpoints, plus monthly usage quotas on logs and evaluation scores per plan tier. For gateway (proxy) traffic, effective throughput is also bounded by the rate limits of the underlying model provider being routed to. Specific per-endpoint request-per-minute values are not published in a single reference and are not reconciled in this artifact.

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

It captures 4 rate-limit definitions, measuring requests, logs, and scores.

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

Tagged areas include AI, LLM, Observability, Gateway, and Monitoring.

4 Limits Throttle: 429
AILLMObservabilityGatewayMonitoringRate LimitingQuotasThrottling

Limits

Gateway Requests account
requests
see provider documentation
Chat completions proxy; effective throughput also bounded by the routed model provider's limits.
Data Endpoint Requests account
requests
see provider documentation
Logging, prompts, threads, traces, evaluators, users, datasets, experiments endpoints.
Monthly Logs Quota account
logs
per plan tier
Free 100k/month; Team unlimited; Enterprise custom. Overage billed per 100k logs.
Monthly Scores Quota account
scores
per plan tier
Free 1k/month; Team 10k/month; Enterprise custom. Overage billed per 1k scores.

Policies

Tiered Limits
Quotas and limits increase across Free, Team, and Enterprise plans.
Backoff Strategy
Clients should implement exponential backoff with jitter and honor Retry-After on 429 responses.

Sources