Helicone Rate Limits
Helicone publishes per-tier ingestion and API call ceilings on its pricing page rather than a dedicated rate-limits doc. The AI Gateway also enforces strict caps on traffic to non-approved target domains. Limits are enforced per organization / API key. Headers and response codes for throttling are not publicly documented; consumers should rely on standard 429 handling and exponential backoff.
Helicone Rate Limits is the machine-readable rate-limit profile for Helicone on the APIs.io network, conforming to the API Commons Rate Limits specification.
It captures 11 rate-limit definitions, across the hobby, pro, team, enterprise, and gateway tiers, measuring logs_per_minute, requests_per_minute, requests_per_month, requests_per_day, and requests_per_second.
The profile also includes 5 backoff/retry policies defined and response codes documented for throttled, quotaExceeded, and serviceUnavailable.
Tagged areas include AI Gateways, AI Monitoring, Gateways, LLM Observability, and LLM Routing.
Limits
Policies
Sources
Work with this as data
Every rate limit here is available over the APIs.io API and to AI agents over MCP.