Tetrate · Rate Limits
Tetrate Rate Limits
Tetrate's Agent Router (LLM Gateway / MCP Gateway / AI Guardrails) and enterprise platform do not publish a public rate-limits reference. The free Developer tier is bounded by free inference credits; enterprise throughput and concurrency are negotiated per engagement.
Tetrate Rate Limits is the machine-readable rate-limit profile for Tetrate on the APIs.io network, conforming to the API Commons Rate Limits specification.
It captures 2 rate-limit definitions, measuring varies.
The profile also includes 2 backoff/retry policies defined.
Tagged areas include Rate Limiting, AI Gateway, and Service Mesh.
2 Limits
Rate LimitingAI GatewayService Mesh
Limits
Developer Tier (Credit-Bounded) account
bounded by free inference credits
Enterprise (Contract-Defined) contract
defined per Tetrate enterprise engagement
Policies
Credit Exhaustion
Developer-tier traffic is paused or throttled once free inference credits are exhausted.
Enterprise Capacity
Throughput, model routing fallbacks, and concurrency for the enterprise tier are sized with Tetrate during onboarding.
Sources
Work with this as data
Every rate limit here is available over the APIs.io API and to AI agents over MCP.