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Tetrate's Agent Router (LLM Gateway / MCP Gateway / AI Guardrails) and enterprise platform do not publish a public rate-limits reference.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
varies
bounded by free inference credits
Enterprise (Contract-Defined) contract
varies
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