Best LLM gateways
LLM gateways sit between your app and one or more model providers. Use this list when you want a unified endpoint, provider failover, observability, or governance without changing the model decision itself.
Filtered router list
Helicone
Subscription
Observability-first AI gateway with routing, caching, rate limiting, and request tracing; Apache 2.0 open-source core with a managed hosted tier for logging and analytics.
Kong Inc.
Subscription
Multi-LLM AI gateway built on Kong Gateway 3.x, adding semantic routing, load balancing, guardrails, and MCP traffic analytics as plugins over Kong's existing API management platform.
BerriAI
~100 models · Free OSS
Open-source Python SDK and proxy server that unifies 100+ LLM APIs behind a single OpenAI-compatible interface, with load balancing, cost tracking, and configurable failover.
Portkey AI
~1.6K models · Subscription
Production AI gateway routing to 1,600+ LLMs with failover, load balancing, semantic caching, and guardrails; Apache 2.0 core is fully self-hostable with the complete feature set.
Related decision paths
These links keep the SEO view tied to the single router store, target-provider graph, and model decision pages.
Compare every verified gateway, router, and hybrid row in the shared store.
Use the directory controls to add openness, hosting, API, and routing-scope filters.
Inspect the provider that one or more listed routers can target.
Inspect the provider that one or more listed routers can target.
Inspect the provider that one or more listed routers can target.
Inspect the provider that one or more listed routers can target.
Compare the provider APIs that gateways route into.
Pair a gateway with models that hold tool contracts well.
Browse adjacent builder tools for serving and routing.
Machine-readable source
This page is generated from data/seed/router.json. Agents can consume the same catalog through /api/routers.