LLM Reference

Directory · Routing layer

Routers & gateways

Can't pick one model? Route per request. 17 verified gateways and routers, updated daily.

Editorial picks are selected independently by our editorial team based on technical merit and breadth of use. We may earn a commission on purchases made through affiliate links; this does not influence editorial picks.

4 of 17 active routers

Hide deprecated
L
LiteLLM

BerriAI

Editorial pick
GatewayOpen sourceSelf-hostedCostReliability

~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.

P
Portkey

Portkey AI

Editorial pick
GatewayOpen sourceHosted SaaSReliabilityCost

~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.

H
Helicone

Helicone

GatewayOpen sourceHosted SaaSReliabilityCost

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.

KA
GatewayCommercialSelf-hostedCostLatency

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.

Popular router comparisons

OpenRouter vs Requesty
  • Policy
  • Providers
  • Pricing
  • API
  • Data
OpenRouter vs Portkey
  • Policy
  • Providers
  • Pricing
  • API
  • Data
LiteLLM vs Kong AI Gateway
  • Policy
  • Providers
  • Pricing
  • API
  • Data
RouteLLM vs vLLM Semantic Router
  • Policy
  • Providers
  • Pricing
  • API
  • Data
AIRouter vs Martian
  • Policy
  • Providers
  • Pricing
  • API
  • Data