LLM Reference

Router compare

Kong AI Gateway vs LiteLLM

Router-vs-router comparison for integration shape, routing policy, target providers, pricing model, and data handling. Use this view for the routing layer; use model compare when choosing the model itself.

Fresh
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.
LiteLLM

BerriAI

Fresh
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.

Facet comparison

Type

Kong AI Gateway

Gateway

LiteLLM

Gateway

Openness

Kong AI Gateway

Commercial

LiteLLM

Open source

Hosting

Kong AI Gateway

Self-hosted

LiteLLM

Self-hosted

Decision mechanism

Kong AI Gateway

Rules / heuristics, Semantic k-NN

LiteLLM

Rules / heuristics, Cascade

Optimizes for

Kong AI Gateway

Cost, Latency, Reliability

LiteLLM

Cost, Reliability, Latency

Routing scope

Kong AI Gateway

Cross-provider

LiteLLM

Cross-provider

Pricing

Kong AI Gateway

Subscription

LiteLLM

Free OSS

Data retention

Kong AI Gateway

Unknown

LiteLLM

Zero retention

Models reachable

Kong AI Gateway

-

LiteLLM

100 models

API compatibility

Kong AI Gateway

OpenAI, Native

LiteLLM

OpenAI

Targets overlap