LLM Gateways & Model Routing Platforms

Gateway for observing, caching, and controlling AI application traffic to model providers.

Open-source LLM observability platform with an AI gateway for routing, caching, and rate limiting.

API gateway extended for AI that routes, secures, and governs LLM, MCP, and agent-to-agent traffic.

Open-source proxy that standardizes API calls to many LLM providers with unified auth and rate limits.

Intelligent model router that selects which LLM handles each request for coding agent workloads.

Unified API for routing requests to a large catalog of language models from multiple providers.

AI gateway providing model routing, caching, fallbacks, and observability for LLM applications.

Managed LLM router with OpenAI-compatible API, fallbacks, caching, guardrails, and cost controls.

Enterprise LLM gateway for routing, guarding, and observing AI traffic across 1,600+ models.

Hosted gateway providing hundreds of models through one API at provider prices with routing and failover.