Platform / AI Gateway
One gateway for models, tools, and inference policy.
Route open-weight and commercial models through a single control plane — with fallbacks, quotas, payload logging, and MCP endpoint governance.
More than an LLM proxy
Enterprise buyers need routing, cost visibility, and policy at the gateway — not just API keys. LiteLLM integration provides unified inference with tenant-scoped quotas and observability hooks.
MCP servers register as first-class connections: owner, ACL, tool list, and PolicyBundle attachment. Coding agents and IDE integrations inherit the same governance model as production agents.
Shipped capabilities
- LiteLLM proxy with model routing and fallback chains
- Per-tenant cost and token tracking with inference logs
- MCP server catalog with policy attachment
- Open-weight and commercial model support
- Embeddings and speech service routing
- Phoenix trace integration for LLM observability
- Hard cost caps and approval workflows (roadmap)