Alpha
One endpoint for self-hosted inference
Route requests across vLLM, Ollama, SGLang, llama.cpp, Infinity, and custom OpenAI-compatible backends using policies, live signals, fallback, authentication, and observability.
Explore the docs
Start with the system overview or go directly to deployment, routing, and API guidance.
Introduction
Learn what Hivenet Router does, when it is useful, and what it does not
provide.
Quickstart
Deploy a router and agents, then send your first routed inference
request.
Architecture overview
Understand the router, agents, control plane, data plane, storage,
and request flow.
Hivenet Router and Hivenet services
See how Hivenet Router differs from Hivenet Inference API and Compute
with Hivenet.
Start here
Introduction
Understand what Hivenet Router does and when to use it.
Quickstart
Deploy a router and an agent and send your first request.
Architecture overview
See the control plane, data plane, and request flow.
Docker quickstart
Deploy a router and two vLLM agents with Docker.
Explore by topic
Deploy
Install the router and agents on Docker, Docker Compose, or bare metal.
Routing and policies
Filter and rank agents with YAML policies and fallback chains.
Security and auth
Authenticate agents and clients, enforce quotas, and rotate keys.
Observability
Monitor routing, agents, engines, and hardware with Prometheus and Grafana.
Integrations
Connect Hivenet Router to Claude Code, OpenCode, Open WebUI, and more.
Reference
Configuration schema, error codes, and performance characteristics.