← All guides

What is an agent router?

An "agent router" is the piece that lets a coding agent send work to different models or providers instead of being hard-wired to one. Here's what it does, why it matters for cost and reliability, and why having it built in beats bolting one on.

TL;DR: An agent router sits between your agent and the models, and picks which model/provider handles a given request — so you can use a cheap model for routine work, a strong one for hard tasks, and fail over when a provider is capped or down. You can bolt a standalone router in front of an agent, but it's cleaner when the agent has multi-model routing built in: you just pick the model in the UI, no proxy plumbing.

The plain definition

A router is the layer that decides which model gets a request. Instead of the agent talking to exactly one endpoint, it talks to a router that can send different requests to different models or providers — by your choice, by cost, or by availability. Think of it like a switchboard between your agent and every model you might use.

Why people want one

Cost control

Route routine edits to a cheap model (GLM/DeepSeek), save the premium model for hard problems.

Reliability / failover

When one provider is rate-limited or down, the router falls back to another so you're not stuck.

No lock-in

You're not married to one vendor's pricing, limits, or outages.

Right tool per task

Different models are better at different things; a router lets you match them.

Two ways to get routing

Standalone router vs built-in

ApproachHow it worksTradeoff
Bolt on a standalone routerRun a proxy in front of the agent that speaks the agent's API and fans out to modelsExtra service to run/configure; another moving part
Built-in routingThe agent itself lets you pick provider/model as a settingSimplest — pick in the UI, no proxy to maintain
Rule of thumb: if you only need to choose models yourself (not auto-route by policy), a built-in model picker does the job with zero extra infrastructure.

Built-in routing, done simply

For most people, "routing" really means: I want to pick which model runs this, and switch easily. An agent with built-in multi-model support gives you that directly — Claude, OpenAI-compatible endpoints, GLM, Kimi, DeepSeek, or a local model, chosen in the UI. No standalone router to deploy, no translating proxy, no restart-to-switch.

FAQ

What does an agent router do?

It sits between your coding agent and the models, and decides which model/provider handles each request — letting you control cost, fail over when a provider is down, and avoid lock-in to one vendor.

Do I need a separate router service?

Not if your agent has multi-model support built in. A standalone router (a proxy in front of the agent) works but adds a moving part. Built-in routing lets you just pick the model in the UI.

Which agent has built-in multi-model routing?

Wuwei has it built in: pick Claude, OpenAI-compatible endpoints, GLM/Kimi/DeepSeek, or a local model from a list and switch in a click — no separate router or proxy to run.

If you want routing without running a separate router service, use an agent that has multi-model switching built in. Wuwei is a free, open-source agent where the provider and model are just settings — pick from a list, switch anytime, and route your work wherever it makes sense.

Windows · macOS · Linux — free, no login