Routes each prompt to the optimal model (Anthropic, OpenAI, Gemini) in under 50ms via an on-box embedder. Router 2.0 adds subscription-aware routing for Claude Code, Codex, and opencode.
Use it now
Keep it with up to 9 other tools you're setting up, then share them all as one link.
Try this first
Ask your coding agent:
- Sub-50ms Routing
Use Workweave Router to route each prompt to the best model: ‹what you need›
Install the CLI
Install it as its own instructions say.
Its page: github.com/weave-os/router
Call the API
Auth An API key from Weave
Its page: github.com/weave-os/router
Compare
Press Compare to add it to the tray at the bottom of the window, then pick up to 2 others anywhere on the site.
- Access
- CLIAPI
- Auth
- API Key
- Skills
- 3
Skills
Sub-50ms Routing
Routes each prompt to the best model in under 50ms using an on-box embedder, no extra network hop.
Drop-In Proxy
Acts as an Anthropic- and OpenAI-compatible proxy for Claude Code, Codex, and opencode.
Cost Reduction
Cuts model spend 40-70% by sending simple prompts to cheaper models and hard ones to frontier models.