multi-router.aidocs

Agents & Editors

OpenWork

Connecting the OpenWork desktop app to an Adaptive Router through an OpenCode provider in the workspace.

OpenWork is a desktop app for agent work, built on OpenCode. It connects to Multi-Router through an OpenAI-compatible provider in the workspace's OpenCode config, which sends Chat Completions requests to an Adaptive Router with the router header.

Creating the router

OpenWork connects through an Adaptive Router, which accepts OpenAI Chat Completions requests and serves each one with the model it names, using the organization's provider key for that model's provider. OpenWork holds only the Multi-Router API key. See Adaptive Router. To set it up:

  1. In Model Groups, create or choose a model group with the models OpenWork should use. See Model Group.
  2. In Routers, choose New router, then Adaptive Router. Name it, choose the model group, and switch on the models to serve.
  3. Choose the organization's provider key for each provider in the group, and create the router. Its id, such as rt_XXXXXXXX, is on the router's page.
  4. In API Keys, create a key with the inference scope. It can be limited to this router. See API Key.

Every request carries the router id in the X-MR-Router header and the API key as a Bearer token, both set in OpenWork's settings below.

Settings

Create opencode.jsonc in the root of the workspace folder, or add the provider to an existing one. OpenWork reads any valid OpenCode config:

opencode.jsoncjson
{
  "provider": {
    "multi-router": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Multi-Router",
      "options": {
        "baseURL": "https://api.multi-router.ai/v1",
        "apiKey": "{env:MR_API_KEY}",
        "headers": { "X-MR-Router": "rt_XXXXXXXX" }
      },
      "models": {
        "anthropic/claude-sonnet-4.6": { "name": "Claude Sonnet 4.6 (Multi-Router)" }
      }
    }
  }
}

Set MR_API_KEY in OpenWork under Settings, then Environment, or in the shell before starting OpenWork. Then run Reload OpenCode config from the command palette, or restart OpenWork.

Models

An Adaptive Router names models by their Multi-Router catalog id, provider/model, such as anthropic/claude-sonnet-4.6, openai/gpt-5 or google/gemini-2.5-flash. The model must be switched on in the router's model group; a request for any other model is refused with a message listing the models the router serves. The settings on this page list each model id explicitly.

Each entry under models appears in the chat model picker under the Multi-Router provider.

Checking the setup

Choose the model in the composer's model picker and say hello.

The request then appears in Traffic with the Adaptive Router in the Router column and the model, tokens and cost in the request detail. A reply with the requested model or router was not found means the router id is wrong, or the API key is not allowed to use that router. See Traffic and Troubleshooting.

LibreChatTroubleshooting
Was this helpful?