Skip to main content
Route every model call OpenCode Desktop makes through the Orq.ai AI Gateway by adding a custom provider in the app. Requests appear in Traces automatically.

​
Prerequisites

  • OpenCode Desktop installed:
Homebrew
brew install --cask opencode-desktop
Or download the installer from opencode.ai/download.

​
Setup

In OpenCode Desktop, open Settings > Providers > Connect custom provider and fill in:
  • ID: orq
  • Display name: Orq
  • Base URL: https://api.orq.ai/v3/router
  • API key: your Orq.ai API key
  • Model ID: any identifier from the AI Gateway catalog, for example anthropic/claude-sonnet-4-6, with a display name
Add more models by giving each its own Model ID and display name. Pick the model from the model selector in the chat input bar.
OpenCode Desktop custom provider form filled in with the Orq ID, Orq display name, router base URL, API key, and a model ID

​
Verification

Send a prompt in OpenCode Desktop. The response appears in the app and the trace appears in Orq.ai Traces with the selected model identifier.

​
Connect via MCP

OpenCode Desktop also acts as an MCP client, so the Orq MCP server can run alongside the gateway routing above. With both connected, OpenCode Desktop routes model calls through the AI Gateway and manages Agents, experiments, Datasets, and Traces through the Orq MCP tools. Add the Orq MCP server to the OpenCode config (~/.config/opencode/opencode.json): 
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "orq": {
      "type": "remote",
      "url": "https://my.orq.ai/v2/mcp",
      "enabled": true,
      "headers": {
        "Authorization": "Bearer YOUR_ORQ_API_KEY"
      }
    }
  }
}
Replace YOUR_ORQ_API_KEY with an API key. See the MCP Quickstart for the full tool reference.
Orq.ai API keys are scoped to a single project, so the Orq MCP server only exposes the Agents, experiments, Datasets, and Traces within that project. Use a key from the project whose entities OpenCode Desktop should manage.