Run OpenCode on every model through one provider block

Configure OpenCode to use the Router One base URL

Add an entry under provider in opencode.json (project-level, or ~/.config/opencode/opencode.json globally) with npm set to @ai-sdk/openai-compatible, options.baseURL on the gateway, and one models entry per catalog model you want in the picker. The key can be read from an environment variable with the {env:VAR} syntax so it never sits in the file. Select a model as provider-id/model-id — router-one/<model-id> here — from the /models command in the TUI, or pin it in the top-level model field:

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "router-one": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Router One",
      "options": {
        "baseURL": "https://api.router.one/v1",
        "apiKey": "{env:ROUTER_ONE_API_KEY}"
      },
      "models": {
        "<model-id-from-/models>": {
          "name": "<label shown in the picker>"
        }
      }
    }
  },
  "model": "router-one/<model-id-from-/models>"
}

Which model ID should OpenCode send?

Copy the exact model ID from the /models page — IDs are case-sensitive, and the page lists each model's context window, capabilities, and current per-token rates. Create a dedicated API key per tool with its own maxSpend cap, so one runaway tool can't affect other workloads.

Verify the OpenCode call in your request trace

After your first request, open Dashboard → Logs to see its full trace: model, tokens, cost, latency, and status code. From here every OpenCode call has a ledger and a trail instead of being a black box.

FAQ