Skip to main content
OpenWork supports two different custom-provider workflows depending on where you want the configuration to live.

​
Use OpenWork Cloud for shared provider access

If your organization uses OpenWork Cloud, open LLM Providers in the org dashboard when you want one shared provider setup for multiple teammates.
  • Add the provider credentials once.
  • Choose which models the org should expose.
  • Grant access to specific people or teams.
This is the best option when the provider should be managed centrally instead of copied into each person’s local config. If you also need non-interactive access for automations or backend services, create an org API Key in the same dashboard and use the docs site’s API Reference tab for the current den-api routes.

​
Use workspace config for local or self-managed providers

Because OpenWork is built on OpenCode primitives, it also supports the same provider configuration you can add to opencode.json, including custom models. For local or self-managed setups, we recommend adding the provider to /path-to-your-workspace/.config/opencode/opencode.json instead of modifying ~/.config/opencode/opencode.json. The reason for this is that you may want to support different models and permissions across several workspaces, especially when sharing them with a team. Inside /path-to-your-workspace/.config/opencode/opencode.json: 
{
  "provider": {
    "my-api": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "My model",
      "options": {
        "baseURL": "https://your API address/v1"
      },
      "models": {
        "model-name": {
          "name": "Model name"
        }
      }
    }
  }
}
We’ve also built a custom skill that you can import in OpenWork by following this guide. The following tutorial covers how to import a custom provider using the skill.