Adding a custom LLM provider/model

How to connect a custom provider with openwork

Because Openwork is built on Opencode primitives, we support everything that you could modify in .opencode.json, like adding a model. However, our recommendation is to add it 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, specially when sharing it 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 following this guide.

The following tutorial covers how to import a custom provider using the skill.