Setup Continue.dev AI Autocomplete in VS Code

1. Open VS Code
2. Click the Extensions icon in the left sidebar (or press Ctrl+Shift+X)
3. Search for Continue
4. Click Install on the extension by Continue.dev

After installing, you'll see a Continue icon in the left sidebar (looks like a play button).

After installation of continue you will see place holders for adding API keys for Openai,anthropics and gemini , you can use either of them

If you installed Ollama (see our Ollama guide), Continue detects it automatically.

1. Click the Continue icon in the VS Code sidebar
2. Click Configure Continue (gear icon)
3. This opens config.json. Add this model block:

{
  "models": [
    {
      "title": "DeepSeek Coder (Local)",
      "provider": "ollama",
      "model": "deepseek-coder:6.7b"
    }
  ],
  "tabAutocompleteModel": {
    "title": "Autocomplete",
    "provider": "ollama",
    "model": "starcoder2:3b"
  }
}

Pull the autocomplete model:

ollama pull starcoder2:3b

If you prefer API-based models (no GPU required), use OpenRouter:

{
  "models": [
    {
      "title": "Llama 3 (Free via OpenRouter)",
      "provider": "openai",
      "model": "meta-llama/llama-3.1-8b-instruct:free",
      "apiBase": "https://openrouter.ai/api/v1",
      "apiKey": "sk-or-v1-your-key-here"
    }
  ]
}

Save the file and Continue will reconnect automatically.

Autocomplete: Just start typing in any file — suggestions appear automatically. Press Tab to accept.

Inline edit:

1. Select some code
2. Press Ctrl+I (or Cmd+I on Mac)
3. Type your instruction: "Add error handling to this function"
4. Press Enter — the AI rewrites the code inline

Chat sidebar:

1. Press Ctrl+L to open the chat panel
2. Ask questions about your code: "What does this file do?"
3. Reference files with @filename