How to set up Continue.dev with LM Studio

What this does

Integrates Continue.dev with the LM Studio local inference server so that AI-assisted coding uses models served through LM Studio's OpenAI-compatible API. After completion, Continue routes completions through the LM Studio backend.

Steps

1. Identify the LM Studio server address. In LM Studio, open the Server tab. The default address is http://localhost:1234.

2. Open the Continue config file. Click the gear icon in the Continue sidebar or open ~/.continue/config.json.

3. Add an OpenAI-compatible model entry pointing to LM Studio.

   {
     "title": "LM Studio",
     "provider": "openai",
     "model": "local-model",
     "apiBase": "http://localhost:1234/v1"
   }
   

4. Set as the default model. Move the entry to the top of the models array.

5. Save the config and reload VS Code. After saving, reload the window so the new backend is recognized.

Verification

curl -s http://localhost:1234/v1/models | python3 -m json.tool | head -20
# Expected: JSON listing model(s) served by LM Studio

Common failures

• LM Studio server not started — The server must be running from the Server tab. Restart it if the process was closed.
• Port conflict — Another application uses port 1234. Change the LM Studio server port and update the config.
• Model not loaded — Load a model in the Local Server tab first.
• API path mismatch — LM Studio uses /v1/chat/completions. The trailing /v1 in apiBase is required.
• Config parse error — JSON syntax mistakes break the file. Validate the JSON before saving.

Operator checkpoint

Before treating this as solved, write down the local runtime, model or package version, hardware/backend if relevant, and the verification output. This keeps the guide useful as a Will-It-Run style decision instead of a one-off command transcript.

Related guides

• How to configure Continue.dev with Ollama
• How to use Continue.dev with custom model endpoints
• Course Ollama Deep Dive