Use LM Studio in GitHub Copilot

Steps

1. 1
   Step 1.

   Start LM Studio's local server (LM Studio docs).

   Terminal

   Copy

   lms server start --port 1234

2. 2
   Step 2.

   In VS Code, open the Language Models editor: select Manage Language Models (gear icon) from the language model picker, or run Chat: Manage Language Models from the Command Palette.

3. 3
   Step 3.

   Select Add Models, then select Custom Endpoint from the list. Enter a group name, then a display name and API key for the endpoint.

4. 4
   Step 4.

   Select the API type: Chat Completions, Responses, or Messages. Make sure the model supports this API type. VS Code opens a chatLanguageModels.json file where you configure the model details.

5. 5
   Step 5.

   Example model entry, combining VS Code's documented Custom Endpoint schema with LM Studio's documented chat completions URL and model id (illustrative, not copied from either page as a whole).

   JSON

   Copy

   [
     {
       "name": "LM Studio",
       "vendor": "customendpoint",
       "apiKey": "${input:lmstudioApiKey}",
       "apiType": "chat-completions",
       "models": [
         {
           "id": "openai/gpt-oss-20b",
           "name": "gpt-oss-20b (LM Studio)",
           "url": "http://localhost:1234/v1/chat/completions",
           "toolCalling": true,
           "vision": false,
           "maxInputTokens": 28000,
           "maxOutputTokens": 4000
         }
       ]
     }
   ]

6. 6
   Step 6.

   Optional: list the model identifiers LM Studio is serving (LM Studio docs).

   Terminal

   Copy

   curl http://localhost:1234/v1/models