Use LM Studio in OpenCode

Steps

1. 1
   Step 1.

   Add the LM Studio provider to the opencode.json file in your project directory (verbatim from the OpenCode LM Studio section).

   JSON

   Copy

   {
     "$schema": "https://opencode.ai/config.json",
     "provider": {
       "lmstudio": {
         "npm": "@ai-sdk/openai-compatible",
         "name": "LM Studio (local)",
         "options": {
           "baseURL": "http://127.0.0.1:1234/v1"
         },
         "models": {
           "google/gemma-3n-e4b": {
             "name": "Gemma 3n-e4b (local)"
           }
         }
       }
     }
   }

2. 2
   Step 2.

   Make sure the LM Studio server is running (LM Studio docs).

   Terminal

   Copy

   lms server start --port 1234

3. 3
   Step 3.

   Optional: list the model identifiers LM Studio is serving, so you can use them as keys under models (LM Studio docs).

   Terminal

   Copy

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