Use Gemini in OpenCode

Steps

1. 1
   Step 1.

   Get a Gemini API key from Google AI Studio (https://aistudio.google.com/apikey).

2. 2
   Step 2.

   In OpenCode, run the /connect command, scroll down to Other, enter a unique provider ID, then enter your API key (OpenCode docs, Custom provider steps 1-3).

   Terminal

   Copy

   $ /connect
   
   ┌  Add credential
   │
   ◆  Select provider
   │  ...
   │  ● Other
   └

3. 3
   Step 3.

   Create or update opencode.json in your project directory. OpenCode documents this shape; the baseURL and model id below are Google's documented OpenAI-compatible endpoint and model id substituted into it (provider ID 'gemini-openai' is an arbitrary example and must match the ID you entered in /connect).

   JSON

   Copy

   {
     "$schema": "https://opencode.ai/config.json",
     "provider": {
       "gemini-openai": {
         "npm": "@ai-sdk/openai-compatible",
         "name": "Google Gemini",
         "options": {
           "baseURL": "https://generativelanguage.googleapis.com/v1beta/openai/"
         },
         "models": {
           "gemini-3.8-flash": {
             "name": "Gemini 3.8 Flash"
           }
         }
       }
     }
   }

4. 4
   Step 4.

   Run the /models command; the custom provider and models appear in the selection list. To make it the default, set model to provider_id/model_id (OpenCode docs: 'the provider_id is key from the provider part of your config, and the model_id is the key from provider.models').

   JSON

   Copy

   {
     "$schema": "https://opencode.ai/config.json",
     "model": "gemini-openai/gemini-3.8-flash"
   }