Connecting in OpenCode

1. Install OpenCode

2. Create the file opencode.json in the project root and fill it with the contents below

   opencode.json

   {
     "$schema": "https://opencode.ai/config.json",
     "provider": {
       "explyt": {
         "npm": "@ai-sdk/openai-compatible",
         "name": "explyt",
         "options": {
           "baseURL": "<YOUR_URL>"
         },
         "models": {
           "auto": {
             "limit": {
               "context": 372000,
               "output": 32768
             }
           },
           "Anthropic/opus-5": {
             "limit": {
               "context": 465536,
               "output": 65536
             }
           },
           "OpenAI/gpt-5.6-sol": {
             "limit": {
               "context": 372000,
               "output": 32768
             }
           }
         }
       }
     }
   }

   • Replace <YOUR_URL> with the OpenAI-compatible URL issued to you
     • If you see these instructions but do not have an OpenAI-compatible URL, contact your organization's administrator
   • The models block lists the main recommended models. To get the full list of models, contact your organization's administrator or open <YOUR_URL>/models
   • To use another model, add it to the models block following the same pattern

3. Start OpenCode:

   opencode

4. Type /connect

   

5. Choose explyt (or another name you specified in the config)

   

6. Enter the API key issued to you

   • If you see these instructions but do not have an API key, contact your organization's administrator

   

For errors, see Error messages.