Opencode Configuration Official guide: https://opencode.ai/v2/docs CLI Version Linux & macOS Download cli version: curl -fsSL https://opencode.ai/v2/install | bash open the application on the terminal with the command: opencode Then exit from the application with the command \quit or by pressing Ctrl+C Open the configuration file .config/opencode/opencode.jsonc in your file explorer and replace its contents with the new settings below. In the "apiKey" line insert your API key { "$schema": "https://opencode.ai/config.json", "provider": { "elettragateway": { "name": "ElettraGateway", "npm": "@ai-sdk/openai-compatible", "options": { "baseURL": "https://llm-api-gw.elettra.eu/v1", "apiKey": "sk_ePkBU....." //insert your apiKey }, "models": { "balanced": { "name": "balanced", "limit": { "context": 262144, "input": 262144, "output": 100000 }, "modalities": { "input": ["text", "image"] } }, "top": { "name": "top", "limit": { "context": 1000000, "input": 1000000, "output": 100000 }, "modalities": { "input": ["text", "image"] } }, "fast": { "name": "fast", "limit": { "context": 131000, "input": 131000, "output": 100000 } } } } } } In a terminal, navigate to the directory of the project you want to work on. Launch Opencode in that directory and type /models, then choose top, balanced, or fast based on your needs. You’ll now have access to everything you need within the project. Windows We suggest you use the Windows Subsystem for Linux (WSL) After activating it, use the same procedure as described in Linux & macOS to install and use it! DESKTOP Version Tutorial: https://kb.elettra.eu/books/scientific-and-quantum-computing/page/opencode-desktop-configuration