Connect an AI Model

DevSignal connects to AI models through a cloud API, a local PC model, or the built-in option.

Choose your model source

Cloud API provider

Use a standard API endpoint to access cloud models. Your prompts and file text travel to that provider. This works for complex logic. The provider may charge separately. You control the endpoint.

Local PC model

Run a model directly on your Windows PC. Nothing leaves your machine when you use this option. Privacy is highest because your game files and notes stay local. You need enough hardware power for smooth operation.

Built-in model

The built-in model is ready to work without your own endpoint. It is the easiest way to start modding immediately. You do not need to configure any extra keys or URLs.

Test your connection

Press the Test button to check your chosen endpoint. The app shows the response time and context window details. This helps you verify that the model is reachable and ready for your Elden Ring tasks.

Pick the right model

Use a bigger model for refactors or complex logic. Use a smaller model for small edits. You can send a hard step to a bigger model using run_on_model. This helps you keep a plain text offline mod notes file with invented names starting with Example, one comment line saying offline play only, and a last comment line with a placeholder date.

Quality varies between models. Always review the diff in Ask first. This mode pauses before actions that change something. You see the exact text changes before they are applied to your files.