Choose your AI model

Orso Connect runs on Windows and lets you pick the AI engine that fits your privacy needs. You can use a cloud provider, a local model, or the built-in option without extra setup.

Select your model provider

Cloud AI provider

Connect a standard API endpoint to use a large cloud model. Your prompts travel to that provider, so sensitive data leaves your machine. This option is ideal for complex analysis when you do not mind the network transfer. The Test button checks an endpoint, shows response time and the context window.

Local PC model

Run a model directly on your Windows computer using your own hardware. Nothing leaves the machine when you use a local model.

Built-in model

Use the built-in model that is ready to use without your own endpoint.

Verify your connection

Press the Test button to check your endpoint. The tool shows the response time and the context window size. This helps you confirm that the model is reachable and ready for your api security assessment tasks.

Match the model to the task

Send complex refactors or logic checks to a bigger model using run_on_model. Use smaller models for simple edits to save resources. The agent orchestrates these steps automatically while you review the results.

Quality varies between models, so always review the output. Use Ask first mode to pause before changes. Check the file diff carefully before accepting any modifications to your code or configuration files.