Connect an AI model

Choose which AI model Zenix Cloud uses. You pick the endpoint, the provider, or the built-in option. The Test button shows response time and context window before you begin.

Three ways to connect

Cloud AI provider

Point Zenix Cloud to a standard API endpoint from a provider you choose. A cloud AI provider may charge separately for usage. The prompt leaves your machine and travels to that provider.

Local model

Run a model directly on your Windows PC. No network traffic leaves your machine for the model inference. Your chats and files stay private. This mode suits users who value strict privacy or work in low-bandwidth environments. You manage the model binary yourself.

Built-in model

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

Test your connection

Press the Test button to verify your chosen endpoint. The tool shows the response time and the context window size. This check happens before any real work begins. It confirms that the model is reachable and responsive. You can adjust settings based on these results.

Pick the right model

Send hard steps to a bigger model using run_on_model. Use smaller models for simple edits. The agent orchestrates the work. You decide which model handles which task.

In Ask first mode the agent pauses before actions that change something; in Auto-run it acts at once; the reader reviews the diff.