LLM Providers

Jan Setup

Connect MLJAR Studio to a local model served by Jan. Use the Jan provider preset and the API key configured in your Jan server.

Before you start

Activate a lifetime MLJAR Studio license to configure your own AI provider. Open AI Provider Settings in MLJAR Studio to choose a provider.

1. Start the model server

Install Jan Desktop and download a local chat model.
Open Settings → Local API Server. Configure a server API key and click Start Server.
Keep the host, port, and API prefix available so you can match them in MLJAR Studio.

Follow the Jan Local API Server guide for configuration. Jan can disable authentication, but the MLJAR Studio Jan preset requires a key: configure one in Jan and use the same value in Studio.

2. Connect MLJAR Studio

In AI Provider Settings, select Jan from Provider.
Set Base URL to http://127.0.0.1:1337/v1 for the default local setup. Use the actual host and port if you changed them. Keep the /v1 suffix.
Enter the key from Jan in Jan server API key. This is the key for your local server.
Wait for models to load automatically, or click Refresh models. Choose your chat model from Model.
Click Test connection, then Save provider once the test succeeds. Changing settings requires another test.
Confirm the success message and the active provider in the sidebar.

Test a notebook request

After saving, send a short request in your notebook. Test connection checks access to the model list and the selected model; a successful test does not guarantee that every model supports the chat or tool features your workflow needs.

Where requests run

The default loopback address connects to the server on the machine running the MLJAR notebook backend. A remote server URL sends prompts and notebook context to that server. Use HTTPS for remote connections. For local inference, keep both the endpoint and model execution on your machine.

Troubleshooting