lms server start

The lms server start command launches the LM Studio local server, allowing you to interact with loaded models via HTTP API calls.

Flags

--port (optional) : number

Port to run the server on. If not provided, uses the last used port

--cors (optional) : flag

Enable CORS support for web application development. When not set, CORS is disabled

--bind (optional) : string

Network address to bind the server to. Use "0.0.0.0" to listen on all IPv4 interfaces, or "127.0.0.1" (default) for localhost only. Can also be set via the LMS_SERVER_HOST environment variable.

Start the server

Start the server with default settings:

lms server start

Specify a custom port

Run the server on a specific port:

lms server start --port 3000

Enable CORS support

For usage with web applications or some VS Code extensions, you may need to enable CORS support:

lms server start --cors

Warning - Security Risk

Enabling CORS can expose your server to security risks; we recommend enabling authentication. Only do this if you know what you're doing.

Bind to a network address

To make the server available on your local network, run:

Heads Up

Any bind other than 127.0.0.1 exposes the server beyond localhost; we recommend enabling authentication. Only do this if you know what you're doing.

lms server start --bind 0.0.0.0

Check the server status

See lms server status for more information on checking the status of the server.