Please help! Scaling up from 0 programmatically

Hello! I am using the Inference Endpoints provided by Hugging Face.
I would like to know how to programmatically pause, resume, and scale up from 0.

I want my user to be able to tell if the endpoint is up and start it if it is scaled to 0. Currently, sending a request via a basic query just returns a server error.

please help!

Hi,

See the docs here: Inference Endpoints