Pricing for Huggingface Endpoint

I am a bit confused about the pricing model. Let’s say I deploy a model on a CPU Basic machine ($0.06/hour). So do I pay as long as the model is deployed or do I pay only for the compute time (e.g. I make 2 requests and every request takes 10 seconds to run, so do I only pay for the 20 seconds). I ask because I want to do a hobby project but don’t want to pay a lot for it. Alternatives like cerebrium only offer 3 models for their starter version :')

You can find the information in the documentation: Pricing