What does “Inference Endpoint” mean?

A structured way for one software system to send requests to and receive responses from another system.

The runtime phase where a trained model generates predictions or outputs.

Pricing where costs scale with API calls, tokens, inference time, or consumed compute.

The amount of processing power consumed while producing each response.

A model that makes predictions through a sequence of if-then feature splits.

Combining predictions from multiple models to improve robustness or accuracy.