Inference
Definition: Inference is when an already-trained model produces an answer from an input — running the model, as opposed to training it.
It's what you pay for per usage via an API. Its cost and speed depend on the model and hardware.
Definition: Inference is when an already-trained model produces an answer from an input — running the model, as opposed to training it.
It's what you pay for per usage via an API. Its cost and speed depend on the model and hardware.