← Concept IndexDEFINITION WHY IT MATTERS COMMONLY CONFUSED WITH
Inference — running the model
Also called: using vs training, prompt to completion, serving
Inference is what happens every time you use a model: your prompt goes in, the trained weights are run over it, and a completion comes out. No learning occurs — the weights are fixed.
Separating inference from training clears up most confusion: your prompts don't teach the model, each request is (by default) independent, and the cost and speed you experience are inference costs, paid per use.
Training. Training builds the model once, at great expense; inference is the cheap, repeated act of using it — and it's the only part most people ever touch.