Inference
Running a trained model to get answers, as opposed to training it. Most of the world's AI computing is now inference.
Also: serving
Inference is what happens every time someone sends a prompt: the model reads the text, in a step called prefill, then generates the answer token by token, in a step called decoding. Prefill runs in parallel and is limited by raw compute; decoding is sequential and limited by how fast weights and cached keys can be read from memory. Providers measure inference by time to first token, tokens per second and cost per million tokens, and use batching, caching, quantisation and speculative decoding to improve all three.