Token

AI basics

Why it matters

Models don't see letters or whole words; they see tokens. A short common word is often one token, while a long or rare word may be split into several, and spaces and punctuation count too.

Tokens matter because they are the unit for everything practical: how much fits in the context window, how fast a model answers and what developers pay. When a price is listed per million input and output tokens, that is the meter running.

Related terms

Context window

How much text a model can consider at once, measured in tokens.

API

A way for software to call a model directly, instead of through a chat app. Grok's is documented at docs.x.ai.

Inference

Inference is running an already-trained AI model to produce an answer, such as a chatbot reply. It is separate from training, which builds the model, and it runs for every user request.