Technique Updated 2026-04
Token
Definition
A token is the basic unit processed by an LLM. It's a piece of word, punctuation or character that the model uses to understand and generate text.
See also in the glossary
L
LLM (Large Language Model)
An LLM is an AI model trained on billions of texts, capable of understanding and generating human language.
P
Prompt
A prompt is the instruction or question you give an AI to get a response. It's the interface between you and the model.
C
Context Window
The context window is the maximum amount of text an LLM can process in a single request.
A
AI Inference
Inference is the process of using a trained AI model to generate predictions or responses from new data.
Tools that use token
Frequently Asked Questions
How many words is a token?
On average, 1 token ≈ 0.75 words in English. The word 'hello' is 1 token, 'artificial' is 3 tokens. Non-Latin languages consume more tokens per word.
Why do tokens matter?
LLMs charge by token usage. The context window (what the model can read at once) is measured in tokens. Claude has 200K tokens of context, Gemini 1M.
