Skip to content
Glossary

Token

A plain-language explanation for writers, not engineers.

What It Means

The basic unit of text that AI models process. A token is typically a word or part of a word - "writing" is one token, "unbelievable" might be split into "un," "believ," and "able." AI models process, generate, and price their services in tokens rather than words.

Why writers should care: When someone says a model "can handle 100,000 tokens," they're describing the amount of text it can process at once - roughly 75,000 words.

In Context

When an AI writes, it generates one token at a time - each new piece chosen based on all the pieces that came before. A single article might involve thousands of these sequential predictions. Understanding tokenization helps writers grasp why detection tools focus on statistical patterns: every token choice leaves a trace of the probability distribution that produced it, creating a subtle signature that detectors try to read.

Related Terms

← Back to the Full Glossary

The Sunday Letter

Every Sunday, one email. A featured essay, a case study update, a craft tip, and a writing prompt. No AI wrote this.