AI BasicsUpdated 2026-04-14

What is a token in AI?

A simple explanation of what tokens are in AI and why they matter for prompts, responses, and costs.

In simple terms

A token is a small chunk of text that an AI model reads and processes.

AI models do not read your message exactly the way a human does.

They break text into smaller parts called tokens.

A token can be a whole word, part of a word, punctuation, or a small text chunk.

The more tokens a task uses, the more context and cost it may involve.

Why it matters

Tokens affect model limits, response length, speed, and pricing. They are one of the most important practical concepts in AI usage.

Related explainers

Continue learning from here

View all in AI Basics
FAQ

Common questions

What is a token in simple terms?

A token is a small chunk of text that an AI model processes.

Why do tokens matter?

Tokens affect model limits, prompt size, response length, and pricing.

What should I learn after tokens?

A good next step is to learn about context windows and LLMs.