Glossary
What Is a Token (AI)? Definition and Example
A token is a small piece of text, often part of a word, that an AI model reads and writes. In English, one token is roughly three quarters of a word.
What it means
Models count text in tokens rather than words. Tokens affect how much fits in the context window and, for some services, how usage is priced. Common words are often one token, and rare words are split into several.
Example
A 750-word article is roughly 1,000 tokens as a rough rule of thumb.
Why it matters
Understanding tokens helps you estimate whether a document fits and what a task might cost on paid usage.
Related terms
- Context Window: A context window is the amount of text an AI model can consider at once, including your prompt, any documents.
- Large Language Model (LLM): A large language model, or LLM, is an AI system trained on huge amounts of text to understand and generate.
- Prompt: A prompt is the instruction or question you give an AI tool. A clear prompt states the role, the context, the.
Learn this live, for free
Join the free 90-minute live masterclass, every Friday, 7 PM IST (India) or 7 PM ET (everywhere else). No tech background needed.
Register for the masterclass nowEducation only. This glossary is general information, not financial, legal or career advice.
Frequently asked questions
Is a token the same as a word?
No. A word can be one or several tokens.
Why do tokens matter?
They limit how much text fits at once and can affect pricing.
Do I need to count tokens?
Not for casual use. It matters for long documents and paid usage.