Core concepts
Tokens
The basic units of text that AI models read and write — roughly ¾ of a word each. Models are priced and limited by token count.
01 ——
In plain English
Tokens are the chunks that AI models break text into before processing it. A token is roughly 3–4 characters or about ¾ of an average English word.
Examples:
- "Hello" = 1 token
- "ChatGPT" = 2 tokens (Chat + GPT)
- "unbelievable" = 3–4 tokens
Why tokens matter:
- Pricing — AI APIs charge per 1,000 tokens (input + output)
- Context limits — every model has a maximum token count per request (its context window)
- Speed — generating tokens takes time; more tokens = slower response
A rough rule of thumb: 1,000 tokens ≈ 750 words ≈ a few paragraphs of text.
02 ——
Related terms
LLM
Large Language Model — the type of AI behind tools like ChatGPT and Claude, trained to understand and generate text.
Context Window
The maximum amount of text (tokens) an AI model can read and remember at once during a single conversation.
Inference
The process of running a trained AI model to generate a response — as opposed to training the model.
Prompt Caching
A feature that stores parts of a prompt the model has already processed, making repeat or follow-up requests much faster and cheaper.
Back to glossaryLast reviewed May 2026