Learn · AI fundamentals
Tokens are the chunks of text an AI model reads and writes. A token is roughly three-quarters of a word in English, so 1,000 tokens is about 750 words. They matter because AI pricing and limits are measured in tokens, not words or characters.
Both your input and the model's output count as tokens, and you pay for both. A long document you paste in plus a long answer back can add up fast. Understanding tokens is how you predict and control what an AI feature will cost to run.
Tokens also define how much a model can consider at once. That limit is called the context window, and it's measured in tokens too.
Updated July 2026
Related
A context window is the maximum amount of text an AI model can hold in mind at once, counted in tokens. It includes your prompt, any documents you attach, the conversation so far, and the answer being written. Once you exceed it, the model loses track of the earliest content.
Two costs stack up: the usage cost of the AI model (billed per token) and the cost of building the product around it. As of July 2026, mid-tier models run roughly $2 to $3 per million input tokens and $10 to $15 per million output tokens, with budget models under $0.50 and frontier models higher.
An AI model breaks your input into tokens (word pieces), then predicts the most likely next token, adds it, and repeats, one token at a time, until the answer is complete. Every word it produces is a probability-weighted guess informed by patterns it learned during training.