TOKENS // AI LITERACY · MODULE
PROTOCOL — you ship it, you own it
Field Manual · The Unit of Everything

AI doesn't read words.
It reads tokens.

Before a model can think about your sentence, it shatters it into small chunks called tokens. Tokens are how models read, how they write — and how every bill is counted.

PARSE IT YOURSELF
Interactive · The Tokenizer

Type anything. Watch it break apart.

Each block below is one token. Notice what happens: common words stay whole, long or unusual words get chopped into pieces, and spaces ride along inside the blocks. Try the presets, or write your own.

0
Tokens
0
Characters
0
Words
Whole word Word-piece (a split) Number Punctuation Emoji / symbol

␣ marks a space living inside a token. Emoji and symbols often cost 2+ tokens (look for the ×2).
This is a teaching simulator using a simple rule. Real models use a learned tokenizer, so exact splits vary — but the patterns you see here are real.

Quick Math · Rule of Thumb

Tokens aren't words — but you can estimate.

For everyday English, one token lands at roughly 4 characters, or about ¾ of a word. So 1,000 tokens ≈ 750 words ≈ a page and a half.

1 TOKENthe unit
4 CHARSletters & spaces
¾ WORDaverage english
cat1 token
language1 token
antidisestablishmentarianism7 tokens
🎮2 tokens
The Meter · How AI Is Billed

Every token is a coin.

You pay for tokens going in (your prompt + everything the model can see) and tokens coming out (the reply). Output is the pricey side — usually 5× the input rate. Pick a model, dial the size of the job, and watch the cost move.

Cost of this exchange
$0.00
on Sonnet 5
Same job, three models
Save Point · What To Remember
01

Tokens, not words

Models chop text into tokens. Common words are one token; long or rare words get split into pieces.

02

Everything counts

Spaces, punctuation, and even a single emoji all become tokens. Nothing is free.

03

~4 chars ≈ 1 token

A rough ruler for English: 1,000 tokens ≈ 750 words. Handy for guessing a bill before you press send.

04

The meter runs both ways

You pay for the prompt in and the reply out — and output costs about 5× more. Cheaper model = smaller bill.

Know the cost of what you build, and you stay in the driver's seat.
Understanding tokens is understanding the real price of every prompt you ship. That's the whole game: you ship it, you own it.