0 XP

Tokenisation · What a token is

The unit of reading

A model never sees your words

Before anything else happens, your text is cut into tokens. Tokens are the only pieces a model can read. Some are whole words. Many are fragments.

un373bel9880ievable45794
3 tokens: un / bel / ievable

3 tokens · o200k_base

Counts come from the real o200k_base vocabulary — the one GPT-4o reads with. Another model will split the same text differently. tiktoken