The unit models actually process.
THE DEFINITION
A fragment of text. Roughly a word, sometimes part of one, sometimes punctuation.
WHY IT MATTERS
Context limits are measured in tokens API pricing is per token Response length limits are in tokens
A ROUGH GUIDE
For English, one token is approximately three-quarters of a word.
A thousand words is roughly 1,300 tokens.
WHY THE RATIO VARIES
Languages other than English frequently use more tokens per word Unusual words and names split into more Code tokenises differently from prose
WHAT THIS MEANS FOR COST
A long prompt costs more every time it is sent.
In a system sending the same lengthy instructions repeatedly, that dominates.
WHEN YOU NEED TO THINK ABOUT IT
Building anything with an API. For ordinary chat use, rarely.
RELATED TERMS
Context window, API, pricing.
