Skip to content

How LLM Tokens Work Explained

See text become tokens — why English runs ~4 characters per token, why code and JSON cost more, and why CJK text is the densest of all.

Animated diagrams · 2 flows

Compare all 2

Sort by any column to find the right fit. Click a name to open its details.

One Text, Three Ratesone-wayinstantconstantin-memoryper-line classificationestimating mixed documents
Text → Tokensone-wayinstantmicrosecondsin-memoryvocabulary merge tablepredicting usage before you send