Token counter

Estimate tokens for prompts, documents and code. Exact counts differ by model, so use your provider's tokenizer or token-counting API when you need precision.

Estimated tokens

~4 chars/token rule

Words

103

Characters

Paste·or·type·any·text·here·to·estimate·how·many·tokens·it·uses.·Try·code,·numbers·or·another·language!

Why token counts matter

LLM pricing, context windows and output limits are all measured in tokens. In English, one token is roughly four characters or three-quarters of a word. Code, numbers and many non-English languages usually need more tokens for the same content.

Turn tokens into dollars with the LLM cost calculator →

▶Practice it hands-onTokens: What Models Actually Read