Paste any text to estimate how many tokens it uses before you send it to an AI model. Everything runs in your browser and nothing you paste is stored or sent anywhere.
Last updated: October 2, 2026
Token counts are estimates for English text. Exact counts depend on each model’s tokenizer.
How the estimate works
AI models split text into tokens: short words, parts of longer words, numbers and punctuation. For typical English text, two common rules of thumb are about four characters per token, or about three-quarters of a word per token. This tool calculates both and shows the average, plus the range between them.
Real counts vary by model. Code, other languages, numbers and unusual words usually take more tokens than plain English prose. If you need an exact figure, check the token count your AI provider returns with each response. To learn more, read How AI API Pricing Works.
When counting tokens helps
- Checking a long document before pasting it, to see if it fits the model’s context window.
- Trimming a system prompt that is sent with every request.
- Budgeting an app: use your token counts in the AI API Cost Calculator to estimate monthly spend.
Frequently asked questions
Is my text saved anywhere?
No. The counting happens in your browser. Your text is not sent to our server or to any AI provider.
Why don’t my numbers match my provider’s count?
Every model family uses its own tokenizer, so the same text can produce different counts. This tool gives a quick estimate, which is usually close enough for planning and budgeting.
Do output tokens count too?
Yes. You pay for the text you send and the text the model writes back, usually at a higher rate for output. This tool counts the text you paste; use the cost calculator to include output.