Home / Token counter
Token counter
Paste your text to estimate how many tokens it is and what it costs to send. The text stays in your browser.
Prices checked October 13, 2026
Example text. Replace it with your own.
| Model | Tokens (est.) | Cost |
|---|
Claude 4.7 and later models get 30% more tokens here, because Anthropic says their newer tokenizer produces about 30% more tokens for the same text than its earlier one. The answer the model writes back is billed separately, at the output price.
Words, characters and tokens
Google’s rule of thumb for Gemini models: one token is about 4 characters, and 100 tokens is about 60 to 80 English words. So:
- 1,000 words is about 1,250 to 1,670 tokens
- 1 million tokens is about 600,000 to 800,000 words
- a 300-page book of about 90,000 words is about 110,000 to 150,000 tokens
Other languages, code, numbers and tables usually take more tokens per word than plain English. Each company splits text its own way, so the same text is a different number of tokens on different models. Anthropic says its Claude 4.7 and later models produce about 30% more tokens for the same text than its earlier tokenizer.
Getting an exact count
This page estimates. For an exact count, ask the company that runs the model:
- Claude: Anthropic’s token counting endpoint counts a request before you send it, and each response reports the tokens it used.
- Gemini: Google’s count tokens guide shows how to count with the API.
Once you know your tokens per request, put them into the cost calculator to compare a month across models.