Count your tokens
| Model | Context window | Window used | Cost as input |
|---|
Estimate only. Real counts differ by tokenizer, language and content type.
Rules of thumb
- 1 token is about 4 characters or 0.75 words of English.
- 100 tokens is about 75 words, a short paragraph.
- 1,000 tokens is about 750 words, roughly a page and a half.
- Code and non-English text use noticeably more tokens per word.
Planning a budget? Feed your token numbers into the API cost calculator.
Frequently asked questions
What is a token?
A token is a chunk of text a model reads or writes: a short word, part of a longer word, or punctuation. In English, one token is about four characters or three quarters of a word.
How accurate is this token counter?
It is an estimate. It blends a character-based and a word-based rule that track real tokenizers closely for ordinary English prose. Code, other languages and unusual symbols usually use more tokens per character, so treat the number as a guide and leave headroom.
Do GPT and Claude count tokens the same way?
No. Each provider uses its own tokenizer, so the same text can differ by roughly 5 to 15 percent between families. That is why the tool shows a range.
What is a context window?
The context window is the most text a model can consider at once, including your prompt, the conversation so far and its reply. The tool shows how much of each model window your text would fill.