AI Word, Character & Token Counter
Count words, characters and tokens, and see how much of ChatGPT’s, Claude’s and Gemini’s context window your text would use.
Tokens to words converter
OpenAI’s rule of thumb for English: 100 tokens ≈ 75 words. Pages assume 500 words per single-spaced page.
| Tokens | ≈ Words | ≈ Pages |
|---|---|---|
| 1,000 | 750 | 2 |
| 10,000 | 7,500 | 15 |
| 100,000 | 75,000 | 150 |
| 128,000 | 96,000 | 192 |
| 200,000 | 150,000 | 300 |
| 1,000,000 | 750,000 | 1,500 |
What is a token?
AI chatbots don’t read text word by word. They split it into tokens: common words are usually one token, while longer or rarer words are split into several pieces. Spaces, punctuation and capital letters all affect how text is split. Limits, speed and API prices are all measured in tokens, which is why it helps to know how many your text uses.
How this counter works
- Tokens are counted with OpenAI’s
o200k_basetokenizer, the one used by GPT-4o and the GPT-5 family, running in your browser. - Words and characters use your browser’s built-in text segmentation, so languages written without spaces (such as Chinese or Japanese) and emoji are counted properly.
- Reading time assumes 238 words per minute, the average silent reading speed for English non-fiction found in a 2019 review of reading studies (Brysbaert). Speaking time assumes 150 words per minute.
- Context windows come from each provider’s own pages and are re-checked regularly. See our methodology.
Frequently asked questions
How many words is 1,000 tokens?
About 750 words of English. OpenAI’s rule of thumb is that one token is roughly four characters, or three quarters of a word, so 100 tokens is about 75 words. The real number depends on the text: code, numbers, unusual words and most non-English languages use more tokens per word.
How many words is 1 million tokens?
Roughly 750,000 words of English, or around 1,500 single-spaced pages at 500 words a page. Google gives a similar figure for Gemini’s 1 million token context window: about 1,500 pages of text.
Is the token count exact?
For ChatGPT models that use OpenAI’s o200k_base tokenizer (GPT-4o and the GPT-5 family), yes: we run the same tokenizer in your browser. Claude and Gemini use their own tokenizers, which aren’t available to run in a browser, so for them the count is an approximation and bars are marked “≈”. Chatbots also add their own hidden instructions, so the space you really have is a little smaller than the published window.
What is a context window?
The maximum amount of text, measured in tokens, that a chatbot can consider at once. It includes your messages, the chatbot’s replies and any files you add. When a conversation goes past it, the chatbot starts to lose track of the earliest parts.
Is my text sent anywhere?
No. Counting happens entirely in your browser. Your text isn’t uploaded or stored.