Online Token Counter for GPT and Claude LLMs
Estimate the number of tokens (and characters/words) of a text for LLMs (GPT, Claude), in your browser.
Heuristic estimate (~4 characters/token). The exact count depends on the model’s tokenizer.
🔒 100% client-side — no data sent
Estimate the number of tokens, words and characters in your text before sending it to an LLM such as GPT or Claude. Perfect for anticipating API costs and staying within the context window. Everything runs 100% in your browser, so your text never leaves your machine.
What is it for?
- ▸ Check that a prompt fits within a model's context window
- ▸ Estimate the cost of an API call billed per token
- ▸ Compare the length of several prompt versions
- ▸ Split a long document into model-friendly chunks
FAQ
What is a token in a language model?
A token is a unit of text (a word, part of a word or a character) that the model processes. On average, one token corresponds to about 4 characters or 0.75 words in English.
How many tokens are in 1000 words?
Roughly 1,300 to 1,400 tokens for English text, slightly more for French. The counter gives you an accurate estimate based on your actual text.
Is the token count the same for GPT and Claude?
No, each model family uses its own tokenizer, so results can vary slightly. This tool provides a reliable estimate to frame your usage.