Tokens
The unit a language model processes. A token can be a whole word, a word piece, punctuation, whitespace, a number, or part of code. For plain English, 1,000 tokens is often about 700 to 800 words.
Token Counter
Paste any text to count its tokens, words, and characters at once, in your browser. It is a simple way to see how your writing maps to the tokens a model actually reads. Counts are Exact for OpenAI and clearly labeled Estimated for other providers.
Private by default · No signup · Local token counting where supported · Exact and estimated results clearly labeled
Your text is processed in your browser for supported local tokenizers. We do not store pasted prompts.
Tokens vs words vs characters
These three counts measure the same text in different ways. The counter shows all of them together so you can compare.
Words
A human writing unit. The counter splits your text on spaces to count words. One short word is usually one token, but longer or unusual words can split into several tokens.
Characters
Every letter, space, and symbol. Character counts help with hard input limits, but models read and bill by tokens, not characters — so watch the token count for cost and context fit.
Token counter FAQ
Beginner answers about tokens, words, characters, and counting.
What is an LLM token?
A token is a chunk of text a language model reads or writes. A token can be a whole word, part of a word, punctuation, whitespace, a number, or part of code.
Are tokens the same as words?
No. Words are a human writing unit. Tokens are a model processing unit. One short word may be one token, while a longer word, code snippet, emoji, or non-English text may split into multiple tokens.
How many words is 1,000 tokens?
For ordinary English prose, 1,000 tokens often lands around 700 to 800 words. The real number changes with language, formatting, code, JSON, punctuation, and the tokenizer used by the selected model.
Can I count tokens for code or JSON?
Yes. You can paste code, JSON, Markdown, prose, or mixed documents. The calculator also shows word and character counts so you can compare text shape alongside tokens.
Why do different models show different token counts?
Different model families use different tokenizers. The same prompt can split into different token pieces for OpenAI, Claude, Gemini, Llama, Mistral, DeepSeek, or Grok models.
Is this calculator exact?
It is Exact only for supported OpenAI encodings counted locally with gpt-tokenizer. Other providers are labeled Estimated and use an OpenAI-compatible tokenizer as a proxy, so real provider counts can vary.
Is my prompt uploaded to your server?
No. Pasted text is processed in your browser. This site has no accounts, saved prompt history, analytics scripts, ad scripts, or server-side text processing.
More token tools
Ready to plan cost and compare models? Try the LLM API cost calculator or the full LLM token calculator.