LLM Token Counter

Paste text to count its tokens, words, and characters. The tokenizer runs in your browser, so your text is not uploaded.

Loading tokenizer…

Frequently asked questions

How many tokens is my text?

Paste the text into the counter above. As a rule of thumb, one token is about four characters of English, so 1,000 tokens is roughly 750 words. Code and non-English text usually use more tokens per word.

Which tokenizer does this token counter use?

It uses o200k_base, the tokenizer used by current OpenAI model families. The count is exact for those models and a close estimate for models from other labs, which use their own tokenizers.

Is my text sent to a server?

No. The tokenizer is downloaded to your browser and the count is computed there. The text you paste never leaves your device.

Why do token counts differ between models?

Each model family splits text with its own tokenizer, so the same text produces a different number of tokens on different models. For billing, rely on the usage figures returned by the API.

Need the price as well? The token cost calculator turns a token count into a cost for each model, and the context window checker shows which models your text fits in.