Token Counter
Estimate how many LLM tokens a piece of text will use, with both character-based and word-based estimates — instantly, in your browser.
Estimate how many LLM tokens a piece of text will use, with both character-based and word-based estimates. Everything runs entirely in your browser.
How it works
Paste your text and see two independent estimates: ~4 characters per token and ~0.75 tokens per word, both commonly cited rules of thumb for English text across GPT-family tokenizers. Shown together rather than as one number, since neither is exact.
FAQs
Is this an exact token count?
No — it’s an approximation using standard character/word ratios, not a real tokenizer for any specific model. For an exact count against a specific model, use that provider’s own tokenizer.
Is my text sent anywhere?
No. The estimate is calculated entirely in your browser.