AI Token Counter — Estimate LLM Tokens & Cost
Estimate how many tokens your prompt uses and what it costs.
✓ updated June 2026
Estimate based on ~4 characters / ~0.75 words per token (English). Code and non-Latin scripts tokenize less efficiently, so treat this as a ballpark — for billing-exact counts use the provider's tokenizer or count API.
Paste a prompt, document or transcript to estimate its token count — the unit LLM APIs like OpenAI's and Anthropic's bill by — along with word and character counts. Enter your model's price per million tokens to see the estimated cost of the text. Estimates use the standard ~4-characters-per-token heuristic and run entirely in your browser, so your prompts stay private.
How to use the AI Token Counter
- Paste your prompt or document into the box.
- Read the estimated tokens, words and characters.
- Optionally set your model's price per 1M input tokens to see the estimated cost.
Frequently asked questions
What is a token?
The unit LLMs read and bill by — a chunk of characters produced by the model's tokenizer. In English, one token averages about 4 characters or ¾ of a word; 1,000 tokens is roughly 750 words.
How accurate is this estimate?
Within roughly ±10–15% for typical English prose. Code, dense punctuation and non-Latin scripts use more tokens per character, so for billing-exact numbers use the provider's own tokenizer or token-count API.
Is my text uploaded anywhere?
No. The estimate is computed locally in your browser — important when your prompts contain confidential material.