LLM token counter

Estimate how many tokens a prompt or document uses.

How it’s calculated

Tokens ≈ Characters ÷ 4, or Words × 4 ÷ 3 (English text)

Each model family uses its own tokenizer, so counts are estimates. Code, numbers and non-English text usually use more tokens. Your text stays in your browser.

Related tools

See all Lodge Tools →

Model prices and limits change often. Check the provider’s current pricing before you budget. Calculations run in your browser; nothing you enter is stored. Read our disclaimer.

About this token counter

This token counter estimates how many tokens your text uses in an AI model. Paste a prompt, document or chat log to see the count. In addition, it shows words, characters and lines. It works as an LLM token counter for ChatGPT, Claude, Gemini and other models. Also, your text stays in your browser.

How to use the token counter

  1. First, paste or type your text into the box.
  2. Next, read the estimated tokens by characters and by words.
  3. Then check the word, character and line counts.
  4. Finally, compare the estimate with your model’s context window or price list.

What is a token in AI?

A token is a small piece of text that an AI model reads and writes. It can be a whole word, part of a word or a punctuation mark. For example, a common short word is often one token. However, a long or rare word may split into several tokens.

How the token estimate works

For English text, OpenAI suggests that 1 token is about 4 characters. Similarly, 100 tokens are about 75 words. So the calculator gives two estimates: characters ÷ 4 and words × 4 ÷ 3. For example, “Hello world” has 11 characters and 2 words. As a result, both methods estimate 3 tokens.

Why token counts differ between models

Each model family uses its own tokenizer. So ChatGPT, Claude and Gemini may count the same text a little differently. In addition, code, numbers and non-English text usually use more tokens per word. For exact counts, use your provider’s own token counting tool.

Token counter FAQs

How many tokens is a word?

In English, one word is about 1.3 tokens on average. In other words, 100 tokens are roughly 75 words.

How many words is 1,000 tokens?

About 750 words of English text. However, code and other languages usually fit fewer words into the same tokens.

Is this an exact ChatGPT or Claude token counter?

No. It gives a quick estimate that works across models. For an exact count, use your provider’s own tokenizer or token counting API.

Is my text sent anywhere?

No. The calculator runs in your browser, so your text never leaves your device.

What is a context window?

A context window is the maximum number of tokens a model can handle in one request. It usually includes both your input and the model’s output. So check your token count against your model’s limit.