Token counter

Paste a prompt, document or chat log to see how many tokens it uses. OpenAI counts are exact; Claude and Gemini counts are estimates. Everything runs in your browser.

Loading tokenizer…

Estimate API cost →
OpenAI tokens (GPT-4o, GPT-5 and later, o200k)
0
Claude (estimate)
0
Gemini (estimate)
0
Characters
0
Words
0
Lines
0
Characters per token
–

What is a token?

Language models read text as tokens: chunks of characters from a fixed vocabulary. In English, one token is about 4 characters or three-quarters of a word, so 1,000 tokens is roughly 750 words. Code, numbers, non-English text and unusual words use more tokens per character.

Why counts differ between models

Each model family has its own tokenizer, so the same text gives a different count on GPT, Claude and Gemini.

Why token counts matter

API prices are per million tokens, and every model has a context window limit measured in tokens. Count your prompt, then use the LLM cost calculator to see what it costs at scale.

Is my text private?

Yes. Tokenizing happens in your browser. The text you paste is not uploaded or stored.

Frequently asked questions

How many tokens is 1,000 words?
About 1,300 tokens of typical English on OpenAI's o200k tokenizer. Paste your own text for an exact count, since code and other languages differ.
How many characters is a token?
About 4 characters of English on average. The calculator shows the ratio for your text.
Is the Claude count exact?
No. Anthropic has not released its tokenizer, so the Claude figure is an estimated range. Use the Claude API's count_tokens endpoint when you need the exact number.
Does this count chat message overhead?
No. It counts the text only. Chat APIs add a few tokens per message for roles and formatting.