How many tokens is this text?

Paste any text to count its tokens and see what it would cost with each AI model. Your text stays in your browser.

Try the same sentence in:
0tokens
0words
0characters

What this text costs

Questions people ask

Is my text sent anywhere?

No. The counting runs entirely in your browser with an open-source tokenizer. Nothing you paste is uploaded, stored or added to the page address.

Which models is the count exact for?

It is exact for OpenAI models that use the o200k_base tokenizer (the GPT-4o and GPT-5 family). Claude, Gemini and DeepSeek use their own tokenizers that do not run in a browser, so for them the count is an estimate: usually in the same range for ordinary English, but it can differ noticeably, especially for other languages and code.

Why does Hindi or Bengali text use more tokens?

Tokenizers are trained mostly on English, so they split Indian scripts into smaller pieces. In our tests with this tokenizer, the same sentence took 1.3 to 1.5 times as many tokens in Hindi and 1.6 to 1.9 times in Bengali; older tokenizers were worse. More tokens means a higher API bill and less text fitting in the model's context.

What do input and output cost mean here?

Input is what you send to the model; output is what it writes back. The table shows what this exact text would cost to send once, and what it would cost if the model wrote it, at each provider's published price. To estimate a whole month of use, try the AI API cost calculator.

Spotted a wrong number? Tell us and we'll fix it.