Token Counter
Paste any text to see an estimated token count, alongside word and character counts. Useful for checking whether something will fit in a context window or roughly what it might cost to process.
Estimated counts
Context window headroom
Why token count matters
AI providers measure both context window limits and API pricing in tokens, not words or characters. A token is often a whole short word, but can also be part of a longer word — which is why token count and word count rarely match exactly. Knowing roughly how many tokens a piece of text uses helps you gauge whether it'll fit in a single request, and roughly what running it will cost.
Frequently asked questions
Is this an exact count?
No — it's an estimate based on roughly 4 characters per token in English, the same rule of thumb providers themselves publish. Real tokenizers vary by model and split words differently, especially for non-English text, code, or unusual punctuation, so treat this as a close approximation rather than an exact bill.
Why does the same text cost different tokens in different models?
Each model family uses its own tokenizer, trained on its own data, so the same sentence can split into a slightly different number of tokens depending on which model reads it. The gap is usually small for English text but can be larger for other languages or code.
Does this tool store or send my text anywhere?
No — everything runs in your browser with JavaScript. Nothing you type is sent to a server.