Token Counter & Cost Estimator
Paste a prompt to estimate its tokens and what it costs on popular AI models. Nothing is uploaded.
- 1Paste your prompt or upload a file
- 2Set the answer length and requests per day
- 3Compare the cost across models
Your text
An estimate, usually within about 15% for English text. Each model splits text its own way, so exact counts differ.
Cost
| Model | Tokens in | Price in / out per 1M | Per request | Per month |
|---|
Cheapest first. Prices change often and exclude discounts such as caching or batch; check the provider before you budget.
How it works
AI models do not read words; they read tokens, which are short pieces of text. A common English word is usually one token, a long or rare word is several. Providers charge per million tokens, with separate prices for the text you send (input) and the text the model writes (output).
This page estimates the tokens in your text and multiplies them by each model's published price. Add how long you expect the answer to be and how many requests you make a day to see the cost per request and per month, cheapest model first.
For RAG, the prompt is the question plus the retrieved passages, so passage size and the number of passages retrieved decide most of the cost. The RAG tool shows the token estimate for each prompt it builds.
Questions
What is a token?
A token is a piece of text that a model treats as one unit: a short word, part of a longer word, a number group or a punctuation mark. In English, 100 tokens is roughly 75 words.
How accurate is the count?
It is an estimate, usually within about 15% for English text. Every model family uses its own tokenizer, so the same text gives different counts on different models. For billing-grade numbers use the provider's own counter.
Why do output tokens cost more?
Writing text takes more computation than reading it, so providers price output several times higher than input. A long answer can cost more than a long prompt.
Where do the prices come from?
From the providers' public price lists on the date shown above the table. Prices change often and do not include discounts such as caching or batch processing.
Can I add a model that is not listed?
Yes. Enter its input and output price per million tokens under "Your model" and it appears as the last row.
Is my text uploaded?
No. Everything runs in your browser tab. Your documents and questions never leave your device.
More
Try RAG on your own document · Chunking Visualizer · What is RAG? · How to choose a chunk size for RAG