Counting happens on this device. Your text is never uploaded. Paste a prompt or open a document, set how many requests you expect, enter your provider's prices, and see what a job should cost before you run it. It is free and private.
How to estimate a cost
- Paste your text, or use Open a text file. Try an example fills in sample text.
- Set Output tokens per request, which is how long you expect each answer to be.
- Set the Number of requests.
- Add Extra input tokens per request for anything sent every time, such as instructions or earlier messages.
- Enter the prices per million tokens for each model in the table.
- Read the cost per request and the total, then use Download CSV to keep the comparison.
Exact and estimated counts
Some tokenizers are published, so counts for those models are exact for the text itself when the exact-counts option is on. Other model families use tokenizers that aren't published in a form that can run here, so their counts are estimates, marked as such, based on about 3.5 to 4 characters per token for English. Code, numbers and other languages usually use more tokens per character.
Working out the cost
Each request costs its input tokens times the input price, plus its output tokens times the output price, with prices given per million tokens. The total multiplies that by the number of requests. Add extra input tokens for anything sent with every request, such as a system message or chat history.
For example, a 2,000 token prompt with a 500 token answer, repeated 1,000 times, is 2 million input tokens and 0.5 million output tokens. Multiply each by its price per million and add them together.
Tips for good planning
- Run the estimate on your longest realistic input, not your shortest, so the budget has room.
- Output usually costs more per token than input, so a long answer can matter more than a long prompt.
- Compare several models side by side before choosing. A cheaper model that needs fewer retries can be the better value.
- Use Download CSV to share the numbers with a client or teammate.
Who uses it
Freelancers quoting a project that processes documents, small businesses checking whether an automation is affordable, and students keeping a project within a budget. To prepare long documents for processing, the text chunker splits them into parts.
Questions
Why are there no prices filled in?
Prices change often and differ by model size, region, batch discounts and caching. Entering the current price from your provider's page keeps the figures right. The example uses round made-up prices only to show how it works.
How close are the estimates?
For ordinary English prose they're usually within about 10 to 20 percent. Treat them as a planning guide, not a bill. Check your provider's usage page or token counting endpoint for exact figures.
Can I add another model?
Yes. Add a model, give it a name, a characters-per-token figure and its prices. It's saved on this device with your other prices, and Clear my prices removes them.
What isn't included?
Formatting tokens added by chat APIs, images, audio, tool definitions, cached-input discounts and reasoning tokens that some models use while thinking. Add an allowance with extra input tokens or output tokens.
What is a token?
A token is a small piece of text, often a short word or part of a longer one. In English, a token is roughly four characters, or about three quarters of a word.
Is my text stored anywhere?
No. The text is counted in your browser. Only the prices you enter are saved, and only on this device.