LLM API Cost Calculator
Enter token counts and the prices from your provider's pricing page. Prices are not preset, so the result always uses your numbers.
Examples use made-up round prices ($1 input, $3 output per 1M tokens) for illustration. They are not any provider's real prices.
- Cost per request
- -
- Cost per day
- -
- Cost per month (30 days)
- -
- Cost per year (365 days)
- -
How it is calculated
Cost per request = (input tokens ÷ 1,000,000 × input price) + (output tokens ÷ 1,000,000 × output price). Daily cost multiplies that by requests per day. Monthly assumes 30 days and annual assumes 365 days.
This is an estimate. It ignores discounts, caching, batch pricing, tool or image charges, taxes and currency conversion.
How to use it
- Estimate input and output tokens for one request. The token counter can help.
- Enter the input and output prices per million tokens from your provider's official pricing page.
- Enter how many requests you expect per day.
- Read the cost per request, day, month and year, then copy the results if needed.
Worked example
Suppose a request uses 1,000 input tokens and 500 output tokens, with illustrative prices of $3 and $15 per million tokens, at 100 requests a day. One request costs $0.003 + $0.0075 = $0.0105. That is $1.05 a day, $31.50 over 30 days and $383.25 over a year.
Frequently asked questions
Where do I find the prices?
On your provider's official pricing page. Prices change, so check the current page and enter the figures yourself.
Why are input and output priced separately?
Most providers charge different rates for tokens you send and tokens the model generates, so the calculator keeps them separate.
Does it include caching, batch discounts or taxes?
No. It is a straightforward estimate from the numbers you enter.