AI cost calculator: estimate API cost per call and month
A free calculator that turns token counts and list prices into a cost per call and per month.
Enter your token counts and a price, and the calculator shows what a call and a month of use would cost. It runs in your browser and sends nothing.
Estimate based on list prices. Taxes, discounts, batch pricing and price tiers are not included. USD per 1 million tokens, list price, excl. tax. Prices as of 26 October 2026.
Same usage on every model (per month)
| Model | Provider | per month |
|---|
How the calculator works
The cost of one call is:
cost = input tokens × input price + output tokens × output price
Each price is per 1 million tokens, so divide the token count by 1,000,000 first. Example with made-up prices: a call with 2,000 input tokens at $3 and 500 output tokens at $15 costs 2,000 ÷ 1,000,000 × 3 = $0.006 for input plus 500 ÷ 1,000,000 × 15 = $0.0075 for output, so $0.0135 in total. Multiply by calls per day and days per month for a monthly figure.
Real prices are in the API price table. The unit is explained under price per million tokens.
Ways to spend less
- Use caching. Prompt caching lowers the price of input you repeat.
- Use batch. The batch API is cheaper if you can wait for the answers.
- Use a smaller model. Many tasks do not need a top model. See how to choose a model.
- Shorten prompts. Fewer input tokens cost less. Cut what the model does not need.
- Limit the output. Ask for short answers when short is enough.
Limits of the result
The result uses list prices only. It leaves out discounts, tax and exchange rate. Treat it as a guide.
Questions and answers
Is my input sent anywhere?
No. The calculator runs in your browser. The numbers you enter stay on your device.
Is the result what I will pay?
No, it is an estimate from list prices. Discounts, caching, batch use, tax and exchange rate change the real bill.
Where do I get the token counts?
Use the token estimator for a rough count, or read the usage figures your provider shows after a call.
Read next
- AI API prices compared: cost per 1 million tokens
A table of AI API list prices per 1 million tokens, with source and check date for every row.
- Token estimator: roughly count tokens in your text
A free tool that estimates how many tokens a text holds. It is a rough guide, not an exact count.
- Price per million tokens
Price per million tokens is the usual way AI APIs state their rates: what you pay for each million tokens sent in or generated.
- Prompt caching
Prompt caching lets an AI provider reuse the already processed start of your prompt, so repeated parts are cheaper and faster.