AI API Cost Calculator
Estimate what an AI feature will cost per month. Pick a model preset or type your own prices, then enter your usage. Everything runs in your browser; nothing is sent anywhere.
- API pricing is per 1 million tokens, billed separately for input and output.
- Roughly 1 token ≈ 4 characters ≈ ¾ of an English word.
- Output tokens usually cost 3-5× more than input tokens.
- Preset prices are standard short-context list prices as of October 2026 and change often: confirm on the provider's pricing page.
How AI API pricing works
Providers charge for the text you send (input tokens) and the text the model writes back (output tokens). Cost per request is input tokens × input price + output tokens × output price, each divided by one million. Multiply by requests per day and days per month for a monthly bill.
To lower the bill: shorten prompts, cap output length, use a smaller model for easy tasks, and cache repeated context where the provider supports it. New to the tools themselves? See our AI tools directory or the latest explainers.
Frequently asked questions
What is a token?
A token is a chunk of text a model reads or writes, often a short word or part of one. In English, 1,000 tokens is about 750 words.
Are the preset prices current?
They are standard short-context list prices checked in October 2026, and providers change them often. Overwrite the two price fields with the numbers from the official pricing page before relying on an estimate.
Does this include batch or cached-input discounts?
No. It uses the plain per-token price. If your provider discounts cached input or batch jobs, enter the lower effective price.