Estimate what an AI model will cost you per request, per day and per month. Enter your token counts and your model’s price per million tokens. Everything runs in your browser and nothing you type is stored.

Last updated: October 1, 2026

How the calculation works

AI providers charge separately for the text you send (input) and the text the model writes back (output). Both are priced per million tokens.

cost per request = (input tokens ÷ 1,000,000 × input price) + (output tokens ÷ 1,000,000 × output price)

The calculator multiplies that by your requests per day, then by the days in your month.

Four ways to lower your AI bill

• Trim your prompts. Long instructions and pasted context are paid on every single request.
• Cap the answer length. Set a maximum output so the model can’t ramble at your expense.
• Match the model to the task. Smaller, cheaper models handle simple sorting and summaries well.
• Use caching and batch discounts. Many providers charge less for repeated context or non-urgent jobs.

Frequently asked questions

What is a token?

A token is a small chunk of text, often part of a word. In English, a token is roughly three-quarters of a word, but the exact count depends on the model.

Why do output tokens cost more?

Generating new text takes more computing work than reading text, so most providers set a higher price for output.

How accurate is this calculator?

It gives an estimate. Your real bill depends on exact token counts, caching, batch discounts, taxes and any minimum charges.