AI API Cost Calculator

Estimate what your usage will cost on Claude, GPT and Gemini models. Everything runs in your browser.

Model

Input tokens per request

Output tokens per request

Requests per month

Cached share of input (%)

Batch mode (discounted, results within 24 hours)

Cost per request

Cost per month

Cost per year

Compare all models

Same usage, every model, cheapest first.

Model	Provider	Input / 1M	Output / 1M	Per request	Per month

How the cost is calculated

Cost per request = (input tokens x input price + output tokens x output price) / 1,000,000. Cached input tokens are billed at the lower cached rate, and batch mode applies the provider's batch discount to the total. Not sure how many tokens your prompt uses? Try the Token Counter.

Prices are list prices in USD and can change. Always confirm on the provider's pricing page before budgeting. Extra charges such as web search or data residency are not included.