Model A
Model B (optional)
Prices change often, so this tool does not include any. Copy the input and output prices per 1 million tokens from your provider pricing page. A month is counted as 30 days. Use the Token Counter to estimate your token numbers.
How AI API pricing works
Most AI providers charge per token, usually quoted as a price per one million tokens. Input tokens (your prompt) and output tokens (the reply) are priced separately, and output tokens usually cost more.
How to use this calculator
Enter the typical number of input and output tokens for one request, how many requests you expect per day, and the input and output prices from your provider pricing page. The calculator shows the cost per request, per day, per 30 days and per year. Add a second model to compare the two.
How to estimate your tokens
Paste a sample prompt into the AI Token Counter to estimate input tokens, and guess the reply length for output. Long system prompts, chat history and attached documents all count as input on every request.
FAQ
Prices change often and differ by model and plan, so built-in numbers would go out of date. Enter the current price from your provider so the result stays accurate.
No. It covers token charges only. Some providers also charge for extras such as cached input, images, tools or batch discounts, which change the total.