AI Token Cost Calculator – LLM API Cost per Request, Day and Month

This AI token cost calculator estimates what an AI model API will cost for your app or workflow. Enter the size of your prompts and responses, how many requests you make and your provider’s prices per million tokens, and see the cost per request, day, month and year.

Measure prompts in

Input per request (prompt + context)

Output per request (response)

Requests per day

Price per 1 million input tokens ($)

Price per 1 million output tokens ($)

Days used per month

How AI API pricing works

Most large language model APIs charge per token, with separate prices for input tokens (your prompt, instructions and any documents) and output tokens (the model’s response). Output tokens usually cost several times more than input tokens.

Cost per request = input tokens ÷ 1,000,000 × input price + output tokens ÷ 1,000,000 × output price

Tokens and words

A token is a piece of text. In English, one token is roughly 4 characters or about 0.75 words, so 1,000 tokens is about 750 words. Code, numbers and other languages often use more tokens per word.

Worked example

An app sends 1,500 input tokens and gets 500 output tokens back per request, 1,000 times a day. At $3 per million input tokens and $15 per million output tokens, each request costs $0.012, which is $12 a day or $360 a month. Output makes up 62.5% of the cost even though it is a quarter of the tokens.

Ways to reduce AI costs

Keep prompts short and avoid resending long documents in every request.
Use prompt caching and batch processing where your provider offers discounts.
Use smaller, cheaper models for simple tasks.
Limit the maximum response length.

Frequently asked questions

How many words are in 1,000 tokens?

About 750 English words. The exact number depends on the model’s tokenizer and the type of text.

Why do output tokens cost more than input tokens?

Generating each output token requires the model to run step by step, which uses more computing power than reading the input.

Where do I find current AI model prices?

On your provider’s pricing page. Prices differ between models and change often, so the calculator lets you enter them yourself.

Does chat history count as input?

Yes. In most APIs, the whole conversation is sent with each new message, so long chats grow more expensive per message.

Related calculators

Last reviewed: October 2026. For information only; not financial, tax or legal advice.