Prompt cost estimator

Estimate what AI API calls will cost

Runs in your browser. Nothing is uploaded.

How it works

AI APIs charge per million tokens, with one price for input and a higher one for output. To estimate your bill, multiply each by your token counts, then by your number of calls. Enter your model’s current prices here, because they change often. A month here means 30 days of calls at your daily rate.

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

Output tokens usually cost several times more than input tokens, so long answers add up fast.

Providers often offer discounts for cached input and batch jobs, which this doesn’t include.

Worked example. At an example price of $1 for input and $5 for output per million tokens, 1,000 tokens in and 500 out costs $0.00350 a call, or $10.50 a month at 100 calls a day.

Examples

Input	Output	Calls a day	Monthly, at $1 and $5
500	200	100	$4.50
1000	500	100	$10.50
5000	1000	1000	$300.00

What this tool doesn’t cover

Prices change, so check them with your provider.
This doesn’t include caching or batch discounts.

Questions

How do I find my token counts?

Paste a typical prompt into our token counter, then use that number.

Why is output more expensive?

Generating each token takes more work than reading one.

Where do the prices come from?

You enter them. Any comparison table shows the date the prices were last reviewed.

How is the cost of an AI prompt worked out?

Providers charge by tokens, with separate rates for input and output. Multiply each count by its rate and add them up.

How do I reduce my AI API bill?

Use a smaller model for simple work, keep prompts short, limit output length, and use prompt caching if your provider offers it.

Was this useful?

Built by QuickToolz.

Sources: OpenAI API pricing (opens in a new tab), Anthropic pricing (opens in a new tab)