AI Token Cost Calculator

Calculate AI token costs per request, day, month and year — editable pricing per 1M tokens for any model.

AI Token Cost Calculator

Calculate AI token costs per request, day, month and year — editable pricing per 1M tokens for any model.

Input tokens

Output tokens

Cached input tokens

Price per 1M input tokens ($)($)

Price per 1M output tokens ($)($)

Cached input price per 1M ($, optional)($)

Requests per day

Enter values above and click Calculate — results will appear here with the formula explained.

Cost/request = input/1M×inputPrice + cached/1M×cachedPrice + output/1M×outputPrice; Cost/day = cost/request×requests; Month = day×30; Year = day×365

How does this work?

All model pricing is user-editable so the calculator stays correct when providers change prices. Enter current pricing from provider docs (OpenAI, Anthropic, Google).

AdSense ready — add NEXT_PUBLIC_GOOGLE_ADSENSE_PUBLISHER_ID

728×90 — AdSense

What is AI Token Cost?

AI pricing is per million tokens, separate for input, cached input and output. Output is typically 2-5× input price. Cached input is cheaper (often 10%). Multiply tokens by price to get cost per request, then by requests per day for daily/monthly/yearly. Formula: Cost/request = input/1M×inputPrice + cached/1M×cachedPrice + output/1M×outputPrice; Cost/day = cost/request×requests; Month = day×30; Year = day×365

Quick Answer

AI Token Cost Calculator: Calculate AI token costs per request, day, month and year — editable pricing per 1M tokens for any model. Formula: Cost/request = input/1M×inputPrice + cached/1M×cachedPrice + output/1M×outputPrice. Example: 2,000 input at $5/1M = $0.

What it does: Calculate AI token costs per request, day, month and year — editable pricing per 1M tokens for any model.
Formula: Cost/request = input/1M×inputPrice + cached/1M×cachedPrice + output/1M×outputPrice; Cost/day = cost/request×requests; Month = day×30; Year = day×365
Inputs: Input tokens · Output tokens · Cached input tokens · Price per 1M input tokens ($) ($) · Price per 1M output tokens ($) ($) · Cached input price per 1M ($, optional) ($) · Requests per day
Example: 2,000 input at $5/1M = $0.

Calculator Inputs at a Glance

Field	What to enter
Input tokens	e.g. 2000
Output tokens	e.g. 500
Cached input tokens	If using prompt caching
Price per 1M input tokens ($) ($)	e.g. 5
Price per 1M output tokens ($) ($)	e.g. 15
Cached input price per 1M ($, optional) ($)	Often 10% of input price
Requests per day	e.g. 1000

All fields use the exact formulas shown below — results include step-by-step breakdowns you can verify by hand.

How to Use This Calculator

1Enter input, output and cached tokens per request, and price per 1M for each.
2Set requests per day to scale to daily, monthly and yearly.
3Compare models by duplicating with different prices (e.g., GPT-4o vs Claude).

Formula Used

Cost/request = input/1M×inputPrice + cached/1M×cachedPrice + output/1M×outputPrice; Cost/day = cost/request×requests; Month = day×30; Year = day×365

All model pricing is user-editable so the calculator stays correct when providers change prices. Enter current pricing from provider docs (OpenAI, Anthropic, Google).

AdSense ready — add NEXT_PUBLIC_GOOGLE_ADSENSE_PUBLISHER_ID

728×90 — AdSense

Worked Example

2,000 input at $5/1M = $0.01, 500 output at $15/1M = $0.0075, total $0.0175 per request. At 1,000 requests/day = $17.50/day, $525/month, $6,387/year. With 1,000 cached at $0.50/1M, save $0.0045 per request.

AdSense ready — add NEXT_PUBLIC_GOOGLE_ADSENSE_PUBLISHER_ID

728×90 — AdSense

Related Calculators

TikTok Shop Profit Calculator

Calculate TikTok Shop profit, margin, break-even ROAS and max CPA from price, costs, fees and commission.

Temu Seller Profit Calculator

Calculate Temu profit from selling price, fees, product cost, shipping, VAT/tax, promotions and returns.

Twitch Earnings Calculator

Estimate Twitch earnings from bits, subs, ads, donations and more — with editable platform share.

Percentage Calculator

Calculate what X% of Y equals, and see the value after adding or removing that percentage.

Frequently Asked Questions

QWhat is a token?

~4 characters or 0.75 words. 1,000 tokens is about 750 words.

QWhy is output more expensive?

Output requires generation, more compute. Input is just encoding.

QWhat is cached input?

Prompt caching reuses prefix — 90% cheaper. Anthropic and OpenAI offer it for repeated system prompts.

QHow to compare models?

Run calculator twice with different prices (e.g., GPT-4o $5/$15 vs Claude $3/$15) to see cost difference for same tokens.

What is AI Token Cost?

Cost/request = input/1M×inputPrice + cached/1M×cachedPrice + output/1M×outputPrice; Cost/day = cost/request×requests; Month = day×30; Year = day×365

Quick Answer

What it does: Calculate AI token costs per request, day, month and year — editable pricing per 1M tokens for any model.

Formula: Cost/request = input/1M×inputPrice + cached/1M×cachedPrice + output/1M×outputPrice; Cost/day = cost/request×requests; Month = day×30; Year = day×365

Inputs: Input tokens · Output tokens · Cached input tokens · Price per 1M input tokens ($) ($) · Price per 1M output tokens ($) ($) · Cached input price per 1M ($, optional) ($) · Requests per day

Example: 2,000 input at $5/1M = $0.

Calculator Inputs at a Glance

Field	What to enter
Input tokens	e.g. 2000
Output tokens	e.g. 500
Cached input tokens	If using prompt caching
Price per 1M input tokens ($) ($)	e.g. 5
Price per 1M output tokens ($) ($)	e.g. 15
Cached input price per 1M ($, optional) ($)	Often 10% of input price
Requests per day	e.g. 1000

All fields use the exact formulas shown below — results include step-by-step breakdowns you can verify by hand.

Formula Used

Cost/request = input/1M×inputPrice + cached/1M×cachedPrice + output/1M×outputPrice; Cost/day = cost/request×requests; Month = day×30; Year = day×365

All model pricing is user-editable so the calculator stays correct when providers change prices. Enter current pricing from provider docs (OpenAI, Anthropic, Google).

Frequently Asked Questions

QWhat is a token?

~4 characters or 0.75 words. 1,000 tokens is about 750 words.

QWhy is output more expensive?

Output requires generation, more compute. Input is just encoding.

QWhat is cached input?

Prompt caching reuses prefix — 90% cheaper. Anthropic and OpenAI offer it for repeated system prompts.

QHow to compare models?

Run calculator twice with different prices (e.g., GPT-4o $5/$15 vs Claude $3/$15) to see cost difference for same tokens.