AI Prompt Cache Savings

Estimate monthly savings from discounted cached AI prompt tokens.

How this calculator works

Enter monthly requests, cached tokens per request, standard input price per 1m ($), cached input price per 1m ($). Select Calculate to apply the displayed formula and review the labeled results.

Formula / method

Savings = requests × cached tokens ÷ 1,000,000 × (standard rate − cached rate)

Worked example

100,000 requests with 3,000 cached tokens and a $1.80/M discount save $540 monthly.

Assumptions and limitations

The entered cached token count receives the entered discounted rate for every request.

Cache eligibility, cache misses, provider minimums and output costs are not included.