Back
Prompt Caching & Batch ROI CalculatorsNVIDIA

NVIDIA: Nemotron 3 Ultra Prompt Caching Calculator

Connect API
Base Input Rate$0.6/M
Cache Hit Read$0.120/M(-80%)
Cache Write SurchargeFree (Automatic)
Output Rate$2.4/M

Simulation Parameters

Monthly Requests100,000
Input Tokens / Req8,000
Prompt Cache Hit Rate75%
Output Tokens800
Gross Uncached Cost$672.00
Net Bill$384.00
Cache Savings$288.00 (-43%)