Cost Simulator

Estimate your monthly API costs across all models and providers. Filtered to Nemotron 3 Super 120B A12B.

Simulation Parameters

Tokens per Month

= 10M total tokens/month

Input / Output Split

70% input30% output

Typical chat: 70% in / 30% out

Filter Model

Prompt Caching

Disabled

1 offer found

Model	Provider	Input cost	Output cost	Cache savings	Total/mo
Nemotron 3 Super 120B A12B	NVIDIA NIM	$1.40/mo	$2.40/mo	—	$3.80/mocheapest