nvidia/NVIDIA-Nemotron-3-Super-120B-A12B

by DeepInfra — Price updated 2026-04-04

Pricing ($/1M tokens)
Input $0.10
Output $0.50
Cache Read $0.04
Specifications
Context Window 262,144
Max Output 262,144
Input text
Output text
About This Model

It supports a context window of 262K tokens with up to 262K output tokens.

Priced at $0.10/1M input tokens, it ranks among the more affordable options in the current market.