nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL

by DeepInfra — Price updated 2026-04-04

Pricing ($/1M tokens)
Input $0.20
Output $0.60
Specifications
Context Window 131,072
Max Output 131,072
Input text
Output text
About This Model

nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL is a budget-friendly language model from DeepInfra.

It supports a context window of 131K tokens with up to 131K output tokens.

With input pricing at $0.20/1M tokens, it sits in the mid-range of available models.