LLM ReferenceLLM Reference

Nemotron 3 Super-120B-A12B on OpenRouter

Nemotron-3 · NVIDIA AI

Serverless

Compare Nemotron 3 Super-120B-A12B Across Providers

ProviderInput (per 1M)Output (per 1M)
NVIDIA NIM
OpenRouter$0.09$0.45

Pricing

TypePrice (per 1M)
Input tokens$0.09
Output tokens$0.45

Capabilities

VisionMultimodalReasoningFunction CallingTool UseStructured OutputsCode Execution

About Nemotron 3 Super-120B-A12B

120B MoE model with 12B active parameters - hybrid Mamba-Transformer with Multi-Token Prediction for agentic workflows

Get Started

Model Specs

Released2026-03-11
Parameters120B
Context1M
ArchitectureDecoder Only

GPU-Hour Providers(1)