Using Nemotron 3 Super-120B-A12B on OpenRouter
Implementation guide · Nemotron-3 · NVIDIA AI
Serverless
Quick Start
- 1
- 2Use the OpenRouter SDK or REST API to call
nvidia/nemotron-3-super-120b-a12b— see the documentation for request format. - 3
About OpenRouter
OpenRouter provides a unified interface for Large Language Models with better pricing, improved uptime, and no subscription requirements. Route across providers for cost optimization and reliability.
Multi-provider LLM aggregator offering unified API access to 300+ models from all major labs and emerging providers, with automatic failover for reliability.
Pricing on OpenRouter
| Type | Price (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
Model Specs
Released2026-03-11
Parameters120B
Context1M
ArchitectureDecoder Only