NVIDIA: Nemotron 3 Super
nvidia/nemotron-3-super-120b-a12bDescription
NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer Mixture-of-Experts architecture with multi-token prediction (MTP), it delivers over 50% higher token generation compared to leading open models.
The model features a 1M token context window for long-term agent coherence, cross-document reasoning, and multi-step task planning. Latent MoE enables calling 4 experts for the inference cost of only one, improving intelligence and generalization. Multi-environment RL training across 10+ environments delivers leading accuracy on benchmarks including AIME 2025, TerminalBench, and SWE-Bench Verified.
Fully open with weights, datasets, and recipes under the NVIDIA Open License, Nemotron 3 Super allows easy customization and secure deployment anywhere — from workstation to cloud.
Specifications
Pricing
| Type | Price / 1M tokens |
|---|---|
| Input | $0.09 |
| Output | $0.45 |
Quick Start
curl https://api.ominigate.ai/v1/chat/completions \
-H "Authorization: Bearer sk-omg-your-api-key" \
-H "Content-Type: application/json" \
-d '{
"model": "nvidia/nemotron-3-super-120b-a12b",
"messages": [{"role": "user", "content": "Hello!"}]
}'