Back to Models

NVIDIA: Nemotron 3 Super

nvidia/nemotron-3-super-120b-a12b
Mar 11, 2026262.1K context$0.09/M in · $0.45/M outReasoning

Description

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

Provider
nvidia
Context Length
262.1K
Max Output
Modality
Intext
Outtext

Pricing

TypePrice / 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!"}]
  }'
NVIDIA: Nemotron 3 Super — Pricing & API on OminiGate