NVIDIA: Nemotron 3 Super
nvidia/nemotron-3-super-120b-a12b
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.
Model specifications
- Input
- text
- Output
- text
- Context
- 262,144 tokens
- Max output
- 262,144 tokens
- Input price
- $0.1 / 1M tokens
- Output price
- $0.5 / 1M tokens
- Released
- 2026-03-19
Capabilities
- Streaming
- Function calling
- Vision
- JSON mode
- Playground
Provider pricing, discounts and data privacy
Compare effective provider prices, published discounts, regions, retention policies, training use, compliance, and privacy links by service tier.
Standard service tier
1 available provider · tier input average $0.1 / 1M tokens · tier output average $0.5 / 1M tokens
DeepInfra
Tier: Standard · Region: US · Quantization: fp16
Pricing
- Input
- $0.1 / 1M tokens
- Output
- $0.5 / 1M tokens
- Cache read
- $0.04 / 1M tokens
No provider discount is currently published.
Data privacy and compliance
- Region
- US
- Zero data retention
- Yes
- Data retention
- Zero retention
- Used for training
- No
- Data collection
- Moderated
- No
- GDPR compliant
- Yes
- HIPAA compliant
- No
- SOC 2 certified
- Yes
- BYOK supported
- Yes
Privacy policy · Terms · Official website · Documentation · Status · Support
Frequently asked questions
- What is NVIDIA: Nemotron 3 Super?
- 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.
- How much does NVIDIA: Nemotron 3 Super cost?
- Input costs start at $0.1 / 1M tokens and output costs start at $0.5 / 1M tokens. Provider-level prices vary by service tier.
- What is the context length of NVIDIA: Nemotron 3 Super?
- NVIDIA: Nemotron 3 Super supports a 262,144 token context window and up to 262,144 output tokens.
- What capabilities does NVIDIA: Nemotron 3 Super support?
- NVIDIA: Nemotron 3 Super supports Streaming, Function calling, Vision, JSON mode, Playground.
- Which providers offer NVIDIA: Nemotron 3 Super?
- NVIDIA: Nemotron 3 Super is available from DeepInfra.
- How do providers handle data privacy for NVIDIA: Nemotron 3 Super?
- 1 of 1 providers report that customer data is not used for training, and 1 offer zero-data-retention routing. Retention, compliance, and privacy-policy links are listed per provider.