Nemotron 3 Models by NVIDIA AI
NVIDIA AI releases · 22 in the last 12 months · this family litChangelog →
9 models2024–2026Up to 1M ctxFrom $0.050/1M input
Last refreshed 2026-09-22. Next refresh: weekly.
Details
ResearcherNVIDIA AI
LicenseNVIDIA Open Model
Commercial usePermitted
Models9
Released2024–2026
Max context1M
Capabilities
Vision2 of 9 models
Multimodal3 of 9 models
Reasoning2 of 9 models
JSON / Tool use3 of 9 models
Structured Outputs2 of 9 models
About
NVIDIA Nemotron 3 is the 2025-2026 open model family covering Nano 30B-A3B, Super 120B-A12B, Content Safety 4B, VoiceChat 12B, and Nano Omni variants for agentic reasoning, safety classification, and multimodal deployment.
Decision facts
- Best fit
- audiomoderationrealtime voice
- Capability starting point
- Nemotron 3 Ultra with 1M context and reasoning and JSON / Tool use
- Lowest tracked input
- Nemotron 3 Nano 30B-A3B · $0.050/1M · Vercel AI Gateway
- Closest related family
- NemoGuard
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
9 in view
Nemotron 3 UltraCurrent
Use when the workload needs 1M context, 550B parameters, and reasoning.
2026-061M context550B parametersreasoning
Nemotron 3 Nano OmniCurrent
Use when the workload needs audio, 256K context, and 30B parameters.
2026-04audio256K context30B parameters
Nemotron 3 Content SafetyCurrent
Use when the workload needs moderation, 128K context, and 4B parameters.
2026-03moderation128K context4B parameters
Nemotron 3 VoiceChatCurrent
Use when the workload needs realtime voice, 12B parameters, and multimodal inputs.
2026-03realtime voice12B parametersmultimodal inputs
Nemotron 3 Super-120B-A12BCurrent
Use when the workload needs 1M context, 120B parameters, and reasoning.
2026-031M context120B parametersreasoning
Nemotron 3 NanoCurrent
Use when the workload needs 256K context, 4.0B parameters, and JSON / Tool use.
2025-12256K context4.0B parametersJSON / Tool use
Nemotron 3 Nano 30B-A3BCurrent
Use when the workload needs structured outputs.
2025-12structured outputs
Use when the workload needs 128K context and 49B parameters.
2025-06128K context49B parameters
Use when the workload needs safety, 4K context, and 70B parameters.
2024-10safety4K context70B parameters
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Nemotron 3 Ultra | Use when the workload needs 1M context, 550B parameters, and reasoning. | 2026-06 | 1M context550B parametersreasoning | Current |
| Nemotron 3 Nano Omni | Use when the workload needs audio, 256K context, and 30B parameters. | 2026-04 | audio256K context30B parameters | Current |
| Nemotron 3 Content Safety | Use when the workload needs moderation, 128K context, and 4B parameters. | 2026-03 | moderation128K context4B parameters | Current |
| Nemotron 3 VoiceChat | Use when the workload needs realtime voice, 12B parameters, and multimodal inputs. | 2026-03 | realtime voice12B parametersmultimodal inputs | Current |
| Nemotron 3 Super-120B-A12B | Use when the workload needs 1M context, 120B parameters, and reasoning. | 2026-03 | 1M context120B parametersreasoning | Current |
| Nemotron 3 Nano | Use when the workload needs 256K context, 4.0B parameters, and JSON / Tool use. | 2025-12 | 256K context4.0B parametersJSON / Tool use | Current |
| Nemotron 3 Nano 30B-A3B | Use when the workload needs structured outputs. | 2025-12 | structured outputs | Current |
| Llama 3.3 Nemotron Super 49B v1 | Use when the workload needs 128K context and 49B parameters. | 2025-06 | 128K context49B parameters | Current |
| Llama 3.1 Nemotron 70B Reward | Use when the workload needs safety, 4K context, and 70B parameters. | 2024-10 | safety4K context70B parameters | Current |
Release Timeline
6 release groups2026-06
1 current
Nemotron 3 Ultra
Current1M context550B parametersreasoning
2026-04
1 current
Nemotron 3 Nano Omni
Currentaudio256K context30B parameters
2026-03
3 current
Nemotron 3 Content Safety
Currentmoderation128K context4B parameters
Nemotron 3 Super-120B-A12B
Current1M context120B parametersreasoning
Nemotron 3 VoiceChat
Currentrealtime voice12B parametersmultimodal inputs
2025-12
2 current
Nemotron 3 Nano
Current256K context4.0B parametersJSON / Tool use
Nemotron 3 Nano 30B-A3B
Currentstructured outputs
2025-06
1 current
Llama 3.3 Nemotron Super 49B v1
Current128K context49B parameters
2024-10
1 current
Llama 3.1 Nemotron 70B Reward
Currentsafety4K context70B parameters
Specifications(9 models)
| Model | Released | Context | Parameters | Vision | Multimodal | Reasoning | JSON / Tool use | Structured Outputs |
|---|---|---|---|---|---|---|---|---|
| Nemotron 3 Ultra | 2026-06 | 1M | 550B | No | No | Yes | Yes | No |
| Nemotron 3 Nano Omni | 2026-04 | 256K | 30B | No | Yes | No | No | No |
| Nemotron 3 Content Safety | 2026-03 | 128K | 4B | Yes | Yes | No | No | No |
| Nemotron 3 VoiceChat | 2026-03 | — | 12B | Yes | Yes | No | No | No |
| Nemotron 3 Super-120B-A12B | 2026-03 | 1M | 120B | No | No | Yes | Yes | Yes |
| Nemotron 3 Nano | 2025-12 | 256K | 3.97B | No | No | No | Yes | No |
| Nemotron 3 Nano 30B-A3B | 2025-12 | — | 30B (3B active) | No | No | No | No | Yes |
| Llama 3.3 Nemotron Super 49B v1 | 2025-06 | 128K | 49B | No | No | No | No | No |
| Llama 3.1 Nemotron 70B Reward | 2024-10 | 4K | 70B | No | No | No | No | No |
Available From(7 providers)
Pricing
| Model | Provider | Input / 1M | Output / 1M | Type |
|---|---|---|---|---|
| Nemotron 3 Nano 30B-A3B | Vercel AI Gateway | $0.05 | $0.24 | Serverless |
| Nemotron 3 Nano 30B-A3B | AWS Bedrock | $0.06 | $0.24 | Serverless |
| Nemotron 3 Super-120B-A12B | OpenRouter | $0.085 | $0.4 | Serverless |
| Nemotron 3 Super-120B-A12B | DeepInfra | $0.1 | $0.5 | Serverless |
| Nemotron 3 Super-120B-A12B | NVIDIA NIM | $0.1 | $0.5 | Serverless |
| Nemotron 3 Super-120B-A12B | Vercel AI Gateway | $0.15 | $0.65 | Serverless |
| Nemotron 3 Super-120B-A12B | Cloudflare Workers AI | $0.5 | $1.5 | Serverless |
| Nemotron 3 Ultra | OpenRouter | $0.5 | $2.2 | Serverless |
Popular comparisons in this family
- Llama 3.2 NV RerankQA 1B v2 vs Llama 3.3 Nemotron Super 49B v1246
- Hunyuan Hy3 Preview vs Llama 3.3 Nemotron Super 49B v1237
- Gemma 3 vs Nemotron 3 Nano Omni221
- Llama 3.3 Nemotron Super 49B v1 vs Nemotron Mini 4B Instruct55
- Gemma 3 12B vs Nemotron 3 Content Safety48
- Falcon 3 7B Instruct vs Llama 3.1 Nemotron 70B Reward42
- Llama 3 Swallow 70B Instruct vs Llama 3.3 Nemotron Super 49B v133
- Hunyuan Hy3 Preview vs Llama 3.1 Nemotron 70B Reward30
- Together AI - Gemma 3n-e4B vs Nemotron 3 Content Safety28
- Bielik 11B v2.6 Instruct vs Llama 3.1 Nemotron 70B Reward20
Related Model Families
Models(9)
Nemotron 3 Ultra
2026-061M550B1 provider
ReasoningOpen Weights
Nemotron 3 Nano Omni
2026-04256K30B1 provider
MultimodalOpen Weights
Nemotron 3 Content Safety
2026-03128K4B
MultimodalOpen Weights
Nemotron 3 VoiceChat
2026-0312B
MultimodalOpen Weights
Nemotron 3 Super-120B-A12B
2026-031M120B6 providers
ReasoningOpen Weights
Nemotron 3 Nano
2025-12256K3.97B1 provider
Open Weights
Nemotron 3 Nano 30B-A3B
2025-1230B (3B active)2 providers
Open Weights
Llama 3.3 Nemotron Super 49B v1
2025-06128K49B1 provider
Open Weights
Llama 3.1 Nemotron 70B Reward
2024-104K70B1 provider
Open Weights