NV
NVIDIA
NVIDIA develops the Nemotron family and supporting AI research and infrastructure for model training and inference.
Official website or profileFamilies
1
Model versions
20
Providers
17
Model families
Nemotron
ActiveNemotron model family by NVIDIA.
20 versions
Model versions
20 of 20 model versions
| Model | Family | Providers | Context | Max output | Input | Output | Reasoning | Tool call | Structured | Temperature | Weights | Price | Released | Updated | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Nemotron 3 Ultra 550B A55B nvidia/nemotron-3-ultra-550b-a55b | Nemotron | 1M | 128K | Yes | Yes | -No | Yes | Open | input $0.5/M · output $2.5/M cache read $0.15/M | 2026-06-04 | 2026-06-04 | ||||
| Nemotron 3.5 Content Safety nvidia/nemotron-3.5-content-safety | Nemotron | 128K | 8.2K | Yes | -No | -No | Yes | Open | Pricing unavailable | 2026-06-04 | 2026-06-04 | ||||
| Nemotron 3 Nano Omni 30B A3B Reasoning nvidia/nemotron-3-nano-omni-30b-a3b-reasoning | Nemotron | 256K | 66K | Yes | Yes | -No | Yes | Open | input $0/M · output $0/M | 2026-04-28 | 2026-04-28 | ||||
| Nemotron 3 Content Safety nvidia/nemotron-3-content-safety | Nemotron | 128K | 4.1K | -No | -No | -No | -No | Open | input $0/M · output $0/M | 2026-04-16 | 2026-04-16 | ||||
| Llama Nemotron Rerank VL 1B v2 nvidia/llama-nemotron-rerank-vl-1b-v2 | Nemotron | 128K | 4.1K | -No | -No | -No | -No | Open | input $0/M · output $0/M | 2026-03-31 | 2026-03-31 | ||||
| Nemotron Cascade 2 30B A3B nvidia/nemotron-cascade-2-30b-a3b | Nemotron | 256K | 33K | Yes | Yes | -No | Yes | Open | Pricing unavailable | 2026-03-24 | 2026-04-09 | ||||
| Nemotron VoiceChat nvidia/nemotron-voicechat | Nemotron | 128K | 8.2K | -No | Yes | -No | Yes | Open | input $0/M · output $0/M | 2026-03-16 | 2026-03-16 | ||||
| Nemotron 3 Super 120B A12B nvidia/nemotron-3-super-120b-a12b | Nemotron | 262K | 262K | Yes | Yes | -No | Yes | Open | input $0.2/M · output $0.8/M | 2026-03-11 | 2026-03-12 | ||||
| Llama Nemotron Embed VL 1B v2 nvidia/llama-nemotron-embed-vl-1b-v2 | Nemotron | 33K | 2K | -No | -No | -No | -No | Open | input $0/M · output $0/M | 2026-02-10 | 2026-02-10 | ||||
| Nemotron Content Safety Reasoning 4B nvidia/nemotron-content-safety-reasoning-4b | Nemotron | 128K | 4.1K | Yes | -No | -No | -No | Open | input $0/M · output $0/M | 2026-01-22 | 2026-01-22 | ||||
| Nemotron 3 Nano 30B A3B nvidia/nemotron-3-nano-30b-a3b | Nemotron | 262K | 262K | Yes | Yes | -No | Yes | Open | input $0/M · output $0/M | 2025-12-15 | 2025-12-15 | ||||
| Llama 3.1 Nemotron Safety Guard 8B v3 nvidia/llama-3.1-nemotron-safety-guard-8b-v3 | Nemotron | 128K | 4.1K | -No | -No | -No | -No | Open | input $0/M · output $0/M | 2025-10-28 | 2025-10-28 | ||||
| Nemotron Nano 12B v2 VL nvidia/nemotron-nano-12b-v2-vl | Nemotron | 128K | 128K | Yes | Yes | -No | Yes | Open | input $0/M · output $0/M | 2025-10-28 | 2025-10-28 | ||||
| Nemotron Nano 9B v2 nvidia/nemotron-nano-9b-v2 | Nemotron | 131K | 131K | Yes | Yes | -No | Yes | Open | Pricing unavailable | 2025-08-18 | 2025-08-18 | ||||
| Llama 3.3 Nemotron Super 49B v1.5 nvidia/llama-3.3-nemotron-super-49b-v1.5 | Nemotron | 131K | 131K | Yes | Yes | -No | Yes | Open | input $0/M · output $0/M | 2025-07-25 | 2025-07-25 | ||||
| Mistral Nemotron nvidia/mistral-nemotron | Nemotron | 128K | 8.2K | -No | Yes | -No | Yes | Open | Pricing unavailable | 2025-06-11 | 2025-06-12 | ||||
| Llama 3.1 Nemotron 70B Instruct nvidia/llama-3.1-nemotron-70b-instruct | Nemotron | 128K | 8.2K | -No | Yes | -No | Yes | Open | input $0/M · output $0/M | 2025-04-15 | 2025-04-15 | ||||
| Llama 3.1 Nemotron Ultra 253B nvidia/llama-3.1-nemotron-ultra-253b | Nemotron | 128K | 8.2K | Yes | Yes | -No | Yes | Open | Pricing unavailable | 2025-04-07 | 2025-04-07 | ||||
| Llama 3.3 Nemotron Super 49B v1 nvidia/llama-3.3-nemotron-super-49b-v1 | Nemotron | 131K | 131K | Yes | Yes | -No | Yes | Open | input $0/M · output $0/M | 2025-04-07 | 2025-08-08 | ||||
| Nemotron Mini 4B Instruct nvidia/nemotron-mini-4b-instruct | Nemotron | 128K | 8.2K | -No | Yes | -No | Yes | Open | input $0/M · output $0/M | 2024-08-21 | 2024-08-26 |