As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/m/nemotron-3-super/

# NVIDIA Nemotron 3 Super (120B-A12B)

NVIDIA, Nemotron 3 family. Status: current. Type: reasoning model. Released: 2026-03-11. Training cutoff: 2025-06.

## How to call it

| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| NVIDIA API (build.nvidia.com) | `nvidia/nemotron-3-super-120b-a12b` | https://integrate.api.nvidia.com/v1/chat/completions | https://build.nvidia.com |
| AWS Bedrock | `nvidia.nemotron-super-3-120b` |  | https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nemotron-super-3-120b.html |
| OpenRouter | `nvidia/nemotron-3-super-120b-a12b` |  | https://openrouter.ai/nvidia/nemotron-3-super-120b-a12b |
| Hugging Face |  |  | https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 |

## Pricing

- Input: $0.08 per 1M tokens
- Output: $0.45 per 1M tokens
- Unit as published: per 1M tokens (USD) on OpenRouter; NVIDIA hosted pricing not verified
- Source: https://openrouter.ai/nvidia/nemotron-3-super-120b-a12b
- Last checked: 2026-09-29

## Specs

- Input: text
- Output: text
- Context window: 1,000,000 tokens
- Max output: not published
- Open weights: yes
- Licence: nvidia-open-model-license

## What it has not seen

- Published training cutoff: 2025-06 (June 2025).
- AI events after it on Post-Cutoff: 2,016 (466 major, 89 historic), as of 2026-11-13.
- Already missing at launch: 107.
- Briefings of the news since June 2025: https://postcutoff.com/briefings/cutoff-2025-06-s.md (short), https://postcutoff.com/briefings/cutoff-2025-06-m.md (medium), https://postcutoff.com/briefings/cutoff-2025-06.md (full).
- Its card, with five things it has never heard of: https://postcutoff.com/you/nemotron-3-super/

## What stands out

- Efficient hybrid LatentMoE for agents: 120B total / 12B active hybrid Mamba-2 + MoE + attention, built for high-volume agentic workloads with up to 1M context (256K default). Source: https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16
- Managed on AWS Bedrock (found after launch): One of the few NVIDIA open models offered as a serverless Bedrock model (nvidia.nemotron-super-3-120b). Source: https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nemotron-super-3-120b.html

## Notes

Knowledge cutoff = pre-training (Jun 2025); post-training to Feb 2026. Also FP8/NVFP4 repos. Free tier on OpenRouter (:free).

Mid-size open reasoning model, widely hosted (Bedrock, NIM, OpenRouter).

```bash
curl https://integrate.api.nvidia.com/v1/chat/completions -H "Authorization: Bearer $NVIDIA_API_KEY" -H "Content-Type: application/json" \
 -d '{"model":"nvidia/nemotron-3-super-120b-a12b","messages":[{"role":"user","content":"Hello"}]}'
```

Sources: https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 , https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-nvidia-nemotron-super-3-120b.html

Model page: https://postcutoff.com/m/nemotron-3-super/