NVIDIA Nemotron 3 Super (120B-A12B)
Knowledge cutoff = pre-training (Jun 2025); post-training to Feb 2026. Also FP8/NVFP4 repos. Free tier on OpenRouter (:free).
- Context window
- 1,000,000 tokens
- Knowledge cutoff
- 2025-06
- Input
- text
- Output
- text
- License
- nvidia-open-model-license
- Pricing
- input: $0.08 · output: $0.45 (per 1M tokens (USD) on OpenRouter; NVIDIA hosted pricing not verified) source
- Verified
- 2026-09-29
How to call it
| Provider | Model id | Endpoint / URL | Docs |
|---|---|---|---|
| NVIDIA API (build.nvidia.com) | nvidia/nemotron-3-super-120b-a12b | https://integrate.api.nvidia.com/v1/chat/completions | docs |
| AWS Bedrock | nvidia.nemotron-super-3-120b | — | docs |
| OpenRouter | nvidia/nemotron-3-super-120b-a12b | openrouter.ai/nvidia/nemotron-3-super-120b-a12b | — |
| Hugging Face | — | huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 | — |
Notable capabilities (2)
- 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
- 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
Mid-size open reasoning model, widely hosted (Bedrock, NIM, OpenRouter).
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
Other NVIDIA models
NVIDIA Nemotron 3.5 Lightning (30B-A3B) · NVIDIA NemotronLabs VoiceChat 11B (and PersonaPlex-7B) · NVIDIA Nemotron 3 Ultra (550B-A55B) · Cosmos 3 (Nano / Super) · NVIDIA Nemotron 3 Nano Omni (30B-A3B Reasoning) · Isaac GR00T N1.7 · Cosmos Reason 2 · NVIDIA MagpieTTS Multilingual 357M · NVIDIA Parakeet / Canary / Nemotron Speech ASR (open) · Isaac GR00T N2 · Cosmos Predict 2.5 / Transfer 2.5 · Isaac GR00T N1 / N1.5 / N1.6