# Nemotron Super

> Nemotron Super is an open-weight language model from NVIDIA, released on 11 Mar 2026. It accepts text and generates text, with a 203K-token context window and up to 203K output tokens per response. As of 4 Oct 2026, the lowest listed API price is $0.08 per million input tokens and $0.45 per million output tokens (OpenRouter), across 7 providers we track.

Source page: https://www.aimodel.directory/models/nemotron-3-super-120b-a12b
Last verified: 4 Oct 2026

## Specifications

- **Developer:** NVIDIA
- **Release date:** 11 Mar 2026 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/baseten/models/nvidia/Nemotron-120B-A12B.toml)
- **Status:** Generally available (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/baseten/models/nvidia/Nemotron-120B-A12B.toml)
- **Weights:** Open weights (source: Hugging Face, https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8)
- **License:** nvidia-nemotron-open-model-license (source: Hugging Face, https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8)
- **Parameters:** 124B (source: Hugging Face, https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8)
- **Context window:** 203K (202,800 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/baseten/models/nvidia/Nemotron-120B-A12B.toml)
- **Max output:** 203K tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/baseten/models/nvidia/Nemotron-120B-A12B.toml)
- **Knowledge cutoff:** Feb 2026 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/baseten/models/nvidia/Nemotron-120B-A12B.toml)
- **Input:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/baseten/models/nvidia/Nemotron-120B-A12B.toml)
- **Output:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/baseten/models/nvidia/Nemotron-120B-A12B.toml)
- **Reasoning mode:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/baseten/models/nvidia/Nemotron-120B-A12B.toml)
- **Tool calling:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/baseten/models/nvidia/Nemotron-120B-A12B.toml)
- **Structured output:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/baseten/models/nvidia/Nemotron-120B-A12B.toml)
- **Hugging Face:** nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8 (source: Hugging Face, https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|
| OpenRouter | $0.08 | $0.45 | – | 262K |
| Amazon Bedrock | $0.15 | $0.65 | – | 262K |
| Vercel AI Gateway | $0.15 | $0.65 | – | 256K |
| NVIDIA NIM | $0.20 | $0.80 | – | 262K |
| Nebius AI Studio | $0.30 | $0.90 | – | 262K |
| Baseten | $0.30 | $0.75 | $0.06 | 203K |
| Cloudflare Workers AI | $0.50 | $1.50 | – | 256K |

## FAQ

### What is the context window of Nemotron Super?

Nemotron Super has a context window of 202,800 tokens (203K) and can generate up to 202,800 tokens in a single response, according to models.dev.

### How much does the Nemotron Super API cost?

Nemotron Super is listed from $0.08 per million input tokens and $0.45 per million output tokens (OpenRouter). Prices last verified 4 Oct 2026.

### Is Nemotron Super open source?

Nemotron Super is an open-weight model: its weights are published on Hugging Face as nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8 under the nvidia-nemotron-open-model-license license. Check the license terms before commercial use.

### When was Nemotron Super released?

NVIDIA released Nemotron Super on 11 Mar 2026, according to models.dev.

### Which providers offer Nemotron Super?

We track Nemotron Super on 7 providers: OpenRouter, Amazon Bedrock, Vercel AI Gateway, NVIDIA NIM, Nebius AI Studio, Baseten, Cloudflare Workers AI.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "Nemotron Super", https://www.aimodel.directory/models/nemotron-3-super-120b-a12b