Nemotron Super
Summary
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.
Nemotron middle tier for collaborative agents and high-volume reasoning workloads
Last verified 4 Oct 2026. Every figure on this page links to its source.
Specifications
| Developer | NVIDIA |
|---|---|
| Release date | 11 Mar 2026 [models.dev] |
| Status | Generally available [models.dev] |
| Weights | Open weights [Hugging Face] |
| License | nvidia-nemotron-open-model-license [Hugging Face] |
| Parameters | 124B [Hugging Face] |
| Context window | 203K (202,800 tokens) [models.dev] |
| Max output | 203K tokens [models.dev] |
| Knowledge cutoff | Feb 2026 [models.dev] |
| Input | Text [models.dev] |
| Output | Text [models.dev] |
| Reasoning mode | Yes [models.dev] |
| Tool calling | Yes [models.dev] |
| Structured output | Yes [models.dev] |
| Hugging Face | nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8 [Hugging Face] |
Nemotron Super API pricing by provider
USD per million tokens. Sorted by input price.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| OpenRouter nvidia/nemotron-3-super-120b-a12b | $0.08 | $0.45 | – | 262K | OpenRouter, 4 Oct 2026 |
| Amazon Bedrock nvidia.nemotron-super-3-120b | $0.15 | $0.65 | – | 262K | models.dev, 4 Oct 2026 |
| Vercel AI Gateway nvidia/nemotron-3-super-120b-a12b | $0.15 | $0.65 | – | 256K | models.dev, 4 Oct 2026 |
| NVIDIA NIM nvidia/nemotron-3-super-120b-a12b | $0.20 | $0.80 | – | 262K | models.dev, 4 Oct 2026 |
| Nebius AI Studio nvidia/nemotron-3-super-120b-a12b | $0.30 | $0.90 | – | 262K | models.dev, 4 Oct 2026 |
| Baseten nvidia/Nemotron-120B-A12B | $0.30 | $0.75 | $0.06 | 203K | models.dev, 4 Oct 2026 |
| Cloudflare Workers AI @cf/nvidia/nemotron-3-120b-a12b | $0.50 | $1.50 | – | 256K | models.dev, 4 Oct 2026 |
Frequently asked questions
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.
Change history
No changes detected since we started tracking this model. We re-check every source daily.
Sources
- https://openrouter.ai/nvidia/nemotron-3-super-120b-a12b
- https://github.com/sst/models.dev/blob/dev/providers/baseten/models/nvidia/Nemotron-120B-A12B.toml
- https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8
- https://github.com/sst/models.dev/blob/dev/providers/amazon-bedrock/models/nvidia.nemotron-super-3-120b.toml
- https://github.com/sst/models.dev/blob/dev/providers/vercel/models/nvidia/nemotron-3-super-120b-a12b.toml
- https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/nvidia/nemotron-3-super-120b-a12b.toml
- https://github.com/sst/models.dev/blob/dev/providers/nebius/models/nvidia/nemotron-3-super-120b-a12b.toml
- https://github.com/sst/models.dev/blob/dev/providers/cloudflare-workers-ai/models/@cf/nvidia/nemotron-3-120b-a12b.toml