NVIDIA: Nemotron 3 Super
The NVIDIA Nemotron 3 Super is a text-based AI model that supports input modalities of plain text and provides tools for reasoning. It has a context length of 262144 tokens and can handle up to 235929 completion tokens at once. This model supports the use of external tools, indicating its ability to interact with users in a more dynamic way. For those on a budget or looking for a model with good benchmark performance, the NVIDIA Nemotron 3 Super is worth considering. Its input price per million tokens is $0.08 and output price per million tokens is $0.45, making it an affordable option. The model's blended benchmark score of 19.8 across one independent benchmark suggests that it can hold its own against other models in certain areas. However, a more comprehensive assessment of its capabilities would require additional testing and evaluation.
Benchmark results
Independent, published benchmarks. Blended score 16.9 across 1 benchmark, last refreshed 2026-09-27. How scoring works →
| Benchmark | Measures | Score |
|---|---|---|
| AI Index | broad capability composite | 21.2 |
- Model ID
- nvidia/nemotron-3-super-120b-a12b
- Vendor
- nvidia
- Released
- March 2026
- Tokenizer
- Other
- Input Modalities
- text
- Output Modalities
- text
- Max Output
- 235,929 tokens
- Tool Calling
- ✓ supported
- Structured Output
- ✓ supported
- Reasoning Mode
- ✓ supported
- Vision
- text only
- Audio
- no
- Moderated
- no
What it costs in practice
Computed from the current $0.08/M input and $0.45/M output rates. Run your own numbers →
| Job | Tokens | Cost |
|---|---|---|
| Summarize a 50-page report | 30k in / 1.5k out | under $0.01 |
| Classify 1,000 customer emails | 500k in / 50k out | $0.06 |
| A month of a busy support chatbot | 5M in / 2M out | $1.30 |
Price & spec history
Tracked daily by PicksByModel since 2026-07-17.
| Date | Input /M | Output /M | Context |
|---|---|---|---|
| 2026-09-15 | $0.08 | $0.45 | 262,144 |
| 2026-09-09 | $0.09 | $0.40 | 262,144 |
| 2026-08-10 | $0.09 | $0.40 | 1,000,000 |
| 2026-08-09 | $0.30 | $0.90 | 1,000,000 |
| 2026-08-08 | $0.09 | $0.40 | 1,000,000 |
| 2026-08-07 | $0.30 | $0.90 | 1,000,000 |
| 2026-07-25 | $0.09 | $0.40 | 1,000,000 |
| 2026-07-21 | $0.08 | $0.45 | 1,000,000 |
| 2026-07-20 | $0.09 | $0.40 | 1,000,000 |
| 2026-07-17 | $0.21 | $0.46 | 1,000,000 |
Similar models
NVIDIA: Nemotron 3.5 Lightning
NVIDIA: Nemotron 3 Nano 30B A3B
NVIDIA: Nemotron 3 Nano Omni (free)
NVIDIA: Nemotron 3 Ultra
NVIDIA: Nemotron 3 Super (free)
NVIDIA: Nemotron 3.5 Lightning (free)
Quick answers
- How much does NVIDIA: Nemotron 3 Super cost?
- $0.08 per million input tokens and $0.45 per million output tokens.
- What is NVIDIA: Nemotron 3 Super's context window?
- 262,144 tokens, roughly 393 pages of text in a single request.
- Does NVIDIA: Nemotron 3 Super support tool calling?
- It supports tool calling, structured output, a reasoning mode.
- Can NVIDIA: Nemotron 3 Super process images?
- No, it is text-only on the input side.