NVIDIA
Nemotron 3 Super
NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications.
At a glance
- Input / 1M
- $0.08
- Output / 1M
- $0.45
- Context
- 262K
- Max output
- 236K
- Intelligence
- 12.8
- Released
- Mar 2026
Pricing
Nemotron 3 Super API pricing
Per-token rates, plus what common tasks actually cost.
| Input tokensPer 1M tokens | $0.08 |
|---|---|
| Output tokensPer 1M tokens | $0.45 |
| Cached input (read)Per 1M tokens | Not available |
| Cache writePer 1M tokens | Not available |
Chat message
2K in, 500 out
$0.39
per 1,000 requests
Coding task
30K in, 4K out
$4.20
per 1,000 requests
Long document summary
150K in, 2K out
$12.90
per 1,000 requests
Benchmarks
Nemotron 3 Super benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
12.8
Coding index
37.7
Agentic index
1.7
Specs
Context window and capabilities
What it can read, what it can write, and which API features it supports.
- Context window
- 262K tokens
- Max output
- 236K tokens
- Input types
- Text
- Output types
- Text
- Reasoning effort
- Medium, Low
- Release date
- March 11, 2026
- Tool calling
- Structured outputs
- JSON mode
- Reasoning
- Temperature
- Stop sequences
- Deterministic seed
- Verbosity control
Compare
Nemotron 3 Super vs other models
See how Nemotron 3 Super stacks up head to head on price, benchmarks, and features.
Nemotron 3 Super vs Gemini 2.5 Flash Lite
NVIDIA vs Google
See comparison
Nemotron 3 Super vs gpt-oss-120b
NVIDIA vs OpenAI
See comparisonNemotron 3 Super vs Gemma 4 31B
NVIDIA vs Google
See comparisonNemotron 3 Super vs GPT-5 Nano
NVIDIA vs OpenAI
See comparisonNemotron 3 Super vs GLM 4.7 Flash
NVIDIA vs Z.ai
See comparison
Nemotron 3 Super vs Qwen3 235B A22B Instruct 2507
NVIDIA vs Qwen
See comparisonAlternatives
Nemotron 3 Super alternatives
Similar models worth considering, and where each one has the edge.
Z.ai
GLM 4.7 Flash
Gemma 4 31B
DeepSeek
DeepSeek V3.1
Want to learn about other models? Browse all models
FAQ
Frequently asked questions
How much does Nemotron 3 Super cost?
Nemotron 3 Super costs $0.08 per 1M input tokens and $0.45 per 1M output tokens through the API. A typical chat message costs about $0.39 per 1,000 messages.
What is the context window of Nemotron 3 Super?
Nemotron 3 Super accepts up to 262K tokens of input and can write up to 236K tokens in a single response.
What is the best alternative to Nemotron 3 Super?
GLM 4.7 Flash from Z.ai is a strong alternative. It offers: 1.1x cheaper output, higher intelligence score.
Can I use Nemotron 3 Super alongside other models?
Yes. Shortcut Chat sends one prompt to Nemotron 3 Super and any other models you pick at the same time, so you can compare answers side by side.
Try Nemotron 3 Super next to every other model.
Use Nemotron 3 Super alongside all the other models. Use one at a time, or multiple together. Get the best answer from every AI.