Nemotron 3 Super pricing
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. Built on a hybrid Mamba-Transformer... Live index: 1 priced offer. Best input $0.090 per million tokens from Openrouter. Best output $0.450 per million tokens from Openrouter.
Pricing across providers
Every row is a seller of Nemotron 3 Super with token pricing we track. The cheapest input in this snapshot is from Openrouter. The bar chart shows the same input and output dollars per million for a quick scan.
| Provider | Input / 1M | Output / 1M | Cached input | Batch |
|---|---|---|---|---|
O Openrouter | $0.090 | $0.450 | — | — |
Input vs output · 1M tokens
Cost calculator
The calculator uses the same dollars per million tokens as the table. Adjust sliders to see how Nemotron 3 Super cost scales with traffic.
0.009000¢ / req
0.022500¢ / req
Model specifications
Context length, caps, and capability flags for Nemotron 3 Super. Values follow the main provider (Nvidia) record in our index.
- Context window
- 262,144 tokens
- Max output
- N/A
- Vision (images)
- No
- Tool / function calling
- Yes
- Streaming
- Yes
- Released
- Mar 2026
- Primary provider
- Nvidia
- Model family
- N/A
Compare Nemotron 3 Super
Jump into a comparison when you want one table for two models instead of two tabs. 6 curated matches for Nemotron 3 Super.
- Nemotron 3 Super vs GPT-4o
Compare pricing side by side
- Nemotron 3 Super vs GPT-4o mini
Compare pricing side by side
- Nemotron 3 Super vs Claude Sonnet 4.6
Compare pricing side by side
- Nemotron 3 Super vs Gemini 2.0 Flash
Compare pricing side by side
- Nemotron 3 Super vs o3
Compare pricing side by side
- Nemotron 3 Super vs Llama 3.1 70B
Compare pricing side by side
Frequently asked questions
Answers pull from the same numbers you see on this page. The short model note from our index: 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. Built on a hybrid Mamba-Transformer...
Also from Nvidia
Other models by Nvidia with live pricing in our catalog.