29
OpenTools Scorenormalized /100
Context262.1K tokens
CategoryLarge Language Model
About Nemotron 3 Super
Nemotron 3 Super is NVIDIA's 120B-parameter model with 12B active parameters. Its default Hugging Face configuration uses 256K context; NVIDIA documents up to 1M model context with additional VRAM. Hosted endpoint limits may differ.
Capabilities
textcode
Input Modalities
text
Output Modalities
text
Technical Details
- API Identifier
- nvidia/nemotron-3-super-120b-a12b:free
- Category
- Large Language Model
- Context Window
- 262,144 tokens
Tags
long-context
Competing Models
Same pricing tier — direct alternatives to Nemotron 3 Super
-- / --Compare
NVIDIAenterprise
The Engine of AI
2 Tools6 ModelsFounded 1993Santa Clara, California, United States
View full profileTools by NVIDIA
Other AI tools from the same organization.
AI Models by NVIDIA
Large language models from the same organization.
| Model | Context Window | Price (In / Out per M) |
|---|---|---|
| Nemotron 3.5 Lightning 30B A3BCurrent | 1.0M | $0.10 / $0.95 |
| Nemotron 3 SuperCurrent | 262K | $0.09 / $0.45 |
| Nemotron 3 Nano 30B A3BCurrent | 256K | -- / -- |
| Nemotron 3 Nano 30B A3BCurrent | 262K | $0.05 / $0.20 |
| EagleCurrent | -- | -- / -- |
Related News
Latest coverage and updates.
AI Costs Spiral as Agentic Systems Burn 1000x More Tokens Than Chatbots
Jun 1, 2026
Meta Cuts 1400 Washington Jobs as $145B AI Bet Reshapes Its Workforce
May 28, 2026
Chinese AI Models Hit 60% of OpenRouter Usage as Pricing War Threatens OpenAI, Anthropic IPOs
May 26, 2026
Anthropic's 80x Growth Sends It Scrambling for SpaceX Compute as Musk Becomes AI Landlord
May 8, 2026
Amazon's Best Quarter in Years Was Half-Built on a $16.8B Anthropic Paper Gain
May 4, 2026
How to Run Local AI Coding Agents Without Rate Limits or Bills
May 3, 2026