Nemotron 3.5 Super VL
NVIDIA's mid-size Nemotron 3.5 that reads images, and one of the fastest models on the board.
NVIDIA, reads images, open weights. Checked 30 October 2026.
Where to use it through an API
NVIDIAnvidia/nemotron-3.5-super-vl-120b-a12bFree key
The maker publishes its own benchmarks and limits on its model page.
How it compares
The models just above and below it on the Artificial Analysis Intelligence Index.
| Model | Index | Context | Speed |
|---|---|---|---|
| DeepSeek V4 Pro | 23 | 1M | 74/s |
| Qwen3.8 27B | 20 | 256K | 36/s |
| MiniMax M3 | 19 | 1M | 103/s |
| Nemotron 3.5 Super VL | 14 | 1M | 444/s |
| Gemini 3.5 Flash-Lite | 12 | 1M | 439/s |
| Nemotron 3 Ultra | 12 | 262K | 158/s |
| Command A+ | 6 | 192K | 158/s |
Use Nemotron 3.5 Super VL with every other AI at once
Put Nemotron 3.5 Super VL in one panel and ChatGPT, Claude, Gemini or any of 300+ models in the others. One message goes to all of them, answers arrive side by side, and test mode times them and hides the names so you judge fairly. Free during the beta with your own keys.
Questions
Is there a free Nemotron 3.5 Super VL API?
Yes, within limits: NVIDIA give free keys that reach Nemotron 3.5 Super VL.
What is the Nemotron 3.5 Super VL model id?
NVIDIA: nvidia/nemotron-3.5-super-vl-120b-a12b.
How does Nemotron 3.5 Super VL score?
14 on the Artificial Analysis Intelligence Index, checked 30 October 2026.
Can I use Nemotron 3.5 Super VL with ChatGPT, Claude and Gemini at the same time?
Yes. MultiScreenAI puts Nemotron 3.5 Super VL in one panel and other models in the others, sends one message to all of them and shows the answers side by side.