N
Nemotron 3.5 Super VLOPEN
NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total.
Prices update automatically — checked daily against provider list prices.
- $0.24 per 1M tokens, assuming 3 input for 1 output the convention used by Artificial Analysis
- cheaper than 57% of the 200 open-weight models tracked here
- 10 of 12 NVIDIA models tracked here, from cheapest
Benchmarks & performance
Independent benchmark scores for Nemotron 3.5 Super VL, measured by Artificial Analysis. Higher is better.
For the same budget, Nemotron 3.5 Super VL delivers 6 times more capability. Open weights also mean you can self-host it and pay nothing per token.
Models at this level cost $0.85 per 1M tokens (median of 5) — this one costs $0.24.
Cheaper and better on this index: Claude Haiku 5.5 · Claude Haiku 5.5 (batch) · GPT-6 Luna and 2 more
About this model
Nemotron 3.5 Super VL is an open-weight AI model by NVIDIA. You can download and self-host it for free; the prices below are hosted-API list prices, tracked daily, for when you prefer convenience over self-hosting.
Frequently asked questions
What is Nemotron 3.5 Super VL?
Nemotron 3.5 Super VL is an AI language model from NVIDIA. It is open-weight: you can download it and run it on your own hardware, for free. It scores 13.6 on the Artificial Analysis intelligence index.
Is Nemotron 3.5 Super VL free?
The weights are free and open — you can self-host Nemotron 3.5 Super VL and pay nothing per token. If you prefer a hosted API, list prices are $0.15 per million input tokens and $0.5 per million output tokens.
What is Nemotron 3.5 Super VL good at?
Independent benchmarks from Artificial Analysis give it Humanity's Last Exam 30.7%, Long Context Reasoning 69%, SciCode 47.8%.
How fast is Nemotron 3.5 Super VL?
It generates about 443.7 tokens per second, with a median 0.52s delay before the first token. Measured independently by Artificial Analysis.
Can I self-host Nemotron 3.5 Super VL?
Yes. Nemotron 3.5 Super VL has open weights, so you can download it and run it on your own GPU or server with tools like Ollama, vLLM or llama.cpp — with no per-token cost.