Nemotron 3.5 Super VL Benchmarks, Pricing & Rankings
NVIDIA · 2026-10-15 · Open · Current
Snapshot 2026-11-06 · updated weekly
Nemotron 3.5 Super VL ranks #59 of 71 on the AMR leaderboard.
Nemotron 3.5 Super VL benchmark scores
Nemotron 3.5 Super VL price, speed & context
Input price
$0.20
per 1M tokens
BaseTen rate card · 2026-10-28
Output price
$0.50
per 1M tokens
Speed
—
tok/s
Context
1.0M
tokens
About Nemotron 3.5 Super VL
Nemotron 3.5 Super VL is NVIDIA’s open multimodal MoE with 120B total / 12B active parameters, taking text, images, documents, GUI screenshots, and video. OpenRouter listed it October 15 at $0.20/$0.50 per million tokens with a 1M context and a free endpoint; Artificial Analysis places the Nemotron 3.5 family between 13 and 26 on its index.
Models around Nemotron 3.5 Super VL in the rankings
More NVIDIA models
Nemotron 3.5 Super VL FAQ
Where does Nemotron 3.5 Super VL rank?
Nemotron 3.5 Super VL ranks #59 of 71 tracked AI models on the AMR aggregate as of October 2026, with an aggregate score of 55.0. Its strongest dimension is AMR at 55.0.
How much does Nemotron 3.5 Super VL cost?
Nemotron 3.5 Super VL costs $0.20 per million input tokens and $0.50 per million output tokens on the standard API. At a typical 1:3 input/output agent workload, that blends to roughly $0.42 per million tokens.
What is the Nemotron 3.5 Super VL context window?
Nemotron 3.5 Super VL supports a 1.0M token context window and generates at a median 0 output tokens per second. That context fits roughly 699 standard documents in a single prompt.
Is Nemotron 3.5 Super VL open source?
Yes — Nemotron 3.5 Super VL ships open weights that you can download and self-host or serve through any compatible inference provider.
What is better than Nemotron 3.5 Super VL?
Clef 2 ranks one place higher at #58 with an AMR score of 56.3. Nemotron 3.5 Super VL still wins 0 of the tracked dimensions head-to-head — check the comparison table to see exactly which.