NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16

nvidia/nvidia-nemotron-3.5-super-vl-120b-a12b-bf16

Full-precision BF16 release of NVIDIA Nemotron 3.5 Super VL for reasoning, coding, tool use and document/video understanding. It combines Mamba-2, MoE and attention with a C-RADIO vision encoder, has 120B total and 12B active parameters, and supports up to 1M tokens of context.

Compare

Context window: 1M
Input: Text · Image · Video
Output: Text
Released: 2026-10-15

Model parameters: 120B
Active parameters: 12B
Weights: Open
License: OpenMDW-1.1
Capabilities: Reasoning, Tool call

Pricing

No official pricing available.

Estimate usage cost

Compare verified public prices for this exact model and region. Enter uncached input and cache usage separately. Estimates exclude unspecified fees, credits and currency conversion. Set requests to zero to estimate token charges only.

Input tokens

Output tokens

Cache read tokens

Cache write tokens

Requests

Context tokens (optional)

Currency

Batch processing

Performance

No evaluation results available.

Providers

No providers found

ModelRegistry · Catalog updated 2026-10-21