ModelBench
Model catalog

Models

Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.

Compare Export CSV
7 models
Video NVIDIA 32K+
NVIDIA: Nemotron 3.5 Super VL 120B A12B T
Reasoning Tools Open weights

NVIDIA vision-language reasoning model for text, image, and video understanding and agentic tool use

nvidia/nemotron-3.5-super-vl-120b-a12b 2026-10-15 1.04858M context $0.08/M input $0.45/M output
5 providers
NVIDIA: Nemotron 3 Nano Omni 30B A3B Reasoning T
Reasoning Tools Open weights

Open Nemotron omni model combining reasoning with text, vision, and audio

nvidia/nemotron-3-nano-omni-30b-a3b-reasoning 2026-04-28 256K context $0.1/M input $0.25/M output
6 providers
NVIDIA: Nemotron Nano 12B v2 VL T
Reasoning Tools Open weights

Nemotron multimodal model for visual reasoning and agentic AI workflows

nvidia/nemotron-nano-12b-v2-vl 2025-10-28 128K context $0.2/M input $0.6/M output
3 providers
NVIDIA: NVIDIA: Nemotron 3 Nano Omni (free) T

NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and...

nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free 256K context Free input Free output
NVIDIA: NVIDIA: Nemotron Nano 12B 2 VL (free) T

NVIDIA Nemotron Nano 2 VL is a 12-billion-parameter open multimodal reasoning model designed for video understanding and document intelligence. It introduces a hybrid Transformer-Mamba architecture, combining transformer-level accuracy with Mamba’s...

nvidia/nemotron-nano-12b-v2-vl:free 128K context Free input Free output
NVIDIA: NVIDIA: Nemotron 3.5 Super VL T

NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...

nvidia/nemotron-3.5-super-vl 262.144K context $0.15/M input $0.5/M output
NVIDIA: NVIDIA: Nemotron 3.5 Super VL (free) T

NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...

nvidia/nemotron-3.5-super-vl:free 1M context Free input Free output