NVIDIA

About NVIDIA

NVIDIA pioneered accelerated computing to tackle challenges no one else can solve. Our work in AI and digital twins is transforming the world's largest industries and profoundly impacting society.

Accelerated computing and AI have fully arrived. The acceleration of deep learning ignited the Big Bang of AI. Now, generative AI is a new computing platform, like the PC, internet, and mobile-cloud.

Credit: Runway AI, Adobe, Tabnine, WPP

Website ↗

Source ↗ · 2026-11-12T02:17:03.556571681Z

366 indexed models

366 matching models

nemotron-3-embed-1b

cheaperInference/nemotron-3-embed-1b

Maximum output
32,768
Output modalities
embeddings
Capabilities
embeddings

nemotron-3-embed-8b

cheaperInference/nemotron-3-embed-8b

Maximum output
32,768
Output modalities
embeddings
Capabilities
embeddings

nemotron-3-nano-30b-a3b

cheaperInference/nemotron-3-nano-30b-a3b

Context window
128,000
Maximum output
262,144
Input modalities
text
Output modalities
text
Capabilities
structuredOutputs, toolCalling

Inference prices

Nemotron 3 Nano 30B A3B

vercelAIGatewayCatalog/nvidia/nemotron-3-nano-30b-a3b

NVIDIA Nemotron 3 Nano is an open reasoning model optimized for fast, cost-efficient inference. Built with a hybrid MoE and Mamba architecture and trained on NVIDIA-curated synthetic reasoning data, it delivers strong multi-step reasoning with stable latency and predictable perfo

Context window
262,144
Maximum output
262,144
Input modalities
text
Output modalities
text
Capabilities
reasoning, toolCalling

Inference prices

nemotron-3-super-120b-a12b

cheaperInference/nemotron-3-super-120b-a12b

Context window
256,000
Maximum output
32,000
Input modalities
text
Output modalities
text
Capabilities
structuredOutputs, toolCalling

Inference prices

Nemotron-3-Super-120B-A12B-BF16 · nvidia-ai v1

azureFoundry/nvidia-ai/Nemotron-3-Super-120B-A12B-BF16@1

NVIDIA's BF16 language model with 120B total parameters and 12B active parameters, designed for reasoning, conversation, and tool use.

Context window
262,144
Input modalities
text
Output modalities
text
Capabilities
reasoning, toolCalling

Nemotron 3 Ultra

vercelAIGatewayCatalog/nvidia/nemotron-3-ultra-550b-a55b

A 550B parameter (55B active) open reasoning model from NVIDIA, built for long-running agent workflows. It uses a hybrid Mamba-Transformer MoE architecture and supports a 1M token context window.

Context window
1,000,000
Maximum output
65,000
Input modalities
text
Output modalities
text
Capabilities
promptCaching, reasoning, structuredOutputs, toolCalling

Inference prices

nemotron-3-ultra-550b-a55b

cheaperInference/nemotron-3-ultra-550b-a55b

Context window
1,000,000
Maximum output
65,000
Input modalities
text
Output modalities
text
Capabilities
reasoning, structuredOutputs, toolCalling

Inference prices

Nemotron-3-Ultra-550B-A55B-BF16 · nvidia-ai v1

azureFoundry/nvidia-ai/Nemotron-3-Ultra-550B-A55B-BF16@1

NVIDIA's BF16 language model with 550B total parameters and 55B active parameters, designed for reasoning, conversation, and tool use.

Context window
262,144
Input modalities
text
Output modalities
text
Capabilities
reasoning, toolCalling

nemotron-asr-streaming

nvidiaNim/nvidia/nemotron-asr-streaming

Real-time speech recognition for English

Capabilities
transcription

nemotron-graphic-elements-v1

nvidiaNim/nvidia/nemotron-graphic-elements-v1

Model for object detection, fine-tuned to detect charts, tables, and titles in documents.

nemotron-nano-12b-v2-vl

cheaperInference/nemotron-nano-12b-v2-vl

Context window
131,072
Maximum output
131,072
Input modalities
text, image
Output modalities
text
Capabilities
multimodal, reasoning, structuredOutputs, toolCalling, visionInput

Inference prices

Nemotron Nano 3 30B

awsBedrock/nvidia.nemotron-nano-3-30b

Input modalities
text
Output modalities
text

nemotron-nano-9b-v2

cheaperInference/nemotron-nano-9b-v2

Context window
128,000
Maximum output
131,072
Input modalities
text
Output modalities
text
Capabilities
reasoning, structuredOutputs, toolCalling

Inference prices

nemotron-ocr-v1

nvidiaNim/nvidia/nemotron-ocr-v1

Powerful OCR model for fast, accurate real-world image text extraction, layout, and structure analysis.

Capabilities
ocr

nemotron-ocr-v2

nvidiaNim/nvidia/nemotron-ocr-v2

Nemotron OCR v2 is a state-of-the-art multilingual text recognition model designed for robust end-to-end optical character recognition (OCR) on complex real-world images.

Capabilities
ocr

nemotron-page-elements-v3

nvidiaNim/nvidia/nemotron-page-elements-v3

Model for object detection, fine-tuned to detect charts, tables, and titles in documents.

nemotron-parse

nvidiaNim/nvidia/nemotron-parse

Cutting-edge vision-language model exceling in retrieving text and metadata from images.

Capabilities
ocr, reasoning, toolCalling

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace