AI Models by NVIDIA | Try NVIDIA NIM APIs

Generates physics-aware video world states for physical AI development using text prompts and multiple spatial control inputs derived from real-world data or simulation.

Model

Synthetic Data Generation

2w

NVIDIA

llama-nemotron-embed-vl-1b-v2

Multimodal question-answer retrieval representing user queries as text and documents as images.

Model

nemo retriever

818K

1mo

NVIDIA

nemotron-content-safety-reasoning-4b

A context‑aware safety model that applies reasoning to enforce domain‑specific policies.

Model

NeMo Guardrails

559K

1mo

NVIDIA

cosmos-reason2-8b

Vision language model that excels in understanding the physical world using structured reasoning on videos or images.

Model

video understanding

221K

2mo

NVIDIA

nemoretriever-page-elements-v3

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

Model

Object Detection

750K

2mo

NVIDIA

nemotron-3-nano-30b-a3b

Open, efficient MoE model with 1M context, excelling in coding, reasoning, instruction following, tool calling, and more

Model

MoE

13.05M

2mo

NVIDIA

riva-translate-4b-instruct-v1_1

Translation model in 12 languages with few-shots example prompts capability.

Model

nvidia nim

558K

2mo

NVIDIA

streampetr

StreamPETR offers efficient 3D object detection for autonomous driving by propagating sparse object queries temporally.

Model

autonomous vehicles

298K

3mo

NVIDIA

nemotron-parse

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

Model

text and table extraction

417K

4mo

NVIDIA

nemotron-nano-12b-v2-vl

Nemotron Nano 12B v2 VL enables multi-image and video understanding, along with visual Q&A and summarization capabilities.

Model

language generation

1.43M

4mo

NVIDIA

llama-3.1-nemotron-safety-guard-8b-v3

Leading multilingual content safety model for enhancing the safety and moderation capabilities of LLMs

Model

content moderation

590K

4mo

NVIDIA

parakeet-ctc-0.6b-zh-tw

Record-setting accuracy and performance for Mandarin Taiwanese English transcriptions.

Model

ASR

384

4mo

NVIDIA

llama-3_2-nemoretriever-300m-embed-v2

Multilingual, cross-lingual embedding model for long-document QA retrieval, supporting 26 languages.

Model

Retrieval Augmented Generation

122K

5mo

NVIDIA

parakeet-ctc-0.6b-zh-cn

Record-setting accuracy and performance for Mandarin English transcriptions.

Model

ASR

7.73K

6mo

NVIDIA

parakeet-ctc-0.6b-es

Accurate and optimized Spanish English transcriptions with punctuation and word timestamps.

Model

ASR

6mo

NVIDIA

parakeet-ctc-0.6b-vi

Accurate and optimized Vietnamese-English transcriptions with punctuation and word timestamps.

Model

ASR

745

6mo

NVIDIA

nvidia-nemotron-nano-9b-v2

High‑efficiency LLM with hybrid Transformer‑Mamba design, excelling in reasoning and agentic tasks.

Model

thinking budget

805K

6mo

NVIDIA

cosmos-reason1-7b

Reasoning vision language model (VLM) for physical AI and robotics.

Model

video understanding

15.93K

7mo

NVIDIA

nemoretriever-ocr-v1

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

Model

Optical Character Recognition

566K

7mo

NVIDIA

parakeet-tdt-0.6b-v2

Accurate and optimized English transcriptions with punctuation and word timestamps

Model

ASR

3.13K

7mo

NVIDIA

llama-3.3-nemotron-super-49b-v1.5

High efficiency model with leading accuracy for reasoning, tool calling, chat, and instruction following.

Model

chat

4.96M

7mo

NVIDIA

llama-3_2-nemoretriever-300m-embed-v1

Multilingual, cross-lingual embedding model for long-document QA retrieval, supporting 26 languages.

Model

Retrieval Augmented Generation

90.75K

7mo

NVIDIA

nemoretriever-ocr

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

Model

Optical Character Recognition

113K

7mo

NVIDIA

magpie-tts-flow

Expressive and engaging text-to-speech, generated from a short audio sample.

Model

TTS

784

8mo

NVIDIA

riva-translate-1.6b

Enable smooth global interactions in 36 languages.

Model

Text Translation

554K

8mo

NVIDIA

llama-3.2-nemoretriever-500m-rerank-v2

GPU-accelerated model optimized for providing a probability score that a given passage contains the information to answer a question.

Model

nemo retriever

1.17K

8mo

NVIDIA

cosmos-transfer1-7b

Generates physics-aware video world states for physical AI development using text prompts and multiple spatial control inputs derived from real-world data or simulation.

Model

Synthetic Data Generation

15.85K

8mo

NVIDIA

Background Noise Removal

Removes unwanted noises from audio improving speech intelligibility.

Model

Nvidia Maxine

389

9mo

NVIDIA

llama-3.2-nemoretriever-1b-vlm-embed-v1

Multimodal question-answer retrieval representing user queries as text and documents as images.

Model

nemo retriever

270K

8mo

NVIDIA

llama-3.1-nemotron-nano-vl-8b-v1

Multi-modal vision-language model that understands text/img and creates informative responses

Model

doc intelligence

8.74M

8mo

NVIDIA

llama-3.1-nemotron-nano-4b-v1.1

State-of-the-art open model for reasoning, code, math, and tool calling - suitable for edge agents

Model

edge

125K

8mo

NVIDIA

magpie-tts-zeroshot

Expressive and engaging text-to-speech, generated from a short audio sample.

Model

TTS

1.26K

9mo

NVIDIA

parakeet-1.1b-rnnt-multilingual-asr

High accuracy and optimized performance for transcription in 25 languages

Model

Automatic Speech Recognition

36.17K

10mo

NVIDIA

llama-3.1-nemotron-ultra-253b-v1

Superior inference efficiency with highest accuracy for scientific and complex math reasoning, coding, tool calling, and instruction following.

Model

chat

8.21M

8mo

NVIDIA

cosmos-predict1-5b

Generates future frames of a physics-aware world state based on simply an image or short video prompt for physical AI development.

Model

Synthetic Data Generation

30.79K

11mo

NVIDIA

sparsedrive

End-to-end autonomous driving stack integrating perception, prediction, and planning with sparse scene representations for efficiency and safety.

Model

autonomous vehicles

109

7mo

NVIDIA

bevformer

Advanced transformer for multi-frame bird's-eye-view 3D perception in autonomous driving.

Model

autonomous vehicles

95

7mo

NVIDIA

llama-3.3-nemotron-super-49b-v1

High efficiency model with leading accuracy for reasoning, tool calling, chat, and instruction following.

Model

chat

1.17M

7mo

NVIDIA

llama-3.1-nemotron-nano-8b-v1

Leading reasoning and agentic AI accuracy model for PC and edge.

Model

chat

647K

8mo

NVIDIA

magpie-tts-multilingual

Natural and expressive voices in multiple languages. For voice agents and brand ambassadors.

Model

TTS

33.87K

8mo

NVIDIA

nv-embedcode-7b-v1

The NV-EmbedCode model is a 7B Mistral-based embedding model optimized for code retrieval, supporting text, code, and hybrid queries.

Model

nemo retriever

263K

9mo

NVIDIA

nemoretriever-table-structure-v1

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

Model

Object Detection

133K

11mo

NVIDIA

nemoretriever-graphic-elements-v1

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

Model

Object Detection

75.25K

11mo

NVIDIA

nemoretriever-page-elements-v2

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

Model

Object Detection

265K

11mo

NVIDIA

nemoretriever-parse

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

Model

optical character recognition

303K

9mo

NVIDIA

canary-1b-asr

Multi-lingual model supporting speech-to-text recognition and translation.

Model

Automatic Speech Recognition

5.07K

11mo

NVIDIA

llama-3.1-nemoguard-8b-topic-control

Topic control model to keep conversations focused on approved topics, avoiding inappropriate content.

Model

nemo guardrails

544K

11mo

NVIDIA

nemoguard-jailbreak-detect

Industry leading jailbreak classification model for protection from adversarial attempts

Model

nemo guardrails

98.93K

8mo

NVIDIA

llama-3.1-nemoguard-8b-content-safety

Leading content safety model for enhancing the safety and moderation capabilities of LLMs

Model

nemo guardrails

566K

11mo

NVIDIA

genmol

Fragment-Based Molecular Generation by Discrete Diffusion.

Model

Chemistry

2.6K

7mo

NVIDIA

cosmos-nemotron-34b

Multi-modal vision-language model that understands text/img/video and creates informative responses

Model

VLM

6

1y

NVIDIA

llama-3.2-nv-embedqa-1b-v2

Multilingual and cross-lingual text question-answering retrieval with long context support and optimized data storage efficiency.

Model

nemo retriever

7.11M

7mo

NVIDIA

llama-3.2-nv-rerankqa-1b-v2

Fine-tuned reranking model for multilingual, cross-lingual text question-answering retrieval, with long context support.

Model

nemo retriever

166K

7mo

NVIDIA

usdcode

State-of-the-art LLM that answers OpenUSD knowledge queries and generates USD-Python code.

Model

OpenUSD

334K

8mo

NVIDIA

nv-yolox-page-elements-v1

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

Model

Object Detection

16.02K

8mo

NVIDIA

audio2face-3d

Converts streamed audio to facial blendshapes for realtime lipsyncing and facial performances.

Model

Speech-to-Animation

9mo

NVIDIA

corrdiff

Generative downscaling model for generating high resolution regional scale weather fields.

Model

AI Weather prediction

909

11mo

NVIDIA

fourcastnet

FourCastNet predicts global atmospheric dynamics of various weather / climate variables.

Model

Weather Simulation

1.16K

11mo

NVIDIA

nemotron-4-mini-hindi-4b-instruct

A bilingual Hindi-English SLM for on-device inference, tailored specifically for Hindi Language.

Model

Indic

526K

9mo

NVIDIA

studiovoice

Enhance speech by correcting common audio degradations to create studio quality speech output.

Model

Nvidia Maxine

640

9mo

NVIDIA

llama-3.1-nemotron-70b-reward

Leaderboard topping reward model supporting RLHF for better alignment with human preferences.

Model

Text-to-text

435K

1y

NVIDIA

nemotron-mini-4b-instruct

Optimized SLM for on-device inference and fine-tuned for roleplay, RAG and function calling

Model

chat

563K

1y

NVIDIA

mistral-nemo-minitron-8b-base

State-of-the-art small language model delivering superior accuracy for chatbot, virtual assistants, and content generation.

Model

language generation

4.84K

1y

NVIDIA

nv-dinov2

NV-DINOv2 is a visual foundation model that generates vector embeddings for the input image.

Model

Image-to-Embedding

1.16M

11mo

NVIDIA

nv-grounding-dino

Grounding dino is an open vocabulary zero-shot object detection model.

Model

Object Detection

3.63K

11mo

NVIDIA

megatron-1b-nmt

Enable smooth global interactions in 36 languages.

Model

Text Translation

11mo

NVIDIA

parakeet-ctc-1.1b-asr

Record-setting accuracy and performance for English transcription.

Model

ASR

42.79K

8mo

NVIDIA

parakeet-ctc-0.6b-asr

State-of-the-art accuracy and speed for English transcriptions.

Model

ASR

8.31K

9mo

NVIDIA

usdsearch

AI-powered search for OpenUSD data, 3D models, images, and assets using text or image-based inputs.

Model

OpenUSD

572

1y

NVIDIA

eyecontact

Estimate gaze angles of a person in a video and redirect to make it frontal.

Model

telepresence

1.36K

11mo

NVIDIA

usdvalidate

Verify compatibility of OpenUSD assets with instant RTX render and rule-based validation.

Model

Validation

790

1y

NVIDIA

nv-embedqa-e5-v5

English text embedding model for question-answering retrieval.

Model

Embedding

3.14M

7mo

NVIDIA

maisi

MAISI is a pre-trained volumetric (3D) CT Latent Diffusion Generative Model.

Model

Image Generation

750

11mo

NVIDIA

llama3-chatqa-1.5-8b

Advanced LLM to generate high-quality, context-aware responses for chatbots and search engines.

Model

text-to-text

554K

9mo

NVIDIA

nvclip

NV-CLIP is a multimodal embeddings model for image and text.

Model

Computer vision

19.7K

9mo

NVIDIA

ocdrnet

OCDNet and OCRNet are pre-trained models designed for optical character detection and recognition respectively.

Model

Optical Character Recognition

735

1y

NVIDIA

nv-embed-v1

Generates high-quality numerical embeddings from text inputs.

Model

Non-Commercial Use Only

1.52M

7mo

NVIDIA

visual-changenet

Visual Changenet detects pixel-level change maps between two images and outputs a semantic change segmentation mask

Model

image

640

1y

NVIDIA

retail-object-detection

EfficientDet-based object detection network to detect 100 specific retail objects from an input video.

Model

Object Detection

823

1y

NVIDIA

rerank-qa-mistral-4b

GPU-accelerated model optimized for providing a probability score that a given passage contains the information to answer a question.

Model

Ranking

151K

1y

NVIDIA

vista-3d

VISTA-3D is a specialized interactive foundation model for segmenting and anotating human anatomies.

Model

Interactive Annotation

718

10mo

NVIDIA

molmim

MolMIM performs controlled generation, finding molecules with the right properties.

Model

Chemistry

16.4K

7mo

NVIDIA

cuopt

World-record accuracy and performance for complex route optimization.

Model

Route Optimization

1.59K

9mo