Try NVIDIA NIM APIs

models

Reasoning Vision Visual Design Retrieval Speech Biology Simulation Safety & Moderation

industries

Most Popular Foundation Models

The leading open models built by the community, optimized and accelerated by NVIDIA's enterprise-ready inference runtime

PREVIEW

nvidia

llama-3.1-nemotron-70b-instruct

chat

language generation

Llama-3.1-Nemotron-70B-Instruct is a large language model customized by NVIDIA in order to improve the helpfulness of LLM generated responses.

RUN ANYWHERE

meta

llama-3.1-405b-instruct

synthetic data generation

chat

Advanced LLM for synthetic data generation, distillation, and inference for chatbots, coding, and domain-specific tasks.

PREVIEW

meta

llama-3.2-90b-vision-instruct

image captioning

image-text retrieval

Cutting-edge vision-Language model exceling in high-quality reasoning from images.

PREVIEW

meta

llama-3.2-3b-instruct

chat

language generation

Advanced state-of-the-art small language model with language understanding, superior reasoning, and text generation.

PREVIEW

nvidia

nemotron-4-340b-reward

reward model

synthetic data generation

Grades responses on five attributes helpfulness, correctness, coherence, complexity and verbosity.

RUN ANYWHERE

meta

llama-3.1-8b-instruct

chat

language generation

Advanced state-of-the-art model with language understanding, superior reasoning, and text generation.

RUN ANYWHERE

nv-mistralai

mistral-nemo-12b-instruct

chat

code generation

Most advanced language model for reasoning, code, multilingual tasks; runs on a single GPU.

RUN ANYWHERE

mistralai

mixtral-8x22b-instruct-v0.1

advanced reasoning

chat

An MOE LLM that follows instructions, completes requests, and generates creative text.

A fast generative text-to-image model that can synthesize photorealistic images from a text prompt in a single network evaluation

PREVIEW

nvidia

nemotron-4-340b-instruct

chat

synthetic data generation

Creates diverse synthetic data that mimics the characteristics of real-world data.

Cutting-edge text generation model text understanding, transformation, and code generation.

PREVIEW

microsoft

phi-3-vision-128k-instruct

language generation

vision assistant

Cutting-edge open multimodal model exceling in high-quality reasoning from images.

Align Models with Human Preferences

RewardBench leaderboard topping Llama 3.1-Nemotron-70B-Reward model improve the quality of your model's responses

Try Now

Explore NIM Agent Blueprints

View All Agent Blueprints

Reference code with guides for customization and deployment of applications built with NVIDIA NIM and partner microservices

Build a Video Search and Summarization Agent

llama-3_1-70b-instruct •nv-embedqa-e5-v5 •nv-rerankqa-mistral-4b-v3

Ingest massive volumes of live or archived videos and extract insights for summarization and interactive Q&A

Build an AI Virtual Assistant

llama-3_1-70b-instruct •nv-rerankqa-mistral-4b-v3 •nv-embedqa-e5-v5

customer service

retrieval-augmented generation

contact center

llm

Create intelligent virtual assistants for customer service across every industry

Vulnerability Analysis for Container Security

Rapidly identify and mitigate container security vulnerabilities with generative AI.

Multimodal PDF Data Extraction

google-deplot •nv-rerankqa-mistral-4b-v3 •nv-embedqa-e5-v5

Ingest and extract highly accurate insights contained in text, graphs, charts, and tables within massive volumes of PDF documents.

Build a Digital Human

audio2face •llama3-8b •parakeet-ctc-1_1b-asr

Create intelligent, interactive avatars for customer service across industries

Build A Generative Virtual Screening Pipeline

alphafold2 •molmim-generate •diffdock

This blueprint shows how generative AI and accelerated NIM microservices can design optimized small molecules smarter and faster.

Integrate Generative AI into OpenUSD Blueprints

Leverage generative AI copilots and agents to develop OpenUSD tools that accelerate the creation of 3D worlds.

PREVIEW

nvidia

usdcode-llama3-70b-instruct

chat

code generation

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

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

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

Trained on Licensed Data with NVIDIA Edify

The latest visual design models built with licensed creative libraries

Shutterstock Generative 3D service for 3D asset generation. Trained on NVIDIA Edify using Shutterstock’s licensed creative libraries

Getty Images’ API service for 4K image generation. Trained on NVIDIA Edify using Getty Images' commercially safe creative libraries.

Explore by Outcome

Discover new use-cases and the right set of APIs to turbocharge your enterprise

Retrieval Augmented Generation

Chat with Your Enterprise Knowledge

Ground large language models in proprietary enterprise intelligence to improve reasoning accuracy

Digital Humans

Bring Avatars to Life with Generative AI

Transforming interactions in customer service, gaming, telepresence, and virtual factories

Combine Visual and Language Intelligence

Multimodal models that can reason against text or image input

Generative AI for Drug Discovery

State- of-the-art protein structure prediction, molecular generation, and molecular docking models

Predicts the 3D structure of a protein from its amino acid sequence.

RUN ANYWHERE

ipd

proteinmpnn

amino acid prediction

bionemo

ProteinMPNN is a deep learning model for predicting amino acid sequences for protein backbones.

Generates embeddings of proteins from their amino acid sequences.

Predicts the 3D structure of a protein from its amino acid sequence.

A generative model of protein backbones for protein binder design.

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

Predicts the 3D structure of how a molecule interacts with a protein.

Predicts the 3D structure of a protein from its amino acid sequence.

Simulate and Optimize Real World Outcomes

Operations research and prediction algorithms to predict plausible real life outcomes

PREVIEW

nvidia

ai-weather-forecasting

ai weather prediction

climate science

AI based weather prediction pipeline with global models and downscaling models.

World-record accuracy and performance for complex route optimization.

Most Popular Foundation Models

Explore NIM Agent Blueprints

Integrate Generative AI into OpenUSD Blueprints

Trained on Licensed Data with NVIDIA Edify

Explore by Outcome

Retrieval Augmented Generation

Chat with Your Enterprise Knowledge

Digital Humans

Bring Avatars to Life with Generative AI

Combine Visual and Language Intelligence

Generative AI for Drug Discovery

Simulate and Optimize Real World Outcomes

Combine Visual and Language Intelligence

microsoft/kosmos-2

adept/fuyu-8b

nvidia/neva-22b