Skip to main content
Explore
Models
Skills
Blueprints
GPUs
Docs
Search
⌘K
Ctrl+K
?
Help Center
Getting Started
1
Set up your account
Create and verify your account to unlock full access to NVIDIA NIM APIs.
Create an Account
2
Generate API Key
3
Make your first API call
4
Prototype in your environment
5
Connect to inference partners
Resources
Developer Forums
Contact Support
FAQs
Login
Discover
Models
Skills
Blueprints
GPUs
Docs
Forums
workstations
Run on RTX
Run on Spark
Run on Station
models
Reasoning
Vision
Visual Design
Retrieval
Speech
Biology
Simulation
Climate & Weather
Safety & Moderation
industries
Automotive
Financial Services
Gaming
Healthcare
Industrial
Robotics
Reasoning
Deploy Models Now with NVIDIA NIM
Optimized inference for the world’s leading models
Get API Key
Free serverless APIs for development
Accelerated by DGX Cloud
Self-Host on your GPU infrastructure
Continuous vulnerability fixes
Fresh Off the Press
The latest innovations in intelligence models
Moonshotai
Downloadable
Free Endpoint
kimi-k3
~2.8T hybrid KDA+MLA multimodal MoE for long-horizon coding, agentic tool use, and image understanding.
Mixture-of-Experts
+2
Multimodal
Reasoning
1d
Last updated on August 27, 2026
DeepSeek AI
Free Endpoint
deepseek-v4-pro-0813
DeepSeek V4 scales to 1M-token context windows with efficient MoE architecture for coding tasks.
Moe
+3
agentic
coding
reasoning
1d
Last updated on August 26, 2026
Wan-ai
Downloadable
wan2.2-animate-2-14b
Wan2.2-Animate-2 is a novel end-to-end character animation framework
character animation
+1
video editing
9d
Last updated on August 19, 2026
DeepSeek AI
Free Endpoint
deepseek-v4-flash-0731
284B MoE (13B active) model ideal for long-context workloads optimized for coding, chat, and agentic workflows
Hybrid Attention
+3
Long Context
MoE
Reasoning
9d
Last updated on August 19, 2026
NVIDIA
Downloadable
Free Endpoint
nemotron-3.5-lightning-30b-a3b
Fastest 30B A3B MoE model with leading domain accuracy for specialized agentic tasks
Customization
+3
Long-running agents
Open
Text-to-Text
17d
Last updated on August 11, 2026
Meta
Downloadable
Free Endpoint
muse-glimmer-30b
Muse Glimmer 30B is a multimodal reasoning model accepting text and images, with native tool-calling and separate reasoning output.
Chat
+5
Image-to-Text
Large Language Models
Multimodal
Reasoning
Text-to-Text
18d
Last updated on August 10, 2026
NVIDIA
Free Endpoint
riva-translate-4b-instruct-v2
Translation model in 37 languages with few-shots example prompts capability.
neural machine translation
+1
nvidia nim
1mo
Last updated on July 27, 2026
NVIDIA
Free Endpoint
ising-calibration-1.5-31b
NVIDIA-Ising-Calibration-1.5 is a dense multimodal vision-language model built on Gemma 4 31B. It analyzes quantum computing calibration experiment plots and generates structured technical text.
Calibration
+3
NVIDIA NIM
Quantum Computing
Vision Language Model
1mo
Last updated on July 23, 2026
NVIDIA
Downloadable
Video Super Resolution NIM
Upscale encoded or ST 2110 video to higher resolutions with NVIDIA Video Super Resolution.
broadcast
+4
nvidia ai for media
streaming
video super resolution
video upscaling
1mo
Last updated on July 22, 2026
NVIDIA
Free Endpoint
nemotron-3-embed-1b
1B embedding model for semantic search, retrieval, and RAG applications.
Agentic Retrieval
+2
Code Retrieval
Nemotron Retriever
1mo
Last updated on July 16, 2026
Developer Favorites
The top large language models for your enterprise AI
Moonshotai
Downloadable
Free Endpoint
kimi-k3
~2.8T hybrid KDA+MLA multimodal MoE for long-horizon coding, agentic tool use, and image understanding.
Mixture-of-Experts
+2
Multimodal
Reasoning
1d
Last updated on August 27, 2026
DeepSeek AI
Free Endpoint
deepseek-v4-pro-0813
DeepSeek V4 scales to 1M-token context windows with efficient MoE architecture for coding tasks.
Moe
+3
agentic
coding
reasoning
1d
Last updated on August 26, 2026
NVIDIA
Downloadable
Free Endpoint
nemotron-3.5-lightning-30b-a3b
Fastest 30B A3B MoE model with leading domain accuracy for specialized agentic tasks
Customization
+3
Long-running agents
Open
Text-to-Text
17d
Last updated on August 11, 2026
NVIDIA
Downloadable
Free Endpoint
nemotron-3-ultra-550b-a55b
Open, efficient hybrid Mamba-Transformer MoE with 1M context, excelling in agentic reasoning, coding, planning, tool calling, and more
Agent
+4
Frontier
Long Context
MoE
Reasoning
52M
52M API calls in the last 30 days
2mo
Last updated on June 4, 2026
NVIDIA
Downloadable
Free Endpoint
cosmos3-nano-reasoner
Vision language model that excels in understanding the physical world using structured reasoning on videos or images.
Physical AI
+7
autonomous vehicles
industrial
reasoning
robotics
smart cities
video understanding
vision language model
2K
2K API calls in the last 30 days
2mo
Last updated on June 1, 2026
NVIDIA
Downloadable
Free Endpoint
nemotron-3-nano-omni-30b-a3b-reasoning
Nemotron 3 Nano Omni is an omni-modal reasoning model that understands images, video, speech, text.
OCR
+3
Omni
VLM
Video
8M
8M API calls in the last 30 days
4mo
Last updated on April 28, 2026
Google
Downloadable
Free Endpoint
gemma-4-31b-it
Dense 31B model delivering frontier reasoning for coding, agentic workflows, and fine-tuning.
agentic
+3
coding
reasoning
text-to-text
6M
6M API calls in the last 30 days
4mo
Last updated on April 2, 2026
OpenAI
Downloadable
Free Endpoint
gpt-oss-20b
Smaller Mixture of Experts (MoE) text-only LLM for efficient AI reasoning and math
chat
+3
math
reasoning
text-to-text
19M
19M API calls in the last 30 days
1y
Last updated on August 5, 2025
NVIDIA
Downloadable
Free Endpoint
nemotron-3-nano-30b-a3b
Open, efficient MoE model with 1M context, excelling in coding, reasoning, instruction following, tool calling, and more
Instruction Following
+3
Long Context
MoE
Reasoning
12M
12M API calls in the last 30 days
8mo
Last updated on December 15, 2025