Models

Moonshotai
DownloadableFree Endpoint
kimi-k3
~2.8T hybrid KDA+MLA multimodal MoE for long-horizon coding, agentic tool use, and image understanding.
Multimodal
Mixture-of-Experts
Reasoning
Image-to-Text
DeepSeek AI
Free Endpoint
deepseek-v4-pro-0813
DeepSeek V4 scales to 1M-token context windows with efficient MoE architecture for coding tasks.
coding
Moe
reasoning
agentic
Wan-ai
Downloadable
wan2.2-animate-2-14b
Wan2.2-Animate-2 is a novel end-to-end character animation framework
video editing
character animation
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
MoE
Reasoning
Long Context
Hybrid Attention
NVIDIA
DownloadableFree Endpoint
nemotron-3.5-lightning-30b-a3b
Fastest 30B A3B MoE model with leading domain accuracy for specialized agentic tasks
Customization
Text-to-Text
Long-running agents
Open
Meta
DownloadableFree Endpoint
muse-glimmer-30b
Muse Glimmer 30B is a multimodal reasoning model accepting text and images, with native tool-calling and separate reasoning output.
Multimodal
Image-to-Text
Reasoning
Chat
Text-to-Text
Large Language Models
NVIDIA
Free Endpoint
riva-translate-4b-instruct-v2
Translation model in 37 languages with few-shots example prompts capability.
nvidia nim
neural machine translation
Text Translation
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.
Quantum Computing
Calibration
NVIDIA NIM
Vision Language Model
NVIDIA
Downloadable
Video Super Resolution NIM
Upscale encoded or ST 2110 video to higher resolutions with NVIDIA Video Super Resolution.
broadcast
video upscaling
streaming
nvidia ai for media
video super resolution
NVIDIA
Free Endpoint
nemotron-3-embed-1b
1B embedding model for semantic search, retrieval, and RAG applications.
Nemotron Retriever
Agentic Retrieval
Code Retrieval
Text-to-Embedding
Retrieval Augmented Generation
Poolside
Free Endpoint
laguna-xs-2.1
Efficient 33B MoE for local, long-horizon agentic coding and terminal tasks
Agentic AI
Coding
Reasoning
Tool Use
NVIDIA
Downloadable
qwen-image-edit-nvpcb-ovsl2sl
An image edit model specialized for Omniverse synthetic to photographic solder-light style captured at NVIDIA PCB inspection stations
Synthetic Data Generation
Image Generation
Physical AI
NVIDIA
Downloadable
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.
Table Extraction
nemo retriever
data ingestion
extraction
Optical Character Recognition
Minimaxai
Deprecation in 2dFree Endpoint
minimax-m3
MiniMax M3 Preview is a multimodal MoE vision-language model with strong reasoning, coding, and tool-calling capabilities.
coding
text-to-text
reasoning
Google
DownloadableFree Endpoint
diffusiongemma-26b-a4b-it
Diffusion-based 26B parameter LLM enabling parallel token generation for real-time text apps
diffusion-llm
text-to-text
reasoning
NVIDIA
DownloadableFree 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
MoE
Frontier
Reasoning
Long Context
Resemble.AI
Downloadable
chatterbox-multilingual-tts
Natural and expressive voices in 23 languages. For voice agents and brand ambassadors.
TTS
Chatterbox
Speech Generation
multilingual
Text-to-Speech
NVIDIA
DownloadableFree Endpoint
nemotron-3.5-content-safety
Multilingual, multimodal model for detecting unsafe and toxic content.
llm safety
safety and moderation
multilingual content safety
ai safety nemo guardrails
NVIDIA
DownloadableFree Endpoint
cosmos3-nano
Generates physics-aware videos from text prompts or an image prompt for physical AI development.
autonomous vehicles
Physical AI
robotics
text-to-world
image-to-world
Synthetic Data Generation
NVIDIA
DownloadableFree Endpoint
cosmos3-nano-reasoner
Vision language model that excels in understanding the physical world using structured reasoning on videos or images.
video understanding
autonomous vehicles
industrial
Physical AI
vision language model
reasoning
robotics
smart cities
Synthetic Data Generation
Qwen
Downloadable
qwen-image
Qwen-Image is a text-to-image foundation model with advanced multilingual text rendering.
Text-to-Image
Image Generation
Qwen
Downloadable
qwen-image-edit
Qwen-Image-Edit is an image editing model with multilingual text editing and strong subject consistency.
Text-to-Image
Image Generation
NVIDIA
DownloadableFree Endpoint
nemotron-3-nano-omni-30b-a3b-reasoning
Nemotron 3 Nano Omni is an omni-modal reasoning model that understands images, video, speech, text.
Image-to-Text
VLM
Video
Omni
OCR
NVIDIA
Downloadable
Relighting
Re-illuminate people in video to match target lighting from a 360 HDRI environment map.
HDRI
remote contribution
lighting
nvidia ai for media