Models

models

• NVIDIA

  Free Endpoint

  nemotron-3.5-parse

  Extract text, tables, and document layout from page images.
• NVIDIA

  Free Endpoint

  Nemotron 3.5 Bolt E4B

  Compact text model for reasoning, tool calling, and agentic chat.
• NVIDIA

  Free Endpoint

  nemotron-3.5-rerank-8b

  8B multimodal reranking model that scores how relevant a text or document-image passage is to a query.
• NVIDIA

  Free Endpoint

  nemotron-3.5-embed-1b

  1B multimodal embedding model for text and document-image retrieval in RAG applications.
• NVIDIA

  Free Endpoint

  nemotron-3.5-embed-8b

  8B multimodal embedding model for text and document-image retrieval in RAG applications.
• NVIDIA

  Free Endpoint

  nemotron-3.5-super-vl-120b-a12b

  Nemotron 3.5 Super early-access reasoning model for agentic, coding, tool-calling, and multimodal workloads
• NVIDIA

  DownloadableFree Endpoint

  Kumo Tabular

  A tabular in-context learning model for classification and regression over structured tables.
• NVIDIA

  DownloadableFree Endpoint

  3D Body Pose

  Estimate 3D human body pose and skeleton from video input.
• NVIDIA

  DownloadableFree Endpoint

  Kumo Relational

  A relational foundation model for prediction over structured, multi-table data.
• NVIDIA

  Downloadable

  nemotron-parse-2.0

  Cutting-edge vision-language model excelling in retrieving text and metadata from images.
• NVIDIA

  Downloadable

  parakeet-tdt-0.6b

  Multilingual ASR across 25 European languages with punctuation, capitalization, and word timestamps
• NVIDIA

  DownloadableFree Endpoint

  nemotron-3.5-lightning-30b-a3b

  Fastest 30B A3B MoE model with leading domain accuracy for specialized agentic tasks
• NVIDIA

  Free Endpoint

  riva-translate-4b-instruct-v2

  Translation model in 37 languages with few-shots example prompts capability.
• 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.
• NVIDIA

  Downloadable

  Video Super Resolution NIM

  Upscale encoded or ST 2110 video to higher resolutions with NVIDIA Video Super Resolution.
• NVIDIA

  Free Endpoint

  nemotron-3-embed-1b

  1B embedding model for semantic search, retrieval, and RAG applications.
• 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
• 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.
• 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
• NVIDIA

  DownloadableFree Endpoint

  nemotron-3.5-content-safety

  Multilingual, multimodal model for detecting unsafe and toxic content.
• NVIDIA

  DownloadableFree Endpoint

  cosmos3-nano

  Generates images, videos and action predictions from text, visual inputs and spatial controls, with mandatory input screening and visual SynthID watermarking.
• NVIDIA

  DownloadableFree Endpoint

  cosmos3-nano-reasoner

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

  Downloadable

  Relighting

  Re-illuminate people in video to match target lighting from a 360 HDRI environment map.