Models
Deploy and scale models on your GPU infrastructure of choice with NVIDIA NIM inference microservices
models
Extract PII character spans and confidence scores with the Fastino GLiNER2 privacy filter.Free Endpointgliner2-pii
3T-class open model with 1M-token context specialized for agentic coding, 3D modeling, and financeDownloadableFree Endpointkimi-k3.1-pro
Mistral Large 4 from Mistral AI, a 1T-total / 52B-active granular MoE for text and image input with reasoning, function calling and structured outputs, served in NVFP4 with DSpark speculative decoding.Free EndpointMistral Large 4
8B multimodal reranking model that scores how relevant a text or document-image passage is to a query.Free Endpointnemotron-3.5-rerank-8b
1B multimodal embedding model for text and document-image retrieval in RAG applications.Free Endpointnemotron-3.5-embed-1b
8B multimodal embedding model for text and document-image retrieval in RAG applications.Free Endpointnemotron-3.5-embed-8b
MiniMax-M3.1-Flash is a native multimodal mixture-of-experts model for coding, agentic workflows, computer use, and cybersecurity.Free Endpointminimax-m3.1-flash
A unified generative model for protein, enzyme, binder and antibody design.Free Endpointrfd4-proteina
FLUX 3 Image Klein is a state-of-the-art open-weight image generation and editing modelDownloadableflux-3-image-klein
Nemotron 3.5 Super early-access reasoning model for agentic, coding, tool-calling, and multimodal workloadsFree Endpointnemotron-3.5-super-vl-120b-a12b
Preview of StepFun's Step 5: ~600B-total / 27B-active multimodal MoE (text and image in, text out) with 1M context, reasoning and tool calling, served in NVFP4.Free EndpointStep 5 Preview
A tabular in-context learning model for classification and regression over structured tables.DownloadableFree EndpointKumo Tabular
A relational foundation model for prediction over structured, multi-table data.DownloadableFree EndpointKumo Relational
Multimodal 320B-total / 18B-active MoE with hybrid KDA and sparse MLA attention, native FP8 weights, reasoning and tool calling.Free Endpointglm-5-3-flash
Multilingual ASR across 25 European languages with punctuation, capitalization, and word timestampsDownloadableparakeet-tdt-0.6b
Wan2.2-Animate-2 is a novel end-to-end character animation frameworkDownloadablewan2.2-animate-2-14b
Fastest 30B A3B MoE model with leading domain accuracy for specialized agentic tasksDownloadableFree Endpointnemotron-3.5-lightning-30b-a3b
Muse Glimmer 30B is a multimodal reasoning model accepting text and images, with native tool-calling and separate reasoning output.DownloadableFree Endpointmuse-glimmer-30b
Translation model in 37 languages with few-shots example prompts capability.Free Endpointriva-translate-4b-instruct-v2
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.Free Endpointising-calibration-1.5-31b
Upscale encoded or ST 2110 video to higher resolutions with NVIDIA Video Super Resolution.DownloadableVideo Super Resolution NIM
Items per page
of 4 pages