Deploy Models Now with NVIDIA NIM
Optimized inference for the world’s leading models
Discover
Build with gpt-oss: OpenAI's Latest Open-Weight Reasoning Model
Try NowAchieves near-parity with o4-mini on core reasoning benchmarks, while running efficiently on a single 80 GB GPU.
Featured Models
View AllThe leading open models built by the community, optimized and accelerated by NVIDIA's enterprise-ready inference runtime.
openaigpt-oss-120b
Mixture of Experts (MoE) reasoning LLM (text-only) designed to fit within 80GB GPU.
openaigpt-oss-20b
Smaller Mixture of Experts (MoE) text-only LLM for efficient AI reasoning and math
nvidiallama-3.3-nemotron-super-49b-v1.5
High efficiency model with leading accuracy for reasoning, tool calling, chat, and instruction following.
moonshotaikimi-k2-instruct
State-of-the-art open mixture-of-experts model with strong reasoning, coding, and agentic capabilities
Customize a Blueprint
View AllGet started with workflows and code samples to build AI applications from the ground up.
nvidiaBuild an AI Agent for Enterprise Research
Build artificial general agents (AGA) powered by AGI models that continuously process and synthesize multimodal enterprise data, enabling reasoning, planning, and refinement to generate comprehensive reports.
nvidiaBuild a Video Search and Summarization (VSS) Agent
Ingest massive volumes of live or archived videos and extract insights for summarization and interactive Q&A
nvidiaBuild an Enterprise RAG pipeline
Continuously extract, embed, and index multimodal data for fast, accurate semantic search. Built on world-class NeMo Retriever models, the RAG blueprint connects AI applications to multimodal enterprise data wherever it resides.
nvidiaSafety for Agentic AI
Improve safety, security, and privacy of AI systems at build, deploy and run stages.