⌘KCtrl+K
Deploy Models Now with NVIDIA NIM
Optimized inference for the world’s leading modelsFree serverless APIs for development
Self-Host on your GPU infrastructure
Continuous vulnerability fixes
Ctrl+K
The top large language models for your enterprise AI
Smaller Mixture of Experts (MoE) text-only LLM for efficient AI reasoning and math
Open, efficient MoE model with 1M context, excelling in coding, reasoning, instruction following, tool calling, and more
Vision language model that excels in understanding the physical world using structured reasoning on videos or images.
DeepSeek V3.1 Instruct is a hybrid AI model with fast reasoning, 128K context, and strong tool use.
The latest innovations in intelligence models
1T multimodal MoE for high‑capacity video and image understanding with efficient inference.
A context‑aware safety model that applies reasoning to enforce domain‑specific policies.
Vision language model that excels in understanding the physical world using structured reasoning on videos or images.
State-of-the-art 685B reasoning LLM with sparse attention, long context, and integrated agentic tools.
Open, efficient MoE model with 1M context, excelling in coding, reasoning, instruction following, tool calling, and more
State-of-the-art open code model with deep reasoning, 256k context, and unmatched efficiency.
