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
The top large language models for your enterprise AI
Mixture of Experts (MoE) reasoning LLM (text-only) designed to fit within 80GB GPU.
Smaller Mixture of Experts (MoE) text-only LLM for efficient AI reasoning and math
High efficiency model with leading accuracy for reasoning, tool calling, chat, and instruction following.
State-of-the-art open mixture-of-experts model with strong reasoning, coding, and agentic capabilities
The latest innovations in intelligence models
DeepSeek-V3.1: hybrid inference LLM with Think/Non-Think modes, stronger agents, 128K context, strict function calling.
80B parameter AI model with hybrid reasoning, MoE architecture, support for 119 languages.
Excels in agentic coding and browser use and supports 256K context, delivering top results.
DeepSeek V3.1 Instruct is a hybrid AI model with fast reasoning, 128K context, and strong tool use.
Mixture of Experts (MoE) reasoning LLM (text-only) designed to fit within 80GB GPU.
Smaller Mixture of Experts (MoE) text-only LLM for efficient AI reasoning and math
High efficiency model with leading accuracy for reasoning, tool calling, chat, and instruction following.
State-of-the-art open mixture-of-experts model with strong reasoning, coding, and agentic capabilities
A general purpose multimodal, multilingual 128 MoE model with 17B parameters.
A multimodal, multilingual 16 MoE model with 17B parameters.
