DeepSeek-V3.1: hybrid inference LLM with Think/Non-Think modes, stronger agents, 128K context, strict function calling.
High efficiency model with leading accuracy for reasoning, tool calling, chat, and instruction following.
Built for agentic workflows, this model excels in coding, instruction following, and function calling
State-of-the-art open model for reasoning, code, math, and tool calling - suitable for edge agents
Superior inference efficiency with highest accuracy for scientific and complex math reasoning, coding, tool calling, and instruction following.
High efficiency model with leading accuracy for reasoning, tool calling, chat, and instruction following.
Leading reasoning and agentic AI accuracy model for PC and edge.
Advanced LLM for reasoning, math, general knowledge, and function calling
Optimized SLM for on-device inference and fine-tuned for roleplay, RAG and function calling