Blog DeepSeek V3
Deepseek v3.2 API
DeepSeek v3.2 is the latest production release in the DeepSeek V3 family: a large, reasoning-first open-weight language model family designed for long-context understanding, robust agent/tool use, advanced reasoning, coding and math.
How to Use Deepseek v3.2 API
DeepSeek released DeepSeek V3.2 and a high-compute variant DeepSeek-V3.2-Speciale, with a new sparse-attention engine (DSA), improved agent/tool behaviour and
What is DeepSeek V3.2— and what official version’s changed
DeepSeek has released DeepSeek V3.2 as the successor to its V3.x line and an accompanying DeepSeek-V3.2-Speciale variant that the company positions as a
How to Access DeepSeek-V3.2-Exp API
DeepSeek released an experimental model called DeepSeek-V3.2-Exp on September 29, 2025, introducing a new sparse-attention mechanism (DeepSeek Sparse
DeepSeek-V3.1-Terminus: Feature, Benchmarks and Significance
DeepSeek-V3.1-Terminus is the most recent refinement of the DeepSeek family — a hybrid, agent-oriented large language model (LLM) that DeepSeek positions as a
How to deploy deepseek-v3.1 locally via ollama: The Eastest Guide
DeepSeek-V3.1 is a hybrid “thinking / non-thinking” MoE language model (671B total, ≈37B activated per token) that can be run locally if you use the right
How to Run DeepSeek-V3.1 on your local device
DeepSeek-V3.1 is a hybrid Mixture-of-Experts (MoE) chat model released by DeepSeek in August 2025 that supports two inference modes — a fast “non-thinking”
DeepSeek V3.1 API
DeepSeek V3.1 is the newest upgrade in DeepSeek’s V-series: a hybrid “thinking / non-thinking” large language model aimed at high-throughput, low-cost general intelligence and agentic tool use. It keeps OpenAI-style API compatibility, adds smarter tool-calling, and—per the company—lands faster generation and improved agent reliability.