DeepSeek-V3
DeepSeek's latest flagship model with enhanced capabilities and efficiency
DeepSeek-V3
DeepSeek • December 2024
Training Data
Up to late 2024
DeepSeek-V3
December 2024
Parameters
671 billion (37B active)
Training Method
Advanced MoE Training
Context Window
128,000 tokens
Knowledge Cutoff
November 2024
Key Features
Advanced Architecture • Improved Efficiency • Enhanced Performance
Capabilities
Reasoning: Outstanding
Coding: Excellent
Efficiency: Outstanding
What's New in This Version
Next-generation architecture with significant efficiency improvements
DeepSeek's latest flagship model with enhanced capabilities and efficiency
What's New in This Version
Next-generation architecture with significant efficiency improvements
Technical Specifications
Key Features
Capabilities
Other DeepSeek Models
Explore more models from DeepSeek
DeepSeek-V4-Pro
DeepSeek's frontier MoE flagship closing the gap with leading proprietary models on reasoning and agentic coding
DeepSeek-V4-Flash
DeepSeek's smaller, fast variant of V4 — same architecture at a fraction of the cost and latency
DeepSeek-V3.2
DeepSeek's latest flagship model matching GPT-5 performance with integrated tool-use thinking
