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-V3.2
DeepSeek's latest flagship model matching GPT-5 performance with integrated tool-use thinking
DeepSeek-V3.2-Speciale
DeepSeek's competition-focused variant (EXPIRED Dec 15, 2025 - was temporary API-only release)
DeepSeek-V2
DeepSeek's flagship MoE model with exceptional efficiency
