DeepSeek-V2
DeepSeek Released May 2024
DeepSeek's flagship MoE model with exceptional efficiency
DeepSeek-V2
DeepSeek • May 2024
Training Data
Up to early 2024
DeepSeek-V2
May 2024
Parameters
236 billion (21B active)
Training Method
Mixture of Experts
Context Window
128,000 tokens
Knowledge Cutoff
February 2024
Key Features
Mixture of Experts • High Efficiency • Open Source
Capabilities
Reasoning: Excellent
Coding: Very Good
Math: Excellent
What's New in This Version
Exceptional performance with MoE architecture efficiency
DeepSeek's flagship MoE model with exceptional efficiency
What's New in This Version
Exceptional performance with MoE architecture efficiency
Technical Specifications
Parameters 236 billion (21B active)
Context Window 128,000 tokens
Training Method Mixture of Experts
Knowledge Cutoff February 2024
Training Data Up to early 2024
Key Features
Mixture of Experts High Efficiency Open Source
Capabilities
Reasoning: Excellent
Coding: Very Good
Math: Excellent
Other DeepSeek Models
Explore more models from DeepSeek
DeepSeek Coder V2
DeepSeek's specialized coding model with advanced programming capabilities
June 2024 236 billion (21B active)
DeepSeek-V3
DeepSeek's latest flagship model with enhanced capabilities and efficiency
December 2024 671 billion (37B active)
DeepSeek-R1-0528
DeepSeek's upgraded reasoning model with 87.5% AIME accuracy and significantly reduced hallucinations
May 2025 671 billion (37B active)