DeepSeek-V3.2-Exp

    Long-context efficiency with DeepSeek Sparse Attention

    Featured
    135 Votes
    DeepSeek-V3.2-Exp - Long-context efficiency with DeepSeek Sparse Attention media 1
    DeepSeek-V3.2-Exp - Long-context efficiency with DeepSeek Sparse Attention media 2
    DeepSeek-V3.2-Exp - Long-context efficiency with DeepSeek Sparse Attention media 3
    DeepSeek-V3.2-Exp - Long-context efficiency with DeepSeek Sparse Attention media 4
    DeepSeek-V3.2-Exp - Long-context efficiency with DeepSeek Sparse Attention media 5

    Description

    DeepSeek-V3.2-Exp is a new experimental model introducing DeepSeek Sparse Attention (DSA). This new architecture boosts long-context efficiency for training and inference while maintaining the performance of V3.1-Terminus. API prices have been cut by over 50%.

    Recommended Products