DeepSeek-V3.2-Exp is an experimental model version, serving as an intermediate step toward the next-generation architecture. Built on the foundation of V3.1-Terminus, it introduces the DeepSeek Sparse Attention (DSA) mechanism—a sparse attention mechanism designed to explore and validate the optimization of training and inference efficiency in long-context scenarios. This experimental version represents the team's continuous research on more efficient Transformer architectures, with a specific focus on improving computational efficiency when processing long text sequences. For the first time, DSA enables fine-grained sparse attention, which significantly enhances the efficiency of long-context training and inference while maintaining almost unchanged model output quality.
返回模型列表
供应商
在多个供应商之间路由请求。复制供应商标识以设置偏好供应商。
供应商缓存命中率上下文
可用率
24 小时AI Gateway 直连请求及各供应商的成功率。
Sep 28, 23:59
NovitaAI100.00%
吞吐量
24 小时AI Gateway 实时流量的 P50 吞吐量，单位为每秒 token 数（TPS）。
Sep 28, 23:00
NovitaAI10.1 tps
延迟
24 小时AI Gateway 实时流量的 P50 首 token 延迟（TTFT），单位为毫秒。
Sep 28, 23:00
NovitaAI2.61s
活动
该模型随时间变化的 token 用量和请求流量。
Token 消耗
Sep 28
NovitaAI9.7K
按实际处理请求的供应商拆分 token 用量。区块越大，表示该供应商处理的模型流量越多。
Artificial Analysis
Apps
Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for. View All
Token 排行
No app usage is available for this period.
相关模型
更多模型来自 DeepSeek