DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...
Tokens processed for this model through Reroute, per day, over the last 30 days.
Daily token volume shows up here as soon as the first request for this model completes.