Subscribe

DeepSeek Sparse Attention (V3.2-Exp)

DeepSeek Sparse Attention (DSA) in V3.2-Exp is fine-grained sparse attention with output quality near V3.1-Terminus, which enabled a 50%+ API price cut.

A trained 'lightning indexer' selects which tokens each query attends to, cutting long-context compute from quadratic toward linear while preserving quality. Released as an experimental model with open weights and an immediate API price cut.

Date
Monday 29 September 2025
Lab
DeepSeek
Kind
paper
Access
open weights
Price
API price cut >50% (2025-09-29)

Figures

MeasureValueMeasured by
API price cut>50%
effective immediately at release
company

The release notes are dated 2025-09-29. The V3.2 paper describes the 'lightning indexer' mechanism.

Sources

  1. api-docs.deepseek.com/news/news250929

This record was checked against its sources on 6 October 2026. How we check

Related