DeepSeek V4.1-Flash cuts KV cache to 1/4 HBM and 1/8 SSD

DeepSeek says its V4.1-Flash model needs only 1/4 the HBM and 1/8 the SSD storage for its KV cache compared with the previous generation. Because cache-hit charges often make up a large share of agent costs, the company says the compressed cache significantly reduces those costs.