智能体
www.aibase.com ·
DeepSeek V4.1 Flash 发布：原生多模态视觉理解，主打低成本与高吞吐
AIbase 报道称 DeepSeek 发布轻量模型 V4.1 Flash，采用 552B 参数 MoE 架构与新的 Causal-Encoder-Decoder 结构，输入激活 8B、输出激活 16B，官方称在多项基准上超过 V4Pro。效率方面 KV Cache 大幅压缩，HBM 需求降至上一代 1/4、SSD 降至 1/8，Agent 场景上下文存储成本下降。模型已上线 DeepSeek API，模型名改为 deepseek-flash，旧版 V4Flash 与 V4Flash Vision Exp 停用，9 月 14 日起 deepseek-v4-pro 请求将路由至 V4.1Flash 并按新单价计费；腾讯 WorkBuddy、CodeBuddy、OpenCode 等合作方已接入。上述性能与成本数据来自媒体报道，尚待官方基准与文档核实。
AI推荐理由 内容给出 DeepSeek V4.1 Flash 的具体架构与成本数据（552B MoE、Causal-Encoder-Decoder、输入激活 8B/输出激活 16B、KV Cache 压缩、HBM 需求降至 1/4、SSD 降至 1/8），并说明 API 模型名切换、旧版本停用与 V4Pro 路由计划，对开发者和 Agent 场景有实际参考价值。但来源为 AIbase 聚合媒体，非官方公告，缺少可核验的基准测试细节与官方链接，'全面超越 Pro 版'等表述需保留不确定性，故质量分中等。
72
正文
Performance Soars and Prices Drop! DeepSeek V4.1 Flash Released: Native Multimodal Visual Understanding Fully Exceeds the Pro Version
AIbase基地
Published inAI News · 4 min read · Sep 10, 2026
3
DeepSeek has officially released the smallest member of its new model architecture series today - DeepSeek V4.1Flash. As a lightweight model with native multi-modal visual understanding capabilities, it is designed to achieve higher capability limits, faster inference speeds, larger throughput, and the potential for expansion to larger parameter models.
In terms of core architecture, DeepSeek V4.1Flash adopts a 552B parameter MoE (Mixture of Experts) architecture and innovatively introduces a new Causal-Encoder-Decoder structure. Due to its asymmetric input and output design, the input activation is only 8B, and the output activation is 16B, significantly reducing the overall cost compared to known models of the same size. Combined with a new pre-training method and larger-scale reinforcement learning post-training, this model has successfully surpassed a range of flagship models including DeepSeek V4Pro in various benchmark tests.
In terms of efficiency optimization and cost control, the new model has significantly reduced the size of the KV Cache. Compared to the previous generation, V4.1Flash's demand for high-bandwidth memory (HBM) has been reduced to 1/4, and the demand for solid-state drives (SSD) has been reduced to 1/8. Especially in Agent use scenarios, where the cost of context storage and cache hits is relatively high, this compression greatly reduces the actual usage cost for related tasks. According to statistics, the KV Cache has been reduced to 1/437 of the original size compared to the initial model.
With the official launch of the new model, DeepSeek has made systematic adjustments to its product line and billing strategy. DeepSeek V4.1Flash is now available on the DeepSeek API, and users can simply change the model name to deepseek-flash to call it. The old versions of V4Flash and V4Flash Vision Exp have been officially discontinued, while the old model names (deepseek-v4-flash and deepseek-v4-flash-vision-exp) are currently temporarily routed to V4.1Flash. Given that V4.1Flash has comprehensively surpassed V4Pro in performance, cost, speed, and total usage time, the official plans to gradually discontinue the V4Pro model: after 12:00 on September 14, 2026, until the release of V4.1Pro, all requests to access deepseek-v4-pro will be routed to V4.1Flash and charged at its unit price. Currently, official partners such as WorkBuddy, CodeBuddy, and OpenCode under Tencent have fully integrated this model.
This article is from AIbase Daily
Scan to view
Welcome to the [AI Daily] column! This is your daily guide to exploring the world of artificial intelligence. Every day, we present you with hot topics in the AI field, focusing on developers, helping you understand technical trends, and learning about innovative AI product applications.
—— Created by the AIbase Daily Team
© Copyright AIbase Base 2024, Click to View Source -