# DeepSeek 发布 V4-Flash-Vision-Exp 多模态模型

- 来源：DeepSeek (@deepseek_ai)
- 发布时间：2026-08-21 17:17
- AIHOT 分数：64
- AIHOT 链接：https://aihot.virxact.com/items/cmt2r7c8b04e1ro6tevmtli4y
- 原文链接：https://x.com/deepseek_ai/status/2090730032574631962

## AI 摘要

DeepSeek 推出实验性多模态模型 DeepSeek-V4-Flash-Vision-Exp，文本能力与 V4-Flash 持平，涵盖智能体、推理与世界知识。

## 正文

DeepSeek-V4-Flash-Vision-Exp is now live on the DeepSeek API Platform! 🚀

🔹 This experimental multimodal model matches DeepSeek-V4-Flash on text capabilities—including agents, reasoning, and world knowledge.
🔹 On multimodal agent benchmarks, V4-Flash-Vision-Exp makes a major leap over V4-Flash, bringing multimodal agent performance close to Opus-4.8.

Try it with model='deepseek-v4-flash-vision-exp'. DeepSeek Harness 0.1.1 was released today with out-of-the-box support for the new model.

1/n