DeepSeek today announced that the new multimodal vision understanding model, DeepSeek-V4-Flash-Vision-Exp, is now available on the DeepSeek API platform. This model is experimental and can be accessed by setting model="deepseek-v4-flash-vision-exp". Its text-only performance is comparable to the official DeepSeek-V4-Flash release, while it demonstrates significantly improved performance on vision-enabled agent benchmarks, with multimodal agent capabilities approaching those of Opus-4.8.
DeepSeek Launches DeepSeek-V4-Flash-Vision-Exp for Multimodal API Service
TechFlowShare
Summary
DeepSeek has launched DeepSeek-V4-Flash-Vision-Exp, a new model listing on its multimodal API platform. Users can now access the experimental model via model="deepseek-v4-flash-vision-exp". On-chain data shows the model outperforms prior versions on visual benchmarks, with multimodal capabilities approaching Opus-4.8 levels. This update enhances functionality for developers and businesses utilizing AI-powered visual analysis.
Source:Show original
Disclaimer: The information on this page may have been obtained from third parties and does not necessarily reflect the views or opinions of KuCoin. This content is provided for general informational purposes only, without any representation or warranty of any kind, nor shall it be construed as financial or investment advice. KuCoin shall not be liable for any errors or omissions, or for any outcomes resulting from the use of this information.
Investments in digital assets can be risky. Please carefully evaluate the risks of a product and your risk tolerance based on your own financial circumstances. For more information, please refer to our Terms of Use and Risk Disclosure.