Skip to content
QbitAI · WeChat

DeepSeek’s multimodal AI has entered testing

确认!DeepSeek多模态AI已经开测

DeepSeek researchers confirmed V4 vision mode is in gray testing, with an image-recognition mode on the homepage. A screenshot shows it identified drinks and cup types in a non-text-heavy image after 4 seconds. The post does not disclose rollout scope, API access, or pricing.

Why it matters: DeepSeek researchers confirm the V4 vision version is in gray-scale testing, with an image recognition entry on the homepage and a screenshot showing drink and cup types identified in 4 seconds.

Read the original ↗Export Markdown