Verified75% confidenceReleaseExact time
DeepSeek launched DeepSeek V4-Flash-Vision-Exp on Hugging Face late on August 31, the first experimental multimodal vision model in the V4 series.
3
Sources
75%
Confidence
Medium-term (~90 days)
Relevance
9/3/2026
First Seen
Valid until: 12/2/2026
Sources
Related Entities
Related Claims
VerifiedDeepSeek has released an experimental multimodal model, DeepSeek V4 Flash Vision EXP, which performs excellently in both text and multimodal tasks.80% similarUnverifiedDeepSeek V4.1 introduces native dynamic vision capabilities, enabling it to understand and process real-time images on screen.74% similarUnverifiedThe DeepSeek team fine-tuned on DeepSeek v4 flash and developed their own visual encoder, DeepSeek ViT.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/849881API
curl https://kongchang.com/api/v1/knowledge/claims/849881MCP
get_claim(id=849881)