DeepSeek's V4-Flash-Vision confirmed, but early users say it underperforms current Flash-Vision

teortaxesTex · x · 2026-09-08

DeepSeek's official page confirmed V4-Flash-Vision (following the leaked model id: new architecture, native multimodality, same price as Flash, 20-request concurrency cap).

However, early user feedback says it's not as capable as even the current Flash-Vision. The poster reads this as expected for a diffusion-based model, speculating deeper diffusion integration in DSpark2.

Original post →

More from Models

Models channel →