DeepSeek releases multimodal model V4-Flash-Vision-Exp with free Files API

heypearlai · x · 2026-08-21

DeepSeek launched V4-Flash-Vision-Exp, an experimental model adding vision capabilities to the V4-Flash text engine, performing close to Opus 4.8 on multimodal agent benchmarks. It also released a free Files API allowing image uploads via fileid to avoid resending data in requests.

Related event: DeepSeek Launches V4-Flash-Vision-Exp, Closing In on Opus 4.8(29 posts)→

Original post →

More from coding & agent

coding & agent channel →