DeepSeek V4-vision-exp launches API with ultra-fast speed and low cost

teortaxesTex · x · 2026-08-21

DeepSeek has released the V4-vision-exp model via API. It processes images using just 117-384 tokens at V4-Flash price points. Early reports highlight its magically fast inference speed, positioning it as a strong contender in terms of speed and cost, potentially disrupting rivals like the Whale Inference Fleet.

Related event: DeepSeek Launches V4-vision-exp: Fast and Low-Cost Vision Model(2 posts)→

Original post →

More from Models

Models channel →