Saturday, August 22, 2026
DeepSeek launches its first multimodal AI model
DeepSeek released DeepSeek-V4-Flash-Vision-Exp on August 21, an experimental model that opens its API to image inputs alongside text for the first time, billed at the same per-token rate as the existing V4-Flash model. The model scored 27.3 on the Agents Last Exam benchmark, ahead of Anthropic's Opus 4.8 at 25.7, and DeepSeek says its vision pipeline uses roughly 90 KV-cache entries per image versus about 870 for Claude's vision system.
/ Sources
/ About this story
Compiled by Venture Atlas from the sources above, using automated AI-assisted research. This is a summary of reporting published elsewhere, not original reporting - follow the source links for the full account. See our editorial standards.
Something wrong here? Email flightatlas.contact@gmail.com and we will fix it.
/ Related
- Anthropic to let enterprises keep AI data on their own cloudSaturday, August 22, 2026
- Unitree Robotics shares surge in Shanghai IPO debutSaturday, August 22, 2026
- Claude autonomously designs protein binders in lab testsSaturday, August 22, 2026
- OpenAI Q2 revenue hits $6.7B as Anthropic overtakes it in salesThursday, August 20, 2026