DeepSeek has released DeepSeek-V4-Flash-Vision-Exp, an experimental multimodal version of its V4-Flash model that gives developers native image understanding through the DeepSeek API for the first time. The model, called by setting model='deepseek-v4-flash-vision-exp', went live on the DeepSeek API platform on August 21, 2026. According to DeepSeek's own release notes, it performs on par with the text-only DeepSeek-V4-Flash on language, reasoning and world-knowledge tasks, while delivering what the company calls a significant leap on benchmarks that require visual understanding — enough, it says, to bring the model's multimodal agent performance close to Anthropic's Opus 4.8.
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.
Unlocking the full article...
Contact us
Questions, corrections, or ideas? Send us a message here. We aim to reply by email within 24 hours.
Thank you. Your message has been sent. We aim to reply by email within 24 hours.Please enter your email address and a message.We could not send your message. Please try again in a little while.