DeepSeek Launches V4-Flash Multimodal Model, Agent Capability Near Opus-4.8
DeepSeek · wechat · 2026-08-21
DeepSeek has released an experimental multimodal vision model, DeepSeek-V4-Flash-Vision-Exp. While its pure text capabilities match the official V4-Flash, it achieves significant improvements in vision-related Agent benchmarks, approaching the performance of Opus-4.8.
The model demonstrates strong multimodal adaptability within Agent frameworks, supporting complex workflows such as generating business custom PPTs, website redesigns, and dynamic frontend demos.
Regarding API, images are billed by tokens (max 384 tokens) at the same rate as V4-Flash. It supports three formats (ChatCompletions, Messages, Responses) and various image input methods. Additionally, the free FilesAPI is now live, allowing image uploads for reuse via fileid.
Related event: DeepSeek Launches V4-Flash-Vision-Exp, Closing In on Opus 4.8(29 posts)→
More from Models
- Meta's coding-optimized open-weight Muse Spark Open lands on Modal with 1M context — AAAzzam · 2026-10-16
- Google launches Gemini 4 Argon frontier model on Cloud with 10 official demos — Saboo_Shubham_ · 2026-10-16
- RL practitioner: ~10,000 tasks still stump every frontier coding model — max_paperclips · 2026-10-16
- SpecID eval falls: Gemini 3.5 Flash scores 67%, beating its human creator at Zimbabwean species ID — johnowhitaker · 2026-10-16
- Researcher criticizes Claude for lecturing users and refusing critical takes on tech firms — BlancheMinerva · 2026-10-16
- Chart: Meta went 492 days without an open-weight release before Muse Spark Open — demian_ai · 2026-10-16