DeepSeek launches V4-Flash Vision model for multimodal agents
AI寒武纪 · wechat · 2026-08-21
DeepSeek released the experimental multimodal model DeepSeek-V4-Flash-Vision-Exp, adding vision capabilities to the Flash series.
- Performance: Text capabilities match V4-Flash; multimodal agent performance approaches Claude Opus-4.8.
- API Updates: Supports ChatCompletions, Messages, and Responses. Images can be sent via base64, URL, or Files API.
- Files API: Now available for free; upload images once and reference by fileid to save bandwidth.
- Cost: Images charged by tokens (max 384 tokens/image), consistent with V4-Flash pricing.
This update significantly expands the operational scope of agents in visual scenarios like screenshot analysis and chart understanding.
Related event: DeepSeek Launches V4-Flash-Vision-Exp, Closing In on Opus 4.8(29 posts)→
More from Models
- Meta releases Muse Spark Open: 816B-param open-weight model with 1M context, natively multimodal — IanAndrewsDC · 2026-10-16
- llama.cpp adds day-0 support for Meta's 816B Muse Spark Open within 30 minutes — ngxson · 2026-10-16
- Muse Spark vs Qwen and GLM: US open models still trail on agentic tasks — zsakib_ · 2026-10-16
- Muse Spark 816B gets llama.cpp support just 30 minutes after release — ngxson · 2026-10-16
- 24 AI Systems Recommend $314 Per Visit in Care vs Physicians' $97, a 3.2x Gap — dvir_a · 2026-10-16
- Are the fastest GPU kernels now written by AI? Kernels are hyper-verifiable, argues one dev — fleetwood___ · 2026-10-16