DeepSeek launches multimodal model V4-Flash-Vision-Exp
智东西 · wechat · 2026-08-21
DeepSeek released an experimental multimodal model, V4-Flash-Vision-Exp, built upon the V4-Flash base. It significantly boosts visual understanding, with multimodal agent capabilities approaching Opus 4.8. The API supports image-text inputs, billing images at a max of 384 tokens at the same rate as text. DeepSeekHarness has been updated to support the model for tasks like visual programming and content generation.
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