DeepSeek launches multimodal visual understanding model V4-Flash-Vision-Exp
Original title:V4-Flash-Vision-Exp 上线,开启多模态 API 服务
AI summary
DeepSeek launched the multimodal visual understanding model V4-Flash-Vision-Exp, with text capabilities on par with the official V4-Flash and multimodal agent capabilities approaching Opus-4.8. The model is available via API, with images billed by token at up to 384 tokens each, at the same price as V4-Flash. The concurrently launched Files API is free and supports uploading images for reuse via file_id.
Key Takeaways
- DeepSeek launched the multimodal visual understanding model V4-Flash-Vision-Exp,with text…
- The model is available via API,with images billed by token at up to 384 tokens each,at the same…
- The concurrently launched Files API is free and supports uploading images for reuse via file_id.
Quick Facts
- Published
- Updated
- Source
- 公众号:DeepSeek(深度求索)
- Category
- Model Releases
- AI score
- 73
比文本能力持平更实际的是多模态 Agent 能力接近 Opus-4.8,同时图片按 token 计费与 V4-Flash 一致,原先依赖外部视觉模型的 Agent 流程可能改用单一 API 且成本更低。
Related entities
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: DeepSeek launches multimodal visual understanding model V4-Flash-Vision-Exp. August 21, 2026. https://new.nat6.net/en/news/cmta7g6l70515roj25ljc0cqj/