DeepSeek-v4-flash-vision-exp
The documentation for the DeepSeek-v4-flash-vision-exp model outlines how developers can integrate image analysis capabilities into their applications. It provides technical instructions for using the OpenAI-compatible API to process images via base64 encoding or external URLs.
Why it matters
As multimodal AI models become more accessible, this documentation facilitates the integration of vision capabilities into software, expanding the utility of AI in data analysis.
API Guides Vision On this page Vision The deepseek-v4-flash-vision-exp model accepts images alongside text, so you can ask the model to describe pictures, read text from screenshots, analyze charts, and more.
Supported image formats: JPEG, PNG, GIF, and WebP . The format is detected from the actual file content, not from the file name or the declared MIME type.
There are three ways to provide an image to the model. All of them use the standard OpenAI-compatible Chat Completions format, where content is an array of blocks instead of a plain string. The same three methods are also available in the Responses API , where images are carried in input_image content parts.
The base_url for the examples below is https://api.deepseek.com .
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in