Anthropic · DeepSeek · OpenAI · api-docs.deepseek.com
DeepSeek-v4-flash-vision-exp
Compiled by KHAO Editorial — aggregated from 1 source + 2 references discovered via search. See llms.txt for citation guidance.
◌ Single Source
Alternatively, a file block can carry the image inline as base64 via file_data instead of file_id (the two are mutually exclusive): For image_url inputs you can optionally set a detail field to control how the image is processed:
Key facts
- The URL must be at most 8192 characters, the image file may be at most 32 MiB, and the download must complete within 60 seconds
- As a result, there is an upper bound of 384 tokens per image: for example, a 2000×2000 image and a 5000×5000 image consume the same number of tokens after resizing
- Unlike inline images, images referenced via Files API file_id may be up to 64 MiB and are not subject to the 32 MiB per-image check
- The encoded data counts toward the 48 MiB request body limit (see Limits )
Summary
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. There are three ways to provide an image to the model. Encode the image and embed it directly in the request as a data: URL. Pass a publicly accessible http(s) link and the model downloads the image for you.