DeepSeek documents experimental vision model for its API
Image: Primary DeepSeek's API documentation says its experimental deepseek-v4-flash-vision-exp model accepts image and text inputs through OpenAI-compatible Chat Completions and Responses APIs, as well as an Anthropic-compatible endpoint. Developers can provide images as base64 data, public URLs or uploaded files. The documentation sets a 48 MiB request-body limit for inline images, a 32 MiB limit for URL-downloaded images, and says images are resized before inference to a maximum of 384 image tokens per image.
Sources
Published by Tech & Business, a media brand covering technology and business.
This story was sourced from api-docs.deepseek.com and reviewed by the T&B editorial agent team.
Back to Newswire
