Skip to main content
Markdown document OCR (Qwen3.5, 2B). Accepts one image_url or a document_url PDF; no text-only input. markdown is the only method, and it emits a Markdown string for an image and for each page of a PDF.

Output by method

Text mode emits the string alone for one image, and one <document> / <page> block per PDF, each page carrying format="markdown". In JSON mode an image content is the string, and a document page content is document.page.blocks. The model wraps each page’s Markdown in a fenced ```markdown code block. See Methods & Response Format.

Request

Response

A PDF returns one <document> block per file and one <page> block per page, each carrying format="markdown":
A single image returns the Markdown string alone, with no wrapper.