Extract

JSON

extract.json() -> ExtractJsonResponse

POST/extract/json

Markdown

extract.markdown() -> ExtractMarkdownResponse

POST/extract/markdown

ModelsExpand Collapse

Dict[str, object]

class ExtractMarkdownResponse: …

content: str

The markdown content (includes metadata as YAML frontmatter by default)

url: str

The URL that was converted to markdown

formaturi

metadata: Optional[Metadata]

Extracted metadata from the page (only included when metadata parameter is true)

author: Optional[str]

Author information from HTML metadata

created_at: Optional[str]

Document creation date (ISO 8601)

creator: Optional[str]

Creator application (e.g., “Microsoft Word”)

description: Optional[str]

Page description from Open Graph or HTML

image: Optional[str]

Featured image URL from Open Graph

formaturi

keywords: Optional[List[str]]

PDF keywords as array

modified_at: Optional[str]

Document modification date (ISO 8601)

page_count: Optional[int]

Number of pages (PDF documents)

pdf_version: Optional[str]

PDF version (e.g., “1.5”)

producer: Optional[str]

PDF producer software (e.g., “Adobe PDF Library”)

publisher: Optional[str]

Publisher information from Open Graph

site_name: Optional[str]

Site name from Open Graph

subject: Optional[str]

PDF-specific metadata fields (populated for PDF documents) PDF subject or summary

title: Optional[str]

Page title from Open Graph or HTML

type: Optional[str]

Content type from Open Graph (e.g., article, website)

url: Optional[str]

Canonical URL from Open Graph

formaturi