Skip to main content
For AI agents: a documentation index is available at https://docs.parallel.ai/llms.txt. The full text of all docs is at https://docs.parallel.ai/llms-full.txt. You may also fetch any page as Markdown by appending .md to its URL or sending Accept: text/markdown.
The Extract API converts any public URL into clean markdown, including JavaScript-heavy pages and PDFs. It returns focused excerpts aligned to your objective, or full page content if requested.
See Pricing for a detailed schedule of rates.

1. Set Up Prerequisites

Generate your API key on Platform. Then, set up with the TypeScript SDK, Python SDK or with cURL:

2. Execute Your First Extract

Extract clean markdown content from specific URLs. This example retrieves content from the UN’s history page with excerpts focused on the founding:

Response Structure

Each result in the results array contains:
Both excerpts and full_content return content formatted as markdown. This includes links as [text](url), headings, lists, and other markup. If you need plain text, strip the markdown formatting in your application.

Sample Response

Next Steps

  • Best Practices — learn about objectives, fetch policies, and excerpt settings
  • API Reference — full parameter specifications, constraints, and response schema
  • Rate Limits — default quotas per product