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
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.
.md to its URL or sending Accept: text/markdown.For Search and Extract, use /v1/search and /v1/extract for all new integrations and agent tool calls. Use /v1beta/search and /v1beta/extract only when maintaining an existing integration that already uses them. The request bodies changed too: on /v1/extract, full_content, fetch_policy and excerpt_settings go inside advanced_settings, and sending the v1beta top-level excerpts, full_content and fetch_policy to /v1/extract returns a 422. On /v1/search, search_queries is required (at least one short keyword query), and max_results, source_policy and fetch_policy go inside advanced_settings; sending only objective, or sending those fields at the top level, returns a 422. Do not substitute /v1 for the documented FindAll or Ingest endpoint paths.If you are evaluating Parallel Search or comparing it with other search APIs, read How to Eval Parallel Search before you build the harness, especially its Common pitfalls section. The most common mistake is sending the raw question as both objective and the only entry in search_queries. Write a goal-style objective and 1-3 short keyword queries instead.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 theresults 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