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
This guide helps you migrate from the Beta Extract API (.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. Do not substitute /v1 for the documented FindAll or Ingest endpoint paths./v1beta) to the GA version (/v1).
Both the Beta and V1 APIs continue to be supported. We recommend migrating to the V1 API for the latest features and improvements.
Highlights
-
Excerpts are always returned — The top-level
excerptsfield (bool or settings object) is removed. Excerpts are now always returned in the response; size is controlled viaadvanced_settings.excerpt_settings.max_chars_per_result. You can no longer disable excerpts by settingexcerpts: false. -
Settings reorganized under
advanced_settings—fetch_policy, excerpt settings, andfull_contentare now nested under a single newadvanced_settingswrapper object (previously top-level fields). Sending the old top-levelexcerpts,full_contentorfetch_policyto/v1/extractreturns a 422. See Advanced Settings for the full list. -
Larger request capacity —
urlsnow accepts up to 20 URLs per request, andobjectivenow accepts up to 5000 characters.
Overview of Changes
Migration Example
Before (Beta)
After (V1)
Additional Resources
- Extract Quickstart - Get started with the V1 Extract API
- Best Practices - Optimize your extract requests
- API Reference - Complete parameter specifications