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.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.
The advanced_settings object on the Extract API lets you tune fetch behavior (cached vs live), excerpt sizing, and full content extraction. Extract uses a dynamic fetch policy by default and may request the source website when indexed content does not meet its freshness criteria. Extract does not offer a documented cache-only security guarantee. For the Search API’s default behavior, see Does Search fetch pages live?.
On /v1/extract, fetch_policy, excerpt_settings and full_content must be inside advanced_settings. Sending the v1beta top-level excerpts, full_content or fetch_policy fields to /v1/extract returns a 422. See the migration guide.

Fields

Fetch Policy

The fetch_policy parameter controls when to return indexed content (faster) or fetch fresh content from the source (fresher). Fetching fresh content may take up to a minute and is subject to rate limits to manage the load on source websites.

Excerpt and Full Content Settings

Both excerpt_settings and full_content are configured inside the advanced_settings object. Enable full content with custom excerpt sizes:
Enable full content with default excerpts:
Notes:
  • When full_content is enabled, you’ll receive both excerpts and full content in the response
  • Excerpts are always focused on relevance; full content always starts from the beginning
  • Without objective or search_queries, excerpts will be redundant with full content. The request still succeeds, but may return less relevant content and may include a warning.
  • max_chars_total (top-level) controls total excerpt size but does not affect full content