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.

Run Statuses and Termination Reasons

FindAll runs normally progress from queued → running → a terminal state (completed, failed, or cancelled). The response schema also defines cancelling and action_required for compatibility with the shared run-status contract. A run is active when status.is_active is true. The shared status schema treats queued, running, and cancelling as active, although current FindAll cancellation moves directly from an active state to cancelled.

Status Definitions

You can extend a non-preview run while it is queued or running. A completed run can be extended only when its termination_reason is match_limit_met. Enrichments can be added after creation; adding one to any terminal run requeues that run while the enrichment is processed. Cancellation applies to active runs.

Termination Reasons

When a run reaches a terminal state, it will have one of these termination reasons:
  • Generators and Pricing: Understand generator options and pricing
  • Preview: Test queries with 5–10 evaluated candidates before running full searches
  • Enrichments: Extract additional structured data for matched candidates
  • Extend Runs: Increase match limits without paying new fixed costs
  • Streaming Events: Receive real-time updates via Server-Sent Events
  • Webhooks: Configure HTTP callbacks for run completion and matches
  • API Reference: Complete endpoint documentation