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
Search offers four modes, in order of latency. Use .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.turbo for the lowest latency and cost in real-time, high-volume workloads; fast for high-quality, sub-second search across most agent workloads; basic for quick retrieval with extended snippets per result; and advanced for the highest-quality, multi-hop results. If mode isn’t set, requests default to advanced.
Not sure which mode to pick? Start with
fast. It delivers high-quality results in around 700ms and is the right choice for most agents. Reach for turbo when latency and cost matter most for simple, high-volume lookups, basic when you want extended snippets and can spend around a second per call, and advanced when result quality matters more than latency.Available modes
Turbo currently supports English and Japanese-language queries. For broader multilingual coverage, use
basic or advanced.The EU endpoint at
https://eu.parallel.ai supports only basic mode. See EU Data Residency.