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 Flights API takes origin and destination airports, a departure date and an optional return date, and returns flight itineraries. Each result includes the flights, local departure and arrival times, stops and layovers, the lowest listed fare when one is known (in US dollars unless you set currency), and a link to book. Use the Flights API when an agent or application needs bookable flight options: planning a trip, comparing routes and departure times, or checking fares for a date.

1. Set Up Prerequisites

Generate your API key on Platform, then export it:
The Python example below uses requests (pip install requests).

2. Make Your First Flights API Request

Sample Request

The samples use a fixed departure_date. The API rejects a date that has passed, so replace it with a future date before you run them.

Sample Response

The API returns a JSON response with the following structure. The results array below is shortened to a one-stop and a nonstop itinerary. Fields that are not known for an itinerary, such as its price, are left out.
See Response for how to read each field.

3. Search a Round Trip

Add "return_date": "2026-12-08" to the request. Each result then also has an inbound leg, on the same airline as outbound, and price is the round-trip fare. See Round Trips for how the return flight is chosen.

Next Steps