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. Do not substitute /v1 for the documented FindAll or Ingest endpoint paths.

​
Have your agent choose an API

Install the choose-your-parallel-api skill to help your coding agent choose the right Parallel API and configuration for your use case. It considers Search and Extract, Responses, and Task, then recommends a mode, reasoning effort, or processor based on your latency, cost, and quality needs.
Install the skill globally so it is available in every project:
Remove --global to install the skill only in your current project. Once installed, describe the integration you are building, including whether a user is waiting for the answer, whether you already have URLs, and how many items you need to process.

View the skill

Read the complete, hosted SKILL.md.

Browse the source

Review the skill and its version history on GitHub.

​
Go straight to a quickstart

Already know which API you want? Jump to its guide.
Choosing an option doesn’t call any Parallel APIs. Try the suggested API with your own examples to see if the results, speed, and cost work for you. See pricing for current rates.