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
Parallel is available on the Google Cloud Marketplace through three listings. Subscribing
through any of them lets you consolidate billing into your Google Cloud account.
.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.Parallel Web Search for Grounding
The Parallel Web Search for Grounding listing provides the Parallel Search API as an external grounding provider in the Google Gemini Enterprise Agent Platform. Requests run through the Gemini Enterprise Agent Platform harness. You can use it either via the API or in Agent Studio. For sensitive workloads, subscribe to the separate Parallel Web Search for Grounding - ZDR listing instead, which adds zero data retention. Using it also requires settingenable_zero_data_retention in your requests.
See Google Gemini Enterprise for setup instructions.
Parallel Web Systems
The Parallel Web Systems listing provides access to the Search, Extract, Task, FindAll, and Monitor APIs with billing consolidated through your Google Cloud account. Zero data retention is available with an enterprise agreement — contactsales@parallel.ai.
This listing does not include Gemini Enterprise grounding. To ground Gemini responses,
subscribe to one of the Parallel Web Search for Grounding listings above.