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 Shopping API takes keyword queries for products and returns products to buy. Each result links to a store’s product page and includes the product’s title, store, brand, price in the market’s currency, rating, condition, availability and an image. Use the Shopping API when an agent or application needs products a shopper can buy: finding a specific model, comparing products in a category, or checking prices within a budget.

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 Shopping API Request

Sample Request

Each request fetches live listings from many stores.

Sample Response

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

3. Filter by Price and Market

Add "max_price": 250 to the request to return only products priced at most 250 US dollars. Results are new by default; set "condition": "used", "refurbished" or "any" to change that. Set "advanced_settings": {"location": "gb"} to search UK stores, with prices in pounds. See Best Practices for every request field.

Next Steps