Sign in

v1

latestOpenAPI 3.0.1Z.AI Developer Agreement and Policy2026-07-131458163.2 KB

The Web Search is a specialized search engine for large language models. Building upon traditional search engine capabilities like web crawling and ranking, it enhances intent recognition to return results better suited for LLM processing (including webpage titles, URLs, summaries, site names, favicons etc.).

post/paas/v4/web_search

Headers

Accept-Language'en-US,en'

Config desired response language for HTTP requests.

Example:en-US,en

Request body

search_engine'search-prime' required

The search engine code to call. search-prime: Z.AI Premium Version Search Engine

search_querystring required

The content to be searched.

countinteger

The number of results to return Fillable range: 1-50, maximum 50 results per single search Default is 10 Supported search engines: search_pro_jina.

search_domain_filterstring

Used to limit the scope of search results and only return content from specified whitelist domains. Whitelist: Directly enter the domain name (e.g., www.example.com) Supported search engines: search_pro_jina

search_recency_filter'oneDay' | 'oneWeek' | 'oneMonth' | 'oneYear' | 'noLimit'

Search for webpages within a specified time range. Default is noLimit Fillable values: oneDay: within one day oneWeek: within one week oneMonth: within one month oneYear: within one year noLimit: no limit (default) Supported search engines: search_pro_jina

request_idstring

Passed by the user side, needs to be unique; used to distinguish each request, 6–64 characters. If not provided by the user side, the platform will generate one by default.

user_idstring

Unique ID for the end user, 6–128 characters. Avoid using sensitive information.

Example request

{
  "search_engine": "search-prime"
}

Response

Processing successful

idstring

Task ID.

createdinteger

Request creation time, Unix timestamp in seconds.