Search the web
web_search is a $0.20 GET request on the Wuthering AI API. Run a search engine query and get the result list back. It answers complete JSON, and a call that fails is not charged.
Endpoint
GET /v1/web_search
Price per successful call
$0.20
Failed calls
Not charged
curl 'https://wutheringai.com/v1/web_search?query=…&token=YOUR_TOKEN'
What does web_search return, and when should you call it?
Run a query against a search engine and return the organic results as titles, URLs, and snippets.
Live results, not a cached index, so this reflects what a searcher sees now. It returns RESULTS, not volume: to learn how often something is searched use wuthering_keyword_volume. Operators like site: and quoted phrases work and are the fastest way to locate a specific profile or document.
If you have a web search of your own, use that instead to find a URL for another tool: it costs you nothing and answers the same site: query. Call this one when you have none, or when you specifically need what a searcher in a given country sees right now.
Returns: title, url, description for each result, in rank order.
Use to find pages, verify a claim, or locate a profile URL for another tool. Don't use to measure demand.
What parameters does web_search take?
web_search accepts 4 parameters, of which 1 is required. Array values are comma-separated on the query string.
| Parameter | Type | Required | Description |
|---|---|---|---|
| query | string | yes | The search query. Supports operators: site:example.com restricts to one domain, and quoting a phrase requires an exact match. |
| engine | string | no | Which search engine to query. Defaults to google.One of: google, bing, yandexDefaults to google |
| geo_location | string | no | Two-letter country code for geo-targeted results, for example 'us' or 'de'. Defaults to us, matching the default every other tool here uses. Without one the results are targeted at whichever country the request happens to leave from, which is not a property of your question and not one you can see in the answer.Defaults to us |
| cursor | string | no | Pagination cursor from a previous response's next page. |
Which playbooks call web_search?
4 of the research playbooks name web_search in their method. Each is free to read and says where in the sequence the call belongs.
- Is there real demand for this?Test an idea against the cheapest evidence that could kill it — search demand, sustained ad spend, posted salaries, and the words buyers use — and return a verdict with the number that decides it.
- What should we build next?Gather the language of people switching into and out of this category, code every quote to the force that drives it, size each theme against real search demand, and return a 50/50 roadmap.
- Is this company actually growing?Read one company's trajectory from public evidence: branded demand year over year, the acquisition engine underneath it, whether that demand was earned or bought, and what payroll says ships next — then name the questions only a data room can close.
- What would prove us wrong?Turn a belief the plan depends on into an explanation that cannot be bent to fit any result, name the rival explanations that would produce the same evidence, and pay only for the observations that would come out differently under each.
Reference for web_search · last updated · published by Wuthering AI