What a searcher is trying to do
keyword_intent is a $0.20 GET request on the Wuthering AI API. Classify keywords as informational, commercial, navigational, or transactional. It answers complete JSON, and a call that fails is not charged.
Endpoint
GET /v1/keyword_intent
Price per successful call
$0.20
Failed calls
Not charged
curl 'https://wutheringai.com/v1/keyword_intent?keywords=…&token=YOUR_TOKEN'
What does keyword_intent return, and when should you call it?
Classify up to 1,000 keywords by what the searcher is trying to accomplish, with a confidence probability for each.
Intent is language-scoped, not location-scoped, so this tool takes no location. High volume on informational terms and none on commercial ones is a demand signal worth acting on.
Returns: keyword, keyword_intent.label, and keyword_intent.probability, which is confidence in the assigned label rather than a score per label.
The four labels: informational wants to learn, navigational wants a specific site, commercial is comparing options before buying, and transactional is ready to buy now. The commercial and transactional split is the one that matters most and the easiest to misread: 'best crm software' is commercial, 'buy crm software' is transactional.
Use to separate people who want to buy from people who want to read. Don't use as a volume source; it reports intent only.
What parameters does keyword_intent take?
keyword_intent accepts 2 parameters, of which 1 is required. Array values are comma-separated on the query string.
| Parameter | Type | Required | Description |
|---|---|---|---|
| keywords | array | yes | Keywords to look up, up to 1000 in one call. This is one billed call regardless of how many you send, so batch aggressively rather than looping. A batch whose rows exceed what one response can carry comes back trimmed, stating how many rows it held and how many it returned; terms missing from a trimmed response were withheld, not measured as having no data. |
| language_code | string | no | ISO language code for results, for example 'en' or 'de'. Defaults to 'en'.Defaults to en |
Which playbooks call keyword_intent?
7 of the research playbooks name keyword_intent 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.
- Where is the unoccupied position in this category?Map the category around one domain as an idea maze — the forks it has already run, who took each branch, which walls are still walls and which have moved — then return the one open position with the offer that takes it: buyer, bundle, price metric and message, decided together.
- Who are we really up against?Work April Dunford's positioning sequence from public evidence: the alternatives a prospect would actually use, what only you do, the value that follows, who cares most, and the category that makes all of it obvious.
- What do we charge, and does the money work?Anchor price against what competitors actually charge and meter on, size willingness to pay from what the problem costs today, then run CAC, LTV and payback across three scenarios.
- Where do the next 1,000 customers come from?Score every plausible channel against the product's own characteristics, measure the reachable demand and the cost of entry for each, and commit to one with its CAC and its ceiling stated.
- 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.
- 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 keyword_intent · last updated · published by Wuthering AI