# keyword-extract

> keyword-extract is a paid API for AI agents from intel.rallylive.ca, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-14).

Extracts the top 20 terms and top bigrams by frequency from a webpage, plus title and description, to summarize what the page is about.

## Facts

- Endpoint: GET https://intel.rallylive.ca/site/keywords
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/keyword-extract-36386084
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_Roh29kqPpwjHrVOTJ7iEV

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability keyword-extract-36386084
```

Example prompt: What are the main keywords and topic phrases on https://example.com/blog/ai-trends? Give me the top terms and bigrams so I can understand what the page is really about.

## When to prefer this

Choose this endpoint when you need a quick, cost-effective single-call summary of what a webpage is about in keyword form, especially for SEO audits, content tagging, or competitive intelligence. It complements the sibling word-frequency endpoint (top 50 words) by also providing bigrams and meta context in one call. Prefer it over general-purpose LLM summarization when you need structured frequency-ranked term lists rather than prose summaries.

## Known failure modes

- URL is unreachable or returns a non-200 status — endpoint may return an error or empty results
- Page has very little text content — keyword and bigram lists may be sparse or empty
- Page is JavaScript-rendered — content may not be extracted if the fetcher does not execute JS
- Invalid or missing URL parameter — request will fail with a validation error
- Payment not included — returns 402 Payment Required

## How this service works

Keyword and topic extraction from a page: the top 20 terms and top bigrams by frequency (stopwords removed), title and description for context. What is this page about, in one call. $0.01 per page.

## Output

Returns the top 20 individual terms by frequency (stopwords removed), the top bigrams (two-word phrases) by frequency, and the page's title and meta description for context — all in a single call.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "properties": {}
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/keyword-extract-36386084/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from intel.rallylive.ca](https://www.zero.xyz/host/intel.rallylive.ca/llms.txt)