# keyword-extract-bulk

> keyword-extract-bulk is a paid API for AI agents from intel.rallylive.ca, paid per call via x402, $0.1/call, status unknown (last checked 2026-09-14).

Extracts keywords and topics from up to 20 URLs concurrently in a single API call, returning results in input order with per-item error reporting.

## Facts

- Endpoint: GET https://intel.rallylive.ca/bulk/site/keywords
- Price: $0.1/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-bulk-32fdc5c8
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_G0oRYlL0Jg4kWVin9GIaQ

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-bulk-32fdc5c8
```

Example prompt: Extract the keywords and main topics from all 20 of these URLs at once and give me the results in the same order I listed them, flagging any that failed.

## When to prefer this

Choose this endpoint when you need to process multiple URLs (up to 20) for keyword and topic extraction in a single call rather than making repeated single-URL requests. It is more efficient and cost-effective for batch workflows, returning results in deterministic input order with graceful per-item error handling so one failed URL does not block the others. Prefer it over the single /site/keywords endpoint whenever your agent holds a list of URLs to process.

## Known failure modes

- URL unreachable or returns non-200 status — per-item error field populated, counted in failure total
- URL returns non-HTML content (PDF, binary) — extraction may fail or return empty results
- Rate limiting or timeout on concurrent fetches — some items may error
- Malformed URL in input list — per-item error, rest of batch continues
- All 20 slots used but some pages have no extractable text — empty keyword arrays returned

## How this service works

Bulk keyword extract: up to 20 urls in one call, processed concurrently, results returned in input order with a per-item error field and a count of failures. Same answer per item as the single /site/keywords endpoint (Keyword and topic extraction from a page). Batch enrichment for agents that hold a list. $0.01 per batch.

## Output

An ordered array of per-URL results matching the input list order. Each item contains the extracted keywords and topics for that page (same schema as the single /site/keywords endpoint), plus a per-item error field if extraction failed for that URL. A top-level failure count indicates how many items errored out across the batch.

## 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-bulk-32fdc5c8/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)