# sentence-split

> sentence-split 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).

Splits the readable text of a webpage into an array of clean sentences with sentence count and average length statistics, optimized for NLP pipelines.

## Facts

- Endpoint: GET https://intel.rallylive.ca/page/sentences
- 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/sentence-split-2a1f86d7
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_mWQ0lM3QxV5JvQBt8PLe9

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 sentence-split-2a1f86d7
```

Example prompt: Can you split the article at https://example.com/blog/ai-trends into individual sentences so I can feed them into my NLP pipeline?

## When to prefer this

Choose this endpoint when you need a page's text pre-segmented into sentences for NLP workflows, translation pipelines, or quote extraction, and want a clean array with metadata (count, average length) rather than raw scraped HTML or a single blob of text. At $0.01 per call it is cost-effective for single-page processing; if you only need raw HTML or navigation links, sibling endpoints on intel.rallylive.ca are more appropriate.

## Known failure modes

- URL is unreachable or returns non-200 status — no sentences returned
- Page has no extractable readable text (e.g. JavaScript-only SPA) — empty or minimal sentence array
- Malformed or missing input URL — request error
- Page returns very short or fragmented text — low sentence count with potentially noisy output

## How this service works

Page text split into sentences: the readable content as an array of clean sentences with counts and average length, ready for NLP, translation or quote mining. $0.01 per page.

## Output

Returns an array of clean, readable sentences extracted from the page's main text content, along with a total sentence count and the average sentence length in words or characters — ready for downstream NLP, translation, or quote-mining tasks.

## 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/sentence-split-2a1f86d7/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)