# sentence-split-bulk

> sentence-split-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).

Splits the text of up to 20 URLs into individual sentences concurrently, returning results in input order with per-item errors and a failure count.

## Facts

- Endpoint: GET https://intel.rallylive.ca/bulk/page/sentences
- 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/sentence-split-bulk-2b7788c9
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_hNz-pbcTwOHzI1E_zaCZG

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-bulk-2b7788c9
```

Example prompt: Split the text of these 15 article URLs into sentences for me — https://example.com/article1, https://example.com/article2, … — and let me know if any of them fail.

## When to prefer this

Use this endpoint when you have a list of multiple URLs (up to 20) and need sentence-level text segmentation for all of them in a single API call. It is more efficient than calling the single /page/sentences endpoint repeatedly, since requests are processed concurrently and results are returned in input order. Choose this when you need bulk sentence extraction for NLP pipelines, content analysis, or dataset building across multiple pages.

## Known failure modes

- URL is unreachable or returns a non-200 status — per-item error field is populated
- Page has no extractable text — empty sentence list returned for that item
- More than 20 URLs supplied — request may be rejected or truncated
- Network timeout on one or more URLs — those items carry error fields while others succeed
- Malformed URL in the input list — per-item error reported for that entry

## How this service works

Bulk sentence split: 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 /page/sentences endpoint (Page text split into sentences). Batch enrichment for agents that hold a list. $0.01 per batch.

## Output

Returns a list of results in the same order as the input URLs. Each item contains the sentences extracted from that page's text (matching the single /page/sentences endpoint output), plus a per-item error field if the URL could not be processed. A top-level count of failures is also included.

## 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-bulk-2b7788c9/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)