# 402utils Sentence Segmentation

> 402utils Sentence Segmentation is a paid API for AI agents from 402utils.com, paid per call via x402, $0.001/call, status unknown (last checked 2026-09-14).

Splits text into sentences using deterministic, rule-based logic robust to abbreviations, decimals, URLs, initials, and ellipses

## Facts

- Endpoint: POST https://402utils.com/v1/sentences
- Price: $0.001/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/402utils-sentence-segmentation-0724f0d8
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_vD9Xket9VahHSvqmjTHVl

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 402utils-sentence-segmentation-0724f0d8 -d '<json body>'
```

Example prompt: Split this paragraph into individual sentences — it has abbreviations like Dr. and e.g. and some decimal numbers, so make sure those periods aren't treated as sentence endings: 'Dr. Smith earned approx. $3.14 per unit. He works at J. R. R. Tolkien Ave. Is that enough?'

## When to prefer this

Choose this endpoint when you need deterministic, rule-based sentence boundary detection that correctly handles common traps like abbreviations, decimals, URLs, initials, and ellipses — especially for English or French text. Prefer it over generic chunkers when you need fine-grained sentence-level splitting rather than paragraph or token-level chunking, and when reproducibility matters (no ML non-determinism). Pairs well with the sibling /v1/chunk endpoint for multi-level text decomposition.

## Known failure modes

- Text exceeding 1 MB is silently truncated before processing
- Unsupported or unrecognized language hint may fall back to default EN/FR abbreviation list
- Very unusual punctuation or non-Latin scripts may produce unexpected boundaries
- Empty or whitespace-only input may return an empty sentence list
- HTTP 402 if payment header is missing or insufficient

## How this service works

Segment text into sentences — robust to the classic traps: abbreviations (Dr., e.g.), decimals ($3.14), URLs/emails (www.x.com), initials (J. R. R.) and ellipses. A period is a boundary only when followed by whitespace and a sentence-like start; !, ? and … are stronger; blank lines split paragraphs. Rule-based (EN/FR tuned), deterministic. A fine-grained chunking primitive, complements /v1/chunk. Over 1 MB truncated.

## Output

Returns a list of sentence strings extracted from the input text, with period disambiguation applied so abbreviations (Dr., e.g.), decimals ($3.14), URLs, initials, and ellipses do not create false sentence breaks. Blank lines are treated as paragraph boundaries. Output is deterministic for the same input.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "lang": {
   "type": "string",
   "description": "Optional language hint (e.g. 'en', 'fr'). The abbreviation list already covers EN+FR."
  },
  "text": {
   "type": "string",
   "description": "The text to segment (max 1 MB UTF-8; larger is truncated)."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/402utils-sentence-segmentation-0724f0d8/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from 402utils.com](https://www.zero.xyz/host/402utils.com/llms.txt)