# ONE Engine Text Tokenization – Sentence Splitter

> ONE Engine Text Tokenization – Sentence Splitter is a paid API for AI agents from one-search.one-engine.workers.dev, paid per call via x402, $0.004/call, status unknown (last checked 2026-10-02).

Splits a text string (up to 50,000 characters) into individual sentences using token-level text analysis.

## Facts

- Endpoint: POST https://one-search.one-engine.workers.dev/v3/text-token/sentences/t6?utm_source=zero.xyz
- Price: $0.004/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-02
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/one-engine-text-tokenization-sentence-splitter-cdb52e62
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_OzoB0m-IsBv3KDWbdOVnB

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 one-engine-text-tokenization-sentence-splitter-cdb52e62 -d '<json body>'
```

Example prompt: Split this paragraph into individual sentences: 'Natural language processing is a branch of AI. It helps computers understand human text. Many tasks rely on sentence segmentation as a first step.'

## When to prefer this

Choose this endpoint when you need lightweight, pay-per-call sentence tokenization without spinning up a local NLP library or paying for a larger, more expensive API. Ideal for autonomous agents running on Base/x402 that need cheap, stateless sentence segmentation as a preprocessing step for downstream tasks like sentiment analysis, summarization, or semantic search indexing.

## Known failure modes

- Text exceeding 50,000 characters may be rejected or truncated
- Empty or whitespace-only text input may return an empty sentence list
- Ambiguous sentence boundaries (e.g. abbreviations, ellipses) may result in incorrect splits
- Payment failure via x402/USDC may block the request
- Malformed JSON body returns an error
- Non-English or mixed-language text may produce degraded segmentation quality

## How this service works

Low-cost pay-per-call utility APIs for autonomous agents using x402 on Base.

## Output

Returns a JSON object containing the input text segmented into individual sentences, likely as an array of sentence strings with possible token-level metadata, suitable for downstream NLP tasks.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "text"
 ],
 "properties": {
  "text": {
   "type": "string",
   "description": "Text up to 50000 characters"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object",
 "additionalProperties": true
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/one-engine-text-tokenization-sentence-splitter-cdb52e62/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from one-search.one-engine.workers.dev](https://www.zero.xyz/host/one-search.one-engine.workers.dev/llms.txt)