# ONE Engine Text-to-Token Paragraphs (t2)

> ONE Engine Text-to-Token Paragraphs (t2) is a paid API for AI agents from one-search.one-engine.workers.dev, paid per call via x402, $0.0007/call, status unknown (last checked 2026-10-02).

Splits or tokenizes input text into structured paragraph-level tokens for downstream NLP processing by autonomous agents.

## Facts

- Endpoint: POST https://one-search.one-engine.workers.dev/v3/text-token/paragraphs/t2?utm_source=zero.xyz
- Price: $0.0007/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-to-token-paragraphs-t2-8468cd10
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_LXwr6jHWadexnnBBLwsu7

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-to-token-paragraphs-t2-8468cd10 -d '<json body>'
```

Example prompt: Split this article text into paragraph-level tokens so I can process each section separately: 'Artificial intelligence is transforming industries worldwide. Companies are investing heavily in machine learning. The results are already visible in healthcare, finance, and logistics.'

## When to prefer this

Choose this endpoint when you need a cheap, pay-per-call paragraph-level tokenization of text up to 50,000 characters, especially in agentic pipelines on Base where x402 micropayments are already set up. Prefer it over heavier NLP frameworks when you only need paragraph segmentation without additional linguistic annotations.

## Known failure modes

- Text exceeds 50,000 character limit — request rejected
- Malformed JSON body or missing required 'text' field — 400 error
- Payment failure via x402 on Base — 402 response requiring USDC payment
- Empty text input returns empty or minimal token structure
- Cloudflare Worker timeout on extremely dense text

## How this service works

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

## Output

Returns a structured object containing the input text parsed into paragraph-level tokens or segments, suitable for downstream NLP tasks such as embedding, summarization, or sentiment analysis per paragraph.

## 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-to-token-paragraphs-t2-8468cd10/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)