# ONE Engine Word Bigrams Top-10 Extractor

> ONE Engine Word Bigrams Top-10 Extractor is a paid API for AI agents from one-search.one-engine.workers.dev, paid per call via x402, $0.03/call, status unknown (last checked 2026-10-02).

Extracts the top 10 most frequent word bigrams (two-word pairs) from a given text using token-level analysis.

## Facts

- Endpoint: POST https://one-search.one-engine.workers.dev/v3/text-token/word-bigrams/t10?utm_source=zero.xyz
- Price: $0.03/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-word-bigrams-top-10-extractor-97835b67
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_Uj742u2ThP--F_AXb-Djf

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-word-bigrams-top-10-extractor-97835b67 -d '<json body>'
```

Example prompt: Analyze this article and give me the top 10 most frequent two-word pairs: 'Artificial intelligence is transforming the way we live and work. AI systems are being deployed across industries, and AI tools are changing workflows everywhere. The impact of artificial intelligence on society is profound.'

## When to prefer this

Choose this endpoint when you need a quick, cheap ($0.03/call) extraction of the most statistically prominent two-word phrases from a block of text without standing up your own NLP pipeline. Ideal for agents doing lightweight text analytics, content auditing, or phrase pattern detection on documents up to 50,000 characters. Prefer this over full NLP suites when you only need bigram frequency data and want pay-per-use pricing.

## Known failure modes

- Text exceeds 50,000 character limit — request rejected or truncated
- Empty or whitespace-only text input — returns empty or minimal bigram list
- Text too short to generate meaningful bigrams — sparse or trivial results
- Payment failure via x402 — 402 response requiring USDC payment on Base
- Malformed JSON input — 400 bad request error

## 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 top 10 most frequent word bigrams extracted from the input text, ranked by occurrence count. Each entry typically includes the word pair and its frequency or rank score.

## 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-word-bigrams-top-10-extractor-97835b67/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)