# ONE Engine Word Bigram T9 Extractor

> ONE Engine Word Bigram T9 Extractor is a paid API for AI agents from one-search.one-engine.workers.dev, paid per call via x402, $0.018/call, status unknown (last checked 2026-10-02).

Extracts word-level bigrams (consecutive two-word pairs) from input text using T9-style tokenization for NLP and text analysis tasks.

## Facts

- Endpoint: POST https://one-search.one-engine.workers.dev/v3/text-token/word-bigrams/t9?utm_source=zero.xyz
- Price: $0.018/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-bigram-t9-extractor-2fd114d8
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_LwZi7oG8oKCIph0a2sHQ5

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-bigram-t9-extractor-2fd114d8 -d '<json body>'
```

Example prompt: Extract all consecutive two-word bigrams from this text using ONE Engine's T9 tokenizer: 'The quick brown fox jumps over the lazy dog' — I need the full bigram list for my NLP feature pipeline.

## When to prefer this

Choose this endpoint when you need a low-cost, per-call word bigram extraction from raw text, especially within an autonomous agent pipeline that uses x402 micropayments on Base. Ideal for NLP feature engineering, search enrichment, or co-occurrence analysis on text up to 50,000 characters without committing to a heavy NLP library or managed NLP service.

## Known failure modes

- Text exceeds 50,000 character limit — request rejected or truncated
- Empty or whitespace-only text input returns empty bigram set
- Non-string input type causes schema validation error
- Payment failure via x402 on Base blocks the call
- Malformed JSON body returns HTTP 400

## How this service works

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

## Output

Returns a JSON object containing word-level bigrams (consecutive two-word token pairs) derived from the input text, suitable for downstream NLP tasks such as feature engineering, search indexing, or co-occurrence analysis.

## 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-bigram-t9-extractor-2fd114d8/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)
