# ONE Engine Word Bigram Tokenizer

> ONE Engine Word Bigram Tokenizer 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).

Extracts word-level bigrams (consecutive two-word pairs) from input text up to 50,000 characters.

## Facts

- Endpoint: POST https://one-search.one-engine.workers.dev/v3/text-token/word-bigrams/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-word-bigram-tokenizer-1a5f1bd9
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_-ihdyTz9DCwu5lXGpTj3z

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-tokenizer-1a5f1bd9 -d '<json body>'
```

Example prompt: Extract all word bigrams from this paragraph: 'The quick brown fox jumps over the lazy dog. Every morning the dog would bark at the fox.'

## When to prefer this

Choose this endpoint when you need lightweight, pay-per-call word bigram extraction without standing up your own NLP infrastructure. It is ideal for agents that process text on-demand in an agentic pipeline and need cost-effective tokenization at sub-cent pricing via x402 on Base.

## Known failure modes

- Text exceeds 50,000 character limit — request rejected or truncated
- Empty text input returns empty bigram list
- Payment of 0.0007 USDC not provided via x402 — 402 Payment Required response
- Malformed JSON body — 400 Bad Request
- Non-string text field — validation 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 word bigrams extracted from the input text — typically a list of consecutive two-word pairs (e.g. ['the quick', 'quick brown', 'brown fox']) derived from the provided string.

## 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-tokenizer-1a5f1bd9/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)