# ONE Engine Text Mention Extractor (t5)

> ONE Engine Text Mention Extractor (t5) is a paid API for AI agents from one-search.one-engine.workers.dev, paid per call via x402, $0.0025/call, status unknown (last checked 2026-10-02).

Extracts mentions (entities, references, or named items) from a block of text up to 50,000 characters using a t5-based model.

## Facts

- Endpoint: POST https://one-search.one-engine.workers.dev/v3/text-extract/mentions/t5?utm_source=zero.xyz
- Price: $0.0025/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-mention-extractor-t5-3deed766
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_AFNLLR_XB6-Gy0hh8JIn7

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-mention-extractor-t5-3deed766 -d '<json body>'
```

Example prompt: Scan this article text for all mentions — people, organizations, locations, or other named references — and return them: "Apple CEO Tim Cook announced today in Cupertino that the company will partner with OpenAI to bring AI features to the iPhone 16 lineup."

## When to prefer this

Choose this endpoint when you need a low-cost, pay-per-call mention or named entity extraction from freeform text without committing to a subscription. Ideal for autonomous agents processing documents on demand where cost-per-call matters. Prefer this over heavier NLP pipelines when you need quick entity mention extraction without fine-grained classification or co-reference resolution.

## Known failure modes

- Text exceeds 50,000 character limit — request rejected or truncated
- Empty or missing 'text' field — validation error
- Malformed JSON request body — 400 error
- Payment not included or insufficient (x402 protocol) — 402 Payment Required
- Upstream model timeout for very dense or complex text — 500 error
- No mentions detected in text — empty or minimal result object returned

## How this service works

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

## Output

A JSON object containing extracted mentions found within the input text — likely including entity names, types, and positions or context depending on the model output. The exact schema is open-ended (additionalProperties: true), so field names and structure may vary.

## 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-mention-extractor-t5-3deed766/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)