# ONE Engine Text Token Mentions Extraction (T5)

> ONE Engine Text Token Mentions Extraction (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 and returns token-level mention entities from a given text string using a T5-style model.

## Facts

- Endpoint: POST https://one-search.one-engine.workers.dev/v3/text-token/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-token-mentions-extraction-t5-9319079c
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_bNNBOS260rmwnrQb2DjkM

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-token-mentions-extraction-t5-9319079c -d '<json body>'
```

Example prompt: Scan this article text and extract all token-level mentions from it — here's the text: 'Apple CEO Tim Cook announced at the Cupertino campus that the new iPhone will launch in September, with partners like Samsung and Google expected to respond.'

## When to prefer this

Choose this endpoint when you need lightweight, low-cost per-call token-level mention extraction from arbitrary text up to 50,000 characters, especially in agentic pipelines where cost-efficiency matters and you are already operating on the Base blockchain with x402 micropayments. Prefer it over heavier NLP APIs when you need fast, pay-per-use extraction without subscriptions.

## Known failure modes

- Text exceeds 50,000 character limit — request rejected or truncated
- Empty or whitespace-only text input — may return empty mentions list
- Malformed JSON body — 400 error
- Payment not attached or insufficient USDC balance — 402 Payment Required
- Model ambiguity on short or context-free text — low-quality mention extraction
- Rate limits or worker timeout on very long texts near the character cap

## 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 token-level mentions detected in the submitted text, including the referenced entities and their spans or labels as identified by the T5 model.

## 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-token-mentions-extraction-t5-9319079c/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)