# ONE Engine Text Extract from URLs (T9)

> ONE Engine Text Extract from URLs (T9) 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 and returns text content from one or more URLs provided within a text payload, up to 50,000 characters.

## Facts

- Endpoint: POST https://one-search.one-engine.workers.dev/v3/text-extract/urls/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-text-extract-from-urls-t9-50640c86
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_wbfWhXBQdxj4DeYhekf2j

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-extract-from-urls-t9-50640c86 -d '<json body>'
```

Example prompt: Extract all the readable text from this URL for me: https://example.com/article/how-to-train-agents — I need the plain text content so I can summarize it.

## When to prefer this

Choose this endpoint when an AI agent needs to retrieve readable text content from one or more web URLs embedded in a text string, especially in low-cost, high-frequency agentic pipelines where per-call pricing matters. Prefer it over full browser automation when you only need plain text (not rendered DOM or screenshots). It is well-suited for pipelines that need to feed web content into LLMs for summarization, analysis, or RAG without the overhead of a full scraping service.

## Known failure modes

- URL is inaccessible or returns a non-200 status — extraction may return empty or error result
- Input text exceeds 50,000 character limit — request rejected
- URL points to non-text content (e.g. PDF, binary file) — unpredictable extraction quality
- Paywalled or JavaScript-rendered pages may yield little or no extractable text
- Invalid or malformed URLs in the text payload — extraction skipped or failed for those entries
- Payment not processed via x402 — 402 response returned before extraction occurs

## 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 extracted text content from the URL(s) embedded in the input text. The response includes the parsed, readable text stripped from the referenced web pages, suitable for downstream processing, summarization, or analysis by an AI agent.

## 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-extract-from-urls-t9-50640c86/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)