# Agent Link HTML Text Extractor

> Agent Link HTML Text Extractor is a paid API for AI agents from agent-link.annushka1190.workers.dev, paid per call via x402, $0.005/call, status unknown (last checked 2026-09-15).

Extracts plain text content from raw HTML input, stripping markup and returning readable text for AI processing.

## Facts

- Endpoint: POST https://agent-link.annushka1190.workers.dev/v1/html/text
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agent-link-html-text-extractor-6f7f33ba
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_phC7hD_AZ-TR7TwDg4s4M

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 agent-link-html-text-extractor-6f7f33ba -d '<json body>'
```

Example prompt: Pull just the readable text out of this HTML snippet for me — strip all the tags and give me the clean plain text: '<html><body><h1>Hello</h1><p>World</p></body></html>'

## When to prefer this

Choose this endpoint when you need a lightweight, pay-per-use HTML-to-text extraction without managing API keys. Ideal for AI agents that occasionally need to process web page content inline, especially in x402-compatible payment flows. Prefer over full headless browser solutions when you already have raw HTML and just need the text stripped out quickly.

## Known failure modes

- Malformed or empty HTML input returns error response
- Non-HTML content passed as input may return empty or garbled text
- Very large HTML documents may timeout or be truncated
- Payment failure via x402 results in 402 response before processing begins
- Missing required 'input' field returns schema validation error

## How this service works

URL and content micro-tools for AI agents: parse URLs, probe HTTP status and security headers, extract text from HTML, text stats, and similarity. Pay with USDC via x402 — no API keys.

## Output

Returns a JSON object with a boolean 'ok' field and the extracted plain text content parsed from the provided HTML, with all markup tags removed and readable prose preserved.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "body": {
     "type": "object"
    },
    "type": {
     "const": "http"
    },
    "method": {
     "enum": [
      "POST"
     ]
    },
    "bodyType": {
     "const": "json"
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "ok": true
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agent-link-html-text-extractor-6f7f33ba/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agent-link.annushka1190.workers.dev](https://www.zero.xyz/host/agent-link.annushka1190.workers.dev/llms.txt)
