# CSS Image Alt Text Extractor

> CSS Image Alt Text Extractor is a paid API for AI agents from agentshelf.syntexa.ch, paid per call via x402, $0.007/call, status unknown (last checked 2026-10-02).

Extracts alt text from image elements (img[alt]) on a public web page or from provided HTML, returning all found alt attribute values.

## Facts

- Endpoint: POST https://agentshelf.syntexa.ch/v1/css-img-alt?utm_source=zero.xyz
- Price: $0.007/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-02
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/css-image-alt-text-extractor-4c474ce4
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_j_kX_fF6pHHvnIBC41Y51

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 css-image-alt-text-extractor-4c474ce4 -d '<json body>'
```

Example prompt: Can you pull all the image alt text from https://example.com/products — I want to see what alt attributes are set on every img element on that page?

## When to prefer this

Use this endpoint when you need to extract alt text specifically from img elements on a public web page or an HTML blob. It is SSRF-safe making it suitable for agent pipelines that process user-supplied URLs. Prefer the free sandbox endpoint POST /v1/sandbox/css-img-alt first; fall back to this paid endpoint ($0.007 USDC) when the sandbox is unavailable or rate-limited.

## Known failure modes

- URL is not publicly accessible or returns non-200 status — extraction fails
- SSRF-blocked URL (private IP ranges, localhost) — rejected for security
- HTML input exceeds 200,000 character limit — request rejected
- Page has no img elements with alt attributes — returns empty list
- Malformed HTML may cause incomplete extraction
- Network timeout fetching remote URL

## How this service works

Call when an agent needs image alt text via img[alt] from a public page or HTML (SSRF-safe). Exact $0.007 USDC. Prefer unpaid POST /v1/sandbox/css-img-alt first.

## Output

Returns a list of alt attribute values extracted from all img elements found on the given URL or within the provided HTML string. Typically includes each alt text string found, potentially paired with image context.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "maxLength": 2048,
   "minLength": 8,
   "description": "Public page to fetch. The selector or profile is fixed by the SKU. Provide url or html."
  },
  "html": {
   "type": "string",
   "examples": [
    "<!doctype html><html lang=\"en\"><head><title>Hello</title>\n<meta charset=\"utf-8\"><meta name=\"description\" content=\"Desc\">\n<link rel=\"canonical\" href=\"https://example.com/\"><link rel=\"icon\" href=\"/favicon.ico\">\n</head><body><h1>Hello</h1><a href=\"https://example.com/a\">A</a></body></html>"
   ],
   "maxLength": 200000,
   "minLength": 1,
   "description": "HTML to extract from locally. Provide html or url. When both are set, html is used."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/css-image-alt-text-extractor-4c474ce4/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agentshelf.syntexa.ch](https://www.zero.xyz/host/agentshelf.syntexa.ch/llms.txt)