# SiteCheck OCR

> SiteCheck OCR is a paid API for AI agents from api.sitecheck-api.workers.dev, paid per call via x402, $0.003/call, status unknown (last checked 2026-10-14).

Extracts text from images (via URL or base64) using vision AI, returning structured lines, language, and MIME type

## Facts

- Endpoint: POST https://api.sitecheck-api.workers.dev/api/ocr?utm_source=zero.xyz
- Price: $0.003/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/sitecheck-ocr-890eb0cd
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_DxtUFouqovAqatxoSnQ_-

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 sitecheck-ocr-890eb0cd -d '<json body>'
```

Example prompt: Can you read all the text out of this invoice image at https://example.com/invoice.png? It's in English if that helps.

## When to prefer this

Choose this endpoint when you need to extract text from an image file (PNG, JPEG, etc.) provided as either a public URL or a base64-encoded blob, especially for documents, invoices, receipts, signs, or screenshots. It is pay-per-call with no signup required, making it ideal for sporadic or agent-driven OCR tasks. Prefer this over general-purpose LLM vision calls when you want structured line-by-line output with language detection and metadata.

## Known failure modes

- Image URL unreachable or returns non-image content — extraction fails
- Base64 payload exceeds 4 MB limit — request rejected
- Image contains no readable text — returns empty text/lines
- Unsupported image format — MIME type mismatch error
- Language hint doesn't match actual content — may reduce accuracy but won't fail
- Network timeout fetching remote image URL

## How this service works

Pay-per-call tools for AI agents: image generation, speech-to-text, text-to-speech, embeddings, LLM chat, website audits and contact enrichment, web page to Markdown reader, PDF to text, sitemap URLs, tech stack detection, translation, exchange rates, e-mail pre-check, domain RDAP/DNS lookup, Solana token checks, trending tokens and wallet holdings, plus business and compliance data (EU VAT/VIES, IBAN, LEI/GLEIF, US recalls, OSHA/EPA violations, UK insolvency notices). Also: SEO metadata, link checking, redirect chains, security headers, mail DNS (SPF, DMARC, DKIM), QR codes, language detection, photo EXIF, identifier validation, image OCR, SEC filings, SEC financials, Congress bills, macro rates, UK company data, GitHub repo stats, Hacker News, Wikipedia, gas prices, Solana swap quotes, ERC-20 token checks, ENS names, EVM wallet balances, EVM balances, transactions and contract calls, Solana transactions and accounts, crypto prices, candles and order books, DeFi TVL, yields and stablecoins, SEC insider trades, weather, geocoding and holidays, IP owners and postcodes, npm, PyPI and crates package data and vulnerabilities, GitHub profiles, arXiv papers and DOIs, structured extraction, summaries, sentiment and reranking, HTML tables and RSS feeds, Bitcoin fees, addresses and transactions, Bitcoin address balances, Bitcoin transaction status, EVM calldata decoding, verified EVM contracts, Hyperliquid perpetual markets, Hyperliquid account positions, Polymarket odds, crypto fear and greed, DeFi fees, DEX volume, company registries of four countries, ISIN, CUSIP and ticker lookup, SEC full-text search, SEC 8-K events, FDA drug labels, FDA adverse event counts, clinical trials, PubMed articles, US federal grants, EU public tenders, NPI provider lookup, US address geocoding, USGS earthquakes, NWS weather alerts, sunrise and moon times, time zone conversion, distance and bearing, GDACS disaster alerts, llms.txt checks, AI crawler access, tracker and cookie audits, certificate transparency, site logos and icons, GitHub releases, GitHub issues, Stack Overflow answers, read-only Wikidata queries, text moderation, image descriptions, text classification, named entity extraction, PII redaction, phone number checks, cron explanations, JSON Schema validation. Plus prediction-market search, briefs, quotes and unsigned buy transactions, powered by Panta. Payment: x402, USDC on Base, Solana or Arc. No signup, no API key.

## Output

Returns a JSON object with the full extracted text as a single string, an array of individual lines, detected language code and name, MIME type of the image, byte size, the vision model used, and a timestamp of when the check was performed.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "description": "https URL of the image"
  },
  "image": {
   "type": "string",
   "description": "Alternative: the image as base64, up to 4 MB"
  },
  "language": {
   "type": "string",
   "description": "Optional hint, e.g. English or German"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "mime": "image/png",
  "text": "Invoice No 4821",
  "bytes": 84210,
  "lines": [
   "Invoice No 4821"
  ],
  "model": "@cf/meta/llama-3.2-11b-vision-instruct",
  "language": "eng",
  "checkedAt": "2026-10-13T09:00:00.000Z",
  "languageName": "English"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/sitecheck-ocr-890eb0cd/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.sitecheck-api.workers.dev](https://www.zero.xyz/host/api.sitecheck-api.workers.dev/llms.txt)