Use when an agent must read text from a scan, photo or screenshot: scanned PDFs ...
https://1gateway.dev/v1/convert/ocrOverview
Use when an agent must read text from a scan, photo or screenshot: scanned PDFs (embedded page images) or PNG/JPEG/WebP up to 5 MB, Korean and English, tables kept as Markdown. Up to 3 pages per call. Input: url via GET, or POST a file (multipart 'file', raw body, or JSON contentBase64). Output: JSON markdown, pages with confidence, warnings. PDFs with selectable text: use /v1/convert/markdown. Example: ?url=https://example.com/scan.png
Protocol
x402
Price
$0.01
Payment Asset
USD Coin
Payment Network
eip155:8453
Category
media/images
Provider
OCR to Markdown
Source
bazaar
Indexed
2026-10-31 11:36:12
Health
Status
unknown
Latency (p50)
—
Uptime (30d)
—
Reliability Score
—
Last Checked
Never
Last Healthy
Never
Consecutive Failures
0
x402 Payment Validation
Payment Requirements
—
Asset Verified
—
Facilitator
—
Input Schema
{
"method": "GET",
"queryParams": {
"contentBase64": "",
"url": "https://example.com/scan.png"
},
"type": "http"
}
Output Schema
{
"example": {
"bytes": 22903,
"costNeurons": 0,
"markdown": "공문\n\n수신: 각 기관장\n\n제목: 2026년 하반기 예산 집행 계획 제출 요청\n\n| 항목 | 기한 |\n| :--- | :--- |\n| 계획서 제출 | 2026-11-15 |\n| 결과 보고 | 2026-12-20 |",
"model": "@cf/google/gemma-4-26b-a4b-it",
"notes": [
"Text read by an open vision model on Cloudflare Workers AI; verify figures against the original. Files are processed in memory and not stored."
],
"pages": [
{
"chars": 119,
"confidence": "ok",
"page": 1
}
],
"pagesRead": 1,
"sourceType": "pdf",
"totalPages": 1,
"warnings": []
},
"type": "json"
}