# Image OCR – Extract Printed & Handwritten Text

> Image OCR – Extract Printed & Handwritten Text is a paid API for AI agents from manyfish-seller.redcliff-d7368db1.westus2.azurecontainerapps.io, paid per call via x402, $0.002/call, status unknown (last checked 2026-09-15).

Extracts printed and handwritten text from a supplied image using optical character recognition (OCR).

## Facts

- Endpoint: POST https://manyfish-seller.redcliff-d7368db1.westus2.azurecontainerapps.io/api/v1/image/ocr
- Price: $0.002/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/image-ocr-extract-printed-handwritten-text-db4fc640
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_r704PE0r9_rapIZhCscNr

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 image-ocr-extract-printed-handwritten-text-db4fc640 -d '<json body>'
```

Example prompt: Can you read all the text out of this JPEG image I'm uploading? It contains both printed and handwritten English notes — extract everything you can find in it.

## When to prefer this

Choose this endpoint when you need to extract text from a raster image (JPEG or PNG) containing printed or handwritten content. Use this over the PDF OCR sibling endpoint when your source is an image file rather than a PDF. Prefer this over the image-to-Markdown endpoint when you want raw OCR text without document structure conversion, or when the image is not a document-style scan.

## Known failure modes

- Image is too large (base64 exceeds ~10MB limit) — returns validation error
- Unsupported content type (not image/jpeg or image/png) — rejected by enum validation
- Malformed base64 string — fails pattern validation
- Image quality too low or text too small/blurry for OCR to recognize — returns empty or partial text
- Invalid locale format — fails regex pattern validation

## How this service works

Extract printed and handwritten text from a supplied image using OCR.

## Output

Returns the recognized text content extracted from the image, covering both printed and handwritten regions, structured as an OCR result with the identified character sequences.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "locale": {
   "type": "string",
   "pattern": "^[A-Za-z]{2,3}(?:-[A-Za-z0-9]{2,8})*$",
   "maxLength": 32,
   "minLength": 2
  },
  "contentType": {
   "enum": [
    "image/jpeg",
    "image/png"
   ]
  },
  "imageBase64": {
   "type": "string",
   "pattern": "^(?:[A-Za-z0-9+/]{4})*(?:[A-Za-z0-9+/]{2}==|[A-Za-z0-9+/]{3}=)?$",
   "maxLength": 13981016,
   "minLength": 8
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "text": "HELLO",
  "image": {
   "width": 200,
   "height": 120,
   "contentType": "image/png"
  },
  "lines": [
   {
    "text": "HELLO",
    "polygon": [
     70,
     40,
     180,
     40,
     180,
     75,
     70,
     75
    ]
   }
  ],
  "textCharacters": 5
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/image-ocr-extract-printed-handwritten-text-db4fc640/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from manyfish-seller.redcliff-d7368db1.westus2.azurecontainerapps.io](https://www.zero.xyz/host/manyfish-seller.redcliff-d7368db1.westus2.azurecontainerapps.io/llms.txt)