# parseapi.info Image OCR

> parseapi.info Image OCR is a paid API for AI agents from parseapi.info, paid per call via x402, $0.004/call, status unknown (last checked 2026-10-16).

Performs OCR on an image, returning extracted words with confidence scores, block groupings, and bounding-box coordinates

## Facts

- Endpoint: POST https://parseapi.info/parse/image?utm_source=zero.xyz
- Price: $0.004/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-16
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/parseapi-info-image-ocr-beae7c95
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_QGGWW_Vb5gS6QfG1r916a

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 parseapi-info-image-ocr-beae7c95 -d '<json body>'
```

Example prompt: Can you OCR this image for me and give me all the words it contains along with their confidence scores and coordinates so I know exactly where each word appears on the page?

## When to prefer this

Choose this endpoint when you need word-level OCR output including confidence scores, text-block groupings, and pixel-level bounding box coordinates from an image — especially when spatial layout matters (forms, receipts, scanned pages). It fits naturally alongside the parseapi.info suite if you are already using that platform for document, audio, or video parsing.

## Known failure modes

- Image cannot be fetched or decoded — returns an error if the URL is inaccessible or the format is unsupported
- Low-quality or blurry images may yield low confidence scores and partial word extraction
- Very large images may time out or exceed payload limits
- Non-image file types submitted as image input will fail
- Payment not included or insufficient — x402 payment required at $0.002 USDC per call

## How this service works

OCR an image into words, confidence, blocks and coordinates

## Output

Returns a structured breakdown of OCR results including individual words recognized in the image, a confidence score for each word, groupings into text blocks, and bounding-box coordinates (position and dimensions) for each word or block within the image.

## 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",
    "bodyType",
    "body"
   ],
   "properties": {
    "body": {
     "properties": {}
    },
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "POST"
     ],
     "type": "string"
    },
    "bodyType": {
     "enum": [
      "json",
      "form-data",
      "text"
     ],
     "type": "string"
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/parseapi-info-image-ocr-beae7c95/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from parseapi.info](https://www.zero.xyz/host/parseapi.info/llms.txt)