# Sift Web Tools OCR

> Sift Web Tools OCR is a paid API for AI agents from sift.srv1996466.hstgr.cloud, paid per call via x402, $0.004/call, status unknown (last checked 2026-10-23).

Extracts text from an image URL using optical character recognition, returning the recognized text and character count

## Facts

- Endpoint: GET https://sift.srv1996466.hstgr.cloud/v1/ocr?utm_source=zero.xyz
- Price: $0.004/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-23
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/sift-web-tools-ocr-fbd6e8b9
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_Y8XM4nVKC1oja6sSF6VTV

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 sift-web-tools-ocr-fbd6e8b9
```

Example prompt: Can you extract all the text from this image — https://example.com/receipt.jpg — using OCR? It's in English.

## When to prefer this

Choose this endpoint when you need to extract text from a remotely hosted image and want pay-per-call pricing with no subscription. It is especially suitable for agents that process images occasionally rather than in high volume, and when you want guaranteed no-charge on failure (only billed on HTTP 200). Prefer this over self-hosted OCR when you want zero infrastructure overhead and multilingual support via language code.

## Known failure modes

- Image URL is unreachable or returns non-200 — endpoint returns an error and no charge is made
- Unsupported image format — non-image URLs (e.g. HTML pages) will fail or return empty text
- Invalid language code — may fall back to default 'eng' or return an error
- Very low-resolution or heavily degraded images may yield empty or garbled text
- Network timeout fetching the image URL

## How this service works

Read text from an image (OCR), 7 languages. Optical character recognition on an image URL (png, jpg, webp, tiff, bmp, gif; up to 15 MB) with Tesseract. Languages eng, deu, fra, spa, ita, por, nld, combinable with + (e.g. eng+fra).

## Output

A JSON object containing a 'text' field with all recognized characters from the image as a plain string, plus a 'characters' integer indicating the total character count extracted.

## 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"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET",
      "HEAD",
      "DELETE"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "required": [
      "url"
     ],
     "properties": {
      "url": {
       "type": "string",
       "description": "Image URL"
      },
      "lang": {
       "type": "string",
       "description": "Language code(s), default eng"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "text": "Sift Web Tools\nOptical character recognition sample",
  "characters": 58
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/sift-web-tools-ocr-fbd6e8b9/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from sift.srv1996466.hstgr.cloud](https://www.zero.xyz/host/sift.srv1996466.hstgr.cloud/llms.txt)