# dt0ur.online OCR – Client-Side Tesseract.js Image Text Extraction

> dt0ur.online OCR – Client-Side Tesseract.js Image Text Extraction is a paid API for AI agents from dt0ur.online, paid per call via x402, $0.1/call, status unknown (last checked 2026-10-03).

Extracts textual content from an image URL using client-side Tesseract.js and returns recognized text with per-word confidence scores.

## Facts

- Endpoint: POST https://dt0ur.online/api/vision/ocr?utm_source=zero.xyz
- Price: $0.1/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-03
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/dt0ur-online-ocr-client-side-tesseract-js-image-text-extraction-81259651
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_m2dy5heq2hTX4xJwGs0Ey

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 dt0ur-online-ocr-client-side-tesseract-js-image-text-extraction-81259651 -d '<json body>'
```

Example prompt: Can you extract all the text from this image — https://example.com/scanned-invoice.png — and tell me how confident the OCR is for each word?

## When to prefer this

Choose this endpoint when you need to extract text from an image or scanned document and want per-word confidence scoring to assess recognition reliability. It is well-suited for processing receipts, invoices, forms, signs, or any printed/handwritten document available as a public image URL. Prefer this over generative vision captioning endpoints when your goal is verbatim text extraction rather than descriptive summarization.

## Known failure modes

- Image URL is not publicly accessible (returns error or empty result)
- Image format not supported by Tesseract.js (e.g., unusual codec or corrupt file)
- Low-quality or blurry image results in very low confidence scores across all words
- Non-Latin scripts or rare fonts may produce poor recognition accuracy
- Very large image files may time out or fail to process

## How this service works

Extracts textual content from images and scans using client-side Tesseract.js with per-word confidence scoring.

## Output

Returns the extracted text content from the image along with per-word confidence scores, allowing the agent to identify which recognized words are high-confidence and which may need manual review.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "image_url": {
   "type": "string",
   "format": "uri",
   "description": "Public URL to the image file"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/dt0ur-online-ocr-client-side-tesseract-js-image-text-extraction-81259651/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from dt0ur.online](https://www.zero.xyz/host/dt0ur.online/llms.txt)