# Tanod Docs OCR

> Tanod Docs OCR is a paid API for AI agents from docs.tanod.dev, paid per call via x402, $0.0025/call, status unknown (last checked 2026-10-13).

Extracts text from an image URL using Tesseract OCR, returning the recognized text, confidence score, and metadata.

## Facts

- Endpoint: POST https://docs.tanod.dev/v1/ocr?utm_source=zero.xyz
- Price: $0.0025/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/tanod-docs-ocr-ec5f16b2
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_-WLlC1T0VOJqBJ4AZa0s7

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 tanod-docs-ocr-ec5f16b2 -d '<json body>'
```

Example prompt: Can you extract all the text from this image — https://example.com/scanned-receipt.png — using English OCR and tell me the confidence score?

## When to prefer this

Choose this endpoint when you need to extract machine-readable text from a raster image (PNG, JPEG, WebP, GIF, single-page TIFF) hosted at a public URL. It is ideal for processing scanned documents, receipts, screenshots, or printed forms where Tesseract OCR accuracy (confidence score included) is sufficient. It is distinct from full PDF pipelines or multi-page document workflows available on the same platform.

## Known failure modes

- Image URL is not publicly accessible or returns a non-200 response
- Image exceeds 10 MB or 40 megapixel limit — likely 4xx error
- Unsupported image format (e.g. multi-page TIFF, SVG, PDF) — will fail
- Requested language code not installed (only 'eng' is listed as installed)
- Low confidence result when image quality is poor or text is handwritten
- Network timeout fetching the remote image URL

## How this service works

Documents: DOCX template fill, Office to PDF, any file to Markdown, PDF to Word, OCR, PDF pipeline.

## Output

Returns a JSON object containing the extracted text string, image dimensions (width/height), number of recognized words, image format, the final resolved URL, a boolean indicating whether the output was truncated, mean OCR confidence score (0–100), and an untrusted_content flag.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "maxLength": 2048,
   "description": "Public http(s) URL of a PNG, JPEG, WebP, GIF (first frame) or single-page TIFF image (at most 10 MB and 40 megapixels)."
  },
  "lang": {
   "type": "string",
   "default": "eng",
   "pattern": "^[a-z][a-z_]{1,15}(\\+[a-z][a-z_]{1,15}){0,2}$",
   "maxLength": 50,
   "minLength": 3,
   "description": "Tesseract language code (installed: eng)."
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "url": "https://tesseract-ocr.github.io/tessdoc/images/eurotext.png",
  "lang": "eng",
  "text": "The (quick) [brown] {fox} jumps!\nOver the $43,456.78 <lazy> #90 dog\n& duck/goose, as 12.5% of E-mail\nfrom aspammer@website.com is spam. ...",
  "width": 640,
  "words": 66,
  "format": "png",
  "height": 500,
  "final_url": "https://tesseract-ocr.github.io/tessdoc/images/eurotext.png",
  "truncated": false,
  "confidence_mean": 90.2,
  "untrusted_content": true
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/tanod-docs-ocr-ec5f16b2/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from docs.tanod.dev](https://www.zero.xyz/host/docs.tanod.dev/llms.txt)