# Arch Tools OCR Extract

> Arch Tools OCR Extract is a paid API for AI agents from archtools.dev, paid per call via x402, $0.015/call, status unknown (last checked 2026-09-13).

Extracts text from images using OCR, accepting either a public image URL or a base64-encoded image

## Facts

- Endpoint: POST https://archtools.dev/v1/tools/ocr-extract
- Price: $0.015/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/arch-tools-ocr-extract-d63767fd
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_UrDPC7Eay8zaOYFEYiYbl

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 arch-tools-ocr-extract-d63767fd -d '<json body>'
```

Example prompt: Can you extract all the text from this image? Here's the URL: https://example.com/receipt.jpg

## When to prefer this

Choose this endpoint when you need to extract text from images programmatically, especially within an AI agent workflow that already uses Arch Tools' suite of data-processing utilities. It supports both URL-based and base64-encoded image input, making it flexible for both remote images and locally encoded files. Ideal for agents automating document digitization, receipt parsing, screenshot reading, or any task requiring machine-readable text from visual content.

## Known failure modes

- Image URL is not publicly accessible or returns a non-200 status
- Base64 string is malformed or not a valid image encoding
- Image format is unsupported (e.g. TIFF, BMP variants)
- Image is too low resolution for reliable text recognition
- No text found in the image returns empty or minimal result
- Both image_url and image_base64 omitted causes a validation error
- Payment not processed correctly due to x402 protocol issues

## How this service works

Extract text from images and screenshots with AI vision. Send a URL or base64 image, get accurate text back in seconds. Pay per call with USDC (x402) or credits - archtools.dev

## Output

A JSON object containing the text extracted from the provided image, typically including recognized characters, words, or lines of text found in the image.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "image_url": {
   "type": "string",
   "description": "Public URL of the image"
  },
  "image_base64": {
   "type": "string",
   "description": "Base64-encoded image (alternative to image_url)"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/arch-tools-ocr-extract-d63767fd/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from archtools.dev](https://www.zero.xyz/host/archtools.dev/llms.txt)