# Pixo Tools Image OCR via Google Gemini

> Pixo Tools Image OCR via Google Gemini is a paid API for AI agents from api.pixo.tools, paid per call via x402, $0.02/call, status unknown (last checked 2026-09-13).

Performs OCR on an uploaded image file using Google Gemini, returning extracted text content

## Facts

- Endpoint: POST https://api.pixo.tools/v1/image/ocr
- Price: $0.02/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/pixo-tools-image-ocr-via-google-gemini-3593a9fe
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_ZED-7Od9za5SMPZowLK6u

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 pixo-tools-image-ocr-via-google-gemini-3593a9fe -d '<json body>'
```

Example prompt: Can you extract all the text from this image file I'm uploading? Run it through OCR and give me the raw text back.

## When to prefer this

Choose this endpoint when you need to extract text from a raster image file (photo, scan, screenshot) and want high-quality AI-powered OCR via Google Gemini. Prefer this over PDF-specific endpoints when your input is an image rather than a PDF document. Use when accuracy matters more than cost, given the AI-based approach versus traditional OCR engines.

## Known failure modes

- Image file is not provided or malformed — returns 400 bad request
- Image format not supported by Gemini — returns error indicating unsupported type
- No readable text found in image — may return empty string or minimal result
- Payment not provided or insufficient — returns 402 Payment Required
- Google Gemini API unavailable — upstream service error propagated
- Image too large or exceeds size limits — returns 413 or similar error

## How this service works

OCR an image via Google Gemini (sends content to a third party)

## Output

The agent receives the text content extracted from the image, as recognized by Google Gemini's vision model, likely as a plain text or JSON response containing the OCR output.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "file"
 ],
 "properties": {
  "file": {
   "type": "string",
   "description": "JPEG, PNG, or WebP (GIF is not accepted for OCR)"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object"
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/pixo-tools-image-ocr-via-google-gemini-3593a9fe/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.pixo.tools](https://www.zero.xyz/host/api.pixo.tools/llms.txt)