# CortexCloud Image Understanding (Caption / OCR / Describe)

> CortexCloud Image Understanding (Caption / OCR / Describe) is a paid API for AI agents from api.cortexcloud.org, paid per call via x402, $0.004/call, status unknown (last checked 2026-09-13).

Analyzes an image URL using Gemini vision (via OpenRouter) to generate captions, extract text via OCR, or produce a detailed description.

## Facts

- Endpoint: GET https://api.cortexcloud.org/v1/ml/image-understand
- Price: $0.004/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/cortexcloud-image-understanding-caption-ocr-describe-7993b7ec
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_FxVkhf1e8S8wgiCFSYJ1R

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 cortexcloud-image-understanding-caption-ocr-describe-7993b7ec
```

Example prompt: Can you look at this image URL and tell me what's in it — describe the scene, any text you can read, and the key objects visible: https://example.com/photo.jpg

## When to prefer this

Choose this endpoint when you need multimodal image understanding — captioning, OCR, or scene description — paid per-call in USDC with no API key setup. Ideal for autonomous agents that need on-demand vision without managing credentials, especially when working within a x402 payment-enabled pipeline on Base.

## Known failure modes

- Invalid or inaccessible image URL returns an error
- Image format not supported by Gemini vision
- Payment failure via x402/USDC on Base blocks the request
- Rate limiting or quota exceeded on OpenRouter/Gemini backend
- Ambiguous or low-resolution images may yield inaccurate descriptions

## How this service works

Vision: caption / OCR / describe an image (Gemini vision via OpenRouter). x402-paid, USDC on Base.

## Output

A text response describing the image contents, including a natural-language caption, description of visible objects and scenes, and any text extracted via OCR — generated by Gemini vision through OpenRouter.

## Request schema (JSON Schema)

```json
{
 "properties": {
  "input": {
   "properties": {
    "body": {
     "type": "object",
     "properties": {}
    }
   }
  },
  "output": {
   "properties": {
    "example": {}
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/cortexcloud-image-understanding-caption-ocr-describe-7993b7ec/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.cortexcloud.org](https://www.zero.xyz/host/api.cortexcloud.org/llms.txt)