# GEDX402 DETR-ResNet-50 Object Detection

> GEDX402 DETR-ResNet-50 Object Detection is a paid API for AI agents from media.gedx402.com, paid per call via x402, $0.0042/call, status unknown (last checked 2026-09-15).

Detects and localizes objects in an image using the DETR ResNet-50 model, returning bounding boxes, labels, and confidence scores

## Facts

- Endpoint: GET https://media.gedx402.com/v1/detect/detr-resnet-50
- Price: $0.0042/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/gedx402-detr-resnet-50-object-detection-f098582a
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_Xw-Ld2fM9qB5KopG2hUTR

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 gedx402-detr-resnet-50-object-detection-f098582a
```

Example prompt: Can you run object detection on this image and tell me what objects are in it with their bounding boxes and confidence scores? Here's the base64-encoded image data: [base64string]

## When to prefer this

Choose this endpoint when you need no-API-key object detection paid via USDC on-chain (Base, Polygon, Arbitrum, World, or Solana) using the proven DETR ResNet-50 architecture. Ideal for agents with crypto wallets needing lightweight, per-call billed computer vision without subscription overhead.

## Known failure modes

- Invalid or malformed base64 image returns an error response
- Image too large or unsupported format may cause processing failure
- Payment not received or insufficient USDC balance results in 402 Payment Required
- Unsupported blockchain network provided for payment causes rejection
- Empty or missing image field returns validation error

## How this service works

x402 workers ai. pay with usdc on base, polygon, arbitrum, world, or solana. no api keys.

## Output

A JSON array of detections, each containing a bounding box as four coordinates [x1, y1, x2, y2], a human-readable object label (e.g. 'person', 'car'), and a confidence score between 0 and 1 indicating detection certainty.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "image": {
   "type": "string",
   "description": "Base64-encoded image to scan for objects."
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "detections": [
   {
    "box": [
     0,
     0,
     100,
     200
    ],
    "label": "person",
    "score": 0.95
   }
  ]
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/gedx402-detr-resnet-50-object-detection-f098582a/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from media.gedx402.com](https://www.zero.xyz/host/media.gedx402.com/llms.txt)