# Image Object Detection with Bounding Boxes

> Image Object Detection with Bounding Boxes is a paid API for AI agents from manyfish-seller.redcliff-d7368db1.westus2.azurecontainerapps.io, paid per call via x402, $0.002/call, status unknown (last checked 2026-09-14).

Detects and localizes objects in a base64-encoded image, returning tags, confidence scores, and bounding box coordinates for each detected object.

## Facts

- Endpoint: POST https://manyfish-seller.redcliff-d7368db1.westus2.azurecontainerapps.io/api/v1/image/objects
- Price: $0.002/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/image-object-detection-with-bounding-boxes-0805d02f
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_289wVAcMHE3NLAZIUaxN6

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 image-object-detection-with-bounding-boxes-0805d02f -d '<json body>'
```

Example prompt: Can you detect all the objects in this JPEG image and tell me their positions and confidence scores? Only include detections you're at least 70% confident about — here's the base64-encoded image data.

## When to prefer this

Choose this endpoint when you need both object classification AND spatial localization (bounding boxes) from a single image in one call. It is ideal for pipelines that need to know not just what objects are present but where they are. Prefer the sibling 'caption + tags + objects' endpoint if you also need a scene caption in the same call; use this dedicated object detection endpoint if you only need bounding boxes and tags without caption overhead.

## Known failure modes

- Invalid base64 encoding returns a validation error
- Unsupported content type (not image/jpeg or image/png) returns an error
- Image too large (exceeds ~10MB base64 limit) returns a payload size error
- No objects detected above the confidence threshold returns an empty results list
- Corrupted or unreadable image data returns a processing error
- Payment not included or insufficient USDC returns a 402 error

## How this service works

Locate objects in a supplied image with tags, confidence scores, and bounding boxes.

## Output

Returns a list of detected objects, each with a human-readable label/tag, a confidence score (0–1), and bounding box coordinates indicating the object's position and size within the image.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "contentType": {
   "enum": [
    "image/jpeg",
    "image/png"
   ]
  },
  "imageBase64": {
   "type": "string",
   "pattern": "^(?:[A-Za-z0-9+/]{4})*(?:[A-Za-z0-9+/]{2}==|[A-Za-z0-9+/]{3}=)?$",
   "maxLength": 13981016,
   "minLength": 8
  },
  "minimumConfidence": {
   "type": "number",
   "default": 0.5,
   "maximum": 1,
   "minimum": 0
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "image": {
   "width": 200,
   "height": 120,
   "contentType": "image/png"
  },
  "objects": []
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/image-object-detection-with-bounding-boxes-0805d02f/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from manyfish-seller.redcliff-d7368db1.westus2.azurecontainerapps.io](https://www.zero.xyz/host/manyfish-seller.redcliff-d7368db1.westus2.azurecontainerapps.io/llms.txt)