# Locate in Image (Object Detection with Bounding Boxes)

> Locate in Image (Object Detection with Bounding Boxes) is a paid API for AI agents from agent402.tools, paid per call via x402, $0.002/call, status unknown (last checked 2026-10-29).

Detects up to 4 specified objects in a single image, returning presence probability and normalized bounding box coordinates for each target.

## Facts

- Endpoint: POST https://agent402.tools/v1/judge/locate?utm_source=zero.xyz
- Price: $0.002/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-29
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/locate-in-image-object-detection-with-bounding-boxes-8e960929
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_DudbeB5rrQ2hSmhIcFKFU

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 locate-in-image-object-detection-with-bounding-boxes-8e960929 -d '<json body>'
```

Example prompt: Look at this JPEG image I'm sending and find me the bounding boxes for 'the red apple', 'the wooden table', and 'the glass of water' — tell me if each one is there and where it is in the image.

## When to prefer this

Choose this endpoint when you need both presence detection and spatial localization (bounding boxes) for a small set of named objects in a single image without running your own computer vision infrastructure. It is ideal for lightweight, pay-per-call object detection tasks where you need normalized box coordinates (0–1 scale) for up to 4 targets at once. Prefer alternatives if you need to detect more than 4 objects, require pixel-perfect deterministic results, or need to process large batches of images efficiently.

## Known failure modes

- Image dimensions outside 256–1568px per side will be rejected
- More than 4 targets specified will be refused
- Unsupported image format (not PNG or JPEG) causes an error
- Model may return low-confidence results for ambiguous or occluded objects — probabilistic, not deterministic
- Base64 encoding errors or malformed image data will cause a parsing failure
- Network timeouts possible for large images

## How this service works

Find up to 4 things in one image: each comes back with whether it is there (a probability) and its box, as edges from 0 to 1. Preview: built on Jev features its maker labels experimental. Answers come from a model, not deterministic code.

## Output

For each of the up to 4 specified target objects, the endpoint returns a probability score indicating likelihood of presence and normalized bounding box coordinates (edges expressed as values between 0 and 1 relative to image dimensions), allowing precise spatial localization within the image.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "image": {
   "type": "object",
   "description": "{ format: \"png\" | \"jpeg\", data_base64 }; each side 280 to 1568 px."
  },
  "targets": {
   "type": "array",
   "items": {
    "type": "string"
   },
   "description": "What to find, up to 4, for example \"the coffee mug\"."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/locate-in-image-object-detection-with-bounding-boxes-8e960929/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agent402.tools](https://www.zero.xyz/host/agent402.tools/llms.txt)