# YOLOX-nano Object Detection API

> YOLOX-nano Object Detection API is a paid API for AI agents from workbot1.oddsys.org, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-12).

Detects and locates objects in an image using YOLOX-nano (COCO classes), returning per-class counts and pixel bounding boxes for 80+ object categories.

## Facts

- Endpoint: POST https://workbot1.oddsys.org/detect?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-12
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/yolox-nano-object-detection-api-b766080c
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_Kx51X69VS9QmpRgcbnYXb

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 yolox-nano-object-detection-api-b766080c -d '<json body>'
```

Example prompt: Can you detect all the objects in this image and tell me what's there, how many of each, and where they are in the frame?

## When to prefer this

Choose this endpoint when you need fast, lightweight object detection across standard COCO categories (people, pets, vehicles, etc.) and you only need bounding boxes and class counts — not face recognition, OCR, or scene captioning. Best suited for clear images with medium-to-large objects. Prefer this over heavier vision models when cost and latency matter and COCO-class coverage is sufficient.

## Known failure modes

- Image too small or blurry — small objects may not be detected reliably
- Image format not supported — non-standard or corrupted image files will return an error
- Object not in COCO classes — custom or niche objects outside the 80 COCO categories won't be detected
- No objects detected — returns empty list if confidence thresholds are not met
- Payload too large — oversized images may be rejected or time out

## How this service works

Detect and locate objects in an image (YOLOX-nano, COCO classes): people, pets (dog/cat/horse), vehicles, and 70+ more. Returns per-class counts and pixel bounding boxes. Detection only — no identification. Best on clear, medium-to-large objects.

## Output

Returns a list of detected objects with their COCO class label (e.g. 'person', 'car', 'dog'), a per-class count summary, and pixel-level bounding box coordinates (x, y, width, height) for each detected instance. Detection only — no individual identity or recognition.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "classes": {
   "type": "array",
   "items": {
    "type": "string"
   },
   "description": "Restrict results to these COCO class names (e.g. person, dog, cat, horse, car, bus, truck, motorcycle, bicycle). Omit for all 80 classes."
  },
  "imageBase64": {
   "type": "string",
   "description": "Base64-encoded image (png/jpeg/webp)."
  },
  "minConfidence": {
   "type": "number",
   "description": "Score threshold 0.05-0.95 (default 0.4)."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/yolox-nano-object-detection-api-b766080c/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from workbot1.oddsys.org](https://www.zero.xyz/host/workbot1.oddsys.org/llms.txt)