KINEVA API - REBOTNIX

How it works.

1. Send image

URL or Base64. Any image format.

2. KINEVA analyzes

CNN, PCNN, or VLLM. Choose model or automatic.

3. JSON back

Bounding boxes, classes, confidence. Structured and immediately usable.

Quick Start

One API call is enough. Send an image, receive detections with bounding boxes and confidence scores.

# Detect objects in an image
curl -X POST https://api.kineva.eu/v1/detect \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "vehicle-detection-v3",
    "image": "https://example.com/street.jpg",
    "confidence_threshold": 0.5
  }'

// Response
{
  "model": "vehicle-detection-v3",
  "detections": [
    {
      "class": "car",
      "confidence": 0.97,
      "bbox": [120, 340, 480, 560]
    },
    {
      "class": "truck",
      "confidence": 0.94,
      "bbox": [600, 280, 900, 520]
    }
  ],
  "inference_time_ms": 42
}

Full model catalog after registration.

CNN, PCNN, VLLM, all models are available via the API. Register for free and get access to the full catalog.