70trust / 100

Detect

by Busker Object Detection in Company & people data

x402 APIPassing, checked 3 h ago

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.

POST https://workbot1.oddsys.org/detect

Last 30 days

All checks passedSome failedAll failedNot checked
Uptime
100%
Response time
2.2 s typical, 2.3 s slowest 5%
Last check
3 h ago
Next check
any minute now

How to call it

# See the payment challenge (nothing is charged)
curl -i -X POST "https://workbot1.oddsys.org/detect" \
  -H "content-type: application/json" \
  -d '{"classes":["person"],"imageBase64":"iVBORw0KGgoAAAANSUhEUgAAAAgAAAAICAAAAADhZOFXAAAADklEQVR42mNogAIGyhgAgIQgARDoahcAAAAASUVORK5CYII=","minConfidence":0.4}'
import { wrapFetchWithPayment } from "@x402/fetch";
import { x402Client } from "@x402/core/client";
import { ExactEvmScheme } from "@x402/evm/exact/client";
import { privateKeyToAccount } from "viem/accounts";

const client = new x402Client().register(
  "eip155:8453",
  new ExactEvmScheme(privateKeyToAccount(process.env.AGENT_KEY)),
);
const pay = wrapFetchWithPayment(fetch, client);

// Not sure it's safe to pay? Preflight it first for $0.005:
// GET https://toolvet.app/api/v1/check?url=https%3A%2F%2Fworkbot1.oddsys.org%2Fdetect
const res = await pay("https://workbot1.oddsys.org/detect", {
  method: "POST",
  headers: { "content-type": "application/json" },
  body: JSON.stringify({"classes":["person"],"imageBase64":"iVBORw0KGgoAAAANSUhEUgAAAAgAAAAICAAAAADhZOFXAAAADklEQVR42mNogAIGyhgAgIQgARDoahcAAAAASUVORK5CYII=","minConfidence":0.4}),
});
console.log(await res.json());

Example input

{
  "classes": [
    "person"
  ],
  "imageBase64": "iVBORw0KGgoAAAANSUhEUgAAAAgAAAAICAAAAADhZOFXAAAADklEQVR42mNogAIGyhgAgIQgARDoahcAAAAASUVORK5CYII=",
  "minConfidence": 0.4
}

Example output

{
  "counts": {
    "dog": 1,
    "person": 2
  },
  "meta": {
    "classesFilter": null,
    "height": 1080,
    "inferenceMs": 1450,
    "inputBytes": 348211,
    "minConfidence": 0.4,
    "model": "yolox-nano",
    "width": 1920
  },
  "objects": [
    {
      "box": {
        "height": 388,
        "width": 143,
        "x": 412,
        "y": 108
      },
      "class": "person",
      "confidence": 0.87
    },
    {
      "box": {
        "height": 371,
        "width": 130,
        "x": 655,
        "y": 121
      },
      "class": "person",
      "confidence": 0.81
    },
    {
      "box": {
        "height": 160,
        "width": 180,
        "x": 220,
        "y": 340
      },
      "class": "dog",
      "confidence": 0.63
    }
  ]
}

Security scan

  • No findings. We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.

Recent checks

WhenResultHTTPTimePrice
3 h agoPassed4022.3 s$0.01
7 h agoPassed4022.1 s$0.01
10 h agoPassed4022.2 s$0.01
14 h agoPassed4022.1 s$0.01
18 h agoPassed402757 ms$0.01
21 h agoPassed4022.2 s$0.01
25 h agoPassed4022.1 s$0.01
28 h agoPassed402121 ms$0.01
32 h agoPassed4022.2 s$0.01
36 h agoPassed4022.2 s$0.01
39 h agoPassed4022.2 s$0.01
44 h agoPassed4022.3 s$0.01
47 h agoPassed4022.2 s$0.01
2 days agoPassed4022.1 s$0.01