
Object Detection API
Object Detection API
TLDR
- Detect objects in images and get labels, confidence scores, and bounding box coordinates via API.
- 100 free queries per month.
Here's a sample response:
[
{
"object_name": "mango",
"confidence_score": 0.61,
"region": {
"top_left_x": 7,
"top_left_y": 177,
"bottom_right_x": 718,
"bottom_right_y": 1262
}
}
]What is this?
The Object Detection API identifies objects in your images using advanced neural networks.
Upload an image, get back detected objects with labels, confidence scores, and exact bounding box coordinates—all in clean JSON.
Perfect for e-commerce product tagging, content moderation, inventory management, or any app that needs to understand what's in an image.
Why use it?
1. Free Plan
100 queries per month. Free. No credit card required.
2. Affordable Pricing
When you need more, our paid plans cost less than alternatives:
- $16 gets you 3K queries/month
- $48 gets you 15K queries/month
- $148 gets you 75K queries/month
3. 99.99% Uptime SLA
Production apps demand reliability.
We maintain a 99.99% uptime SLA.
How to use it?
Simple REST API. Here's how it works:
-
Sign up on Omkar Cloud by visiting this link.

-
Visit the API Key Page.
-
Copy your API key.

-
Make a request with it:
cURL:
curl -X POST "https://object-detection-api.omkar.cloud/detect" \
-H "API-Key: YOUR_API_KEY" \
-F "image=@photo.jpg"Python:
import requests
api_key = "YOUR_API_KEY"
with open("photo.jpg", "rb") as image_file:
response = requests.post(
"https://object-detection-api.omkar.cloud/detect",
headers={"API-Key": api_key},
files={"image": image_file}
)
print(response.json())JavaScript (Node.js axios):
import axios from "axios";
import FormData from "form-data";
import fs from "fs";
const apiKey = "YOUR_API_KEY";
const form = new FormData();
form.append("image", fs.createReadStream("photo.jpg"));
const response = await axios.post(
"https://object-detection-api.omkar.cloud/detect",
form,
{
headers: {
"API-Key": apiKey,
...form.getHeaders()
}
}
);
console.log(response.data);- Get detected objects and use them in your app.
That's it. Image to object detection in milliseconds.
API Reference
Endpoint
POST https://object-detection-api.omkar.cloud/detect
Request
- Content-Type:
multipart/form-data - image (required, file): Image file in JPEG or PNG format. Max file size: 10MB.
Response
Returns an array of detected objects:
[
{
"object_name": "mango",
"confidence_score": 0.61,
"region": {
"top_left_x": 7,
"top_left_y": 177,
"bottom_right_x": 718,
"bottom_right_y": 1262
}
}
]❓ What data does the API return?
You get:
- object_name — What the object is (e.g., "mango", "car", "person")
- confidence_score — How confident the model is (0.0 to 1.0)
- region — Bounding box coordinates with top_left_x, top_left_y, bottom_right_x, bottom_right_y
All in structured JSON. Ready to use in your app.
❓ How accurate is the data?
We use neural networks optimized for precision and recall.
For most common objects (people, vehicles, animals, everyday items), accuracy is reliable for production use.
❓ What image formats are supported?
JPEG and PNG.
❓ What is the maximum image size?
10MB
❓ Can I detect multiple objects in one image?
Yes.
The API returns all detected objects in the image. Upload a photo with 10 objects, get 10 detection results back—each with its own label, confidence score, and bounding box.
❓ What's the difference between confidence score and bounding box?
Confidence score tells you how sure the model is about the detection. Range is 0.0 to 1.0. Higher is better. Use this to filter out low-confidence detections.
Bounding box tells you where the object is in the image. Four coordinates define a rectangle around the detected object. Use this to crop, highlight, or locate objects in your UI.
❓ How fast is the API?
Typical response time is under 800ms for standard images.
❓ Do you store my images?
No. We delete your image after processing.
❓ Tell me about Omkar Cloud.
We're an API services company with 20+ tools for OCR, document processing, and developer APIs.
Some things we are proud of:
- We built Botasaurus, an open-source Python framework with 3.7K+ GitHub stars
- Sponsored by 1000+ developers on GitHub
❓ How much does it cost?
- Free — $0 — 100 queries/month
- Starter — $16 — 3,000 queries/month
- Grow — $48 — 15,000 queries/month
- Scale — $148 — 75,000 queries/month
Why we're affordable: Low overhead. We run lean and pass the savings to you.
Note: You get 100 free queries every month.
❓ How do I get a refund?
If the product doesn't meet your needs within 90 days, get a refund in 2 clicks.
-
Go to Transactions Page

-
Click "Request Refund"

-
Confirm by clicking Request Refund again. The amount will be refunded within 1-2 business days. We'll email you updates.

No emails. No explanations. Simple 2-click process.
❓ Is there a catch in refunds?
No catch.
It's a simple 2-click process, exactly as described above.
Questions? We have answers.
Reach out anytime. We will solve your query within 1 working day.

