Name: Roboflow RF-DETR Object Detection API
Brand: magicapi
SKU: api-magicapi-real-time-object-detection-api-hardikdava-rf-detr
Availability: InStock
Author: API Market

Shashank Agarwal

# 🎯 Object Detection API (Roboflow RF-DETR)

## Overview
RF-DETR is an object detection model from Roboflow, built on the detection transformer (DETR) approach. Its developer describes it as a state-of-the-art real-time object detection model.

Send an `image` URL and, optionally, a `confidence_threshold` (default `0.5`). The response lists every detected object with its bounding box, class ID, label and confidence score, and links to a copy of the image with the detections drawn on it.

## Features
- **Labeled detections**: each object comes with a `label` (for example `dog` or `bicycle`), a `class_id` and a `confidence` from 0 to 1.
- **Bounding boxes**: `bbox` gives the box corners `[x_min, y_min, x_max, y_max]` in pixels.
- **Annotated image**: `result_image` links to the input with boxes and labels drawn on it.
- **Adjustable threshold**: `confidence_threshold` (default `0.5`) drops weaker detections; lower it to see more objects.

## Use Cases
1. **Image tagging**: list the objects in photos for search and cataloging.
2. **Counting**: count people, vehicles or animals in a scene.
3. **Cropping pipelines**: pass each `bbox` to a cropping or classification step.
4. **Visual checks**: use `result_image` to review what was found at a glance.

## Visual Examples
### Example Input
![Example input: a dog sitting next to a bicycle, with a car in the background](https://blog.api.market/wp-content/uploads/2026/10/yolox-input-api-market.jpg)

- `confidence_threshold`: `0.3`

### Example Output
![RF-DETR output: the photo with boxes and labels drawn around the bicycle, dog, car and motorcycle](https://blog.api.market/wp-content/uploads/2026/11/rf-detr-output-yr140d17-api-market.jpg)

Four objects were found: bicycle (0.94), dog (0.93), car (0.88) and motorcycle (0.61). The `detections` list:

```json
[
  {"bbox": [124.75785827636719, 130.89669799804688, 567.4163818359375, 422.29840087890625], "class_id": 2, "confidence": 0.9423940181732178, "label": "bicycle"},
  {"bbox": [130.60609436035156, 222.05580139160156, 310.8648376464844, 541.7166137695312], "class_id": 18, "confidence": 0.9284785985946655, "label": "dog"},
  {"bbox": [467.5155944824219, 74.26083374023438, 683.6790161132812, 170.23785400390625], "class_id": 3, "confidence": 0.8793465495109558, "label": "car"},
  {"bbox": [55.50226593017578, 70.88336944580078, 113.48277282714844, 123.92130279541016], "class_id": 4, "confidence": 0.6100765466690063, "label": "motorcycle"}
]
```

## Input Parameters
| Field | Type | Required | Default | Allowed values | Description |
| --- | --- | --- | --- | --- | --- |
| `image` | string (URL) | Yes | none |  | Image URL to detect objects in |
| `confidence_threshold` | number | No | `0.5` |  | Minimum confidence for a detection to be returned |

## Pricing
- **Pay As You Go (PAYG) pricing**: you only pay for what you use.
- **Price**: $0.001 per API unit.
- **1 API unit = 1 request with up to 8 seconds of processing.** Typical requests take about a second and cost one unit ($0.001). A request that needs more processing time is billed one more unit for each started 8-second block.
- **Example cost**: the example request processed for 1.24 seconds, so it used 1 API unit and cost $0.001.
- **Failed or cancelled predictions are not billed.**
- **GET requests to check prediction status** are free and don't count toward API unit usage.
- **No monthly subscription fee.**

## API Documentation

### Base URL
All API requests go to: `https://prod.api.market/api/v1/magicapi/real-time-object-detection-api-hardikdava-rf-detr`

### Authentication
Send your api.market API key in the `x-api-market-key` header:
```
x-api-market-key: YOUR_API_MARKET_KEY
```

### Asynchronous Processing
**IMPORTANT**: This API is asynchronous. The flow is:
1. Send a POST request to `/predictions`. A successful request returns **201 Created** with a prediction `id` and a `status` of `starting` or `processing`.
2. Poll GET `/predictions/{id}` with that ID.
3. Keep polling while `status` is `starting` or `processing`.
4. Stop when `status` is `succeeded` (read `output`), `failed` or `canceled` (read `error`).

A polling interval of 1 second and an overall timeout of 600 seconds (10 minutes) work well.

### Endpoints

#### Create a Prediction
```bash
curl -X POST "https://prod.api.market/api/v1/magicapi/real-time-object-detection-api-hardikdava-rf-detr/predictions" \
  -H "Content-Type: application/json" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY" \
  -d '{
    "version": "dea9702918a05642aaaae7ace8c6fcc4ed8ed7d89a9b062f8a58ac564cd2a675",
    "input": {
      "image": "https://blog.api.market/wp-content/uploads/2026/10/yolox-input-api-market.jpg",
      "confidence_threshold": 0.3
    }
  }'
```

Response (201 Created):
```json
{
  "id": "yr140d171hrmt0d1mvkrnb921r",
  "version": "dea9702918a05642aaaae7ace8c6fcc4ed8ed7d89a9b062f8a58ac564cd2a675",
  "status": "starting",
  "created_at": "2026-11-04T14:12:09.1Z"
}
```

#### Check Prediction Status
```bash
curl -X GET "https://prod.api.market/api/v1/magicapi/real-time-object-detection-api-hardikdava-rf-detr/predictions/{id}" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY"
```

Response when the prediction has finished (200 OK):
```json
{
  "id": "yr140d171hrmt0d1mvkrnb921r",
  "status": "succeeded",
  "output": {
    "detections": [
      {
        "bbox": [124.75785827636719, 130.89669799804688, 567.4163818359375, 422.29840087890625],
        "class_id": 2,
        "confidence": 0.9423940181732178,
        "label": "bicycle"
      },
      {
        "bbox": [130.60609436035156, 222.05580139160156, 310.8648376464844, 541.7166137695312],
        "class_id": 18,
        "confidence": 0.9284785985946655,
        "label": "dog"
      },
      {
        "bbox": [467.5155944824219, 74.26083374023438, 683.6790161132812, 170.23785400390625],
        "class_id": 3,
        "confidence": 0.8793465495109558,
        "label": "car"
      },
      {
        "bbox": [55.50226593017578, 70.88336944580078, 113.48277282714844, 123.92130279541016],
        "class_id": 4,
        "confidence": 0.6100765466690063,
        "label": "motorcycle"
      }
    ],
    "result_image": "https://blog.api.market/wp-content/uploads/2026/11/rf-detr-output-yr140d17-api-market.jpg"
  },
  "error": null,
  "created_at": "2026-11-04T14:12:09.1Z",
  "started_at": "2026-11-04T14:12:31.672159906Z",
  "completed_at": "2026-11-04T14:12:32.916673865Z"
}
```

`output` is an object. `detections` is a list of objects, each with `bbox` (`[x_min, y_min, x_max, y_max]` in pixels), `class_id`, `confidence` and `label`. `result_image` is the URL of the annotated image.

### Status Codes
- **201 Created**: prediction created (POST `/predictions`). This is the normal success response.
- **200 OK**: prediction details returned (GET `/predictions/{id}`).
- **400 Bad Request**: invalid input, for example a missing `image` or a `confidence_threshold` that is not a number.
- **401 Unauthorized**: missing or invalid API key.
- **404 Not Found**: no prediction with that ID.
- **429 Too Many Requests**: rate limit exceeded.
- **500 Internal Server Error** or **503 Service Unavailable**: temporary server problem; retry later.

## Rate Limits
Requests are rate limited to keep usage fair. If you receive a 429 response, wait and retry with exponential backoff.

## Error Handling
- Check the HTTP status code of every request and read the response body for the error message.
- A prediction can also end with `status` set to `failed`; the `error` field then explains why. Failed predictions are not billed.
- Retry 429, 500 and 503 responses with exponential backoff. Fix the input before retrying a 400.

## Implementation Guide
### Example Code

#### JavaScript
```javascript
const apiKey = "YOUR_API_MARKET_KEY";
const baseUrl = "https://prod.api.market/api/v1/magicapi/real-time-object-detection-api-hardikdava-rf-detr";

async function createAndWaitForPrediction(input) {
  const response = await fetch(`${baseUrl}/predictions`, {
    method: "POST",
    headers: {
      "Content-Type": "application/json",
      "x-api-market-key": apiKey
    },
    body: JSON.stringify({ version: "dea9702918a05642aaaae7ace8c6fcc4ed8ed7d89a9b062f8a58ac564cd2a675", input })
  });

  if (response.status !== 201) {
    throw new Error(`API error: ${response.status} ${await response.text()}`);
  }

  const prediction = await response.json();
  return pollForResults(prediction.id);
}

const delay = (ms) => new Promise((resolve) => setTimeout(resolve, ms));

async function pollForResults(predictionId) {
  const maxTimeout = 600000;
  const pollInterval = 1000;
  const startTime = Date.now();

  while (Date.now() - startTime < maxTimeout) {
    const response = await fetch(`${baseUrl}/predictions/${predictionId}`, {
      headers: { "x-api-market-key": apiKey }
    });

    if (!response.ok) {
      throw new Error(`API error: ${response.status} ${await response.text()}`);
    }

    const prediction = await response.json();

    if (prediction.status === "succeeded") {
      return prediction.output;
    }

    if (prediction.status === "failed" || prediction.status === "canceled") {
      throw new Error(`Prediction ${prediction.status}: ${prediction.error || "Unknown error"}`);
    }

    await delay(pollInterval);
  }

  throw new Error("Prediction timed out after 10 minutes");
}

createAndWaitForPrediction({
  "image": "https://blog.api.market/wp-content/uploads/2026/10/yolox-input-api-market.jpg",
  "confidence_threshold": 0.3
}).then((output) => output.detections.forEach((d) => console.log(d.label, d.confidence, d.bbox)));
```

#### Python
```python
import time
import requests

API_KEY = "YOUR_API_MARKET_KEY"
BASE_URL = "https://prod.api.market/api/v1/magicapi/real-time-object-detection-api-hardikdava-rf-detr"


def create_and_wait_for_prediction(input_data):
    headers = {"Content-Type": "application/json", "x-api-market-key": API_KEY}
    response = requests.post(
        f"{BASE_URL}/predictions",
        headers=headers,
        json={"version": "dea9702918a05642aaaae7ace8c6fcc4ed8ed7d89a9b062f8a58ac564cd2a675", "input": input_data},
    )

    if response.status_code != 201:
        raise Exception(f"API error: {response.status_code} {response.text}")

    return poll_for_results(response.json()["id"])


def poll_for_results(prediction_id):
    max_timeout = 600
    poll_interval = 1
    headers = {"x-api-market-key": API_KEY}
    start_time = time.time()

    while time.time() - start_time < max_timeout:
        response = requests.get(f"{BASE_URL}/predictions/{prediction_id}", headers=headers)

        if response.status_code != 200:
            raise Exception(f"API error: {response.status_code} {response.text}")

        prediction = response.json()

        if prediction["status"] == "succeeded":
            return prediction["output"]

        if prediction["status"] in ("failed", "canceled"):
            raise Exception(f"Prediction {prediction['status']}: {prediction.get('error') or 'Unknown error'}")

        time.sleep(poll_interval)

    raise Exception("Prediction timed out after 10 minutes")


result = create_and_wait_for_prediction({
    "image": "https://blog.api.market/wp-content/uploads/2026/10/yolox-input-api-market.jpg",
    "confidence_threshold": 0.3
})
for d in result["detections"]:
    print(d["label"], d["confidence"], d["bbox"])
print(result["result_image"])
```

## FAQ
- **What objects can it detect?**
  - Everyday object classes such as the bicycle, dog, car and motorcycle found in the example. Each detection names its class in `label`.
- **How do I get more or fewer detections?**
  - Change `confidence_threshold`. Lower values (the example uses 0.3) return weaker detections too; higher values return only confident ones.
- **What format are the boxes in?**
  - `bbox` is `[x_min, y_min, x_max, y_max]` in pixels of the input image.
- **Do I have to use the annotated image?**
  - No. `result_image` is a convenience; the coordinates in `detections` are enough to draw your own boxes.
- **Is the 201 response from POST an error?**
  - No. 201 Created means the prediction was accepted. Use the returned `id` to poll GET `/predictions/{id}` until `status` is `succeeded`, `failed` or `canceled`.
- **What if my prediction fails?**
  - Failed predictions are not billed. Read the `error` field, check that the image URL is reachable and try again.

## Contact Us
If you have any questions, reach out to us through the chat on the bottom right of the page.


Detect objects in images with RF-DETR: labeled bounding boxes, class IDs, confidence scores and an annotated result image. $0.001 per request, pay as you go.