Name: Grounding DINO API: Zero-Shot Object Detection
Brand: magicapi
SKU: api-magicapi-zero-shot-object-detection-api-hautechai-grounding-dino
Availability: InStock
Author: API Market

Shashank Agarwal

# 🔍 Zero-Shot Object Detection API (IDEA Research Grounding DINO)

## Overview
Grounding DINO (SwinT-OGC) is a zero-shot, text-prompted object detection model from IDEA Research. You name the objects in plain text and it finds them, with no training for your classes.

Send an `image` and a `query` listing the object names, separated by commas. The model returns a list of detections, each with a label, a confidence score and a bounding box, plus the URL of a copy of the image with the boxes drawn on it when `show_visualisation` is `true`.

## Features
- **Text-prompted detection**: name any objects in `query`, for example `pink mug` or `person, dog, bicycle`.
- **Confidence thresholds**: `box_threshold` and `text_threshold` (0 to 1, default 0.25) filter low-confidence results.
- **Structured results**: each detection has `label`, `confidence` and `bbox`.
- **Visualisation**: `show_visualisation` (default `true`) returns `result_image`, the input image with the boxes drawn.

## Use Cases
1. **Product and inventory counting**: find and count named items in shelf or warehouse photos.
2. **Dataset labelling**: create draft bounding boxes for new classes before manual review.
3. **Image search and filtering**: check whether an image contains a given object.
4. **Cropping**: use the returned boxes to crop objects out of an image.

## Visual Examples
### Example Input
![Example input image with several mugs](https://blog.api.market/wp-content/uploads/2026/10/grounding-dino-input-api-market.webp)

Query: `pink mug`. Settings: `box_threshold` 0.25, `text_threshold` 0.25, `show_visualisation` `true`.

### Example Output
![Detection result with boxes drawn around each pink mug found](https://blog.api.market/wp-content/uploads/2026/10/grounding-dino-output-sd4jyx6f-api-market.jpg)

The model returned 4 detections labelled `pink mug`, with confidence scores from 0.43 to 0.81.

## Input Parameters
| Field | Type | Required | Default | Allowed values | Description |
| --- | --- | --- | --- | --- | --- |
| `image` | string (URL) | No | none |  | Input image to query |
| `query` | string | No | none |  | Comma-separated names of the objects to detect in the image |
| `box_threshold` | number | No | `0.25` | `0` to `1` | Confidence level for object detection |
| `text_threshold` | number | No | `0.25` | `0` to `1` | Confidence level for object detection |
| `show_visualisation` | boolean | No | `true` |  | Draw and visualize bounding boxes on the image |

## Pricing
- **Pay As You Go (PAYG) pricing**: you only pay for what you use.
- **Price**: $0.067 per API unit.
- **1 API unit = 1 request covering up to 39 seconds of processing.** A request that takes longer uses one more unit for each started 39-second block (for example, 40 seconds of processing is 2 units, $0.134).
- **Example cost**: the example request took 3.72 seconds of processing, so it used 1 API unit = **$0.067**.
- **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/zero-shot-object-detection-api-hautechai-grounding-dino`

### 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/zero-shot-object-detection-api-hautechai-grounding-dino/predictions" \
  -H "Content-Type: application/json" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY" \
  -d '{
    "version": "e1ab4da0c9a2841ed63fa4343c4a1bd42ba413a80146b763a77c644e12289b02",
    "input": {
      "image": "https://blog.api.market/wp-content/uploads/2026/10/grounding-dino-input-api-market.webp",
      "query": "pink mug",
      "box_threshold": 0.25,
      "text_threshold": 0.25,
      "show_visualisation": true
    }
  }'
```

Response (201 Created):
```json
{
  "id": "sd4jyx6fthrp40d1d0yvak7f68",
  "version": "e1ab4da0c9a2841ed63fa4343c4a1bd42ba413a80146b763a77c644e12289b02",
  "status": "starting",
  "created_at": "2026-10-23T10:10:43.957Z"
}
```

#### Check Prediction Status
```bash
curl -X GET "https://prod.api.market/api/v1/magicapi/zero-shot-object-detection-api-hautechai-grounding-dino/predictions/{id}" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY"
```

Response when the prediction has finished (200 OK):
```json
{
  "id": "sd4jyx6fthrp40d1d0yvak7f68",
  "status": "succeeded",
  "output": {
    "detections": [
      {
        "bbox": [
          19,
          204,
          408,
          563
        ],
        "confidence": 0.8069838881492615,
        "label": "pink mug"
      },
      {
        "bbox": [
          545,
          263,
          952,
          650
        ],
        "confidence": 0.7634527683258057,
        "label": "pink mug"
      },
      {
        "bbox": [
          416,
          60,
          764,
          380
        ],
        "confidence": 0.47547340393066406,
        "label": "pink mug"
      },
      {
        "bbox": [
          909,
          161,
          1078,
          487
        ],
        "confidence": 0.4319826066493988,
        "label": "pink mug"
      }
    ],
    "result_image": "https://blog.api.market/wp-content/uploads/2026/10/grounding-dino-output-sd4jyx6f-api-market.jpg"
  },
  "error": null,
  "created_at": "2026-10-23T10:10:43.957Z",
  "started_at": "2026-10-23T10:11:29.789Z",
  "completed_at": "2026-10-23T10:11:33.510Z"
}
```

`output` is an object. `detections` is an array with one entry per object found: `label` (the query term that matched), `confidence` (0 to 1) and `bbox` (four pixel coordinates, `[x_min, y_min, x_max, y_max]`). `result_image` is the URL of the input image with the boxes drawn, returned when `show_visualisation` is `true`.

### 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 `box_threshold` above 1.
- **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
All plans allow 10 requests per second. Requests above that return `429 Too Many Requests`; back off before retrying and honour any `Retry-After` header. Polling a prediction with GET is free but still counts toward the per-second limit, so poll every 1 to 5 seconds rather than in a tight loop.

## 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/zero-shot-object-detection-api-hautechai-grounding-dino";

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: "e1ab4da0c9a2841ed63fa4343c4a1bd42ba413a80146b763a77c644e12289b02", 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/grounding-dino-input-api-market.webp",
    "query": "pink mug",
    "box_threshold": 0.25,
    "text_threshold": 0.25,
    "show_visualisation": true
  }).then((output) => console.log(JSON.stringify(output, null, 2)));
```

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

API_KEY = "YOUR_API_MARKET_KEY"
BASE_URL = "https://prod.api.market/api/v1/magicapi/zero-shot-object-detection-api-hautechai-grounding-dino"


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": "e1ab4da0c9a2841ed63fa4343c4a1bd42ba413a80146b763a77c644e12289b02", "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")


output = create_and_wait_for_prediction({
    "image": "https://blog.api.market/wp-content/uploads/2026/10/grounding-dino-input-api-market.webp",
    "query": "pink mug",
    "box_threshold": 0.25,
    "text_threshold": 0.25,
    "show_visualisation": True
})
print(json.dumps(output, indent=2))
```

## FAQ
- **How do I search for several kinds of object?**
  - List them in `query`, separated by commas, for example `person, dog, bicycle`. Each detection's `label` tells you which term matched.
- **I get too many or too few detections. What should I change?**
  - Raise `box_threshold` and `text_threshold` (default 0.25) to keep only confident matches, or lower them to find more objects.
- **Do I need the drawn image?**
  - No. Set `show_visualisation` to `false` if you only need the `detections` data.
- **What format is `bbox`?**
  - Four pixel coordinates of the box: `[x_min, y_min, x_max, y_max]`.
- **How is a request billed?**
  - $0.067 per request for up to 39 seconds of processing. The example took 3.72 seconds, so it cost one unit.
- **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`.

## Contact Us
If you have any questions, reach out to us through the chat on the bottom right of the page. You can also email our support team at hello@magicapi.com.


Detect objects named in a text query with Grounding DINO: labelled bounding boxes, confidence scores and an annotated image. $0.067 per request, pay as you go.