# Grounding DINO > Text-prompted object detection (39M+ runs) — describe what to find in natural language and get bounding boxes with confidence scores, plus an annotated visualization. - **Provider**: replicate - **Model ID**: adirik/grounding-dino - **Category**: object_detection_segmentation - **Credits**: 2 per request - **Pricing Type**: fixed ## API Endpoint Base URL: https://api.core.today/v1 ### Create Prediction POST /predictions ### Get Status GET /predictions/{job_id} ### Cancel DELETE /predictions/{job_id} ## Authentication Header: `X-API-Key: YOUR_API_KEY` ## Input Parameters - `box_threshold` (number, optional): Confidence level for object detection (Default: `0.25`; Range: min: 0, max: 1) - `query` (string, optional): Comma seperated names of the objects to be detected in the image - `text_threshold` (number, optional): Confidence level for object detection (Default: `0.25`; Range: min: 0, max: 1) - `show_visualisation` (boolean, optional): Draw and visualize bounding boxes on the image (Default: `True`) - `image` (string, optional): Input image to query ## Example Request ```json { "model": "adirik/grounding-dino", "input": { "image": "https://replicate.delivery/pbxt/JlgUQIQCDemKg7bnfn5zKMqLgAPrZdpMMHzkXgHX5HUlbw9z/mugs.webp", "box_threshold": 0.2, "text_threshold": 0.2, "show_visualisation": true, "query": "pink mug" } } ``` ## Response Format ```json { "job_id": "abc123", "status": "pending", "provider": "replicate", "model": "black-forest-labs/flux-schnell", "created_at": "2026-01-01T00:00:00Z", "result": null, "error": null } ``` Status values: `pending`, `processing`, `completed`, `failed`, `cancelled` ## Usage Flow 1. POST /predictions with model and input → receive job_id 2. Poll GET /predictions/{job_id} until status is `completed` or `failed` 3. Result contains output URL(s) or data ## Output Type json ## Tags object-detection, grounding-dino, vision, bounding-boxes, zero-shot ## Documentation https://replicate.com/adirik/grounding-dino