Link to this sectionInference#

Ultralytics Platform provides an inference API for testing trained models. Use the browser-based Predict tab for quick validation or the REST API for programmatic access.

Link to this sectionPredict Tab#

Every model includes a Predict tab for browser-based inference:

1. Navigate to your model
2. Click the Predict tab
3. Upload an image, use an example, or open your webcam
4. View predictions instantly with bounding box overlays

Link to this sectionInput Methods#

The predict panel supports multiple input methods:

graph LR
    A[Upload Image] --> D[Auto-Inference]
    B[Example Image] --> D
    C[Webcam Capture] --> D
    D --> E[Results + Overlays]

    style D fill:#2196F3,color:#fff
    style E fill:#4CAF50,color:#fff

Link to this sectionUpload Image#

Drag and drop or click to upload:

• Supported formats: JPEG, PNG, WebP, AVIF, HEIC, JP2, TIFF, BMP, DNG, MPO
• Max size: 10MB
• Auto-inference: Results appear automatically after upload

Link to this sectionExample Images#

The predict panel shows example images from your model's linked dataset. If no dataset is linked, default examples are used:

For OBB models, aerial images of boats and airports are shown instead.

Link to this sectionWebcam#

Click the webcam card to start a live camera feed:

1. Grant camera permission when prompted
2. Click the video preview to capture a frame
3. Inference runs automatically on the captured frame
4. Click again to restart the webcam

Link to this sectionView Results#

Inference results display:

• Bounding boxes with class labels as SVG overlays
• Confidence scores for each detection
• Class colors from your dataset's color palette (or the Ultralytics default palette)
• Speed breakdown: Preprocess, inference, postprocess, and network time

The results panel shows:

Link to this sectionInference Parameters#

Adjust detection behavior with parameters in the collapsible Parameters section:

Link to this sectionConfidence Threshold#

Filter predictions by confidence:

• Higher (0.5+): Fewer, more certain predictions
• Lower (0.1-0.25): More predictions, some noise
• Default (0.25): Balanced for most use cases

Link to this sectionIoU Threshold#

Control Non-Maximum Suppression:

• Higher (0.7+): Allow more overlapping boxes
• Lower (0.3-0.5): Merge nearby detections more aggressively
• Default (0.7): Balanced NMS behavior for most use cases

Link to this sectionDeployment Predict#

Each running dedicated endpoint includes a Predict tab directly on its deployment card. This uses the deployment's own inference service rather than the shared predict service, letting you test your deployed endpoint from the browser.

Link to this sectionREST API#

Access inference programmatically:

Link to this sectionAuthentication#

Include your API key in requests:

Authorization: Bearer YOUR_API_KEY

Link to this sectionEndpoint#

POST https://platform.ultralytics.com/api/models/{modelId}/predict

Link to this sectionRequest#

import requests

url = "https://platform.ultralytics.com/api/models/MODEL_ID/predict"
headers = {"Authorization": "Bearer YOUR_API_KEY"}
files = {"file": open("image.jpg", "rb")}
data = {"conf": 0.25, "iou": 0.7, "imgsz": 640}

response = requests.post(url, headers=headers, files=files, data=data)
print(response.json())

Link to this sectionRequest Parameters#

Link to this sectionResponse#

{
    "images": [
        {
            "shape": [1080, 1920],
            "results": [
                {
                    "class": 0,
                    "name": "person",
                    "confidence": 0.92,
                    "box": { "x1": 100, "y1": 50, "x2": 300, "y2": 400 }
                },
                {
                    "class": 2,
                    "name": "car",
                    "confidence": 0.87,
                    "box": { "x1": 400, "y1": 200, "x2": 600, "y2": 350 }
                }
            ],
            "speed": {
                "preprocess": 1.2,
                "inference": 12.5,
                "postprocess": 2.3
            }
        }
    ],
    "metadata": {
        "imageCount": 1,
        "functionTimeCall": 0.018,
        "model": "model.pt",
        "version": {
            "ultralytics": "8.x.x",
            "torch": "2.6.0",
            "torchvision": "0.21.0",
            "python": "3.13.0"
        }
    }
}

Link to this sectionResponse Fields#

Link to this sectionTask-Specific Responses#

Response format varies by task:

{
  "class": 0,
  "name": "person",
  "confidence": 0.92,
  "box": {"x1": 100, "y1": 50, "x2": 300, "y2": 400}
}

Link to this sectionBilling#

Shared inference (the Predict tab and /api/models/{id}/predict endpoint) is included at no additional cost on all plans. There are no per-request charges for shared inference.

For production workloads requiring higher throughput, deploy a dedicated endpoint.

Link to this sectionRate Limits#

Shared inference is rate-limited to 20 requests/min per API key. When throttled, the API returns 429 with a Retry-After header. See the full rate limit reference for all endpoint categories.

Link to this sectionError Handling#

Common error responses:

Link to this sectionFAQ#

Link to this sectionCan I run inference on video?#

Both inference methods accept video files:

• Dedicated endpoints accept video files directly. Supported formats (up to 100 MB): ASF, AVI, GIF, M4V, MKV, MOV, MP4, MPEG, MPG, TS, WEBM, WMV. Each frame is processed individually and results are returned per frame. See dedicated endpoints for details.
• Shared inference (/api/models/{id}/predict) uses the same predict service and accepts the same video formats. However, the browser Predict tab in the UI only uploads images — use the REST API directly or a dedicated endpoint for video workflows. The shared endpoint is also rate-limited to 20 req/min, so dedicated endpoints are the better choice for heavy video workloads.

Link to this sectionHow do I get the annotated image?#

The API returns JSON predictions. To visualize:

1. Use predictions to draw boxes locally
2. Use Ultralytics plot() method:

from ultralytics import YOLO

model = YOLO("yolo26n.pt")
results = model("image.jpg")
results[0].save("annotated.jpg")

See the Predict mode documentation for the full results API and visualization options.

Link to this sectionWhat's the maximum image size?#

• Upload limit: 10MB
• Recommended: <5MB for fast inference
• Auto-resize: Images are resized to the selected Image Size parameter

Large images are automatically resized while preserving aspect ratio.

Link to this sectionCan I run batch inference?#

The current API processes one image per request. For batch:

1. Send concurrent requests
2. Use a dedicated endpoint for higher throughput
3. Consider local inference for large batches

import concurrent.futures

import requests

url = "https://predict-abc123.run.app/predict"
headers = {"Authorization": "Bearer YOUR_API_KEY"}
images = ["img1.jpg", "img2.jpg", "img3.jpg"]

def predict(image_path):
    with open(image_path, "rb") as f:
        return requests.post(url, headers=headers, files={"file": f}).json()

with concurrent.futures.ThreadPoolExecutor(max_workers=4) as executor:
    results = list(executor.map(predict, images))