Can I deploy the same model to multiple regions?

Yes. Each model can be deployed to multiple regions simultaneously. Your plan determines the total number of endpoints available: 3 for Free, 10 for Pro, and unlimited for Enterprise. This allows you to serve users globally with low-latency endpoints in each region.

How much does deployment cost?

Dedicated endpoints are billed based on CPU, memory, and request volume. With scale-to-zero enabled by default, you only pay for active inference time. There is no cost when your endpoint isn't receiving requests. Shared inference is included with your platform plan.

What's the difference between shared and dedicated inference?

Shared inference runs on a multi-tenant service across 3 regions and is rate-limited to 20 requests per minute. It's best for development and quick testing. Dedicated endpoints are single-tenant services deployed to any of 43 regions with no rate limits, consistent latency, and configurable resources, built for scalable production workloads.

How long does deployment take?

Dedicated endpoint deployment typically takes one to two minutes. This includes container provisioning, startup, and an initial health check to validate the service is ready. Once the endpoint is ready, it begins accepting inference requests immediately.

What is model deployment?

Model deployment is the process of making a trained computer vision model available to receive and process real-world data. Once deployed, computer vision applications can send images and video frames to the model via API and receive predictions, enabling everything from automated quality inspection to real-time object detection in production systems. On Ultralytics Platform, deployment is integrated directly into the end-to-end training workflow. Once your model is trained, you can test it in the browser, deploy it to a dedicated endpoint in any of 43 global regions, and monitor its performance, all from the same workspace.

Ultralytics Platform

Deploy computer vision models across 42 global regions

Take trained models from browser testing to production endpoints in a few clicks, with auto-scaling, deployment monitoring, and 20 export formats.

Request license Try browser inference

Ultralytics deployment interface showing model deployment options.

Deploy at global production scale

Move trained models into production with worldwide availability, broad export support, and the usage volume proven by the Ultralytics ecosystem.

42+

Deployment regions

19+

Export formats

—

Daily usages

Test your model in the browser

Every trained model includes a built-in Predict tab functionality. Upload an image, or open your camera; the bounding boxes appear instantly.

Inference runs the top model performance automatically when you upload an image or change a parameter.

Fine-tune confidence thresholds, IoU settings, and image size to see how they affect predictions in real time.

Detection, instance segmentation, semantic segmentation, classification, pose estimation, and OBB are clearly depicted for your task.

Cloud endpoint deployment tab in Ultralytics Platform.

Deploy to 42 regions worldwide

Deploy your models to dedicated endpoints across the Americas, Europe, Asia-Pacific, and the Middle East. Each endpoint has its own URL, auto-scaling, and monitoring for requests, latency, errors, and logs.

Auto-scaling that matches your traffic

Dedicated endpoints scale up for traffic spikes and down to zero when idle.

Scale to zero by default: No cost when your endpoint isn't receiving requests.
No rate limits: Dedicated endpoints have no throughput caps.
Configurable resources: Choose CPU (1-8 cores) and memory (1-32 GB) to match your workload.

Model export format selector for ONNX, TensorRT, CoreML, LiteRT, and other formats.

20 export formats. Your model. Any environment.

Ultralytics Platform supports cloud and edge deployment for high-performance. All Ultralytics YOLO models are natively optimized to run efficiently across environments, delivering high accuracy, reliable performance, and compatibility even on edge devices with limited compute resources.

Ultralytics monitoring dashboard for deployed model inference.

Monitor everything in production

Track endpoint requests, latency, errors, and logs from the deployments dashboard. Paid dedicated endpoints also provide live prediction statistics and temporary examples you can inspect and save to a dataset.

Requests, latency, and errors: 24-hour HTTP volume, volume-weighted P95 latency, and error-rate alerts above 5%.
Health checks and logs: Live endpoint health with auto-retry, plus severity-filtered logs to diagnose issues fast.
Temporary examples: Inspect sampled predictions on paid dedicated endpoints. Examples are held in endpoint memory; save useful images to a dataset to keep them.
Prediction statistics: Class counts, confidence, inference time, and spatial heatmaps, where supported by the model task. Statistics reset when the serving instance is replaced.

Python code snippet for sending an image to a deployment endpoint.

Integrate in minutes

Every deployed endpoint comes with auto-generated code examples in Python, JavaScript, and cURL, pre-populated with your actual endpoint URL and API key. Copy, paste, and start sending inference requests from any application.

Request license Get started

Try YOLO26 Inference

Drag and drop an image to see real-time object detection

Input Image

Upload an image or select an example to test YOLO26n. Predict Docs

Live Demo

Drop an image here

or click to browse

Supports JPEG, PNG, WebP, AVIF, HEIC, JP2, TIFF, BMP & more (max 10MB)

Or try an example

Confidence

0.25

IoU

0.70

Image Size

640

API Docs

Deploy your model to get a dedicated inference endpoint with API key authentication — then replace the placeholder URL and key below with your deployment values. Deploy docs

Note: This is example code. Deploy your model first to get your endpoint URL and API key.

import requests

# Deployment URL and API key
url = "https://your-deployment-url.run.app/predict"
api_key = "YOUR_API_KEY"

# Optional inference parameters (conf, iou, imgsz)
args = {"conf": 0.25, "iou": 0.7, "imgsz": 640}

with open("image.jpg", "rb") as f:
    response = requests.post(
        url,
        headers={"Authorization": f"Bearer {api_key}"},
        data=args,
        files={"file": f},
    )

print(response.json())

Learn how to deploy!

Watch how to test a trained model, deploy it to a global endpoint, and monitor requests, latency, and live predictions.

Need to train a model first?

Ultralytics Platform connects annotation, training, and deployment in a single platform.

1Annotate

2Train

3Deploy

Explore training

Explore industry solutions

See how teams apply Ultralytics computer vision across production environments.

Computer vision for aerial imagery

Transform drone and aerial imagery into real-time insights for agriculture, aquaculture, environmental monitoring, conservation, and geospatial analysis with Ultralytics YOLO.

Deploy computer vision models across 42 global regions

Deploy at global production scale

Test your model in the browser

Deploy to 42 regions worldwide

Auto-scaling that matches your traffic

20 export formats. Your model. Any environment.

Monitor everything in production

Integrate in minutes

Try YOLO26 Inference

Learn how to deploy!

Need to train a model first?

Explore industry solutions

Computer vision for aerial imagery

Computer vision in aerospace

Computer vision in security

Computer vision in robotics

Computer vision in logistics

Computer vision in retail

Computer vision in healthcare

Computer vision in manufacturing

Computer vision in automotive

Computer vision in agriculture

Computer vision for aerial imagery

Computer vision in aerospace

Computer vision in security

Computer vision in robotics

Computer vision in logistics

Computer vision in retail

Computer vision in healthcare

Computer vision in manufacturing

Computer vision in automotive

Computer vision in agriculture

Computer vision for aerial imagery

Computer vision in aerospace

Computer vision in security

Computer vision in robotics

Computer vision in logistics

Computer vision in retail

Computer vision in healthcare

Computer vision in manufacturing

Computer vision in automotive

Computer vision in agriculture

Enterprise-grade security, certified

SOC 2 Type I

ISO 27001:2022

Encryption

GDPR & CCPA

Frequently asked questions

Can I deploy the same model to multiple regions?

How much does deployment cost?

What's the difference between shared and dedicated inference?

How long does deployment take?

What is model deployment?

Start deploying today!