Link to this sectionDeployment#

Ultralytics Platform provides comprehensive model deployment options for putting your YOLO models into production. Test models with browser-based inference, deploy to dedicated endpoints across 42 global regions, and monitor performance in real-time.

Link to this sectionOverview#

The Deployment section helps you:

• Test models directly in the browser with the Predict tab
• Deploy to dedicated endpoints in 42 global regions
• Monitor request metrics, logs, and health checks
• Scale to zero when idle (deployments currently run a single active instance)

Link to this sectionDeployment Options#

Ultralytics Platform offers multiple deployment paths:

Link to this sectionWorkflow#

graph LR
    A[✅ Test]:::start --> B[⚙️ Configure]:::proc
    B --> C[🌐 Deploy]:::proc
    C --> D[📊 Monitor]:::out

    classDef start fill:#4CAF50,color:#fff
    classDef proc fill:#2196F3,color:#fff
    classDef out fill:#9C27B0,color:#fff

Link to this sectionArchitecture#

Link to this sectionShared Inference#

The shared inference service runs in 3 key regions, automatically routing requests based on your data region:

graph TB
    User[User Request]:::start --> API[Platform API]:::proc
    API --> Router{Region Router}:::decide
    Router -->|US users| US["US Predict Service<br/>Iowa"]:::out
    Router -->|EU users| EU["EU Predict Service<br/>Belgium"]:::out
    Router -->|AP users| AP["AP Predict Service<br/>Taiwan"]:::out

    classDef start fill:#4CAF50,color:#fff
    classDef proc fill:#2196F3,color:#fff
    classDef decide fill:#FF9800,color:#fff
    classDef out fill:#9C27B0,color:#fff

Link to this sectionDedicated Endpoints#

Deploy to 42 regions worldwide on Ultralytics Cloud:

• Americas: 14 regions
• Europe: 13 regions
• Asia-Pacific: 12 regions
• Middle East & Africa: 3 regions

Each endpoint is a single-tenant service with:

• Default resources of 1 CPU, 2 GiB memory, minInstances=0, maxInstances=1
• Scale-to-zero when idle
• Unique endpoint URL
• Independent monitoring, logs, and health checks

Link to this sectionDeployments Page#

Access the global deployments page from the sidebar under Deploy. This page shows:

• World map with deployed region pins (interactive map)
• Overview cards: Total Requests (24h), Active Deployments, Error Rate (24h), P95 Latency (24h)
• Deployments list with three view modes: cards, compact, and table
• New Deployment button to create endpoints from any completed model

Link to this sectionKey Features#

Link to this sectionGlobal Coverage#

Deploy close to your users with 42 regions covering:

• North America, South America
• Europe, Middle East, Africa
• Asia Pacific, Oceania

Link to this sectionScaling Behavior#

Endpoints currently behave as follows:

• Scale to zero: minInstances defaults to 0
• Single active instance: maxInstances is currently capped at 1 on all plans

Link to this sectionRegional Deployment#

Use the measured region latency to place an endpoint near its callers. Actual inference latency depends on the model, input size, endpoint state, and network path.

Link to this sectionHealth Checks#

Each running deployment includes an automatic health check with:

• Live status indicator (healthy/unhealthy)
• Response latency display
• Auto-retry when unhealthy (polls every 20 seconds)
• Manual refresh button

Link to this sectionQuick Start#

Create a deployment:

1. Train or upload a model to a project
2. Go to the model's Deploy tab
3. Select a region from the latency table
4. Click Deploy and wait for the deployment status to become Ready

Model → Deploy tab → Select region → Click Deploy → Endpoint URL ready

Link to this sectionQuick Links#

• Inference: Test models in browser
• Endpoints: Deploy dedicated endpoints
• Monitoring: Track deployment performance

Link to this sectionFAQ#

Link to this sectionWhat's the difference between shared and dedicated inference?#

Link to this sectionHow long does deployment take?#

The deployment remains in a creating or deploying state while its service starts. It becomes usable when the status changes to Ready; timing varies by model and region.

Link to this sectionCan I deploy multiple models?#

Yes, each model can have multiple endpoints in different regions. Deployment counts are limited by plan: Free 3, Pro 10, Enterprise unlimited.

Link to this sectionWhat happens when an endpoint is idle?#

With scale-to-zero enabled:

• Endpoint scales down after inactivity
• First request triggers cold start
• Subsequent requests are fast

First requests after an idle period trigger a cold start.