Dedicated Endpoints#

Ultralytics Platform enables deployment of YOLO models to dedicated endpoints in 42 global regions. Each endpoint is a single-tenant service with scale-to-zero behavior, a unique endpoint URL, and independent monitoring.

Create Endpoint#

From the Deploy Tab#

Deploy a model from its Deploy tab:

1. Navigate to your model
2. Click the Deploy tab
3. Review the world map and the region table, which is sorted by measured latency from your location
4. Click Deploy in the region row you want to use

Deployment starts immediately with no naming step: the name is generated from the model name and the region city (for example yolo26n-iowa). The model must have weights, or the tab shows an empty state instead of the region table.

From the Deployments Page#

Create a deployment from the global Deploy page in the sidebar:

1. Click New Deployment
2. Select a model from the model selector, which lists your completed models
3. Select a region from the mini map or the latency table
4. Review the auto-generated deployment name, which you can edit here
5. Click Deploy Model

Deployment Lifecycle#

stateDiagram-v2
    [*] --> Creating: Deploy
    Creating --> Deploying: Service starting
    Deploying --> Ready: Service URL published
    Ready --> Stopping: Stop
    Ready --> Deploying: Replace model
    Stopping --> Stopped: Stopped
    Stopped --> Deploying: Start
    Deploying --> Stopped: Start failed
    Ready --> [*]: Delete
    Stopped --> [*]: Delete
    Creating --> Failed: Error
    Deploying --> Failed: Error
    Failed --> [*]: Delete

    classDef proc fill:#2196F3,color:#fff
    classDef out fill:#9C27B0,color:#fff
    classDef error fill:#F44336,color:#fff
    classDef extern fill:#607D8B,color:#fff
    class Creating,Deploying,Stopping proc
    class Ready out
    class Failed error
    class Stopped extern

Connect Slack alerts to receive a message when a deployment becomes ready or fails to start.

Region Selection#

Choose from 42 regions worldwide. The interactive region map and table show:

• Region pins: Color-coded by latency on a green-to-red gradient (faster regions are greener, slower regions are redder)
• Deployed regions: Highlighted with a "Deployed" badge in the table
• Deploying regions: Animated pulse indicator on the pin and the table row
• Bidirectional highlighting: Hover on the map highlights the table row, and vice versa

The region table on the model Deploy tab includes:

The table is searchable by city, country, and zone, and is sorted by latency by default.

Available Regions#

Endpoint Configuration#

New Deployment Dialog#

The New Deployment dialog collects three inputs:

Below the name, a read-only Resources panel carries a Custom resources coming soon badge. Resources are not configurable today: every endpoint runs as a single instance that scales to zero when idle.

Deploy Tab (Quick Deploy)#

Deploying from the model's Deploy tab uses the same fixed resources and auto-generated name, with no dialog step. The deployment appears immediately in the Active Deployments list below the region table while it is created.

Manage Endpoints#

View Modes#

The deployments list supports three view modes:

Deployment Card (Cards View)#

Each deployment card in the cards view shows:

• Header: Name, region flag, status badge, and the action buttons available for the current status — replace and stop when Ready, start when Stopped, delete at any time
• Endpoint URL: Copyable URL with a link to the endpoint's own API reference
• Metrics: Request count (24h), P95 latency, error rate, or "No traffic yet"
• Health check: Live health indicator with latency and manual refresh
• Tabs: Logs, Code, and Predict
• Footer: The API key prefix bound to the deployment and the date it became ready
• Status message: The failure reason, when a deployment failed

The URL, metrics, health check, and tabs appear only while the deployment is Ready. The Logs tab shows recent log entries with severity filtering (All / Errors). The Code tab shows ready-to-use code examples in Python, JavaScript, and cURL with your endpoint URL, plus the bound API key for workspace owners (see Monitoring). The Predict tab provides an inline predict panel for testing directly on the deployment.

Replace a Model#

Replace the model behind a ready endpoint without changing its URL:

1. Open the deployment in Cards view
2. Click Replace model
3. Select another completed model from the same workspace
4. Optionally edit the deployment name
5. Click Replace Model

The current model continues serving while the replacement starts up. Once the replacement is ready, traffic moves to the new model. The deployment ID, URL, region, and API key remain unchanged; its display name changes only when you enter a new one. If replacement fails, the previous model and name remain active.

Replacement requires all of the following, and is rejected otherwise:

• The deployment is Ready and has no other lifecycle operation in flight
• The replacement model has weights and belongs to the same workspace as the deployment
• The replacement model is not the one already deployed

Deployment Statuses#

Endpoint URL#

Each endpoint has a unique URL, for example:

https://predict-<deployment-id>-<hash>-<region>.a.run.app

Click the copy button to copy the URL. Click the docs icon to open the endpoint's own API reference. The endpoint serves these paths:

Lifecycle Management#

Control your endpoint state:

graph LR
    R[Ready]:::out -->|Stop| S[Stopped]:::extern
    S -->|Start| R
    R -->|Delete| D[Deleted]:::error
    S -->|Delete| D

    classDef out fill:#9C27B0,color:#fff
    classDef error fill:#F44336,color:#fff
    classDef extern fill:#607D8B,color:#fff

Stop Endpoint#

Stop an endpoint when you do not want it to accept requests:

1. Click the pause icon on the deployment card
2. Endpoint status changes to "Stopping" then "Stopped"

Stopped endpoints:

• Don't accept requests, and report no metrics or health status
• Keep their URL, region, and bound API key, and can be restarted anytime
• Still count against your plan's deployment quota — delete an endpoint to free its slot

Delete Endpoint#

Permanently remove an endpoint:

1. Click the delete (trash) icon on the deployment card
2. Confirm deletion in the dialog

Deployments are also removed when their model or project is permanently deleted, or when a trashed model or project reaches the end of its retention window.

Using Endpoints#

Authentication#

Each deployment is bound to a single API key from the workspace that owns the model. Include it in requests:

Authorization: Bearer YOUR_API_KEY

The endpoint accepts only the key bound at creation, so no other key opens it — not even another active key in the same workspace. To control which key gets bound, deploy via the API authenticated with the workspace owner's key: that exact key is bound, and you already hold it. Deployments created any other way (the Platform UI, or an API call authenticated as a team member) bind one of the owning workspace's active keys automatically — identify it by the key prefix shown in the deployment card footer, and ask the workspace owner for its value, since only the owner can view key values (see API Keys). Team members without the bound key can still run inference through the Platform predict proxy in the browser.

Direct Endpoint Requests#

Send production requests directly to the URL shown on the deployment card. These requests do not pass through the Platform API rate limiter, so the 20 requests/minute predict limit does not apply. The endpoint still has its own capacity ceiling:

• A single instance serves each endpoint, processing a limited number of requests at once
• Requests that cannot be served promptly return 429 with a Retry-After header
• A single request may run for up to 1 hour, which allows video inference to complete
• Responses larger than 1 KB are gzip-compressed, and cross-origin browser requests are allowed

Request Example#

import requests

# Deployment endpoint
url = "https://YOUR_DEPLOYMENT_URL.run.app/predict"

# Headers with your deployment API key
headers = {"Authorization": "Bearer YOUR_API_KEY"}

# Inference parameters
data = {"conf": 0.25, "iou": 0.7, "imgsz": 640}

# Send image for inference
with open("image.jpg", "rb") as f:
    response = requests.post(url, headers=headers, data=data, files={"file": f})

print(response.json())

Request Parameters#

See Depth responses for how bits changes the returned depth map and how to decode it.

Response Format#

Same as shared inference with task-specific fields.

FAQ#