Whitelist IPs for Model Endpoint

Whitelist IPs for Model Endpoint

The Whitelist IP feature enhances the security of Model Endpoints by allowing customers to define a list of trusted client IP addresses using CIDR notation. Only traffic from these authorized IPs is permitted to access the model endpoint, ensuring precise access control and reducing exposure to unauthorized requests.  

This feature includes two core capabilities:  
  1. View Whitelisted IPs: Display all currently authorized CIDR blocks configured for the model endpoint.  
  2. Update Whitelist: Dynamically add, remove, or update CIDR entries to manage access in real time without needing to redeploy or restart the endpoint.

Usage Instructions

  1. Viewing the Whitelist
    1. After successfully deploying a Model Endpoint, navigate to the Model Endpoint Detail Page.  
    2. Select the Whitelist IP tab under the detail information section.  
    3. A table will display all currently whitelisted CIDR blocks authorized to access the endpoint.  
  2. Updating the Whitelist
    1. Go to the Model Endpoint Detail Page.  
    2. Open the Whitelist IP tab in the detail section.  
    3. Click the Edit button to modify the whitelist.  
    4. Add, remove, or update CIDR entries in the popup input field.  
    5. Click Save to apply the changes. Updates take effect immediately.

CIDR Rules & Access Control

  1. Supported CIDR Formats: 0.0.0.0/0, 203.0.113.5/32, etc.  
  2. Validation Rules:  
    1. Only valid CIDR blocks are accepted.  
    2. 255.255.255.255/32 is explicitly disallowed.  
  3. Limitations:  A maximum of 20 CIDR blocks is supported per model endpoint.  
  4. Whitelist updates are applied immediately, without requiring a restart.  
  5. Supported endpoint statuses: updates can be made when the endpoint is active or inactive.

API Support

      POST /v1/model-endpoints/${id}/client-ip
            Description: Update whitelist IP for model endpoints
            Request body: {"allowedCidrBlocks": ["0.0.0.0/0"]}

    • Related Articles

    • Whitelist IPs for Notebook Instances

      The Whitelist IP feature enhances the security of Notebook Instances by enabling customers to specify a list of trusted client IP addresses using CIDR notation. Only these authorized IPs are allowed to access the notebook, providing fine-grained ...

    • Manage a model endpoint

      This guide will walk you through the key features and steps involved in deploying your models, optimizing costs through undeployment, and removing endpoints when they are no longer needed. After creating a model endpoint, follow these steps to ...

    • Automated Scheduling for Model Endpoint

      The Automated Scheduling feature allows users to define specific times for automatically starting or stopping Model Endpoint. This helps optimize cloud usage, reduce unnecessary costs, and ensure that compute resources are only active when needed. ...

    • Deploy a model endpoint with custom container

      In this section, you will learn how to deploy and serve your custom machine-learning models using a custom container in our Greennode AI Platform. Follow the steps below to configure and deploy your model for online prediction: Step 0: Import a model ...

    • Create an endpoint

      After training and registering the model, the online prediction component enables the deployment and serving of models to make real-time predictions or inferences on new data. This component provides endpoints or APIs that can be integrated into ...