Home icon

How to configure cross-account model deployment using Amazon Bedrock Custom Model Import

Machine Learning Blog



This article explains how to configure cross-account model deployment using Amazon Bedrock Custom Model Import, addressing the challenge of securely sharing model artifacts between different AWS accounts.

  • Enables organizations to separate model development and hosting teams across different AWS accounts
  • Supports importing custom models with Hugging Face safetensors from S3 or SageMaker
  • Requires configuring cross-account S3 bucket and IAM role permissions
  • Supports optional AWS KMS encryption for model artifacts
  • Available in US East (N. Virginia) and US West (Oregon) regions

The comprehensive guide provides step-by-step instructions for setting up cross-account access, including S3 bucket policies, IAM role configurations, and KMS key permissions, to streamline model deployment workflows while maintaining security.



Go to article

The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.

Related articles

Jun 13
2025
Deploy Qwen models with Amazon Bedrock Custom Model Import
Apr 23
2024
Import custom models in Amazon Bedrock (preview)
Nov 24
2025
Deploy GPT-OSS models with Amazon Bedrock Custom Model Import
Nov 26
2025
Enhanced performance for Amazon Bedrock Custom Model Import

The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.