Deploy GPT-OSS models with Amazon Bedrock Custom Model Import
aws.amazon.com - machine-learningAmazon Bedrock Custom Model Import now supports OpenAI models with open weights, including GPT-OSS variants with 20-billion and 120-billion parameters. GPT-OSS models offer reasoning capabilities and can be used with OpenAI Chat Completions API. By preserving full OpenAI API compatibility, organizations can migrate their existing applications to AWS, gaining enterprise-grade security, scaling, and cost control.
In this post, we show how to deploy the GPT-OSS-20B model on Amazon Bedrock using Custom Model Import while maintaining complete API compatibility with your current applications.
Overview of Amazon Bedrock Custom Model Import
Amazon Bedrock Custom Model Import lets you bring customized models into the same serverless environment where you access foundation models (FMs). You get one unified API for everything; you don’t need to juggle multiple endpoints or manage separate infrastructure.
To use this feature, upload your model files to Amazon Simple Storage Service (Amazon S3), then initiate the import through the ...
Copyright of this story solely belongs to aws.amazon.com - machine-learning . To see the full text click HERE

