Amazon Bedrock Custom Model Import now supports Open AI GPT OSS models. You can import custom weights for gpt-oss-120b and gpt-oss-20b models. This enables you to bring your own customized GPT OSS models into Amazon Bedrock and deploy them in a fully managed, serverless environment—without having to manage infrastructure or model serving.
GPT OSS models are text-to-text models designed for reasoning, agentic, and developer tasks. The larger gpt-oss-120b model is optimized for production, general purpose, and high reasoning use cases, while the smaller gpt-oss-20b model is best suited for lower latency, or specialized used cases such as data processing or domain-specific summarization.
Amazon Bedrock Custom Model Import for GPT OSS models is generally available in the US-East (N. Virginia) AWS Region. You can get started by importing your custom GPT OSS models in the custom models section of the Amazon Bedrock console . To learn more about OpenAI models in Amazon Bedrock visit the product page . To see what all architectures are supported visit the documentation .