AWS continues to expand access to the most advanced foundation models with OpenAI open weight models now available in Amazon Bedrock and Amazon SageMaker JumpStart. Accessing these new open weight models from OpenAI on AWS, gpt-oss-120b and gpt-oss-20b, gives you more freedom to innovate and choose the optimal models for your specific use cases while maintaining complete control over your data.
These OpenAI open weight models excel at coding, scientific analysis, and mathematical reasoning tasks, with performance comparable to leading alternatives. Both feature a 128K context window and adjustable reasoning levels (low/medium/high) to match specific requirements. They support external tool integration and can be used in agentic workflows through frameworks like Strands Agents. With full chain-of-thought output capabilities, you get detailed visibility into the model’s reasoning process. Access these models through Amazon Bedrock’s unified API, allowing you to seamlessly experiment and switch between providers without rewriting code. You can use the OpenAI SDK to call Amazon Bedrock directly by simply updating the endpoint. The models give you the flexibility to modify and customize them for your specific business needs while benefiting from enterprise-grade security and seamless scaling.
The new OpenAI open weight models are now available in Amazon Bedrock in the US West (Oregon) AWS Region, while Amazon SageMaker JumpStart supports these models in the US East (Ohio, N. Virginia) and Asia Pacific (Mumbai, Tokyo) AWS Regions. Deploy them through either Amazon Bedrock’s serverless experience or Amazon SageMaker JumpStart’s comprehensive machine learning development capabilities. To learn more, read the blog, product page, and Amazon Bedrock pricing. Get started today in the Amazon Bedrock console or Amazon SageMaker AI console.
Categories:
Source: Amazon Web Services