aws AWS What's New ·

SageMaker Inference Supports OpenAI-Compatible APIs

aiawsengineermediaaws-sagemaker
feature announcement

Amazon SageMaker Inference now supports OpenAI-compatible APIs, allowing direct integration with tools like OpenAI SDK and LangChain by simply changing the endpoint URL. This feature simplifies connecting to SageMaker endpoints, enabling users to leverage existing code and authentication with custom models and VPCs. It offers flexibility in instance choice, data privacy, model execution, and autoscaling, with authentication managed via AWS credentials. The capability is available today in multiple AWS regions.

  • OpenAI-compatible API support for SageMaker inference endpoints
  • Enhanced flexibility and control
  • Simplified integration and authentication
  • Global Availability
Features (2)
  • OpenAI-compatible API support for SageMaker inference endpoints

    SageMaker Inference now supports OpenAI-compatible APIs, enabling direct integration with tools like the OpenAI SDK, LangChain, and Strands Agents. Users can connect to SageMaker endpoints simply by updating the endpoint URL, without requiring custom integration code or SDK wrappers.

  • Enhanced flexibility and control

    Users can now choose their own GPU instances, maintain data within their VPC, run any open-source or fine-tuned model, and utilize auto-scaling policies tailored to specific workloads.

Enhancements (1)
  • Simplified integration and authentication

    This update eliminates the need to adopt different API formats or change authentication approaches. Existing SDK calls, streaming logic, and framework integrations continue to function seamlessly with automatic AWS credential management and token refresh.

Notes (1)
  • Global Availability

    This capability is now available in numerous AWS regions across North America, Asia Pacific, Europe, and South America.

Read the original announcement →

https://aws.amazon.com/about-aws/whats-new/2026/05/amazon-sagemaker-ai-openai-apis/

Related releases