{"author":{"name":"Marc Karp","slug":"marc-karp","article_count":1,"latest_published_at":"2026-05-21T10:30:14.063+00:00","profile_url":"https://vff.ai/authors/marc-karp","api_url":"https://vff.ai/api/authors/marc-karp"},"articles":[{"slug":"announcing-openai-compatible-api-support-for-amazon-sagemaker-ai-endpoints","title":"SageMaker adds OpenAI-compatible APIs for self-hosted inference","url":"https://vff.ai/article/2026/05/21/announcing-openai-compatible-api-support-for-amazon-sagemaker-ai-endpoints","content_type":"aggregated_news","summary":"Amazon SageMaker AI now supports OpenAI-compatible APIs for real-time inference endpoints, allowing developers to invoke models by simply changing the endpoint URL without custom clients or code rewrites. The feature exposes a /openai/v1 path that accepts Chat Completions requests and works with OpenAI SDK, LangChain, and Strands Agents. SageMaker routes requests based on endpoint name and supports time-limited bearer tokens, enabling multi-model hosting, agentic workflows on owned infrastructure, and deployment of fine-tuned models without application changes.","published_at":"2026-05-21T10:30:14.063+00:00","updated_at":"2026-05-21T16:57:05.784836+00:00","source":{"url":"https://aws.amazon.com/blogs/machine-learning/announcing-openai-compatible-api-support-for-amazon-sagemaker-ai-endpoints/","name":"AWS Machine Learning Blog"},"featured_image":{"url":"https://d1.awsstatic.com/onedam/marketing-channels/website/aws/en_US/global-nav/m9y25-discover-aws-reinvent-session-catalog.0f0f06f8b5f05d7c8f32a8dd40ab11e2b2e6e5de.jpg","alt":null},"categories":[{"name":"AI Agents","slug":"ai-agents"},{"name":"Infrastructure","slug":"infrastructure"},{"name":"Generative AI","slug":"generative-ai"},{"name":"AWS","slug":"aws"}]}]}