What's new at AWS π’
π° Amazon Bedrock now supports customers to allocate and track on-demand foundation model usage.
π° With this, customers can categorize their GenAI inference costs by department, team, or application using AWS cost allocation tags.
β οΈ What is Amazon Bedrock:
βοΈ It is a fully managed service that offers a choice of high-performing foundation models from leading AI companies via a single API.
βοΈ It also provides a broad set of capabilities such as security, privacy, and responsible AI capabilities built in.
π° These capabilities help customer to build tailored applications for multiple use cases across different industries.
π° Importantly it is helping organizations by ensuring customer trust and data governance.
π° You can leverage this feature by creating an application inference profile and tagging it.
β οΈ What is Inference profiles:
βοΈ These profiles are a resource in Amazon Bedrock that define a model and one or more Regions
βοΈ Inference profile can route model invocation requests.
β οΈ Types of inference profiles:
1οΈβ£ Cross region inference profiles
2οΈβ£ Application inference profiles
β οΈ When to use inference profiles:
βοΈ Track usage metrics
βοΈ Use tags to monitor costs
βοΈ Cross-region inference
π Explore more about cross-region inference profiles:
https://aws.amazon.com/blogs/machine-learning/getting-started-with-cross-region-inference-in-amazon-bedrock/
Top comments (0)