A company is developing three specialized NLP models that support a customer service application.

Deploy all three models to a single Amazon SageMaker AI multi-model endpoint. Enable dynamic scaling on the endpoint. Use a compute optimized instance type. Configure auto scaling policies that are based on invocation metrics to handle peak loads.

Deploy each model to a separate Amazon SageMaker Serverless Inference endpoint. Set provisioned concurrency to handle peak loads. Configure maximum concurrency limits and memory sizing based on each model ' s specific requirements.

Deploy the models by using Amazon Bedrock with provisioned throughput to handle peak loads. Configure the number of model units (MUs) based on expected token throughput needs. Implement request batching for each model.

Deploy each model to a separate Amazon SageMaker AI endpoint. Use an asynchronous inference configuration. Store model requests and responses in Amazon S3. Use Amazon SNS to send alerts to users when the application finishes processing requests.