AWS Offers DeepSeek-R1 as Fully Managed Serverless Model, Recommends Guardrails

• By David Ramel
• 03/14/25

Amazon Web Services (AWS) has announced the availability of DeepSeek-R1 as a fully managed serverless AI model, enabling developers to build and deploy it without having to manage the underlying infrastructure.

Amazon has embraced controversial new DeepSeek AI tech from a Chinese startup despite concerns about data security, privacy, compliance, and national security risks that resulted in some usage restrictions. That embrace included integrating DeepSeek AI into its SageMaker and Bedrock platforms in the AWS cloud, announced in January.

This week the company announced the fully managed DeepSeek-R1 model is now generally available in Amazon Bedrock. "You can accelerate innovation and deliver tangible business value with DeepSeek on AWS without having to manage infrastructure complexities," the announcement post said. "You can power your generative AI applications with DeepSeek-R1's capabilities using a single API in the Amazon Bedrock's fully managed service and get the benefit of its extensive features and tooling."

Taking into account those concerns about the Chinese tech, which resulted in some organizations banning its usage, yesterday's post advised users to take precautions.

"We strongly recommend integrating Amazon Bedrock Guardrails and using Amazon Bedrock model evaluation features with your DeepSeek-R1 model to add robust protection for your generative AI applications," said AWS, which advised users to give careful consideration to data privacy requirements when implementing the model in production environments, checking for bias in output, and monitoring results.

When implementing publicly available models like DeepSeek-R1, AWS said users should consider the following:

• Data security. You can access the enterprise-grade security, monitoring, and cost control features of Amazon Bedrock that are essential for deploying AI responsibly at scale, all while retaining complete control over your data. Users' inputs and model outputs aren't shared with any model providers. You can use these key security features by default, including data encryption at rest and in transit, fine-grained access controls, secure connectivity options, and download various compliance certifications while communicating with the DeepSeek-R1 model in Amazon Bedrock.
• Responsible AI. You can implement safeguards customized to your application requirements and responsible AI policies with Amazon Bedrock Guardrails. This includes key features of content filtering, sensitive information filtering, and customizable security controls to prevent hallucinations using contextual grounding and Automated Reasoning checks. This means you can control the interaction between users and the DeepSeek-R1 model in Bedrock with your defined set of policies by filtering undesirable and harmful content in your generative AI applications.
• Model evaluation. You can evaluate and compare models to identify the optimal model for your use case, including DeepSeek-R1, in a few steps through either automatic or human evaluations by using Amazon Bedrock model evaluation tools. You can choose automatic evaluation with predefined metrics such as accuracy, robustness, and toxicity. Alternatively, you can choose human evaluation workflows for subjective or custom metrics such as relevance, style, and alignment to brand voice. Model evaluation provides built-in curated datasets, or you can bring in your own datasets.

"Just as guardrails on a highway prevent cars from veering off the road, Amazon Bedrock Guardrails aid in preventing an application from producing harmful or inappropriate content," AWS said in another post. "This includes helping to block offensive language, explicit content, or other material deemed unsuitable for end users, as well as helping identify and remove personal data to protect user privacy."

For more information, visit the AWS blog.