DeepSeek-R1 models now available on AWS

Updated on March 10, 2025 — DeepSeek-R1 now available as a fully managed serverless model in HAQM Bedrock

Updated on February 5, 2025 — DeepSeek-R1 Distill Llama and Qwen models are now available in HAQM Bedrock Marketplace and HAQM SageMaker JumpStart.

During this past AWS re:Invent, HAQM CEO Andy Jassy shared valuable lessons learned from HAQM’s own experience developing nearly 1,000 generative AI applications across the company. Drawing from this extensive scale of AI deployment, Jassy offered three key observations that have shaped HAQM’s approach to enterprise AI implementation.

First is that as you get to scale in generative AI applications, the cost of compute really matters. People are very hungry for better price performance. The second is actually quite difficult to build a really good generative AI application. The third is the diversity of the models being used when we gave our builders freedom to pick what they want to do. It doesn’t surprise us, because we keep learning the same lesson over and over and over again, which is that there is never going to be one tool to rule the world.

As Andy emphasized, a broad and deep range of models provided by HAQM empowers customers to choose the precise capabilities that best serve their unique needs. By closely monitoring both customer needs and technological advancements, AWS regularly expands our curated selection of models to include promising new models alongside established industry favorites. This ongoing expansion of high-performing and differentiated model offerings helps customers stay at the forefront of AI innovation.

This leads us to Chinese AI startup DeepSeek. DeepSeek launched DeepSeek-V3 on December 2024 and subsequently released DeepSeek-R1, DeepSeek-R1-Zero with 671 billion parameters, and DeepSeek-R1-Distill models ranging from 1.5–70 billion parameters on January 20, 2025. They added their vision-based Janus-Pro-7B model on January 27, 2025. The models are publicly available and are reportedly 90-95% more affordable and cost-effective than comparable models. Per Deepseek, their model stands out for its reasoning capabilities, achieved through innovative training techniques such as reinforcement learning.

Today, you can now deploy DeepSeek-R1 models in HAQM Bedrock and HAQM SageMaker AI. HAQM Bedrock is best for teams seeking to quickly integrate pre-trained foundation models through APIs. HAQM SageMaker AI is ideal for organizations that want advanced customization, training, and deployment, with access to the underlying infrastructure. Additionally, you can also use AWS Trainium and AWS Inferentia to deploy DeepSeek-R1-Distill models cost-effectively via HAQM Elastic Compute Cloud (HAQM EC2) or HAQM SageMaker AI.

With AWS, you can use DeepSeek-R1 models to build, experiment, and responsibly scale your generative AI ideas by using this powerful, cost-efficient model with minimal infrastructure investment. You can also confidently drive generative AI innovation by building on AWS services that are uniquely designed for security. We highly recommend integrating your deployments of the DeepSeek-R1 models with HAQM Bedrock Guardrails to add a layer of protection for your generative AI applications, which can be used by both HAQM Bedrock and HAQM SageMaker AI customers.

You can choose how to deploy DeepSeek-R1 models on AWS today in a few ways: 1/ HAQM Bedrock Marketplace for the DeepSeek-R1 model, 2/ HAQM SageMaker JumpStart for the DeepSeek-R1 model, 3/ HAQM Bedrock Custom Model Import for the DeepSeek-R1-Distill models, and 4/ HAQM EC2 Trn1 instances for the DeepSeek-R1-Distill models.

Let me walk you through the various paths for getting started with DeepSeek-R1 models on AWS. Whether you’re building your first AI application or scaling existing solutions, these methods provide flexible starting points based on your team’s expertise and requirements.

1. The DeepSeek-R1 model in HAQM Bedrock Marketplace
HAQM Bedrock Marketplace offers over 100 popular, emerging, and specialized FMs alongside the current selection of industry-leading models in HAQM Bedrock. You can easily discover models in a single catalog, subscribe to the model, and then deploy the model on managed endpoints.

To access the DeepSeek-R1 model in HAQM Bedrock Marketplace, go to the HAQM Bedrock console and select Model catalog under the Foundation models section. You can quickly find DeepSeek by searching or filtering by model providers.

After checking out the model detail page including the model’s capabilities, and implementation guidelines, you can directly deploy the model by providing an endpoint name, choosing the number of instances, and selecting an instance type.

You can also configure advanced options that let you customize the security and infrastructure settings for the DeepSeek-R1 model including VPC networking, service role permissions, and encryption settings. For production deployments, you should review these settings to align with your organization’s security and compliance requirements.

With HAQM Bedrock Guardrails, you can independently evaluate user inputs and model outputs. You can control the interaction between users and DeepSeek-R1 with your defined set of policies by filtering undesirable and harmful content in generative AI applications. The DeepSeek-R1 model in HAQM Bedrock Marketplace can only be used with Bedrock’s ApplyGuardrail API to evaluate user inputs and model responses for custom and third-party FMs available outside of HAQM Bedrock. To learn more, read Implement model-independent safety measures with HAQM Bedrock Guardrails.

HAQM Bedrock Guardrails can also be integrated with other Bedrock tools including HAQM Bedrock Agents and HAQM Bedrock Knowledge Bases to build safer and more secure generative AI applications aligned with responsible AI policies. To learn more, visit the AWS Responsible AI page.

Updated on 1st February – You can use the Bedrock playground for understanding how the model responds to various inputs and letting you fine-tune your prompts for optimal results.

When using DeepSeek-R1 model with the Bedrock’s playground or InvokeModel API, please use DeepSeek’s chat template for optimal results. For example, <｜begin_of_sentence｜><｜User｜>content for inference<｜Assistant｜>.

Refer to this step-by-step guide on how to deploy the DeepSeek-R1 model in HAQM Bedrock Marketplace. To learn more, visit Deploy models in HAQM Bedrock Marketplace.

2. The DeepSeek-R1 model in HAQM SageMaker JumpStart
HAQM SageMaker JumpStart is a machine learning (ML) hub with FMs, built-in algorithms, and prebuilt ML solutions that you can deploy with just a few clicks. To deploy DeepSeek-R1 in SageMaker JumpStart, you can discover the DeepSeek-R1 model in SageMaker Unified Studio, SageMaker Studio, SageMaker AI console, or programmatically through the SageMaker Python SDK.

In the HAQM SageMaker AI console, open SageMaker Studio and choose JumpStart and search for “DeepSeek-R1” in the All public models page.

You can select the model and choose deploy to create an endpoint with default settings. When the endpoint comes InService, you can make inferences by sending requests to its endpoint.

You can derive model performance and ML operations controls with HAQM SageMaker AI features such as HAQM SageMaker Pipelines, HAQM SageMaker Debugger, or container logs. The model is deployed in an AWS secure environment and under your virtual private cloud (VPC) controls, helping to support data security.

As like Bedrock Marketpalce, you can use the ApplyGuardrail API in the SageMaker JumpStart to decouple safeguards for your generative AI applications from the DeepSeek-R1 model. You can now use guardrails without invoking FMs, which opens the door to more integration of standardized and thoroughly tested enterprise safeguards to your application flow regardless of the models used.

Refer to this step-by-step guide on how to deploy the DeepSeek-R1 model in HAQM SageMaker JumpStart. To learn more, visit Discover SageMaker JumpStart models in SageMaker Unified Studio or Deploy SageMaker JumpStart models in SageMaker Studio.

3. DeepSeek-R1-Distill models using HAQM Bedrock Custom Model Import
HAQM Bedrock Custom Model Import provides the ability to import and use your customized models alongside existing FMs through a single serverless, unified API without the need to manage underlying infrastructure. With HAQM Bedrock Custom Model Import, you can import DeepSeek-R1-Distill models ranging from 1.5–70 billion parameters. As I highlighted in my blog post about HAQM Bedrock Model Distillation, the distillation process involves training smaller, more efficient models to mimic the behavior and reasoning patterns of the larger DeepSeek-R1 model with 671 billion parameters by using it as a teacher model.

After storing these publicly available models in an HAQM Simple Storage Service (HAQM S3) bucket or an HAQM SageMaker Model Registry, go to Imported models under Foundation models in the HAQM Bedrock console and import and deploy them in a fully managed and serverless environment through HAQM Bedrock. This serverless approach eliminates the need for infrastructure management while providing enterprise-grade security and scalability.

Updated on 1st February – After importing the distilled model, you can use the Bedrock playground for understanding distilled model responses for your inputs.

Watch a demo video made by my colleague Du’An Lightfoot for importing the model and inference in the Bedrock playground.

Refer to this step-by-step guide on how to deploy DeepSeek-R1-Distill models using HAQM Bedrock Custom Model Import. To learn more, visit Import a customized model into HAQM Bedrock.

4. DeepSeek-R1-Distill models using AWS Trainium and AWS Inferentia
AWS Deep Learning AMIs (DLAMI) provides customized machine images that you can use for deep learning in a variety of HAQM EC2 instances, from a small CPU-only instance to the latest high-powered multi-GPU instances. You can deploy the DeepSeek-R1-Distill models on AWS Trainuim1 or AWS Inferentia2 instances to get the best price-performance.

To get started, go to HAQM EC2 console and launch a trn1.32xlarge EC2 instance with the Neuron Multi Framework DLAMI called Deep Learning AMI Neuron (Ubuntu 22.04).

Once you have connected to your launched ec2 instance, install vLLM, an open-source tool to serve Large Language Models (LLMs) and download the DeepSeek-R1-Distill model from Hugging Face. You can deploy the model using vLLM and invoke the model server.

To learn more, refer to this step-by-step guide on how to deploy DeepSeek-R1-Distill Llama models on AWS Inferentia and Trainium.

You can also visit DeepSeek-R1-Distill models cards on Hugging Face, such as DeepSeek-R1-Distill-Llama-8B or deepseek-ai/DeepSeek-R1-Distill-Llama-70B. Choose Deploy and then HAQM SageMaker. From the AWS Inferentia and Trainium tab, copy the example code for deploy DeepSeek-R1-Distill models.

Since the release of DeepSeek-R1, various guides of its deployment for HAQM EC2 and HAQM Elastic Kubernetes Service (HAQM EKS) have been posted. Here is some additional material for you to check out:

• Leveraging DeepSeek-R1 with CPU and GPU options on AWS by Daniel Wirjo
• Benefits of installing DeepSeek on an HAQM EC2 instance by Enrique Aguilar Martinez
• Deploying DeepSeek Llama models on HAQM EC2 inferentia instance by Irshad Chohan
• How to deploy and fine-tune DeepSeek models on AWS by Hugging Face
• Hosting DeepSeek-R1 on HAQM EKS Auto Mode by Tiago Reichert

Things to know
Here are a few important things to know.

• Pricing – For publicly available models like DeepSeek-R1, you are charged only the infrastructure price based on inference instance hours you select for HAQM Bedrock Markeplace, HAQM SageMaker JumpStart, and HAQM EC2. For the Bedrock Custom Model Import, you are only charged for model inference, based on the number of copies of your custom model is active, billed in 5-minute windows. To learn more, check out the HAQM Bedrock Pricing, HAQM SageMaker AI Pricing, and HAQM EC2 Pricing pages.
• Data security – You can use enterprise-grade security features in HAQM Bedrock and HAQM SageMaker to help you make your data and applications secure and private. This means your data is not shared with model providers, and is not used to improve the models. This applies to all models—proprietary and publicly available—like DeepSeek-R1 models on HAQM Bedrock and HAQM SageMaker. To learn more, visit HAQM Bedrock Security and Privacy and Security in HAQM SageMaker AI.

Now available
DeepSeek-R1 is generally available today in HAQM Bedrock Marketplace and HAQM SageMaker JumpStart in US East (Ohio) and US West (Oregon) AWS Regions. You can also use DeepSeek-R1-Distill models using HAQM Bedrock Custom Model Import and HAQM EC2 instances with AWS Trainum and Inferentia chips.

Give DeepSeek-R1 models a try today in the HAQM Bedrock console, HAQM SageMaker AI console, and HAQM EC2 console, and send feedback to AWS re:Post for HAQM Bedrock and AWS re:Post for SageMaker AI or through your usual AWS Support contacts.

— Channy

Updated on 1st February — Added more screenshots and demo video of HAQM Bedrock Playground.

Updated on 3rd February — Fixed unclear message for DeepSeek-R1 Distill model names and SageMaker Studio interface.