Today, we are thrilled to reveal that DeepSeek R1 distilled Llama and Qwen designs are available through Amazon Bedrock Marketplace and Amazon SageMaker JumpStart. With this launch, you can now deploy DeepSeek AI’s first-generation frontier design, DeepSeek-R1, together with the distilled versions varying from 1.5 to 70 billion criteria to develop, experiment, and responsibly scale your generative AI ideas on AWS.

In this post, we demonstrate how to start with DeepSeek-R1 on Amazon Bedrock Marketplace and SageMaker JumpStart. You can follow comparable actions to release the distilled versions of the designs also.

Overview of DeepSeek-R1

DeepSeek-R1 is a big language design (LLM) established by DeepSeek AI that uses reinforcement finding out to boost reasoning capabilities through a multi-stage training process from a DeepSeek-V3-Base structure. A crucial differentiating function is its reinforcement learning (RL) step, which was used to refine the design’s actions beyond the basic pre-training and tweak procedure. By including RL, DeepSeek-R1 can adapt better to user feedback and objectives, ultimately boosting both significance and clearness. In addition, DeepSeek-R1 utilizes a chain-of-thought (CoT) technique, meaning it’s geared up to break down complicated questions and factor through them in a detailed manner. This directed thinking process allows the design to produce more precise, transparent, and detailed answers. This model integrates RL-based fine-tuning with CoT capabilities, aiming to generate structured actions while focusing on interpretability and user interaction. With its comprehensive capabilities DeepSeek-R1 has actually captured the industry’s attention as a flexible text-generation design that can be integrated into different workflows such as agents, logical thinking and data analysis jobs.

DeepSeek-R1 uses a Mix of Experts (MoE) architecture and is 671 billion specifications in size. The MoE architecture permits activation of 37 billion parameters, enabling efficient inference by routing queries to the most relevant expert “clusters.” This technique allows the design to concentrate on various issue domains while maintaining general performance. DeepSeek-R1 needs a minimum of 800 GB of HBM memory in FP8 format for reasoning. In this post, we will utilize an ml.p5e.48 xlarge circumstances to release the model. ml.p5e.48 xlarge includes 8 Nvidia H200 GPUs offering 1128 GB of GPU memory.

DeepSeek-R1 distilled models bring the thinking capabilities of the main R1 model to more efficient architectures based on popular open designs like Qwen (1.5 B, 7B, 14B, and 32B) and Llama (8B and 70B). Distillation refers to a process of training smaller sized, more efficient designs to imitate the habits and thinking patterns of the larger DeepSeek-R1 model, using it as an instructor model.

You can deploy DeepSeek-R1 model either through SageMaker JumpStart or Bedrock Marketplace. Because DeepSeek-R1 is an emerging model, we recommend deploying this model with guardrails in place. In this blog site, we will utilize Amazon Bedrock Guardrails to present safeguards, avoid hazardous material, and evaluate models against essential security criteria. At the time of composing this blog, for DeepSeek-R1 deployments on SageMaker JumpStart and Bedrock Marketplace, Bedrock Guardrails supports only the ApplyGuardrail API. You can produce multiple guardrails tailored to various usage cases and apply them to the DeepSeek-R1 design, enhancing user experiences and standardizing safety controls across your generative AI applications.

Prerequisites

To deploy the DeepSeek-R1 design, you need access to an ml.p5e circumstances. To inspect if you have quotas for P5e, open the Service Quotas console and under AWS Services, pick Amazon SageMaker, and confirm you’re utilizing ml.p5e.48 xlarge for endpoint use. Make certain that you have at least one ml.P5e.48 xlarge instance in the AWS Region you are deploying. To ask for a limit boost, create a limit boost demand and reach out to your account team.

Because you will be deploying this design with Amazon Bedrock Guardrails, make certain you have the proper AWS Identity and Gain Access To Management (IAM) authorizations to utilize Amazon Bedrock Guardrails. For instructions, see Establish authorizations to utilize guardrails for material filtering.

Implementing guardrails with the ApplyGuardrail API

Amazon Bedrock Guardrails allows you to present safeguards, avoid harmful content, and examine designs against key safety criteria. You can carry out precaution for the DeepSeek-R1 model utilizing the Amazon Bedrock ApplyGuardrail API. This permits you to apply guardrails to assess user inputs and design responses deployed on Amazon Bedrock Marketplace and SageMaker JumpStart. You can produce a guardrail utilizing the Amazon Bedrock console or the API. For the example code to create the guardrail, see the GitHub repo.

The basic circulation involves the following steps: First, the system gets an input for the model. This input is then processed through the ApplyGuardrail API. If the input passes the guardrail check, it’s sent to the model for reasoning. After getting the model’s output, another guardrail check is applied. If the output passes this last check, it’s returned as the final result. However, if either the input or output is stepped in by the guardrail, a message is returned showing the nature of the intervention and whether it took place at the input or output stage. The examples showcased in the following areas show reasoning utilizing this API.

Deploy DeepSeek-R1 in Amazon Bedrock Marketplace

Amazon Bedrock Marketplace gives you access to over 100 popular, emerging, and specialized structure designs (FMs) through Amazon Bedrock. To gain access to DeepSeek-R1 in Amazon Bedrock, complete the following steps:

1. On the Amazon Bedrock console, choose Model catalog under Foundation models in the navigation pane. At the time of writing this post, you can use the InvokeModel API to conjure up the design. It does not support Converse APIs and other Amazon Bedrock tooling.

1. Filter for DeepSeek as a provider and select the DeepSeek-R1 design.
   
   The design detail page offers necessary details about the design’s capabilities, pricing structure, and application standards. You can discover detailed usage guidelines, including sample API calls and code bits for combination. The model supports different text generation tasks, consisting of content production, code generation, and concern answering, using its support learning optimization and CoT reasoning capabilities. The page also consists of implementation options and licensing details to assist you get going with DeepSeek-R1 in your applications.
2. To start using DeepSeek-R1, choose Deploy.
   
   You will be prompted to set up the implementation details for DeepSeek-R1. The design ID will be pre-populated.
3. For Endpoint name, go into an endpoint name (between 1-50 alphanumeric characters).
4. For Number of circumstances, go into a variety of circumstances (in between 1-100).
5. For Instance type, choose your instance type. For ideal efficiency with DeepSeek-R1, a GPU-based instance type like ml.p5e.48 xlarge is advised. Optionally, you can set up advanced security and facilities settings, consisting of virtual private cloud (VPC) networking, service role permissions, and encryption settings. For most use cases, the default settings will work well. However, for production deployments, you may desire to evaluate these settings to align with your organization’s security and compliance requirements.
6. Choose Deploy to begin utilizing the model.
   
   When the deployment is complete, you can evaluate DeepSeek-R1’s capabilities straight in the Amazon Bedrock play area.
7. Choose Open in play area to access an interactive user interface where you can experiment with various triggers and change model parameters like temperature level and optimum length. When using R1 with Bedrock’s InvokeModel and Playground Console, use DeepSeek’s chat template for ideal outcomes. For example, content for inference.
   
   This is an excellent way to explore the design’s reasoning and text generation capabilities before integrating it into your applications. The play ground supplies immediate feedback, helping you understand how the design reacts to different inputs and letting you fine-tune your triggers for ideal results.
   
   You can rapidly evaluate the design in the playground through the UI. However, to invoke the deployed model programmatically with any Amazon Bedrock APIs, you need to get the endpoint ARN.
   
   Run reasoning using guardrails with the released DeepSeek-R1 endpoint
   
   The following code example shows how to perform inference utilizing a released DeepSeek-R1 design through Amazon Bedrock using the invoke_model and ApplyGuardrail API. You can develop a guardrail using the Amazon Bedrock console or the API. For the example code to develop the guardrail, see the GitHub repo. After you have developed the guardrail, use the following code to implement guardrails. The script initializes the bedrock_runtime customer, configures reasoning specifications, and sends out a demand to based on a user timely.
   
   Deploy DeepSeek-R1 with SageMaker JumpStart
   
   SageMaker JumpStart is an artificial intelligence (ML) center with FMs, integrated algorithms, and prebuilt ML options that you can deploy with simply a couple of clicks. With SageMaker JumpStart, you can tailor pre-trained models to your use case, with your data, and deploy them into production utilizing either the UI or SDK.
   
   Deploying DeepSeek-R1 design through SageMaker JumpStart uses 2 convenient approaches: using the user-friendly SageMaker JumpStart UI or implementing programmatically through the SageMaker Python SDK. Let’s explore both approaches to help you choose the method that best matches your needs.
   
   Deploy DeepSeek-R1 through SageMaker JumpStart UI
   
   Complete the following steps to deploy DeepSeek-R1 using SageMaker JumpStart:
   
   1. On the SageMaker console, select Studio in the navigation pane.
8. First-time users will be prompted to create a domain.
9. On the SageMaker Studio console, select JumpStart in the navigation pane.
   
   The model browser shows available models, with details like the service provider name and design abilities.
   
   4. Look for DeepSeek-R1 to view the DeepSeek-R1 model card. Each model card shows essential details, consisting of:
   
   - Model name
10. Provider name
11. Task category (for instance, Text Generation). Bedrock Ready badge (if applicable), indicating that this model can be signed up with Amazon Bedrock, permitting you to use Amazon Bedrock APIs to conjure up the model
    
    5. Choose the design card to see the design details page.
    
    The model details page includes the following details:
    
    - The model name and supplier details. Deploy button to deploy the model. About and Notebooks tabs with detailed details
    
    The About tab includes important details, such as:
    
    - Model description.
12. License details.
13. Technical specifications.
14. Usage standards
    
    Before you release the model, it’s suggested to review the design details and license terms to validate compatibility with your use case.
    
    6. Choose Deploy to proceed with release.
    
    7. For Endpoint name, use the instantly generated name or create a customized one.
15. For example type ¸ pick a circumstances type (default: ml.p5e.48 xlarge).
16. For Initial circumstances count, enter the variety of circumstances (default: 1). Selecting appropriate circumstances types and counts is vital for expense and performance optimization. Monitor your release to change these settings as needed.Under Inference type, Real-time inference is selected by default. This is enhanced for sustained traffic and low latency.
17. Review all setups for accuracy. For this design, we highly suggest sticking to SageMaker JumpStart default settings and making certain that network seclusion remains in place.
18. Choose Deploy to release the model.
    
    The implementation procedure can take several minutes to complete.
    
    When implementation is total, your endpoint status will change to InService. At this point, the model is ready to accept reasoning demands through the endpoint. You can keep an eye on the release development on the SageMaker console Endpoints page, which will show relevant metrics and status details. When the deployment is complete, you can conjure up the design utilizing a SageMaker runtime customer and incorporate it with your applications.
    
    Deploy DeepSeek-R1 utilizing the SageMaker Python SDK
    
    To begin with DeepSeek-R1 using the SageMaker Python SDK, you will require to set up the SageMaker Python SDK and make certain you have the necessary AWS consents and environment setup. The following is a detailed code example that demonstrates how to deploy and utilize DeepSeek-R1 for inference programmatically. The code for releasing the design is offered in the Github here. You can clone the notebook and range from SageMaker Studio.
    
    You can run additional requests against the predictor:
    
    Implement guardrails and run reasoning with your SageMaker JumpStart predictor
    
    Similar to Amazon Bedrock, you can likewise use the ApplyGuardrail API with your SageMaker JumpStart predictor. You can develop a guardrail using the Amazon Bedrock console or the API, and execute it as revealed in the following code:
    
    Clean up
    
    To prevent unwanted charges, complete the actions in this section to clean up your resources.
    
    Delete the Amazon Bedrock Marketplace deployment
    
    If you deployed the model using Amazon Bedrock Marketplace, complete the following steps:
    
    1. On the Amazon Bedrock console, under Foundation models in the navigation pane, pick Marketplace implementations.
19. In the Managed implementations area, find the endpoint you wish to erase.
20. Select the endpoint, and on the Actions menu, choose Delete.
21. Verify the endpoint details to make certain you’re deleting the correct deployment: 1. Endpoint name.
22. Model name.
23. Endpoint status
    
    Delete the SageMaker JumpStart predictor
    
    The SageMaker JumpStart design you released will sustain costs if you leave it running. Use the following code to delete the endpoint if you wish to stop sustaining charges. For more details, see Delete Endpoints and Resources.
    
    Conclusion
    
    In this post, we checked out how you can access and deploy the DeepSeek-R1 model using Bedrock Marketplace and SageMaker JumpStart. Visit SageMaker JumpStart in SageMaker Studio or Amazon Bedrock Marketplace now to get started. For more details, describe Use Amazon Bedrock tooling with Amazon SageMaker JumpStart designs, SageMaker JumpStart pretrained designs, Amazon SageMaker JumpStart Foundation Models, Amazon Bedrock Marketplace, and Beginning with Amazon SageMaker JumpStart.
    
    About the Authors
    
    Vivek Gangasani is a Lead Specialist Solutions Architect for Inference at AWS. He helps emerging generative AI business build innovative services using AWS services and accelerated calculate. Currently, he is concentrated on establishing techniques for fine-tuning and optimizing the reasoning performance of big language models. In his spare time, Vivek delights in treking, watching motion pictures, higgledy-piggledy.xyz and trying various cuisines.
    
    Niithiyn Vijeaswaran is a Generative AI Specialist Solutions Architect with the Third-Party Model Science group at AWS. His area of focus is AWS AI accelerators (AWS Neuron). He holds a Bachelor’s degree in Computer technology and Bioinformatics.
    
    Jonathan Evans is an Expert Solutions Architect dealing with generative AI with the Third-Party Model Science group at AWS.
    
    Banu Nagasundaram leads item, engineering, and tactical collaborations for Amazon SageMaker JumpStart, SageMaker’s artificial intelligence and generative AI hub. She is enthusiastic about constructing options that assist consumers accelerate their AI journey and unlock business worth.