DeepSeek-R1 now accessible as a completely managed serverless mannequin in Amazon Bedrock

As of January 30, DeepSeek-R1 fashions turned accessible in Amazon Bedrock by the Amazon Bedrock Market and Amazon Bedrock Customized Mannequin Import. Since then, 1000’s of consumers have deployed these fashions in Amazon Bedrock. Clients worth the strong guardrails and complete tooling for protected AI deployment. Right this moment, we’re making it even simpler to make use of DeepSeek in Amazon Bedrock by an expanded vary of choices, together with a brand new serverless resolution.

The absolutely managed DeepSeek-R1 mannequin is now usually accessible in Amazon Bedrock. Amazon Internet Companies (AWS) is the primary cloud service supplier (CSP) to ship DeepSeek-R1 as a completely managed, usually accessible mannequin. You possibly can speed up innovation and ship tangible enterprise worth with DeepSeek on AWS with out having to handle infrastructure complexities. You possibly can energy your generative AI functions with DeepSeek-R1’s capabilities utilizing a single API within the Amazon Bedrock’s absolutely managed service and get the good thing about its in depth options and tooling.

In keeping with DeepSeek, their mannequin is publicly accessible underneath MIT license and gives robust capabilities in reasoning, coding, and pure language understanding. These capabilities energy clever resolution assist, software program improvement, mathematical problem-solving, scientific evaluation, information insights, and complete data administration methods.

As is the case for all AI options, give cautious consideration to information privateness necessities when implementing in your manufacturing environments, test for bias in output, and monitor your outcomes. When implementing publicly accessible fashions like DeepSeek-R1, contemplate the next:

• Knowledge safety – You possibly can entry the enterprise-grade safety, monitoring, and price management options of Amazon Bedrock which might be important for deploying AI responsibly at scale, all whereas retaining full management over your information. Customers’ inputs and mannequin outputs aren’t shared with any mannequin suppliers. You should utilize these key safety features by default, together with information encryption at relaxation and in transit, fine-grained entry controls, safe connectivity choices, and obtain varied compliance certifications whereas speaking with the DeepSeek-R1 mannequin in Amazon Bedrock.
• Accountable AI – You possibly can implement safeguards custom-made to your utility necessities and accountable AI insurance policies with Amazon Bedrock Guardrails. This consists of key options of content material filtering, delicate info filtering, and customizable safety controls to stop hallucinations utilizing contextual grounding and Automated Reasoning checks. This implies you may management the interplay between customers and the DeepSeek-R1 mannequin in Bedrock along with your outlined set of insurance policies by filtering undesirable and dangerous content material in your generative AI functions.
• Mannequin analysis – You possibly can consider and evaluate fashions to establish the optimum mannequin in your use case, together with DeepSeek-R1, in a couple of steps by both automated or human evaluations by utilizing Amazon Bedrock mannequin analysis instruments. You possibly can select automated analysis with predefined metrics comparable to accuracy, robustness, and toxicity. Alternatively, you may select human analysis workflows for subjective or customized metrics comparable to relevance, type, and alignment to model voice. Mannequin analysis gives built-in curated datasets, or you may herald your individual datasets.

We strongly advocate integrating Amazon Bedrock Guardrails and utilizing Amazon Bedrock mannequin analysis options along with your DeepSeek-R1 mannequin so as to add strong safety in your generative AI functions. To be taught extra, go to Defend your DeepSeek mannequin deployments with Amazon Bedrock Guardrails and Consider the efficiency of Amazon Bedrock assets.

Get began with the DeepSeek-R1 mannequin in Amazon Bedrock
Should you’re new to utilizing DeepSeek-R1 fashions, go to the Amazon Bedrock console, select Mannequin entry underneath Bedrock configurations within the left navigation pane. To entry the absolutely managed DeepSeek-R1 mannequin, request entry for DeepSeek-R1 in DeepSeek. You’ll then be granted entry to the mannequin in Amazon Bedrock.

Subsequent, to check the DeepSeek-R1 mannequin in Amazon Bedrock, select Chat/Textual content underneath Playgrounds within the left menu pane. Then select Choose mannequin within the higher left, and choose DeepSeek because the class and DeepSeek-R1 because the mannequin. Then select Apply.

Utilizing the chosen DeepSeek-R1 mannequin, I run the next immediate instance:

A household has $5,000 to save lots of for his or her trip subsequent yr. They'll place the cash in a financial savings account incomes 2% curiosity yearly or in a certificates of deposit incomes 4% curiosity yearly however with no entry to the funds till the holiday. In the event that they want $1,000 for emergency bills through the yr, how ought to they divide their cash between the 2 choices to maximise their trip fund?

This immediate requires a fancy chain of thought and produces very exact reasoning outcomes.

To be taught extra about utilization suggestions for prompts, discuss with the README of the DeepSeek-R1 mannequin in its GitHub repository.

By selecting View API request, you can too entry the mannequin utilizing code examples within the AWS Command Line Interface (AWS CLI) and AWS SDK. You should utilize us.deepseek.r1-v1:0 because the mannequin ID.

Here’s a pattern of the AWS CLI command:

aws bedrock-runtime invoke-model 
     --model-id us.deepseek-r1-v1:0 
     --body "{"messages":[{"role":"user","content":[{"type":"text","text":"[n"}]}],max_tokens":2000,"temperature":0.6,"top_k":250,"top_p":0.9,"stop_sequences":["nnHuman:"]}" 
     --cli-binary-format raw-in-base64-out 
     --region us-west-2 
     invoke-model-output.txt

The mannequin helps each the InvokeModel and Converse API. The next Python code examples present how you can ship a textual content message to the DeepSeek-R1 mannequin utilizing the Amazon Bedrock Converse API for textual content technology.

import boto3
from botocore.exceptions import ClientError

# Create a Bedrock Runtime shopper within the AWS Area you wish to use.
shopper = boto3.shopper("bedrock-runtime", region_name="us-west-2")

# Set the mannequin ID, e.g., DeepSeek-R1 Mannequin.
model_id = "us.deepseek.r1-v1:0"

# Begin a dialog with the consumer message.
user_message = "Describe the aim of a 'howdy world' program in a single line."
dialog = [
    {
        "role": "user",
        "content": [{"text": user_message}],
    }
]

attempt:
    # Ship the message to the mannequin, utilizing a primary inference configuration.
    response = shopper.converse(
        modelId=model_id,
        messages=dialog,
        inferenceConfig={"maxTokens": 2000, "temperature": 0.6, "topP": 0.9},
    )

    # Extract and print the response textual content.
    response_text = response["output"]["message"]["content"][0]["text"]
    print(response_text)

besides (ClientError, Exception) as e:
    print(f"ERROR: Cannot invoke '{model_id}'. Motive: {e}")
    exit(1)

To allow Amazon Bedrock Guardrails on the DeepSeek-R1 mannequin, choose Guardrails underneath Safeguards within the left navigation pane, and create a guardrail by configuring as many filters as you want. For instance, for those who filter for “politics” phrase, your guardrails will acknowledge this phrase within the immediate and present you the blocked message.

You possibly can check the guardrail with completely different inputs to evaluate the guardrail’s efficiency. You possibly can refine the guardrail by setting denied subjects, phrase filters, delicate info filters, and blocked messaging till it matches your wants.

To be taught extra about Amazon Bedrock Guardrails, go to Cease dangerous content material in fashions utilizing Amazon Bedrock Guardrails within the AWS documentation or different deep dive weblog posts about Amazon Bedrock Guardrails on the AWS Machine Studying Weblog channel.

Right here’s a demo walkthrough highlighting how one can make the most of the absolutely managed DeepSeek-R1 mannequin in Amazon Bedrock:

Now accessible
DeepSeek-R1 is now accessible absolutely managed in Amazon Bedrock within the US East (N. Virginia), US East (Ohio), and US West (Oregon) AWS Areas by cross-Area inference. Verify the full Area listing for future updates. To be taught extra, take a look at the DeepSeek in Amazon Bedrock product web page and the Amazon Bedrock pricing web page.

Give the DeepSeek-R1 mannequin a attempt within the Amazon Bedrock console right now and ship suggestions to AWS re:Publish for Amazon Bedrock or by your regular AWS Assist contacts.

— Channy

Up to date on March 10, 2025 — Mounted screenshots of mannequin choice and mannequin ID.