Migrate from Anthropic’s Claude 3.5 Sonnet to Claude 4 Sonnet on Amazon Bedrock

Anthropic’s Claude 4 Sonnet is designed to observe directions extra exactly. It is a main benefit, however would possibly imply it’s much less verbose or elaborative than Claude 3.5 Sonnet until explicitly prompted to be. Your system prompts defining the AI’s persona would possibly want changes.

New reasoning options

Anthropic’s Claude 4 Sonnet mannequin’s built-in prolonged considering is a strong functionality. To unlock the deep reasoning capabilities of the brand new fashions, builders can allow prolonged considering by together with the considering key phrase argument of their API name. However ensure that to make use of it strategically—prolonged considering incurs further prices as a result of reasoning tokens are billed as output tokens at commonplace mannequin charges. You can be charged for the complete considering course of (not simply the abstract you see), and prices can scale with the considering funds you set.

We advocate enabling prolonged considering for duties requiring deep, multi-step evaluation the place accuracy is paramount (for instance, complicated scientific issues or superior coding challenges).

We advocate disabling prolonged considering for easy queries or latency-sensitive purposes. The function provides to each price (reasoning tokens are billed) and response time. For a lot of duties, a well-crafted CoT immediate continues to be probably the most environment friendly selection.

To make use of prolonged considering, merely replace the Converse API name by including the additionalModelRequestFields parameter with the considering configuration. You may specify the utmost considering tokens that the mannequin can use by setting a price for budget_tokens. Word that maxTokens ought to be bigger than budget_tokens for prolonged considering. See the next code:

import boto3

bedrock_runtime = boto3.consumer(service_name="bedrock-runtime")

# Add configurations to allow prolonged considering
response = bedrock_runtime.converse(
    modelId='us.anthropic.claude-sonnet-4-20250514-v1:0',
    messages=[{'role': 'user', 'content': [{'text': "Your prompt here"}]}],
    inferenceConfig={'maxTokens': 2048},
    additionalModelRequestFields={"considering":{"kind": "enabled",
     "budget_tokens": 1024}}
)

reasoning_text = response['output']['message']['content'][0]['reasoningContent']['reasoningText']['text']
assistant_response = response['output']['message']['content'][1]['text']

The next desk reveals an instance of prolonged considering and the way it can enhance response accuracy. We immediate Anthropic’s Claude 3.5 Sonnet v2 and Claude 4 Sonnet (with considering enabled) with an instance immediate:

Alan, Bob, Colin, Dave and Emily are standing in a circle. Alan is on Bob's quick left. Bob is on Colin's quick left. Colin is on Dave's quick left. Dave is on Emily's quick left. Who's on Alan's quick proper?

The desk reveals responses from the 2 fashions. With prolonged considering, the mannequin is ready to rigorously cause by means of the issue and arrive on the appropriate reply.

With prolonged considering enabled, the API will, by default, return a abstract of the mannequin’s full thought course of slightly than all the chain of reasoning. It is a safeguard designed to stop misuse whereas nonetheless offering the complete intelligence advantages. Builders ought to be conscious that this may end up in a chunky or delayed sample in streaming responses and may account for this of their software’s consumer expertise.

Anthropic’s Claude 4 fashions function the interleaved considering functionality when utilizing prolonged considering with instruments, permitting the mannequin to carry out intermediate reasoning between software calls and develop extra nuanced analytical conclusions primarily based on the software outcomes obtained. To allow interleaved considering for software calling, add the extra parameter "anthropic_beta": ["interleaved-thinking-2025-05-14"] to additionalModelRequestFields within the Converse API request.

For extra particulars on utilizing prolonged considering, consult with Prolonged considering.

Strong analysis is non-negotiable

You have to confirm that the brand new mannequin performs in addition to or higher than the outdated one in your particular duties. Create a curated set of prompts and anticipated outputs which can be extremely consultant of your manufacturing site visitors. This practice benchmark is way extra useful than reported benchmark scores.

Combine this dataset into an automatic analysis pipeline. This pipeline ought to turn into a part of your steady integration and steady supply (CI/CD) course of, serving as a everlasting regression suite for future mannequin or immediate adjustments. For tooling, groups can use built-in options like Amazon Bedrock evaluations or open supply analysis frameworks like RAGAS and DeepEval.

Managing built-in security and governance

A mannequin’s security profile adjustments with every model. This should be examined as a part of an built-in system. By no means take a look at the brand new mannequin in isolation. Your migration take a look at plan is barely legitimate if it evaluates the brand new mannequin with the very same guardrail configuration you employ in manufacturing, for instance, Amazon Bedrock Guardrails. A brand new mannequin’s conversational type would possibly set off present guardrails in sudden methods, resulting in a spike in blocked responses.

Implementing protected deployment methods

When deploying Anthropic’s Claude 4 Sonnet to manufacturing, implement a phased rollout technique to attenuate dangers. Take into account shadow testing to check mannequin efficiency utilizing mirrored site visitors with out impacting customers, then conduct A/B testing to measure affect on enterprise KPIs. For the precise rollout, use both a canary launch strategy by regularly exposing a small proportion of customers to the brand new mannequin, or a blue/inexperienced deployment technique that maintains parallel environments for immediate rollback functionality. This structured strategy facilitates protected validation of the brand new mannequin’s efficiency whereas sustaining enterprise continuity.

Conclusion

By treating the transition from Anthropic’s Claude 3.5 Sonnet (v1 and v2) to Claude 4 Sonnet as a structured engineering challenge, you’ll be able to de-risk the migration course of and unlock important advantages. Understanding the important thing mannequin variations, adapting your prompts and API calls, and implementing a strong, automated analysis technique are the pillars of a profitable improve.

This transition is a chance to take care of enterprise continuity and improve your software with next-generation capabilities. We encourage you to start your evaluation and testing at this time.

For extra particulars, consult with Migrating to Claude 4 and Anthropic’s Claude in Amazon Bedrock, and attain out to us for migration-specific inquiries.

In regards to the authors

Melanie Li, PhD, is a Senior Generative AI Specialist Options Architect at AWS primarily based in Sydney, Australia, the place her focus is on working with clients to construct options utilizing state-of-the-art AI/ML instruments. She has been actively concerned in a number of generative AI initiatives throughout APJ, harnessing the ability of LLMs. Previous to becoming a member of AWS, Dr. Li held information science roles within the monetary and retail industries.

Deepak Dalakoti, PhD, is a Deep Studying Architect on the Generative AI Innovation Centre in Sydney, Australia. With experience in AI, he companions with shoppers to speed up their generative AI adoption by means of custom-made, revolutionary options. Outdoors the world of AI, he enjoys exploring new actions and experiences.

Mahsa Paknezhad, PhD, is a Deep Studying Architect on the AWS Generative AI Innovation Middle. With a give attention to scalability and manufacturing readiness, Mahsa helps organizations throughout numerous industries harness superior generative AI fashions to attain significant enterprise outcomes. Mahsa has a confirmed observe file of efficiently delivering tasks particularly inside the mining business and the healthcare sector.

Nicholas Moore is a Options Architect at AWS, serving to startups and companies of all sizes flip concepts into actuality. He makes a speciality of cloud options with a give attention to AI, analytics, and trendy software improvement.

Derrick Choo is a Senior Options Architect at AWS who accelerates enterprise digital transformation by means of cloud adoption, AI/ML, and generative AI options. He makes a speciality of full-stack improvement and ML, designing end-to-end options spanning frontend interfaces, IoT purposes, information integrations, and ML fashions, with a selected give attention to pc imaginative and prescient and multi-modal methods.

Sovik Kumar Nath is an AI/ML and Generative AI Senior Options Architect with AWS. He has intensive expertise designing end-to-end ML and enterprise analytics options in finance, operations, advertising and marketing, healthcare, provide chain administration, and IoT. He has grasp’s levels from the College of South Florida and College of Fribourg, Switzerland, and a bachelor’s diploma from the Indian Institute of Know-how, Kharagpur. Outdoors of labor, Sovik enjoys touring, taking ferry rides, and watching films.

Saurabh Trikande is a Senior Product Supervisor for Amazon Bedrock and Amazon SageMaker Inference. He’s captivated with working with clients and companions, motivated by the objective of democratizing AI. He focuses on core challenges associated to deploying complicated AI purposes, inference with multi-tenant fashions, price optimizations, and making the deployment of generative AI fashions extra accessible. In his spare time, Saurabh enjoys mountain climbing, studying about revolutionary applied sciences, following TechCrunch, and spending time along with his household.

Gareth Jones is a Product Supervisor at Anthropic targeted on the Claude API. His work contains collaboration with AWS on Amazon Bedrock to make Claude broadly accessible to builders.