Today, we are thrilled to announce the release of Anthropic’s most advanced Sonnet model, Claude Sonnet 5, now accessible on Amazon Bedrock and the Claude Platform on AWS. This marks a significant milestone as Claude Sonnet 5 is the first model of Anthropic’s latest generation, designed to deliver exceptional performance for coding, agents, and daily professional activities at scale. With Claude Sonnet 5 integrated into Amazon Bedrock, you can enhance your existing AWS environment, ensuring enterprise security, regional data residency, and scalable inference capabilities. Additionally, Claude Sonnet 5 is available on the Claude Platform on AWS, allowing you to experience native Anthropic functionalities through the AWS Management Console, with seamless integration of AWS billing and authentication.
This article delves into the enhancements brought by Sonnet 5 and provides practical advice for AI engineers on integrating the model into agentic systems and production inference workloads on Amazon Bedrock. For further details, refer to the Claude Platform documentation on AWS.
What makes Claude Sonnet 5 different
Claude Sonnet 5 exhibits superior performance in tasks related to coding, agents, and professional work. It brings Opus-like intelligence while maintaining a balance of capacity, cost, and speed, making it ideal for large-scale everyday tasks. When strong reasoning, coding, and agent reliability are needed at scale without the higher costs of Opus, Claude Sonnet 5 is the go-to choice. With its ability to guide plans through various stages, track progress, and resolve issues with fewer intervention cycles, it ensures more predictable behavior at scale.
In terms of coding, Sonnet 5 is adept at navigating real codebases, executing multi-file changes, and completing extensive debugging and refactoring tasks. It generates cleaner, maintainable code with minimal oversight. For autonomous agents, Claude Sonnet 5 offers a reliable backbone for automated operations, managing complex dependency chains, and multi-step tool usage, making it ideal for both in-house and customer-facing agents. In professional settings, Sonnet 5 synthesizes long, complex, and unstructured sources into structured deliverables such as briefs, analyses, and reports, positioning itself as a clear upgrade from Sonnet 4.6.
Industry Use Cases
Claude Sonnet 5 is particularly beneficial in industries where reliability and structured reasoning are crucial. In financial services, it powers spreadsheet modeling, financial analysis, and reporting agents, ensuring accurate number checking and supporting end-to-end workflows from data ingestion to validated output. In productivity work, it excels in report creation, auditing, document writing, and structured analysis with high consistency. Equipped with computing capabilities, it automates browser and desktop workflows traditionally requiring human intervention. For agent and workflow automation, Claude Sonnet 5 serves as the backbone for production agents that invoke tools and execute multi-step tasks without supervision.
Getting Started with Claude Sonnet 5 on Amazon Bedrock
You can begin using Claude Sonnet 5 by accessing the Amazon Bedrock console.
- In the Amazon Bedrock console, navigate to the Test section and choose Playground.
- Select the Claude Sonnet 5 template to test your complex coding prompts.
Amazon Bedrock Playground console with Claude Sonnet 5 selected
For programmatic access, utilize the Anthropic Messages API to invoke the Bedrock Runtime through the Anthropic SDK or Mantle Rock endpoints, or continue using the Invoke and Converse APIs on the Bedrock Runtime via the AWS Command Line Interface (AWS CLI) and the AWS SDK.
Prerequisites
- Active AWS account with access to Amazon Bedrock
- AWS CLI installed and configured
- Python 3.8+
- Boto3 installed: pip install boto3
- Anthropic SDK installed: pip install anthropic[bedrock]
- IAM permissions: Bedrock: InvokeModel, Bedrock: InvokeModelWithResponseStream, and Bedrock: CreateInference
Here’s a quick example using the AWS SDK for Python (Boto3):
import boto3
import json
# Create a Bedrock Runtime client
bedrock_runtime = boto3.client(
service_name="bedrock-runtime",
region_name="us-east-1"
)
# Invoke Claude Sonnet 5
answer = bedrock_runtime.invoke_model(
modelId="us.anthropic.claude-sonnet-5",
contentType="application/json",
accept="application/json",
body=json.dumps({
"anthropic_version": "bedrock-2023-05-31",
"max_tokens": 4096,
"messages": [
{
"role": "user",
"content": "Design a distributed architecture on AWS in Python that should support 100k requests per second across multiple geographic regions."
}
]
})
)
result = json.loads(response["body"].read())
print(result["content"][0]["text"])You can also use Claude Sonnet 5 with the Amazon Bedrock Converse API for a unified multi-model experience:
import boto3
bedrock_runtime = boto3.client("bedrock-runtime", region_name="us-east-1")
response = bedrock_runtime.converse(
modelId="us.anthropic.claude-sonnet-5",
messages=[
{
"role": "user",
"content": [
{
"text": "Design a distributed architecture on AWS in Python that should support 100k requests per second across multiple geographic regions."
}
]
}
],
inferenceConfig={
"maxTokens": 4096
}
)
print(response["output"]["message"]["content"][0]["text"])You can also use Claude Sonnet 5 with the Anthropic Messages API using the anthropic API[bedrock] SDK package for a simplified experience:
from anthropic import AnthropicBedrockMantle
# Initialize Bedrock Mantle client (automatically uses SigV4 authentication)
mantle_client = AnthropicBedrockMantle(aws_region="us-east-1")
# Create message using Messages API
message = mantle_client.messages.create(
model="anthropic.claude-sonnet-5",
max_tokens=4096,
messages=[
{"role": "user", "content": "Design a distributed architecture on AWS in Python that should support 100k requests per second across multiple geographic regions"}
]
)
print(message.content[0].text)Availability
Claude Sonnet 5 is available today on Amazon Bedrock, with a full list of supported AWS Regions detailed in the Amazon Bedrock documentation. It is also accessible on the Claude platform on AWS across North America, South America, Europe, and Asia Pacific.
Explore Claude Sonnet 5 through the Amazon Bedrock console, the Claude platform on AWS, or the getting started notebooks available on GitHub. The model is offered at a promotional price until August 31, 2026. For further details, refer to Amazon Bedrock pricing. Enhance the potential of Sonnet 5 by leveraging advanced prompt optimization on Amazon Bedrock, which refines your prompts and generates production-ready rewrites based on evaluation criteria.
About the authors
Aamna Najmi
Aamna is a Senior Specialist Solutions Architect for Generative AI, focusing on anthropogenic models and operationalizing and governing large-scale generative AI systems on Amazon Bedrock. She helps ISVs solve their challenges, embrace innovation, and create new business opportunities with Amazon Bedrock. In her free time, she pursues her passion for experimenting with food and discovering new places.
Antonio Rodriguez
Antonio is a senior technical lead for Generative AI at Amazon Web Services. It helps businesses of all sizes solve challenges, embrace innovation, and create new business opportunities with Amazon Bedrock. Outside of work, he enjoys spending time with his family and playing sports with his friends.
Eugénio single
Eugenio is a Senior Product Marketing Manager for Amazon Bedrock at AWS. With years of experience in generative AI, he helps clients navigate the changing landscape of core models and generative AI to adopt solutions that deliver measurable value.
Sofiane Hamiti
Sofian is a technology leader with over 12 years of experience building AI solutions and leading high-performing teams to maximize client outcomes. He is passionate about empowering diverse talents to make a global impact and achieve their professional aspirations.
Ryan Ray
Ayan is a Senior Partner Solutions Architect and AI Technical Lead at AWS, serving as the Global Technical Lead for Anthropic at AWS. He works at the intersection of cloud architecture and artificial intelligence, helping organizations adopt and scale Anthropic technologies on AWS.
Daniel Mitchell
Dani is a Sr. GenAI Specialist Solutions Architect at AWS and SA Lead for Amazon Bedrock Knowledge Bases. It helps businesses around the world design and deploy generative AI solutions using models and capabilities from Amazon Bedrock and Anthropic to create scalable, production-ready applications.
For more information on Claude Sonnet 5, visit the official blog post here.
“`
