Introducing Claude Sonnet 5 on AWS: Anthropic Sonnet's most capable model

Today, we are excited to announce the availability of Anthropic's most advanced Sonnet model, Claude Sonnet 5, on Amazon Bedrock and the Claude Platform on AWS. Claude Sonnet 5 is the first Sonnet model of the latest Anthropic generation and represents a logical step forward. It brings high-level intelligence to Sonnet's pricing for coding, agents, and the daily work of professionals at scales. With Claude Sonnet 5 on Amazon Bedrock you can build within your existing AWS environment, maintain business security and regional data integrity, and scale. Claude Sonnet 5 is also available through the Claude Platform on AWS, which gives you access to Anthropic's native platform knowledge and capabilities through the AWS Management Console. Build, test, and deploy with the same APIs, features, and console experience you'd get working directly with Anthropic, combined with AWS billing and authentication.

This post covers Sonnet 5 development and practical guidelines for AI developers integrating the model into agent systems and targeted production workloads on Amazon Bedrock. See the documentation for the Claude Platform on AWS.

What makes Claude Sonnet 5 different

Claude Sonnet 5 shows strong performance in all coding, agent functions, and professional work. Claude Sonnet 5 brings the near-intelligence of Opus while maintaining the same balance of power, cost, and speed, so teams can rely on Sonnet for day-to-day tasks at scale. Use Claude Sonnet 5 when you need robust logic, coding, and agency reliability at scale without Opus-tier pricing. Use Claude Opus when your work demands a high level of thought that justifies the cost. Sonnet 5 can hold a program at every stage, keep track of what it has done and what is left, and solve problems in a few cycles of correction. This leads to predictable behavior at scale.

For coding, Sonnet 5 is designed to navigate real codebases, convert multiple file changes, and carry long debugging and reinstallation tasks to completion. It writes cleaner, more maintainable code with reduced oversight. For independent agents, Claude Sonnet 5 serves as a more reliable backbone for automation, managing complex dependency chains and the use of multi-step tools, making it a strong fit for both customer-facing and internal agents. In professional work, Sonnet 5 combines long, complex, unstructured sources into structured deliverables such as briefs, analyses, and reports. Claude Sonnet 5 is designed as a clear improvement over Sonnet 4.6.

Industry use cases

Claude Sonnet 5 is strongly suited to industries where reliability and systematic thinking are paramount. For financial services teams, Sonnet 5 enables spreadsheet modeling, financial analysis, and reporting agents check their numbers on the go. This supports an end-to-end workflow from data entry to verified output. For production work, it handles report creation and audits, documentation, and systematic analysis with high consistency. With its computing power, you can automate browser and desktop workflows that previously required human interaction. In agent automation and workflow, Claude Sonnet 5 serves as the backbone of production agents that call tools and perform multi-step tasks without supervision.

Getting Started with Claude Sonnet 5 on Amazon Bedrock

You can start with Claude Sonnet 5 on the Amazon Bedrock console.

1. In the Amazon Bedrock console, under Tests, select Playground.
2. In the model, select Claude Sonnet 5. Now, you can test your complex code information with the model.

Amazon Bedrock console Playground with Claude Sonnet 5 selected

You can also access the model programmatically using the Anthropic Messages API to make calls bedrock-runtime by using the Anthropic SDK or bedrock-mantle finally, or continue to use the Invoke and Converse API is open bedrock-runtime by using the AWS Command Line Interface (AWS CLI) and the AWS SDK.

What is required

1. An active AWS account with Amazon Bedrock access
2. The AWS CLI is installed and configured
3. Python 3.8+
4. Boto3 included: pip install boto3
5. Anthropic SDK included: pip install anthropic[bedrock]
6. IAM permissions: bedrock:InvokeModel, bedrock:InvokeModelWithResponseStreamagain 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
response = 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 to get integrated information for multiple models:

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[bedrock] SDK package for simple experience:

from anthropic import AnthropicBedrockMantle

# Initialize the Bedrock Mantle client (uses SigV4 auth automatically)
mantle_client = AnthropicBedrockMantle(aws_region="us-east-1")

# Create a message using the 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 oClaude Sonnet 5 is available today on Amazon Bedrock, with a complete list of supported AWS regions available in the Amazon Bedrock documentation. Claude Sonnet 5 is also available on the Claude Platform on AWS in North America, South America, Europe and Asia Pacific.

Try Claude Sonnet 5 on the Amazon Bedrock console, the Claude Platform on AWS, or check out the Getting Started notebooks on GitHub. Sonnet 5 is available at promotional prices until August 31, 2026. For details, see Amazon Bedrock pricing. You can also unlock the full potential of Sonnet 5 by using Advanced Prompt Optimization on Amazon Bedrock. It takes your current information, evaluates it against your test criteria, and rewrites it to produce the output.

About the writers