Introducing Anthropic Claude 3.5 Sonnet: A New Era of Intelligent AI on Amazon Bedrock

Introducing Anthropic Claude 3.5 Sonnet: A New Era of Intelligent AI on Amazon Bedrock

We are excited to announce the launch of the Anthropic Claude 3.5 Sonnet model, now available on Amazon Bedrock. This latest addition to the Claude family sets new standards in the realm of generative AI, offering remarkable improvements over its predecessors.

Model Overview

Claude 3.5 Sonnet stands out as the most intelligent model in the Claude series, delivering superior performance across a wide range of tasks. Whether it's natural language processing or vision capabilities, Claude 3.5 Sonnet outshines even the highly acclaimed Claude 3 Opus model.

Key Improvements

  • Enhanced customer support and natural language processing capabilities.
  • Improved understanding of multistep workflows.
  • 10% better performance in vision benchmarks compared to Claude 3 Opus.
  • 80% cost reduction while maintaining or exceeding performance and speed.

Availability and Access

The Claude 3.5 Sonnet model is accessible via the Amazon Bedrock console in the US East (N. Virginia) AWS Region. To enable access, navigate to the Amazon Bedrock Model Access console. If you encounter an "Unavailable" status, contacting AWS Support may be necessary to resolve access issues.

API Usage

To utilize Claude 3.5 Sonnet, construct a request in line with the Amazon Bedrock API structure. Here’s a sample API request:

{
  "anthropic_version": "bedrock-2023-05-31",
  "max_tokens": 300,
  "temperature": 0.7,
  "messages": [
    {"role": "user", "content": "Your message here"}
  ]
}

For invocation using the AWS CLI:

aws bedrock-runtime invoke-model --model-id anthropic.claude-3-5-sonnet-20240620-v1:0 --body '{"messages":[{"role":"user","content":[{"type":"text","text":"hello."}]}],"anthropic_version":"bedrock-2023-05-31","max_tokens":2000,"temperature":1,"top_k":250,"top_p":0.999,"stop_sequences":[]}' --cli-binary-format raw-in-base64-out --region us-east-1 invoke-model-output.txt

For Python integration, use the following example:

request_body = json.dumps({
  "anthropic_version": "bedrock-2023-05-31",
  "max_tokens": 300,
  "temperature": 0.7,
  "messages": [
    {"role": "user", "content": "Your message here"}
  ]
})

response = bedrock_runtime.invoke_model(
  modelId='anthropic.claude-3-5-sonnet-20240620-v1:0',
  body=request_body
)

Error Handling and Integration

Ensure your AWS credentials are properly configured with the necessary permissions for Bedrock services. Common errors include missing required keys such as prompt or max_tokens_to_sample, and using incorrect keys like Messages, MaxTokens, and AnthropicVersion.

Use Cases

Claude 3.5 Sonnet is ideal for advanced research, complex problem-solving, and sophisticated language generation. It also shows significant potential in healthcare and life sciences, enhancing imaging analysis and summarizing research findings.

Pricing

With an input price of $3 per million tokens and an output price of $15 per million tokens, Claude 3.5 Sonnet offers a cost-effective solution for businesses and researchers. For detailed pricing information, please refer to the Amazon Bedrock pricing page.

Explore the possibilities with the new Claude 3.5 Sonnet model on Amazon Bedrock, and leverage its unmatched intelligence and cost-efficiency for your next project.

Read more