AWS Claude

Use Claude models through AWS Bedrock with Kern agents.

Use Claude models through AWS Bedrock. This provides a native Claude integration optimized for AWS infrastructure.

We recommend experimenting to find the best-suited model for your use-case. Here are some general recommendations:

anthropic.claude-sonnet-4-20250514-v1:0 model is their most capable model (Claude Sonnet 4).
anthropic.claude-3-5-sonnet-20241022-v2:0 model is good for most use-cases and supports image input.
anthropic.claude-3-5-haiku-20241022-v2:0 model is their fastest model.

Authentication

AWS Claude supports three authentication methods:

Method 1: API Key Authentication (Recommended)

Use the AWS Bedrock API key for simplified authentication:

1export AWS_BEDROCK_API_KEY=***
2export AWS_REGION=***

1setx AWS_BEDROCK_API_KEY ***
2setx AWS_REGION ***

Or pass them directly to the model:

1from kern.agent import Agent
2from kern.models.aws import Claude
3
4agent = Agent(
5    model=Claude(
6        id="us.anthropic.claude-sonnet-4-20250514-v1:0",
7        api_key="your-api-key",
8        aws_region="us-east-1"
9    )
10)

Method 2: Access Key and Secret Key

Set your AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY and AWS_REGION environment variables.

Get your keys from here.

1export AWS_ACCESS_KEY_ID=***
2export AWS_SECRET_ACCESS_KEY=***
3export AWS_REGION=***

1setx AWS_ACCESS_KEY_ID ***
2setx AWS_SECRET_ACCESS_KEY ***
3setx AWS_REGION ***

Or pass them directly:

1from kern.agent import Agent
2from kern.models.aws import Claude
3
4agent = Agent(
5    model=Claude(
6        id="us.anthropic.claude-sonnet-4-20250514-v1:0",
7        aws_access_key="your-access-key",
8        aws_secret_key="your-secret-key",
9        aws_region="us-east-1"
10    )
11)

Method 3: Boto3 Session

Use a pre-configured boto3 Session for advanced authentication scenarios:

1from boto3.session import Session
2from kern.agent import Agent
3from kern.models.aws import Claude
4
5# Create a boto3 session with your preferred authentication
6session = Session(
7    aws_access_key_id="your-access-key",
8    aws_secret_access_key="your-secret-key",
9    region_name="us-east-1"
10)
11
12agent = Agent(
13    model=Claude(
14        id="us.anthropic.claude-sonnet-4-20250514-v1:0",
15        session=session
16    )
17)

Note

The authentication methods are checked in this order: Session → API Key → Access Key/Secret Key. The first available method will be used.

Example

Use Claude with your Agent:

1from kern.agent import Agent
2from kern.models.aws import Claude
3
4agent = Agent(
5    model=Claude(id="us.anthropic.claude-sonnet-4-20250514-v1:0"),
6    markdown=True
7)
8
9# Print the response on the terminal
10agent.print_response("Share a 2 sentence horror story.")

Note View more examples here.

Parameters

Parameter	Type	Default	Description
`id`	`str`	`"anthropic.claude-sonnet-4-20250514-v1:0"`	The specific AWS Bedrock Claude model ID to use
`name`	`str`	`"AwsBedrockAnthropicClaude"`	The name identifier for the AWS Bedrock Claude model
`provider`	`str`	`"AwsBedrock"`	The provider of the model
`api_key`	`Optional[str]`	`None`	The AWS Bedrock API key for authentication (defaults to AWS_BEDROCK_API_KEY env var)
`aws_access_key`	`Optional[str]`	`None`	The AWS access key to use (defaults to AWS_ACCESS_KEY env var)
`aws_secret_key`	`Optional[str]`	`None`	The AWS secret key to use (defaults to AWS_SECRET_KEY env var)
`aws_region`	`Optional[str]`	`None`	The AWS region to use (defaults to AWS_REGION env var)
`session`	`Optional[Session]`	`None`	A boto3 Session object to use for authentication
`max_tokens`	`int`	`4096`	Maximum number of tokens to generate in the chat completion
`temperature`	`Optional[float]`	`None`	Controls randomness in the model's output
`top_p`	`Optional[float]`	`None`	Controls diversity via nucleus sampling
`top_k`	`Optional[int]`	`None`	Controls diversity via top-k sampling
`stop_sequences`	`Optional[List[str]]`	`None`	A list of strings that the model should stop generating text at
`request_params`	`Optional[Dict[str, Any]]`	`None`	Additional parameters to include in the request
`client_params`	`Optional[Dict[str, Any]]`	`None`	Additional parameters for client configuration

Claude (AWS) extends the Anthropic Claude model with AWS Bedrock integration and has access to most of the same parameters.