AWS Bedrock

Use AWS Bedrock foundation models with Agno agents.

Use AWS Bedrock to access various foundation models on AWS. Manage your access to models on the portal.

See all the AWS Bedrock foundational models. Not all Bedrock models support all features. See the supported features for each model.

For async support with AWS Bedrock, you need to install aioboto3:

uv pip install aioboto3

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

• For a Mistral model with generally good performance, look at mistral.mistral-large-2402-v1:0.
• You can play with Amazon Nova models. Use amazon.nova-pro-v1:0 for general purpose tasks.
• For Claude models, see our Claude integration.

Authentication

AWS Bedrock supports three authentication methods:

Method 1: Access Key and Secret Key (Recommended)

Set your AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, and AWS_REGION environment variables.

Get your keys from here.

Mac

export AWS_ACCESS_KEY_ID=***
export AWS_SECRET_ACCESS_KEY=***
export AWS_REGION=***

setx AWS_ACCESS_KEY_ID ***
setx AWS_SECRET_ACCESS_KEY ***
setx AWS_REGION ***

Or pass them directly to the model:

from agno.agent import Agent
from agno.models.aws import AwsBedrock

agent = Agent(
    model=AwsBedrock(
        id="mistral.mistral-large-2402-v1:0",
        aws_access_key_id="your-access-key",
        aws_secret_access_key="your-secret-key",
        aws_region="us-east-1"
    )
)

Method 2: SSO Authentication

Use SSO authentication by leveraging your current AWS profile’s authentication:

from agno.agent import Agent
from agno.models.aws import AwsBedrock

agent = Agent(
    model=AwsBedrock(
        id="mistral.mistral-large-2402-v1:0",
        aws_sso_auth=True,
        aws_region="us-east-1"
    )
)

Method 3: Boto3 Session

Use a pre-configured boto3 Session for advanced authentication scenarios (including SSO, role assumption, etc.):

from boto3.session import Session
from agno.agent import Agent
from agno.models.aws import AwsBedrock

# Create a boto3 session with your preferred authentication
session = Session(
    aws_access_key_id="your-access-key",
    aws_secret_access_key="your-secret-key",
    region_name="us-east-1"
)

agent = Agent(
    model=AwsBedrock(
        id="mistral.mistral-large-2402-v1:0",
        session=session
    )
)

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

Example

Use AwsBedrock with your Agent:

agent.py

from agno.agent import Agent
from agno.models.aws import AwsBedrock

agent = Agent(
    model=AwsBedrock(id="mistral.mistral-large-2402-v1:0"),
    markdown=True
)

# Print the response on the terminal
agent.print_response("Share a 2 sentence horror story.")

View more examples here.

Parameters

Parameter	Type	Default	Description
id	str	"mistral.mistral-small-2402-v1:0"	The specific model ID used for generating responses.
name	str	"AwsBedrock"	The name identifier for the AWS Bedrock agent.
provider	str	"AwsBedrock"	The provider of the model.
aws_access_key_id	Optional[str]	None	The AWS access key ID for authentication. Can also be set via AWS_ACCESS_KEY_ID environment variable.
aws_secret_access_key	Optional[str]	None	The AWS secret access key for authentication. Can also be set via AWS_SECRET_ACCESS_KEY environment variable.
aws_region	Optional[str]	None	The AWS region to use for API requests. Can also be set via AWS_REGION environment variable.
session	Optional[Session]	None	A boto3 Session object for advanced authentication scenarios (SSO, role assumption, etc.).
aws_sso_auth	Optional[bool]	False	Removes the need for an access and secret access key by leveraging the current profile’s authentication.
max_tokens	Optional[int]	None	The maximum number of tokens to generate in the response.
temperature	Optional[float]	None	The sampling temperature to use, between 0 and 2. Higher values like 0.8 make the output more random, while lower values like 0.2 make it more focused and deterministic.
top_p	Optional[float]	None	The nucleus sampling parameter. The model considers the results of the tokens with top_p probability mass.
stop_sequences	Optional[List[str]]	None	A list of sequences where the API will stop generating further tokens.
request_params	Optional[Dict[str, Any]]	None	Additional parameters for the request, provided as a dictionary.
client_params	Optional[Dict[str, Any]]	None	Additional client parameters for initializing the AwsBedrock client, provided as a dictionary.
client	Optional[AwsClient]	None	A pre-configured AWS client instance.

AwsBedrock is a subclass of the Model class and has access to the same params.