Use AWS Bedrock to access the Claude models. Manage your access to models here.

See all the AWS Bedrock foundational models here.

  • For an Anthropic Claude model with generally good performance, look at anthropic.claude-3-5-sonnet-20241022-v2:0.
  • For an open-source Meta model, consider meta.llama3-70b-instruct-v1:0.

Authentication

Set your AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY and AWS_DEFAULT_REGION environment variables.

Get your keys from here.

Example

Use AWS BedrockClaude with your Agent:

View more examples here.

Params

ParameterTypeDefaultDescription
idstr"anthropic.claude-3-5-sonnet-20240620-v1:0"The specific model ID used for generating responses.
namestr"AwsBedrockAnthropicClaude"The name identifier for the Claude agent.
providerstr"AwsBedrock"The provider of the model.
max_tokensint4096The maximum number of tokens to generate in the response.
temperatureOptional[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_pOptional[float]"None"The nucleus sampling parameter. The model considers the results of the tokens with top_p probability mass.
top_kOptional[int]"None"The number of highest probability vocabulary tokens to keep for top-k-filtering.
stop_sequencesOptional[List[str]]"None"A list of sequences where the API will stop generating further tokens.
anthropic_versionstr"bedrock-2023-05-31"The version of the Anthropic API to use.
request_paramsOptional[Dict[str, Any]]"None"Additional parameters for the request, provided as a dictionary.
client_paramsOptional[Dict[str, Any]]"None"Additional client parameters for initializing the AwsBedrock client, provided as a dictionary.

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