AWS Bedrock

AWS Bedrock model parameters and configuration.

The AWS Bedrock model provides access to models hosted on AWS Bedrock.

Parameters

Parameter	Type	Default	Description
id	str	"mistral.mistral-small-2402-v1:0"	The id of the AWS Bedrock model to use
name	str	"AwsBedrock"	The name of the model
provider	str	"AwsBedrock"	The provider of the model
temperature	Optional[float]	None	Controls randomness in the model’s output
max_tokens	Optional[int]	None	Maximum number of tokens to generate
top_p	Optional[float]	None	Controls diversity via nucleus 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
append_trailing_user_message	Optional[bool]	None	Append a trailing user message when required. When unset, enabled for models without prefill support
trailing_user_message_content	str	"continue"	Content of the appended trailing user message
aws_region	Optional[str]	None	The AWS region to use (defaults to AWS_REGION env var)
aws_access_key_id	Optional[str]	None	AWS access key ID (defaults to AWS_ACCESS_KEY_ID env var)
aws_secret_access_key	Optional[str]	None	AWS secret access key (defaults to AWS_SECRET_ACCESS_KEY env var)
aws_session_token	Optional[str]	None	AWS session token (defaults to AWS_SESSION_TOKEN env var)
aws_sso_auth	Optional[bool]	False	Authenticate with the current profile’s SSO session instead of access keys
session	Optional[Session]	None	boto3 Session object to use for authentication
async_session	Optional[Any]	None	aioboto3 Session object for async calls
client	Optional[AwsClient]	None	Pre-configured Bedrock runtime client
async_client	Optional[Any]	None	Pre-configured async Bedrock runtime client
model_type	ModelType	ModelType.MODEL	Functional role of this model (MODEL, OUTPUT_MODEL, PARSER_MODEL). Set by the agent
supports_native_structured_outputs	bool	False	Whether the model supports structured outputs natively
supports_json_schema_outputs	bool	False	Whether the model uses JSON schema for structured outputs
system_prompt	Optional[str]	None	System prompt from the model added to the agent
instructions	Optional[List[str]]	None	Instructions from the model added to the agent
tool_message_role	str	"tool"	Role of tool messages
assistant_message_role	str	"assistant"	Role of assistant messages
cache_response	bool	False	Cache model responses to avoid redundant API calls during development
cache_ttl	Optional[int]	None	Time-to-live for cached responses, in seconds
cache_dir	Optional[str]	None	Directory for the response cache. Defaults to ~/.agno/cache/model_responses
retries	int	0	Number of retries to attempt before raising a ModelProviderError
delay_between_retries	int	1	Delay between retries, in seconds
exponential_backoff	bool	False	If True, the delay between retries is doubled each time
retry_with_guidance	bool	True	Retry a failed model invocation once with a guidance message appended
retry_with_guidance_limit	int	1	Number of times to retry the model invocation with guidance