AWS Bedrock Cloud

Use AWS-hosted foundation models (e.g., Claude, Titan, etc.) with your own AWS credentials

Description

The AWS Bedrock component allows you to integrate foundation models hosted by AWS (such as Anthropic Claude, Amazon Titan, AI21, and others) into your flows using your own AWS credentials. You can choose a specific model and construct dynamic prompts using data from other nodes in your automation.

The interface will adapt based on the selected model and available configuration options. This component supports both text-based and conversational interactions, depending on the model.

The AWS Bedrock component has the identifier bedrock-X, where X represents the instance number in your flow.

Inputs

The AWS Bedrock Cloud component has the following input connections.

Input Name	Description	Constraints
From Input	The user’s input message or query that will be processed by the Bedrock model.	Must come from a text-producing component such as Trigger, Form, or Input.

Component settings

Parameter Name	Description
Credentials	Use your own AWS credentials with access to Bedrock (access key & secret key).
Model	Select the desired foundation model (e.g., anthropic.claude-sonnet-4-20250514).
Prompt	Customize how the model should respond. You can reference values from other components using @, and structure the prompt using dynamic variables.

Advanced configurations

Options	Description
Enable caching	When enabled, stores the result of this component to be reused if input hasn't changed.
Caching time	Set how long the result should be cached (e.g., 1m, 5m, 10m, etc.).

Outputs

The AWS Bedrock component has the following output connections.

Output Name	Description	Constraints
To Output	Contains the response generated by the AWS Bedrock model.	Can be passed to any downstream component that accepts text.