> For the complete documentation index, see [llms.txt](https://docs.diaflow.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.diaflow.io/workflow-builder/nodes/public-ai-llm-models/aws-bedrock-cloud.md).

# AWS Bedrock Cloud

<figure><img src="/files/fHFB5vAGLbWktttGmSeZ" alt=""><figcaption></figcaption></figure>

## **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

<table><thead><tr><th width="190.4296875">Parameter Name</th><th>Description</th></tr></thead><tbody><tr><td>Credentials</td><td>Use your own AWS credentials with access to Bedrock (access key &#x26; secret key).</td></tr><tr><td>Model</td><td></td></tr><tr><td>Prompt</td><td>Customize how the model should respond. You can reference values from other components using <code>@</code>, and structure the prompt using dynamic variables.</td></tr></tbody></table>

| Select the desired foundation model (e.g., `anthropic.claude-sonnet-4-20250514`). |
| --------------------------------------------------------------------------------- |

## Advanced configurations

<table><thead><tr><th width="188.21484375">Options</th><th>Description</th></tr></thead><tbody><tr><td>Enable caching</td><td>When enabled, stores the result of this component to be reused if input hasn't changed.</td></tr><tr><td>Caching time</td><td>Set how long the result should be cached (e.g., 1m, 5m, 10m, etc.).</td></tr></tbody></table>

## Outputs

The AWS Bedrock component has the following output connections.

<table><thead><tr><th width="188.21484375">Output Name</th><th>Description</th><th>Constraints</th></tr></thead><tbody><tr><td>To Output</td><td>Contains the response generated by the AWS Bedrock model.</td><td>Can be passed to any downstream component that accepts text.</td></tr></tbody></table>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.diaflow.io/workflow-builder/nodes/public-ai-llm-models/aws-bedrock-cloud.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.