> For the complete documentation index, see [llms.txt](https://docs.darcyiq.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.darcyiq.com/build/integration-overview/aws/aws-bedrock-integration.md).

# AWS Bedrock LLM

DarcyIQ supports using your organization's AWS Bedrock credentials, giving you control over your AI infrastructure and costs.

{% hint style="info" %}
**Consider Bedrock Mantle instead.** [AWS Bedrock Mantle](/build/integration-overview/aws/bedrock-mantle-integration.md) is the newer way to bring your own models. It uses a scoped Bedrock API key rather than long-lived IAM credentials, and it lets you choose which model powers each of Darcy's workload tiers. Only one routing option can be active at a time.
{% endhint %}

## Benefits

| Benefit             | Description                                                                              |
| ------------------- | ---------------------------------------------------------------------------------------- |
| **Cost Control**    | All LLM consumption happens on your AWS account, providing direct visibility and control |
| **Load Management** | Scale your AI workloads independently based on your organization's needs                 |
| **Security**        | Keep all AI processing within your AWS security boundary                                 |

## How It Works

{% stepper %}
{% step %}
**Create IAM credentials** In your AWS account, create an access key pair with permission to invoke Bedrock models.
{% endstep %}

{% step %}
**Enable model access** In the AWS Console, request access to the Anthropic Claude models under **Amazon Bedrock → Model access** in the region you plan to use.
{% endstep %}

{% step %}
**Configure it in Darcy** Go to **Settings → Organization → Model Routing**, choose **AWS Bedrock**, and enter your access key, secret key, and region.
{% endstep %}

{% step %}
**Save** Darcy begins routing inference through your account. If a call to your account fails, Darcy falls back to its own managed models so your work isn't interrupted.
{% endstep %}
{% endstepper %}

{% hint style="info" %}
Model routing is limited to organization administrators and owners, and it lives under the **Organization** settings tab rather than the integrations directory.
{% endhint %}

## Security Considerations

* All AI processing runs on your AWS infrastructure
* Data remains within your security boundary
* Compliance with your existing AWS security policies
* Full audit trail through AWS CloudTrail

## Related

* [AWS Bedrock Mantle](/build/integration-overview/aws/bedrock-mantle-integration.md) — bring your own models with per-tier model selection
* [Organization Management](/settings-and-configuration/organization-management.md) — the rest of your organization's settings


---

# 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.darcyiq.com/build/integration-overview/aws/aws-bedrock-integration.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.