AWS Bedrock LLM

Route Darcy's inference through your own AWS account using IAM credentials

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

Consider Bedrock Mantle instead. AWS Bedrock Mantle 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.

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

1

Create IAM credentials In your AWS account, create an access key pair with permission to invoke Bedrock models.

2

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.

3

Configure it in Darcy Go to Settings → Organization → Model Routing, choose AWS Bedrock, and enter your access key, secret key, and region.

4

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.

Model routing is limited to organization administrators and owners, and it lives under the Organization settings tab rather than the integrations directory.

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 — bring your own models with per-tier model selection

• Organization Management — the rest of your organization's settings