Skip to main content

Connect to Amazon Bedrock

Connect to Amazon Bedrock and use their models for AI-powered apps and automations in Retool.

Amazon Bedrock is a fully managed service that provides access to advanced AI models from leading AI companies. You can create an Amazon Bedrock resource so you can build AI-powered apps and workflows that leverage multiple AI models through a single service.

What you can do with Amazon Bedrock in Retool​

After you create an Amazon Bedrock resource in Retool, you can:

  • Generate, summarize, classify, and extract information from text using foundation models from multiple AI providers.
  • Build conversational, multi-turn chat experiences with context-aware responses.
  • Analyze images to generate captions, extract entities, or answer questions about visual content.
  • Access models from Anthropic, Meta, Cohere, Mistral, Amazon, and AI21 through a single AWS service.

Supported models​

Amazon Bedrock resources require you to bring your own key for authentication. Retool-managed keys aren't available for Amazon Bedrock.

The following models are available with your own API key:

ModelResource queriesAgent supportAssist support
Amazon Bedrock Model
Claude Haiku 4.5
Claude Opus 4.1
Claude Opus 4.5
Claude Opus 4.6
Claude Opus 4.7
Claude Opus 4.8
Claude Sonnet 4
Claude Sonnet 4.5
Claude Sonnet 4.6
Claude Sonnet 5

Amazon Bedrock also provides access to foundation models from multiple AI providers through a single API. You can use any foundation model you have enabled in your AWS Bedrock console, including:

  • All Llama models (Meta).
  • All Command models (Cohere).
  • All Mistral models.
  • All Amazon Nova and Titan models.
  • All AI21 Jamba models.
  • Regional model variants.

Available models depend on which foundation models you've enabled in your AWS Bedrock console and your AWS region. Specify the model ID in your queries (e.g., us.anthropic.claude-sonnet-4-5-20250929-v1:0, us.amazon.nova-pro-v1:0). Refer to AWS Bedrock model access documentation for details on enabling models and finding model IDs.

Before you begin​

Before creating an Amazon Bedrock resource, you need:

  • Retool permissions: Ability to create and manage resources in your Retool organization.
  • AWS account: An AWS account with Amazon Bedrock enabled.
  • IAM credentials: AWS IAM access credentials with permissions to invoke Bedrock models.
  • Model access: Enabled access to foundation models in your AWS Bedrock console.

Create an Amazon Bedrock resource​

Create a resource to connect Retool to Amazon Bedrock and configure authentication. Once connected, you can then select it when writing queries to make use of its available models.

Follow these steps to create an Amazon Bedrock resource in Retool.

Create a new resource​

Navigate to Resources in the main navigation and click Create new > Resource. Search for Amazon Bedrock. Then, click the Amazon Bedrock tile to create a new resource.

Configure connection settings​

Specify a name for the resource that identifies it within your organization. Include a description that can provide more context to users and Assist about how to use the resource.

Configure authentication​

Bring your own key only

This resource requires you to provide your own API key. Retool-managed keys are not available for Amazon Bedrock.

Amazon Bedrock resources require AWS IAM credentials for authentication.

  1. Access Key ID: Your AWS IAM access key ID.
  2. Secret Access Key: Your AWS IAM secret access key.
  3. Session Token (optional): Temporary session token if using temporary credentials or assumed roles.
  4. Region: The AWS region where your Bedrock models are configured (e.g., us-east-1, us-west-2).

Retrieve your AWS credentials from the IAM Console. Ensure the IAM user or role has permissions to invoke Bedrock models.

Amazon Bedrock resource configuration
Amazon Bedrock resource configuration
Create dedicated IAM credentials for Retool

Create dedicated IAM credentials for Retool with minimal required permissions. All credentials used with Retool are encrypted and stored securely.

Recommended IAM policy:

{
  "Version": "2012-10-17",
  "Statement": [
    {
      "Effect": "Allow",
      "Action": [
        "bedrock:InvokeModel",
        "bedrock:InvokeModelWithResponseStream"
      ],
      "Resource": "*"
    }
  ]
}

Save the resource​

Click Create resource to save your Amazon Bedrock resource. The resource is now available for use in apps and workflows.

Note

AI resources do not have a Test connection button. To verify your configuration, create a new app and ask the agent to test the resource for you.

Interact with Amazon Bedrock data​

Once you've created an Amazon Bedrock resource, you can interact with foundation models using Retool.

Switch to the new app builder

Retool recommends using the new app builder so you can use natural language to build React-based apps using AI.

  • To use Amazon Bedrock models in the app builder, reference the resource in the prompt with @, such as @Amazon Bedrock. Refer to the data and functions documentation to learn more.
  • For classic apps, workflows, and agents, refer to the AI queries documentation to learn how to write a resource query.

Best practices​

Follow these best practices to keep your Amazon Bedrock usage secure and cost-efficient.

Security​

  • Create dedicated IAM credentials for Retool: Use IAM credentials scoped to only the bedrock:InvokeModel and bedrock:InvokeModelWithResponseStream actions, so you can revoke or rotate access without disrupting other integrations.
  • Rotate credentials regularly: Roll your AWS access keys periodically from the IAM Console, and immediately if a key is ever exposed.
  • Use resource environments: Organizations on an Enterprise plan can configure multiple resource environments to maintain separate AWS credentials for production, staging, and development.

Manage token usage and cost​

  • Choose the smallest capable model: Use a faster, cheaper model (e.g. Claude Haiku) for simple tasks like classification or extraction, and reserve larger models for tasks that need deeper reasoning.
  • Set output token limits: Configure a maximum output token limit appropriate to the task to avoid paying for unnecessarily long responses.
  • Trim conversation history: For chat use cases, truncate or summarize older messages instead of sending the full history on every request. Bedrock bills for all input tokens, including message history.
  • Monitor usage: Track token consumption and spend in the AWS Cost Explorer to catch unexpected usage spikes early.