Configure AI platforms and models in Retool AI

Learn how to use your own API keys for AI providers.

You can get started with Retool AI without needing any API credentials using the Retool-managed OpenAI connection. This enables you to evaluate and test AI queries before using them in production. When you're ready to use Retool AI in production, configure one of the supported platforms with your own API credentials.

Supported AI platforms

Retool supports a number of AI platforms and their models for which you can use.

Platform	Models
OpenAI	GPT-4o GPT-4 GPT 3.5 Turbo DALL·E
Anthropic	Claude 3 Claude 2.1 Claude 2 Claude Instant 1.2
Amazon Bedrock	Amazon Bedrock is a managed service that can be configured for different AI models, such as Anthropic or Cohere models. The models available for use with Retool AI depend on the models you configure for Bedrock.
Azure OpenAI	Rather than a predefined set of models from which you select, you create and deploy an Azure OpenAI service with a specific model. You then provide the endpoint and model name when configuring the API credentials.
Google	Gemini 1.5 Pro Gemini 1.0 Pro
Cohere	command command-light

Set up your AI platform credentials

To configure an AI platform with your API key, navigate to the Resources tab and select Retool AI. Select the AI model below for configuration instructions.

OpenAI

info

Configuring your own OpenAI API key disables the Retool-managed OpenAI connection. All existing AI Action queries using OpenAI automatically start using your connection.

To configure OpenAI with your API credentials:

1. Navigate to the Resources tab and select Retool AI.
2. Click Edit for the OpenAI platform.
3. Enter the required credentials.
4. Click Enable.

You can retrieve your OpenAI API key from the API Keys page in your OpenAI account.

Create separate API credentials for Retool

Where possible, create API credentials for each service you use to interact with your chosen AI platform. This allows you to best manage and revoke access without disruption. All API credentials used with Retool are encrypted and stored securely.

Anthropic

To configure Anthropic with your API credentials:

1. Navigate to the Resources tab and select Retool AI.
2. Click Edit for the Anthropic platform.
3. Enter the required credentials.
4. Click Enable.

You can retrieve your Anthropic API key from your Account settings.

Create separate API credentials for Retool

Where possible, create API credentials for each service you use to interact with your chosen AI platform. This allows you to best manage and revoke access without disruption. All API credentials used with Retool are encrypted and stored securely.

Amazon Bedrock

Amazon Bedrock requires the following credentials:

• AWS IAM access key ID.
• AWS IAM secret access key.
• AWS Region.

You can also provide an optional AWS IAM Session Token, if required.

To configure Amazon Bedrock with your API credentials:

1. Navigate to the Resources tab and select Retool AI.
2. Click Edit for the Amazon Bedrock platform.
3. Enter the required credentials.
4. Click Enable.

You can retrieve your Amazon Bedrock credentials from the AWS IAM dashboard.

Create separate API credentials for Retool

Where possible, create API credentials for each service you use to interact with your chosen AI platform. This allows you to best manage and revoke access without disruption. All API credentials used with Retool are encrypted and stored securely.

Azure OpenAI

Azure OpenAI requires the following credentials:

• API key.
• Azure endpoint URL.
• Deployment name (AI model).

To configure Azure OpenAI with your API credentials:

1. Navigate to the Resources tab and select Retool AI.
2. Click Edit for the Azure OpenAI platform.
3. Enter the required credentials.
4. Click Enable.

You can retrieve your Azure OpenAI credentials from the Azure Portal.

Create separate API credentials for Retool

Where possible, create API credentials for each service you use to interact with your chosen AI platform. This allows you to best manage and revoke access without disruption. All API credentials used with Retool are encrypted and stored securely.

When using Azure OpenAI, all AI Actions use the model specified in this configuration.

Google

To configure Google with your API credentials:

1. Navigate to the Resources tab and select Retool AI.
2. Click Edit for the Google platform.
3. Enter the required credentials.
4. Click Enable.

You can retrieve your Google API key from either the Google AI Studio dashboard.

Create separate API credentials for Retool

Where possible, create API credentials for each service you use to interact with your chosen AI platform. This allows you to best manage and revoke access without disruption. All API credentials used with Retool are encrypted and stored securely.

Cohere

To configure Cohere with your API credentials:

1. Navigate to the Resources tab and select Retool AI.
2. Click Edit for the Cohere platform.
3. Enter the required credentials.
4. Click Enable.

You can retrieve your Cohere API key from either the Cohere dashboard or CLI tool.

Create separate API credentials for Retool

Where possible, create API credentials for each service you use to interact with your chosen AI platform. This allows you to best manage and revoke access without disruption. All API credentials used with Retool are encrypted and stored securely.