Skip to main content

Configure AI platforms and models in Retool AI

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

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

PlatformModels
OpenAIGPT-4
GPT 3.5 Turbo
DALL·E
AnthropicClaude 3
Claude 2.1
Claude 2
Claude Instant 1.2
AWS BedrockAmazon 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 OpenAIRather 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.
GoogleGemini 1.5 Pro
Gemini 1.0 Pro
Coherecommand
command-light

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.

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.