Skip to main content
Configure your Google Gemini integration to access advanced AI capabilities from your Jinba Flow workflows.

​
Prerequisites

  • A Google Cloud account
  • Access to Google AI Studio or Google Cloud Console

​
Getting Started with Gemini

  1. Visit Google AI Studio
  2. Sign in with your Google account
  3. Navigate to the “Get API key” section
  4. Click “Create API key”
  5. Copy your API key (starts with AIza)

​
Option 2: Google Cloud Console (For advanced users)

  1. Go to Google Cloud Console
  2. Create a new project or select an existing one
  3. Enable the Gemini API:
    • Go to “APIs & Services” > “Library”
    • Search for “Gemini API”
    • Click “Enable”
  4. Create credentials:
    • Go to “APIs & Services” > “Credentials”
    • Click “Create Credentials” > “API Key”
    • Copy your API key

​
API Key Security

  • Never share your API key publicly
  • Store it securely in environment variables
  • Use the key only in trusted applications
  • Monitor your usage in Google Cloud Console

​
Setting Up in Jinba Flow

  1. Go to your workspace settings in Jinba Flow
  2. Navigate to the “Secret” section
  3. Click “Create Secret” and choose the generic type OTHER (there is no Gemini-specific secret type)
  4. Enter a name and paste your Google AI Studio or Cloud Console API key
  5. Click “Save” to store your credentials

​
Available Models

Once configured, select the saved secret in the Google API Key field (token config) of GEMINI_INVOKE and the other Gemini tools. If you leave the field at its default, {{ secrets.JINBA_CREDIT_KEY }}, the step runs on Jinba Credits instead of your own key. Current model IDs for the version config include:
  • gemini-flash-latest (default)
  • gemini-3.8-flash
  • gemini-3.1-pro-preview
  • gemini-2.5-pro
The Gemini tools are GEMINI_INVOKE, GEMINI_INVOKE_WITH_FILE, GEMINI_INVOKE_WITH_IMAGE and GEMINI_GENERATE_IMAGE. See the Gemini tools page for the full model list and the tool inputs.

​
Usage Examples

Once configured, you can use Gemini in your flows to:
  • Generate creative content and text
  • Analyze and summarize documents
  • Answer questions based on context
  • Process and understand images
  • Create structured data from unstructured text
  • Translate content between languages