Google Gemini
App · AI Models · 2 actions
Generate text and images with Google's Gemini AI models.
Generate image
Generate an image from a text prompt.
Inputs
- Prompt
prompttextRequired - The text prompt describing the image to generate
- Model
modeltext - Which model to use. Defaults to gemini-3.1-flash-image.One of:
gemini-3.1-flash-image(Nano Banana 2 (highest quality)),gemini-3.1-flash-lite-image(Nano Banana Lite (fastest, cheapest)),gemini-3-pro-image(Nano Banana Pro). Default:gemini-3.1-flash-image.
Outputs
image_countnumber- Number of images generated
imageslist- Base64-encoded generated images
Example output
{
"image_count": 1,
"images": [
"base64encodedimagedata..."
]
}Generate text response
Generate a text response using a Gemini model.
Inputs
- Prompt
prompttextRequired - The text prompt to send to the model
- Model
modeltext - Which Gemini model to use. Defaults to gemini-3.5-flash.One of:
gemini-3.5-flash(Gemini 3.5 Flash),gemini-3.1-flash-lite(Gemini 3.1 Flash-Lite (faster, lower cost)). Default:gemini-3.5-flash.
Outputs
response_texttext- The generated text response
Example output
{
"response_text": "This is a sample generated response."
}