Google Gemini

Connect to Google Gemini AI for advanced language processing, multimodal capabilities, text embeddings, and intelligent content generation.

Triggers & Actions

Use Google Gemini as a trigger to kick off a workflow, or use it as an action to do something automatically in your workflow.

No triggers available

Generate Content

Generate content using Google Gemini models. Supports text, images, and multi-turn conversations.
Count Tokens

Count the number of tokens in the provided content. Useful for estimating costs and staying within model limits.
Embed Content

Generate text embeddings using Gemini embedding models. Useful for semantic search, clustering, and similarity comparisons.
Batch Embed Contents

Generate embeddings for multiple pieces of content in a single request. More efficient than multiple single requests.
List Models

List all available Gemini models and their capabilities.
Get Model

Get detailed information about a specific Gemini model.
Upload File

Upload a file to Google Gemini for use in content generation. Supports images, audio, video, and documents.
List Files

List all files uploaded to Google Gemini.
Get File

Get metadata about a specific uploaded file.
Delete File

Delete an uploaded file from Google Gemini.
Generate Image

Generate images using Gemini 2.0 Flash native image generation. Creates high-quality images from text prompts.
Generate Video (Veo 3)

Start video generation using Google Veo 3. Returns an operation ID immediately - use "Check Video Status" action to poll for completion.
Check Video Status

Check the status of a video generation operation. Use the operationName from "Generate Video" action. Returns video URL when complete.