n8n has three built-in nodes for Google Gemini: the Google Gemini app node, a normal workflow step for text, images, video, audio, documents and file search; the Google Gemini Chat Model sub-node, which gives an AI Agent its model; and Embeddings Google Gemini for vector stores. All three use one Gemini API key. Community nodes add other ways to call Gemini and a few extra features. This guide covers the built-in nodes (from n8n’s documentation) and the most used Gemini community packages (from our own npm data).
Which Gemini node do you need?
| You want to | Use |
|---|---|
| Message Gemini, analyze or generate images and video, transcribe audio, analyze documents, or run file search, as a workflow step | Google Gemini node (built in) |
| Give an AI Agent a Gemini model | Google Gemini Chat Model (built in, sub-node) |
| Create embeddings for a vector store | Embeddings Google Gemini (built in, sub-node) |
| A feature or setting the built-in nodes don’t offer | A community node (see below) |
Set up the Gemini credential
The credential is called Google Gemini(PaLM) and uses an API key. You need a Google Cloud account and a Google Cloud project. Then:
- Open the API key page in Google AI Studio and select Create API Key.
- Create it in a new project or pick an existing Google Cloud project.
- Copy the key into the n8n credential. Leave the Host at
https://generativelanguage.googleapis.com.
On n8n Cloud you can skip the credential: select Use Gateway credits in the credential field and the node runs without a Google account.
The Google Gemini node
- Audio: Analyze Audio, Transcribe a Recording
- Document: Analyze Document
- File Search: Create, Delete and List File Search Stores, Upload to File Search Store (for retrieval augmented generation)
- Image: Analyze Image, Generate an Image, Edit Image
- Media File: Upload Media File
- Text: Message a Model
- Video: Analyze Video, Generate a Video, Download Video
The Google Gemini Chat Model sub-node
Use it to give Gemini models to a conversational agent. n8n loads the Model list from the Gemini API, so you only see the models your account can use. Options: Maximum Number of Tokens, Sampling Temperature, Top K, Top P and Safety Settings, which map to Google’s adjustable Gemini safety filters.
A limitation from n8n’s docs: the node uses Google’s SDK, which doesn’t support proxy configuration.
Embeddings Google Gemini
Generates embeddings for text, for use with a vector store. Its one parameter is the embedding Model.
Gemini community nodes
Our Gemini hub lists 23 packages that pass our quality rule, with 3,001 npm downloads a week between them. The most downloaded Google Gemini packages, with the description each author gives on npm (weekly npm downloads as of 27 October 2026):
| Package | Weekly downloads | Author’s description |
|---|---|---|
| n8n-nodes-gemini-wolfhub | 1,684 | Google AI Studio nodes: text, transcription, music, speech, images and videos |
| n8n-nodes-gemini-search | 469 | Gemini API for search and content generation |
| @leolin310148/n8n-nodes-gemini-ai-studio | 156 | Gemini API via direct AI Studio REST calls |
| @fixtse/n8n-nodes-google-gemini-embeddings-extended | 102 | Gemini embeddings sub-node with output dimensions support |
| n8n-nodes-gemini-nano-banana-pro | 79 | Image generation with the Gemini API |
| @intrvls/n8n-nodes-google-gemini | 65 | Gemini Chat Model built on a port of the LangChain Google GenAI library to Google’s newer SDK |
| @prama13/n8n-nodes-advance-gemini | 63 | Gemini node with advanced image generation |
Note that not every package with “gemini” in its name is about Google Gemini: n8n-nodes-gemini, for example, describes itself as a Gemini Exchange node. Read each README to see what it connects to and which settings it adds compared with the built-in nodes, and check its node page here for the latest release and, where it has one, its GitHub repository for open issues.
How to choose
- Most Gemini work, including images, video, audio and file search: the built-in Google Gemini node, which already covers a wide set of operations.
- Gemini in an AI Agent: the built-in Google Gemini Chat Model.
- Embeddings with a set output dimension: the extended embeddings package.
- Something specific, such as music or speech generation: compare the community READMEs.
To install a package on a self-hosted instance, an owner or admin enters its npm name in Settings > Community Nodes; full steps are in How to Install n8n Community Nodes. On n8n Cloud only verified community nodes can be installed, see Verified vs Unverified n8n Community Nodes. Related: OpenAI in n8n, Claude in n8n and DeepSeek in n8n.
FAQ
Can I use Gemini in n8n without a Google account?
On n8n Cloud, yes: select Use Gateway credits in the credential field. Self-hosted n8n needs a Gemini API key from Google AI Studio.
Can the n8n Gemini node generate images and videos?
Yes. The Google Gemini node has Generate an Image, Edit Image and Generate a Video operations, plus Download Video.
Does the Gemini Chat Model work behind a proxy?
Not directly. n8n’s docs say the node uses Google’s SDK, which doesn’t support proxy configuration.
What is the most used Gemini community node?
n8n-nodes-gemini-wolfhub, with 1,684 weekly npm downloads on 27 October 2026.
