Skip to main content
Connect your Gemini API key and describe the AI feature you need in chat. Rocket handles all the integration code automatically so you can focus on what your features should do.
This connector is only available for Next.js TypeScript web build tasks.

​
What you can do

Image analysis

Let users upload images and get detailed descriptions, alt text, or extracted information using Gemini’s vision capabilities.

Multimodal chat

Let users send both text and images in a conversation, with Gemini responding using context from both.

Content generator

Generate blog posts, product descriptions, social media copy, or marketing content from simple prompts.

Visual search

Let users search by uploading an image and finding similar items or related information.

Document OCR

Extract text, tables, and structured data from photos of documents, receipts, or handwritten notes.

​
Before you connect

Get your Gemini API key from Google AI Studio.
Never paste your API key directly into chat. Always use the secure connector flow. If you believe your key has been exposed, rotate it immediately from Google AI Studio.
The API key is scoped to the task you connect it in. Each task stores its own key. Connecting in one task does not affect others.

​
Connect Gemini

You can connect from two places. Both open the same popup.Option 1: From chatType a prompt that mentions Gemini, for example Connect Gemini and add an image upload that generates descriptions and alt text. Rocket detects the intent and shows a Connect button inline. Click it and the popup opens.
Gemini connection prompt in the Rocket chat panel.Gemini connection prompt in the Rocket chat panel.

Gemini connection prompt in chat

Option 2: From the Connectors tabClick the ... button in the preview toolbar, then select Connectors.
Toolbar dropdown with Connectors option highlighted.Toolbar dropdown with Connectors option highlighted.

Open Connectors from the toolbar

Click the Gemini card, then click Connect.
Connectors panel showing the Gemini card with a Connect button.Connectors panel showing the Gemini card with a Connect button.

Gemini card in the Connectors panel

After clicking ConnectA popup opens. Paste your API key and click Connect.
Connect Gemini popup with an API key input field.Connect Gemini popup with an API key input field.

Connect Gemini popup

A green dot appears next to Gemini when the connection is active.Update or disconnectGo to Connectors > Gemini. Click Edit to update the key or Disconnect to remove the integration.
Gemini card showing Edit and Disconnect buttons.Gemini card showing Edit and Disconnect buttons.

Edit and Disconnect options on a connected Gemini card

​
Example prompts

​
Tips

  • Best for multimodal tasks. If your app needs to understand images, screenshots, or documents alongside text, Gemini is the strongest choice among Rocket’s AI connectors.
  • Image size limits apply. Images passed inline must be under 20MB per request. For larger files, Rocket uses the Gemini Files API which supports up to 100MB.
  • API billing is separate from Rocket. Google charges based on token usage and input type. Image inputs consume more tokens than text. See Google AI pricing.
  • Key is scoped to this task. Each Rocket task connects to one Gemini API key.