Model provider · Bring your own keyGoogle Gemini in a visual AI workflow
Run Google's Gemini models in NodeTool — long-context multimodal chat with image and audio understanding, called with your own Gemini API key.
Google's Gemini models handle text, images, and audio in a single long-context window, which makes them a strong fit for document understanding, multimodal extraction, and agents. In NodeTool, Gemini is available on chat, agent, and LLM nodes.
Gemini is bring-your-own-key: set `GEMINI_API_KEY` and NodeTool calls Google directly at list price. Related Google media models (Imagen, Veo) are also reachable through the media aggregators NodeTool integrates.
Calls go straight to Google Gemini with your key at their list price — NodeTool never proxies or marks up the request.
What Google Gemini does in NodeTool
Featured Google Gemini models
NodeTool queries Google Gemini for the exact models your key can access and exposes each as a node. These are the families you can build with.
Google's most capable multimodal model for complex tasks.
Fast, cost-efficient multimodal model for high volume.
Google's image generation model (via media providers).
Google's text-to-video model (via media providers).
Frequently asked
- How do I use Gemini in NodeTool?
- Add your `GEMINI_API_KEY` in settings and select a Gemini model on any chat or agent node. NodeTool calls Google's API directly.
- Can Gemini read images and audio in NodeTool?
- Yes — Gemini is multimodal, so you can wire images or audio into a Gemini node and prompt over them in one long-context call.
- What does Gemini cost in NodeTool?
- Google's list price. NodeTool is bring-your-own-key with no added fee.
Other providers
Run Google Gemini your way.
Download NodeTool Studio and build across image, video, audio, and text with your own keys.