Googleβs Gemini 3.7 Flash is available in Make AI apps for multimodal automation
Bring text, audio, images, code, and video into your AI workflows, then use text output to keep the next steps in your scenario moving.
Googleβs Gemini 3.7 Flash is now available in Make AI apps. Use its multimodal understanding, tool-use capabilities, and adjustable thinking levels in the workflows you build.
Whatβs New in Gemini 3.7 Flash
- Multimodal understanding with text output: Give Gemini 3.7 Flash text, audio, images, code, or video, and receive text output for the next module in your scenario.
- Function calling: Add model-driven function calls to workflows that need to take action based on a request or result.
- Search as a tool and computer use: Build workflows that use Search as a tool or computer use where those capabilities fit your process.
- Tunable thinking levels: Choose
low,medium, orhighthinking levels to match the task at hand.
Gemini 3.7 Flash Use Cases for Make Automation
- Review a customer-submitted image or video, return a text summary, and route that summary to your support or review workflow.
- Build a research workflow that uses Search as a tool to gather context before Gemini 3.7 Flash returns a text response.
- Create an agentic process that uses function calling or computer use when a task needs to take the next step beyond text analysis.
How to use Gemini 3.7 Flash in Make
Gemini 3.7 Flash is available in these Make native apps:
πππ€π ππ ππ¨π¨π₯π€π’π for quick setup
ππ¨π¨π π₯π πππ¦π’π§π’ ππ for structured prompts
πππ€π ππ ππ ππ§ππ¬ for agentic workflow automations
Try my starter scenario to see the latest Gemini AI models automated with Make: https://ma.ke/gemini-ai-demo
Gemini 3.7 Flash gives your Make AI workflows multimodal input, text output, tool-use capabilities, and control over thinking levels. Put those capabilities to work in the scenarios that need them.
Happy automating! 
Valery from Make
Helpful resources
π₯ App update: Gemini 3.6 Flash for high-volume AI Automation in Make