Gemini 3.7 Flash is our intelligent everyday driver for developers, and delivers a step forward in software engineering, feeling distinctly better to build with. This model brings better intelligence for complex tasks, instruction following, and tool calling into your daily workflows.
3.7 Flash serves as the primary agentic workhorse in the Gemini 3 family, bridging the gap between deep-reasoning Pro models and high-throughput Flash-Lite models while delivering high token efficiency and multi-step multimodal processing.
Try in Agent Studio Deploy example app Developer guide Pricing
| Model ID | gemini-3.7-flash |
|
|---|---|---|
| Modalities |
Input and output Input only Input only Input only |
|
| Token limits | Context window | 1,048,576 |
| Maximum output tokens | 65,536 | |
| Capabilities |
|
|
| Tools |
|
|
| Consumption options |
|
|
| Technical specifications | Image photo |
|
| Text description |
|
|
| Video videocam |
|
|
| Audio mic |
|
|
| Parameter defaults tune |
|
|
| Supported regions |
|
|
|
||
|
||
|
||
| Versions |
|
|
| Security controls | Online prediction |
|
| Batch inference |
|
|
| Context caching |
|
|
| See Security controls for more information. | ||