Gemini 3.5 Flash provides sustained frontier-level intelligence optimized for real-world tasks at a higher speed and lower cost. Designed for the agentic era, it excels at sub-agent deployment, multi-step workflows, and long-horizon tasks at scale. This model is particularly effective for rapid agentic loops involving complex coding cycles and iterations.
Documentation
Visit the Gemini 3 Developer Guide page for full coverage of features and capabilities.
gemini-3.5-flash
| Property | Description |
|---|---|
| Model code | gemini-3.5-flash |
| Supported data types |
Inputs Text, Image, Video, Audio, and PDF Output Text |
| Token limits[*] |
Input token limit 1,048,576 Output token limit 65,536 |
| Capabilities |
Audio generation Not supported Batch API Supported Caching Supported Code execution Supported Computer use Not supported File search Supported Flex inference Supported Function calling Supported Grounding with Google Maps Supported Image generation Not supported Live API Not supported Priority inference Supported Search grounding Supported Structured outputs Supported Thinking Supported URL context Supported |
| Versions |
|
| Latest update | May 2026 |
| Knowledge cutoff | January 2025 |