Nano Banana 2 provides high-quality image generation and conversational editing at a mainstream price point and low latency. It serves as the high-efficiency counterpart to Gemini 3 Pro Image, optimized for speed and high-volume developer use cases.
Key updates:
- New output resolution options:
- New support for 0.5K, 2K and 4K, default 1K
- New Image Search Grounding:
- Integration of both text and image search results to inform generation with real-time web data
- Supported with Thinking on or off
- New 1:4, 4:1, 1:8 and 8:1 aspect ratios
- Improved aspect ratio adherence
- Improved image quality and consistency
- Improved i18n text rendering
Documentation
Visit the Image generation page for full coverage of features and capabilities.
gemini-3.1-flash-image
| Property | Description |
|---|---|
| Model code | gemini-3.1-flash-image |
| Supported data types | Inputs Text, Image, Video, and PDF Output Image and Text |
| Token limits[1](https://ai.google.dev/gemini-api/docs/tokens)^ | Input token limit 131,072 Output token limit 32,768 |
| Capabilities | Audio generation Not supported Caching Not supported Code execution Not supported File search Not supported Function calling Not supported Grounding with Google Maps Not supported Image generation Supported Live API Not supported Search grounding Supported Structured outputs Not supported Thinking Supported URL context Not supported |
| Consumption options | Batch API Supported Flex inference Not supported Priority inference Not supported |
| Versions | Read the model version patterns for more details. - Stable: gemini-3.1-flash-image |
| Latest update | February 2026 |
| Model card | Model card |
[*] ↩︎