Gemini 3.1 Flash-Lite Image (Nano Banana 2 Lite) is our fastest image generation model enabling rapid creation and iteration.
Try in Agent Studio Deploy example app
| Model ID | gemini-3.1-flash-lite-image |
|
|---|---|---|
| Modalities |
|
|
| Token limits | Maximum input tokens | 65,536 |
| Maximum output tokens | 4,096 | |
| Capabilities |
|
|
| Consumption options |
|
|
| See Consumption options for more information. | ||
| Input size limit | 500 MB | |
| Technical specifications | Images |
|
| Documents |
|
|
| Parameter defaults |
|
|
| Supported regions |
Model availability |
|
| See Deployments and endpoints for more information. | ||
| Knowledge cutoff date | January 2025 | |
| Versions |
|
|
| Security controls | Online prediction |
|
| Batch inference |
|
|
| Context caching |
|
|
| See Security controls for more information. | ||
| Pricing | See Pricing. | |
Image generation specifications
Gemini 3.1 Flash-Lite Image consumes 1120 input image tokens per input image. Gemini 3.1 Flash-Lite Image consumes 1120 output image tokens for 1K (roughly 1MP).
Videos are sampled at 1 frame per second, and each video frame accounts for 70 tokens. Audio in video files isn't used.
Additional charges for input and output tokens for other modalities such as text and video also apply. Refer to the pricing page for the latest.
For more information about image generation using Gemini 3.1 Flash-Lite Image, see Generate and edit images with Gemini.