Gemini 3 Pro Image (Nano Banana Pro), is designed to tackle the most challenging image generation by incorporating state-of-the-art reasoning capabilities. It's the best model for complex and multi-turn image generation and editing, having improved accuracy and enhanced image quality.
Try in Agent Studio View in Model Garden Deploy example app Pricing
| Model ID | gemini-3-pro-image |
|
|---|---|---|
| Modalities |
|
|
| Token limits | Context window | 65,536 |
| Maximum output tokens | 32,768 | |
| Capabilities |
|
|
| Tools |
|
|
| Consumption options |
|
|
| Input size limit | 500 MB | |
| Technical specifications | Image |
|
| Text |
|
|
| Parameter defaults |
|
|
| Supported regions |
|
|
| Versions |
|
|
| Security controls | Online prediction |
|
| Batch inference |
|
|
| Context caching |
|
|
| See Security controls for more information. | ||
Image generation specifications
Gemini 3 Pro Image consumes 560 tokens per input image.
Output image token consumption varies based on the generated image resolution:
| Output resolution | Approximate megapixels | Output image tokens |
|---|---|---|
| 1K | 1 | 1,120 |
| 2K | 4 | 1,120 |
| 4K | 16 | 2,000 |
For more information about image generation using Gemini 3 Pro Image, see Generate and edit images with Gemini.