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. | ||
† Listed retirement dates refer to retirement of support in Gemini Enterprise Agent Platform. Models may remain accessible through the Gemini API after these dates have passed. The Gemini API is not a Google Cloud offering and is subject to its own terms of service. For details, see the Gemini API documentation.
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.