Gemini 3 Pro Image (Nano Banana Pro)

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 Platform View in Model Garden (Preview) Deploy example app

Note: To use the "Deploy example app" feature, you need a Google Cloud project with billing and Agent Platform API enabled.

Model ID gemini-3-pro-image Supported inputs & outputs

Inputs:
Text, Images
Outputs:
Text and image

Token limits

Maximum input tokens: 65,536

Maximum output tokens: 32,768

Capabilities

Supported

Not supported

Consumption options

Supported

Not supported

Priority PayGo

See Consumption options for more information. Input size limit 500 MB Technical specifications Images

Maximum images per prompt: 14
Maximum file size per file for inline data or direct uploads through the console: 7 MB
Maximum file size per file from Google Cloud Storage: 30 MB
Maximum number of output images per prompt: Limited to 32,768 output tokens
Supported aspect ratios: 1:1, 3:2, 2:3, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9, 9:16
Supported resolutions: 1K, 2K, 4K (Preview)
Supported MIME types:
image/png, image/jpeg, image/webp, image/heic, image/heif

Documents

Maximum number of files per prompt: As supported by the 65,536 token context window
Maximum number of pages per file: As supported by the 65,536 token context window
Maximum file size per file: 50 MB (API and Cloud Storage imports) or 7 MB (direct upload through Google Cloud console)
Supported MIME types:
application/pdf, text/plain

Parameter defaults

Temperature: 0.0-2.0
topP: 0.0-1.0 (default 0.95)
topK: 64 (fixed)
candidateCount: 1

Supported regions

Model availability

Global

global

See Deployments and endpoints for more information. Knowledge cutoff date January 2025 Versions

gemini-3-pro-image

Launch stage: GA
Release date: May 28, 2026

Security controls Online prediction

Data residency
CMEK
VPC-SC
AXT

Batch inference

Data residency
CMEK
VPC-SC
AXT

See Security controls for more information. Supported languages See Supported languages. Pricing See Pricing.

Image generation specifications

Gemini 3 Pro Image consumes 560 input image tokens per input image. Gemini 3 Pro Image consumes 1120 tokens for 1K (roughly 1MP) and 2K (roughly 4MP), and 2000 tokens for 4K (roughly 16MP). 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 Pro Image, see Generate and edit images with Gemini.

Preview features

Preview

This product or feature is a Generative AI Preview offering, subject to the "Pre-GA Offerings Terms" of the Google Cloud Service Specific Terms, as well as the Additional Terms for Generative AI Preview Products. For this Generative AI Preview offering, Customers may elect to use it for production or commercial purposes, or disclose Generated Output to third-parties, and may process personal data as outlined in the Cloud Data Processing Addendum, subject to the obligations and restrictions described in the agreement under which you access Google Cloud. Pre-GA products are available "as is" and might have limited support. For more information, see the launch stage descriptions.

The following features remain in Preview on this GA endpoint:

4K image outputs

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2026-06-10 UTC.