Google: Nano Banana Pro (Gemini 3 Pro Image Preview)

Text input Image input Text output Image output
Author's Description

Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...

Key Specifications
Cost
$$$$$
Context
65K
Released
Nov 20, 2025
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Seed Structured Outputs Top P Response Format Reasoning Temperature Stop Include Reasoning Max Tokens
Features

This model supports the following features:

Structured Outputs Response Format Reasoning
Performance Summary

Google's Nano Banana Pro (Gemini 3 Pro Image Preview) demonstrates exceptional performance across several key metrics. The model consistently ranks among the fastest available, indicating highly efficient processing for its advanced capabilities. Furthermore, it offers highly competitive pricing, making it an attractive option for a wide range of users. Reliability is a significant strength, with the model achieving a 100% success rate in benchmarks, signifying minimal technical failures and consistent operational stability. In terms of benchmark results, the model exhibited a 0.0% accuracy on the "Hallucinations (Baseline)" test, which specifically measures the model's ability to acknowledge uncertainty by selecting "I don't know" for fictional concepts. This result suggests that Nano Banana Pro currently struggles with identifying and deferring on entirely fabricated information, instead attempting to generate content or answers. Key strengths include its industry-leading text rendering, consistent multi-image blending, accurate identity preservation for multiple subjects, and fine-grained creative controls. Its ability to generate context-rich graphics, incorporate real-time information via Search grounding, and support high-resolution outputs (2K/4K) positions it as a powerful tool for professional-grade design and complex compositions. The primary weakness identified is its current inability to effectively acknowledge uncertainty regarding fictional concepts, leading to potential hallucination in such scenarios.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $2
Completion $12
Image Generation $0.002 per 1K images
Input Cache Read $0.2
Input Cache Write $0.375
Internal Reasoning $12

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Google
Google | google/gemini-3-pro-image-preview-20251120 65K $2 / 1M tokens $12 / 1M tokens
Google AI Studio
Google AI Studio | google/gemini-3-pro-image-preview-20251120 65K $2 / 1M tokens $12 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by google