Google: Nano Banana 2.1 (Gemini Nano Banana 2.1) is an upgraded multi-modal inference image model designed for production-level image generation and editing. It features greater prompt following capabilities, multi-reference editing capabilities, and higher visual fidelity. The model understands text, image, video, and PDF inputs, supports alternate generation of text and images, and can reason about complex spatial and compositional instructions before generating images. Additionally, the model supports basic validation through Google Search and Google Image Search, enabling better long-tail entity recognition, visual understanding, and output accuracy.
This model has not been released yet — pricing and providers will appear once it is live.
Related models
More models from Google
Google: Nano Banana 2 Lite (Gemini 3.1 Flash-Lite Image)66K contextfrom $0.2125 / M tokens2 providersGoogle: Nano Banana 2 Lite (Gemini 3.1 Flash-Lite Image) is Google's fastest and most cost-effective Gemini image model, built for high-frequency development pipelines and rapid visual exploration. It can complete text-to-image generation in about 5 seconds, which is about 2.7 times faster than Gemini 3.1 Flash Image, while maintaining the character consistency, precise editing capabilities and real-world knowledge of the Nano Banana series. A single embedded API handles text-to-image, image editing, and multi-image composition. As a multi-modal model, it can also generate text while returning images. Output resolution is 1K, supports 14 aspect ratios, and comes with an invisible SynthID watermark for easy identification as AI-generated. The best balance of quality and speed in the Nano Banana 2 series, it generates thousands of images at a fraction of the cost of heavyweight production models, making it ideal for prototyping, real-time applications and large-scale visual workflows.
Google: Nano Banana 2 (Gemini 3.1 Flash Image)66K contextfrom $0.425 / M tokens2 providersGoogle: Nano Banana 2 (Gemini 3.1 Flash Image) is designed for speed and efficiency, enabling fast, interactive responses and high throughput.
Google: Nano Banana Pro (Gemini 3 Pro Image)66K contextfrom $1.7 / M tokens2 providersGoogle: Nano Banana Pro (Gemini 3 Pro Image) is an AI image generation model based on Google Gemini 3 Pro, and is a major upgrade of its previous products. It aims to go beyond simple pattern matching, turn to a more rationally driven system, and make improvements in terms of physical understanding, text rendering, and image consistency. Its main features include faster processing speed, native 2K resolution, and the ability to edit existing images with higher precision, aiming to provide more reliable, professional-level generated results.