The new Nano Banana Pro is built on Google's latest major speech model, Gemini 3 , which was released earlier this week. The company claims that the Nano Banana Pro outperforms its predecessor by producing more detailed images and more accurate text, as well as generating text in a variety of styles, fonts, and languages. The model also has web search capabilities.
The new Nano Banana Pro is built on Google's latest major speech model, Gemini 3 , which was released earlier this week. The company claims that the Nano Banana Pro outperforms its predecessor by producing more detailed images and more accurate text, as well as generating text in a variety of styles, fonts, and languages. The model also has web search capabilities.
Google says the Nano Banana Pro is aimed at giving professionals more control over their images, allowing users to adjust aspects such as shooting angles, scene lighting, depth of field, focus, and color correction. Additionally, unlike the Nano Banana's resolution limit of 1024×1024 pixels, Nano Banana Pro users can generate images in 2K or 4K.
The company noted that while the Nano Banana Pro can generate higher-quality images, it is slower and more expensive than the original model, which cost $0.039 per 1024-pixel image. By comparison, the new model costs $0.139 per 1080p or 2K image, and $0.24 per 4K image.
The new model can use six high-definition frames or blend up to 14 objects within a single image. It can also maintain consistency and similarity for up to five people. The company has released a demo app where you can try out some of these features.
Nano Banana Pro is gradually being rolled out across many of Google’s existing AI tools. The Gemini app will now use the new model to generate images by default, although free users will be able to generate a limited number of images using this model, after which they will be automatically redirected to the original Nano Banana model.
Google AI Plus, Pro, and Ultra subscribers will get higher generation limits, although the company didn't disclose the exact limits. These subscribers will also get access to the model within the Notebook LM service.
Google is also making the model searchable through AI mode for AI Pro and Ultra subscribers in the U.S. Ultra subscribers can access the model in the company’s Flow video tool, and it’s also available to Workspace enterprise customers in Google Slides and Vids.
Developers can use Nano Banana Pro through the Gemini API, Google AI Studio, and the company's new IDE, Antigravity.
The company is also embedding SynthID, its proprietary technology for watermarking and detecting AI-generated images, into the Gemini app. Users can upload an image and a chatbot will tell them whether the image was created or altered using the company’s image models.
