Google unveils Nano Banana Pro, its most advanced image-generation model
What's the story
Google has introduced its new image-generation model, Nano Banana Pro, an upgrade to the earlier Nano Banana and powered by the company's latest LLM, Gemini 3. The company says the Pro version delivers more detailed visuals, handles text more accurately, and can generate writing in a variety of styles, fonts, and languages.
Enhanced functionality
Advanced features and capabilities
The new model also adds web-search capabilities, enabling users to look up information and create flash cards. It gives professionals greater control over their visuals, with options to fine-tune camera angles, lighting, depth of field, focus, and color grading. And unlike the previous model's 1024×1024 pixels limit, Nano Banana Pro can produce high-resolution images at 2K and even 4K.
Cost comparison
Performance and pricing
While the new model can generate higher quality images, it is slower and more expensive than its predecessor. The original model cost $0.039 per 1024p image, while Nano Banana Pro costs $0.139 for each 1080p or 2K image and $0.24 for every 4K image. The new model can use six high-fidelity shots or blend up to 14 objects within an image while maintaining consistency and resemblance of up to five people.
User access
Integration and accessibility
Google is rolling out Nano Banana Pro across its existing AI tools. The Gemini app will now default to the new model for image generation, though free-tier users will have limited use before it switches back to the earlier version. Subscribers to Google AI Plus, Pro, and Ultra will receive higher generation limits and full access through NotebookLM.
Developer integration
Availability and developer access
Google is also making the model available in search through AI mode for AI Pro and Ultra subscribers in the US. Ultra subscribers can access it in Flow, Google's video tool. Developers can use Nano Banana Pro via the Gemini API, Google AI Studio, and Antigravity, a new IDE from Google.