Google Launches Nano Banana 2.1, New Image Model at Nearly Half the Cost
In Short
Google has launched Nano Banana 2.1, a new image generation and editing model belonging to the Gemini 3 family. According to Google, it is more capable and cost-effective than its predecessor, offering improved image quality, superior editing capabilities, and lower costs for developers.
Share :
Google Launches Nano Banana 2.1, New Image Model at Nearly Half the Cost
Google has released Nano Banana 2.1, its latest AI model for image generation and editing. The company claims the new model can create better-looking images, follow instructions more precisely, and handle image edits better than its predecessor. There is also the matter of cost: according to Google, Nano Banana 2.1 can generate images at nearly half the price of the previous model.
Nano Banana 2.1 is based on Google’s Gemini 3.6 Flash model and is being rolled out across the company’s products, including the Gemini app, Google AI Studio, the Gemini API, Google Search’s AI mode, Google Ads, Flow, and Stitch.
So, what’s new in Nano Banana 2.1?
Like earlier versions, Nano Banana 2.1 lets users create images simply by describing what they want in a text prompt. Google says the new model is better at understanding detailed instructions and keeping important elements consistent when making changes to an image.
Users can also add multiple reference images and ask the model to bring them together in a new image. Nano Banana 2.1 supports up to 14 reference images at the same time and can keep up to four characters and 10 objects consistent. This could be useful for people creating a set of images where the same person, product or object needs to look the same across different scenes.
The model can also edit existing images based on simple text instructions. Users can change a person’s clothes, replace or edit the background, add or remove objects, or give the image a different look and style. These changes can be made without starting the image creation process all over again.
Google says that Nano Banana 2.1 also makes AI-generated images handle text better. This means it should give results when making posters, diagrams, infographics and other visuals where reading the text clearly matters. It works with image generation in 1K, 2K and 4K resolutions. Users can pick levels of AI reasoning based on how much processing power they want to use.
Another notable novelty is the integration with Google Search (Search grounding). Nano Banana 2.1 may use information from Google Search and Google Image Search when generating an image. This feature is useful when users want to create images based on real-world information.
Price per image of Nano Banana 2.1
However, the most significant change might be the price. A 1K image generated through the API now costs around $0.0336, up from $0.067 previously. A 4K image costs about $0.0756, compared to $0.151 previously. In other words, developers can generate images for about half the previous cost.
For developers and companies that generate large volumes of images, that price difference can mean considerable savings in a short time. Therefore, Nano Banana 2.1 is not just an update to Google's imaging model; It also makes generating large-scale images much more economical.
The model is currently being deployed in Google products, giving both developers and regular users access to its new image generation and editing features.
