Tech Desk 
Aug 28, 2025
Google has officially launched a new artificial intelligence (AI) image model, Gemini 2.5 Flash Image, calling it the company's best editing model to date.
The Mountain View-based tech giant revealed that Gemini 2.5 Flash Image enhances both the generation speed and element-based editing. Interestingly, the model went viral on the crowdsourced AI model ranking platform LMArena weeks before its official announcement.
Notably, in stealth mode, the model was named Nano Banana, and it has received praise from users for its high-quality image editing and consistent character.
Gemini 2.5 Flash Image provides improved editing capabilities
In a blog post, Google admitted that the Nano Banana AI model ranked first on LMArena and was, in fact, Google's Gemini 2.5 Flash Image.
According to the company, the new AI model can now maintain a higher character consistency while editing elements within the image.
Moreover, the Gemini 2.5 Flash Image receives a new image blending feature, which allows users to take two different images and ask the AI to blend them into a single image.
The success rate is mixed, and it largely depends on both the input images and the prompt.
Notably, end consumers can access the model in the Gemini app, developers can access it via the Gemini application programming interface (API), Google AI Studio, and Vertex AI (for enterprises). It is priced at $30 (roughly INR 2,600) per million output tokens, with each image consuming 1290 tokens.
