Google has introduced Gemini 2.5 Flash Image, also known internally as nano-banana, its most advanced model for AI-powered image generation and editing. Now available through the Gemini API, Google AI Studio, and Vertex AI, the new release builds on the speed and affordability of its predecessor while delivering higher-quality visuals and deeper creative control.
“When we first launched native image generation in Gemini 2.0 Flash earlier this year, you told us you loved its low latency, cost-effectiveness, and ease of use. But you also gave us feedback that you needed higher-quality images and more powerful creative control,” Google said in its announcement. With this upgrade, the company aims to meet those expectations.
Gemini 2.5 Flash Image introduces advanced features such as multi-image blending, character consistency across edits, and precise transformations — all powered by natural language prompts. Users can now go beyond simple generation to perform detailed edits like erasing stains, removing people, adjusting body poses, or even adding color to old black-and-white photos, all with a single instruction.
To highlight its capabilities, Google has launched template applications in AI Studio, including tools for photo retouching, brand asset design, and multi-image fusion. “We built a template app in Google AI Studio to demonstrate the model’s character consistency capabilities,” the company noted.
The model is priced at $30 per million output tokens (roughly $0.039 per image), making it accessible to a broad developer base. It also integrates with third-party platforms such as OpenRouter.ai and fal.ai, expanding its reach globally. Every generated or edited image will include Google’s SynthID invisible watermark for transparency and authenticity.
Currently in preview, Gemini 2.5 Flash Image is expected to roll out as a stable release soon. Reaffirming its vision, Google added: “We can’t wait to see what you build with Gemini 2.5 Flash Image.”
