Google has made Gemini 2.5 Flash Image generally available for production use, giving developers powerful new tools for AI image creation and editing. This latest update supports 10 different aspect ratios, allowing users to create images in formats ranging from wide cinematic landscapes to vertical social media posts. It also supports image-only output, making it easier to get exactly the kind of visuals needed.
Gemini 2.5 Flash Image can blend multiple images smoothly, maintain character consistency for rich storytelling, and carry out detailed edits based on natural language commands. The AI leverages extensive world knowledge to generate or modify images accurately.
Developers are already using this technology in creative ways. For example, Cartwheel combines it with a 3D posing tool for precise character control, and the game creators at Volley use it to generate character portraits and dynamic scenes in real time during gameplay—all while enabling easy editing via chat or voice input.
The model is accessible through Google AI Studio, which provides a “build mode” for quickly creating AI-powered apps, and through Vertex AI for enterprise use. Examples of applications include animated GIF creation, photo upscaling with infinite zoom, and virtual fitting rooms for trying out outfits using AI.
Pricing for Gemini 2.5 Flash Image is set at $0.039 per image or $30.00 per million output tokens. Users can try it out now via the Gemini API, Google AI Studio, and Vertex AI, opening exciting possibilities for advanced and creative image generation and editing.
This update makes Gemini 2.5 Flash Image a versatile and efficient tool for developers looking to bring AI-powered visuals into their apps and projects.