Overview
- Built on Gemini 3.1 Flash, the new model brings web-informed visuals and stronger in-image text rendering, including translation and localization, to the mainstream tier.
- Google says outputs are faster with higher detail and richer textures, and the model can keep up to five characters and 14 objects consistent across iterations at up to 4K.
- The release is live now in the Gemini app, where it replaces Nano Banana Pro in many modes, though Pro and Ultra subscribers can still access Pro for maximum fidelity tasks.
- Integration spans the Gemini API, AI Studio (preview), Vertex AI, Google Ads, Flow (as the default image model), Google Lens, and the AI mode of Google Search.
- API image generation is cheaper, with a 4K image priced at about $0.15 versus $0.24 on the Pro model, a reduction of roughly 40 percent.