Google DeepMind Publishes Model Card for Nano Banana 2.1 Image Model
Summary
Google DeepMind published the model card for Nano Banana 2.1, an image generation and editing model in the Gemini 3 series, on 6 October 2026. The model, built on Gemini 3.6 Flash, accepts text and image inputs with a 1M token context window. October evaluations show its Thinking variant scoring 1050 in text-to-image preference and 1026 in general editing.
Key Points
- Google DeepMind publishes the model card for Nano Banana 2.1, an image generation and editing model in the Gemini 3 series, on 6 October 2026.
- Nano Banana 2.1 is based on Gemini 3.6 Flash, accepts text and image inputs with a 1M token context window, and outputs 4K token images and 64K token text.
- October 2026 evaluations show Nano Banana 2.1 Thinking scoring 1050 overall preference in text-to-image and 1026 in general editing, with image output available via the Gemini App, AI Studio, and API.