Back to models
Google DeepMindactive

Nano Banana 2

State-of-the-art image generation and editing model (Gemini 3.1 Flash Image) combining Pro-level quality, advanced world knowledge, real-time web search grounding, subject consistency, and precise text rendering with Flash-level speed.

Input / 1M tokens

N/A

Output / 1M tokens

N/A

Context window

N/A

Capabilities

  • Image Generation
  • Image Editing
  • Real-time Web Knowledge Integration
  • Subject Consistency
  • Accurate Text Rendering
  • Multi-Resolution Output (up to 4K)
  • Reference Image Support (up to 14)