Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image 🍌) API
Nano Banana Lite is designed as the efficiency specialist of the image generation family, offering ultra-low latency and cost-effective image generation and editing. By targeting a sub-2 second latency and significantly reduced TPU compute costs, this model enables high-volume interactive developer use cases and real-time consumer applications.
- Context window: 65,536 tokens
- Max output: 32,768 tokens
- Input: text, image
- Output: image
- Reasoning: Supported
- File input: Supported
- Released: 2026-06-29
- Knowledge cutoff: 2024-12-31
Frequently Asked Questions
What is the context window of Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image 🍌)?
Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image 🍌) supports a context window of up to 65,536 tokens.
Does Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image 🍌) support reasoning?
Yes. Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image 🍌) is a reasoning-capable model.
What is the knowledge cutoff of Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image 🍌)?
The knowledge cutoff of Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image 🍌) is 2024-12-31.