Back to Models
Google: Nano Banana 2 (Gemini 3.1 Flash Image)
Googleimage8.9 / 10 Overall Rating
Developed by Google, Gemini 3.1 Flash Image (Nano Banana 2) provides integrated text and image generation with editing capabilities within a 131K token context window. Operating at $0.50 per million input tokens and $3.00 per million output tokens, it delivers fast multimodal visual synthesis. It serves as a cost-effective solution for workflows requiring combined visual creation and prompt processing.
Context Window
131K
Knowledge Cutoff
2025
Max Output
16K
License
Proprietary
Where it Excels (Pros)
- Native image generation and editing
- Fast inference at low cost
- Large 131K multimodal context window
Limitations (Cons)
- Weaker text reasoning than GPT-4o
- Lower complex coding performance
Benchmark Breakdown
Reasoning (MMLU)82%
Coding (HumanEval)78%
Mathematics (MATH)76%
Long-Context Retrieval82%
Pricing Matrix
Input cost / 1M tokens$0.50
Output cost / 1M tokens$3.00
Compare Google: Nano Banana 2 (Gemini 3.1 Flash Image) with other frontier models: