Google: Nano Banana Pro (Gemini 3 Pro Image)
Google's Nano Banana Pro (Gemini 3 Pro Image) is a paid model from Google that accepts both text and image inputs, making it usable for tasks that involve visual content alongside written prompts. It supports a 131,072-token context window with up to 32,768 output tokens, and it includes tool use and reasoning capabilities. Structured output support is not confirmed for this model. At $2.00 per million input tokens and $12.00 per million output tokens, it sits at a moderate-to-elevated price tier, so cost-sensitive teams should compare it carefully against alternatives with similar modalities. The more significant caveat is that no independent benchmark coverage exists yet, which means its real-world performance relative to competitors is unverified. Buyers who need image-plus-text handling, a large context window, and reasoning support may want to shortlist it, but should factor in the unproven track record before committing at scale.
- Model ID
- google/gemini-3-pro-image
- Vendor
- Tokenizer
- Gemini
- Input Modalities
- image, text
- Output Modalities
- image, text
- Max Output
- 32,768 tokens
- Tool Calling
- ✓ supported
- Structured Output
- ✓ supported
- Reasoning Mode
- ✓ supported
- Vision
- ✓ accepts images
- Audio
- no
- Moderated
- no
Strong choice for
Category rankings
Where Google: Nano Banana Pro (Gemini 3 Pro Image) places across the 1 category it ranks in. How we rank →
| # | Category | Score |
|---|---|---|
| #3 | Image GenerationVision · of 8 ranked | 104 |