Nano Banana Pro (Gemini 3 Pro Image)
Nano Banana Pro (Gemini 3 Pro Image) is a multimodal model made by Google, added to the catalog on 18 Jun 2026. It has a context window of 131,072 tokens and costs $2.00 per 1M input tokens and $12.00 per 1M output tokens. It accepts text and images and produces text and images. Typical uses: generating images from text prompts, editing images using written directions and discussing visual content.
Price checked ยท source: OpenRouter
What Nano Banana Pro (Gemini 3 Pro Image) is
Google Nano Banana Pro (Gemini 3 Pro Image) is an image-generation and editing model built on Gemini 3 Pro. It accepts text and images as input and can produce both images and text. This makes it a multimodal model for requests that combine written directions with visual material, as well as requests centered on generating or editing images. The catalog also describes improved multimodal reasoning and real-world grounding compared with the original Nano Banana, without specifying further details about those capabilities.
It has a context window of 131,072 tokens and a maximum output of 32,768 tokens. Its context can accommodate extensive input in a single request, though the catalog does not detail how those limits are allocated between text and images. Supported options include tools, structured outputs, response formats, and reasoning. These features support workflows where outputs need a defined structure or where tool support is part of the interaction; the catalog does not name specific tools or formats. Its combination of text and image input and output suits image creation, image editing, and tasks involving discussion of visual content. It can also return text, so interactions need not be limited to producing an image. The available information does not specify image dimensions, file formats, or controls for editing.
Key features
- Accepts text and image inputs
- Produces images and text
- Has a 131,072-token context window
- Supports tools, structured outputs, response formats, and reasoning
Typical uses
- Generating images from text prompts
- Editing images using written directions
- Discussing visual content
- Producing structured text outputs
Nano Banana Pro (Gemini 3 Pro Image) pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $2.00 |
| Output, per 1M tokens | $12.00 |
| Cached input read, per 1M tokens | $0.20 |
| Cache write, per 1M tokens | $0.375 |
| Image input, per image | $0.000002 |
| Web search, per search | $0.014 |
No price change since it was added on 18 Jun 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0046 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.060 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.084 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.318 |
Nano Banana Pro (Gemini 3 Pro Image) specifications
| Model id | google/gemini-3-pro-image |
|---|---|
| Version | gemini-3-pro-image-20260528 |
| Context window | 131,072 tokensAbout 98,304 English words |
| Max output | 32,768 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 18 Jun 2026 |
| Input types | image, text |
|---|---|
| Output types | image, text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | No |
| Content moderation | Not applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
No output has been recorded for Nano Banana Pro (Gemini 3 Pro Image) yet.
Compare Nano Banana Pro (Gemini 3 Pro Image)
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.