Nano Banana 2 (Gemini 3.1 Flash Image)
Nano Banana 2 (Gemini 3.1 Flash 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 $0.50 per 1M input tokens and $3.00 per 1M output tokens. It accepts text and images and produces text and images. Typical uses: generating images from text prompts, editing images and working with text and image inputs.
Price checked · source: OpenRouter
What Nano Banana 2 (Gemini 3.1 Flash Image) is
Google Nano Banana 2, also listed as Gemini 3.1 Flash Image, is an image generation and editing model from Google. It accepts text and images as input and can produce images and text. Its stated modalities suit workflows that use written prompts, image inputs, or a combination of the two, with image output as a central use. The catalog does not specify image dimensions, file formats, or editing controls, so those details should not be inferred from the model name or its modality list.
It has a context length of 131,072 tokens and a maximum output of 32,768 tokens. These limits describe the model’s available context and output capacity; they do not establish how much information any particular image task will require. The model also lists reasoning, structured outputs, and response format as supported features. Structured-output and response-format support may suit workflows that need responses arranged in a defined format, while reasoning is a listed capability rather than a guarantee of a particular result. The provided facts do not specify supported formats, image editing operations, latency, or performance. Evaluation can focus on whether its text-and-image inputs, image-and-text outputs, context size, and listed output controls fit the intended task. The description specifically identifies image generation and editing, while the other catalog details describe its input, output, and supported features.
Key features
- Accepts text and image inputs
- Produces image and text outputs
- 131,072-token context length
- Maximum output of 32,768 tokens
- Supports reasoning, structured outputs, and response format
Typical uses
- Generating images from text prompts
- Editing images
- Working with text and image inputs
- Producing text or image outputs
Nano Banana 2 (Gemini 3.1 Flash Image) pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $0.50 |
| Output, per 1M tokens | $3.00 |
| 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 | $0.0012 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.015 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.021 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.080 |
Nano Banana 2 (Gemini 3.1 Flash Image) specifications
| Model id | google/gemini-3.1-flash-image |
|---|---|
| Version | gemini-3.1-flash-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 | No |
| Structured outputs | Yes |
| Reasoning effort control | Yes |
| 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 2 (Gemini 3.1 Flash Image) yet.
Compare Nano Banana 2 (Gemini 3.1 Flash Image)
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.