Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)
Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is a multimodal model made by Google, added to the catalog on 30 Jun 2026. It has a context window of 65,536 tokens and costs $0.25 per 1M input tokens and $1.50 per 1M output tokens. It accepts text and images and produces text and images. Typical uses: text-to-image generation, rapid visual exploration and image generation in developer pipelines.
Price checked · source: OpenRouter
What Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is
Google Nano Banana 2 Lite, also named Gemini 3.1 Flash Lite Image, is an image-generation model from Google. Its catalog description identifies text-to-image generation and says the model is built for developer pipelines and rapid visual exploration. It accepts both text and images, and can produce both images and text. This gives it listed input and output modalities that extend beyond a text-only exchange, although the catalog does not specify particular image-editing or image-analysis functions.
The model has a context length of 65,536 tokens and a maximum output of 58,982 tokens. It supports reasoning and a response_format parameter. These details may matter in workflows that include substantial context, request image or text output, or configure the response format. The catalog does not explain which response formats are available, how reasoning is exposed, or how the maximum output applies to image generation. It also does not describe image sizes, supported file types, or controls for shaping generated images.
Google describes the model as intended for developer pipelines and rapid visual exploration. The listed text-to-image capability makes image creation from written prompts a stated fit. Its ability to accept images as well as text and return either images or text may also suit workflows that combine these modalities. The available facts establish these input, output, context, and parameter details, but do not specify further specialized tasks or provide performance measures. People evaluating it can use those stated capabilities to judge whether its modality support and context capacity match a proposed workflow.
Key features
- Accepts text and image inputs
- Produces image and text outputs
- Has a 65,536-token context length
- Supports reasoning and response_format
Typical uses
- Text-to-image generation
- Rapid visual exploration
- Image generation in developer pipelines
- Workflows combining text and image inputs
Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $0.25 |
| Output, per 1M tokens | $1.50 |
| Web search, per search | $0.014 |
No price change since it was added on 30 Jun 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0006 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0075 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.011 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.040 |
Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) specifications
| Model id | google/gemini-3.1-flash-lite-image |
|---|---|
| Version | gemini-3.1-flash-lite-image-20260630 |
| Context window | 65,536 tokensAbout 49,152 English words |
| Max output | 58,982 tokens |
| Knowledge cutoff | 2025-01-01 |
| Added to catalog | 30 Jun 2026 |
| Input types | image, text |
|---|---|
| Output types | image, text |
| Tool calling | No |
| Structured outputs | No |
| 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 Lite (Gemini 3.1 Flash Lite Image) yet.
Compare Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.