Nano Banana 2 (Gemini 3.1 Flash Image Preview)
VerifiedGoogle's fast multimodal preview for image and text tasks.
About Nano Banana 2 (Gemini 3.1 Flash Image Preview)
Built on Google's Gemini architecture, this model emphasizes speed for image preview operations. It combines text and visual modalities without requiring open weights. Developers use it where quick iteration on image-related prompts matters most.
Its design prioritizes low-latency responses for both generation previews and understanding tasks. The 131072-token context supports extended conversations that mix images and text. Typical applications include prototyping visual content and refining multimodal prompts in closed environments.
Capabilities
How Nano Banana 2 (Gemini 3.1 Flash Image Preview) compares
Nano Banana 2 (Gemini 3.1 Flash Image Preview) (striped bar) vs other image models on intelligence, speed and price.
Price
USD per 1M output tokens · Lower is better · Nano Banana 2 (Gemini 3.1 Flash Image Preview) ranks #3 of 6
Sources: Artificial Analysis (intelligence, speed) · OpenRouter (price).
Best for
Rapid visual concept iteration
The model excels at generating image previews from detailed text prompts, enabling designers to quickly explore variations in a single session thanks to its 131072-token context window.
Multimodal document review
It handles image analysis alongside long-form text inputs, making it suitable for reviewing illustrated reports or storyboards where context spans many pages.
Lightweight app integration
As an image-focused preview model, it supports fast embedding in tools that require on-the-fly visual output without heavy compute overhead.
Strengths & limitations
Strengths
- +Efficient handling of image+text inputs
- +Strong long-context multimodal support
- +Fast responses suitable for preview workflows
Limitations
- –Preview model may have reduced feature completeness
- –Less depth on pure-text or code tasks versus larger Gemini variants
- –Image-focused specialization limits non-visual use cases
Cost calculator
Estimate what Nano Banana 2 (Gemini 3.1 Flash Image Preview) would cost for your usage.
Based on Nano Banana 2 (Gemini 3.1 Flash Image Preview)'s $0.50/1M input · $3.00/1M output. Estimate only — actual cost varies by provider and caching.
Quick start
OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. Only the model slug changes between models.
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://openrouter.ai/api/v1",
apiKey: process.env.OPENROUTER_API_KEY,
});
const completion = await client.chat.completions.create({
model: "google/gemini-3.1-flash-image-preview",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(completion.choices[0].message.content);Model slug: google/gemini-3.1-flash-image-preview
Editor's verdict
Nano Banana 2 (Gemini 3.1 Flash Image Preview) is Google's proprietary image models with a 131K-token context window.
At $3.00 per 1M output tokens, it is mid-priced for its class.
It is available through Google's API and aggregators like OpenRouter.
Best suited to efficient handling of image+text inputs and strong long-context multimodal support.
Frequently asked questions
Nano Banana 2 supports a context length of 131072 tokens.
User reviews
Real, verified reviews from the community shape this model's rating.
Loading reviews…
Other Nano models
Sibling versions in the Nano family from Google.
Similar models
Other image models worth comparing.