Nano Banana 2

gemini-3.1-flash-image-preview

Gemini 3.1 Flash image preview, also known as "Nano Banana 2", is Google's latest state-of-the-art image generation and editing model, delivering professional-grade visual quality at Flash speed. It combines advanced contextual understanding with fast, cost-efficient inference, making complex image generation and iterative editing more accessible than ever.

Context window66K

ProviderGemini

Released2026/03/02

Playground

Pricing

The same model is available through multiple service channels — choose based on latency, reliability and cost.

Prices in $ / 1M tokens

To pick a channel, add a provider field to the request body, for example "provider": { "channel": "direct" }. Valid values are direct / stable / economical; omit it to use the default channel.

Direct

Direct upstream connection — best when you need native behavior and the full context window.

Input	Output
0.50/M	60.00/M

Overview

Input

Text

Output

Image

API

API integration

Model ID

gemini-3.1-flash-image-preview

Use this value as the model in image generation requests

API Key

View it in API key management

Bearer token (OAuth 2.0) used to authenticate image generation requests

Image API

https://api.atalk-ai.com/v2/images/generations

Image size

1:1

Square — avatars and icons

2:3

Portrait — phone wallpapers and posters

3:2

Landscape — scenery and banners

3:4

Portrait — Instagram vertical

4:5

Portrait — social media content

5:4

Landscape — presentation slides

9:16

Vertical — full-screen mobile and Stories

16:9

Widescreen — video thumbnails and desktop wallpapers

21:9

Ultrawide — cinematic framing

Multiple aspect ratios are supported for different use cases — social media, ads, wallpapers and more.

gemini-3.1-flash-image-preview usage examples

The SeaWhale AI image generation endpoint is compatible with the OpenAI Images API and can be called with standard HTTP requests.

cURLPythonNode.js

curl https://api.atalk-ai.com/v2/images/generations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer <API_KEY>" \
  -d '{
    "model": "gemini-3.1-flash-image-preview",
    "prompt": "A cute kitten playing in the sunshine",
    "aspect_ratio": "1:1"
  }'

import requests

url = "https://api.atalk-ai.com/v2/images/generations"
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer <API_KEY>",
}
payload = {
    "model": "gemini-3.1-flash-image-preview",
    "prompt": "A cute kitten playing in the sunshine",
    "aspect_ratio": "1:1",
}

response = requests.post(url, json=payload, headers=headers)
response.raise_for_status()

data = response.json()
print(data["data"][0]["url"])

const response = await fetch('https://api.atalk-ai.com/v2/images/generations', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'Authorization': 'Bearer <API_KEY>',
  },
  body: JSON.stringify({
    model: 'gemini-3.1-flash-image-preview',
    prompt: 'A cute kitten playing in the sunshine',
    aspect_ratio: '1:1',
  }),
})

const data = await response.json()
console.log(data.data[0].url)