Gemini 3.1 Flash-Lite Image (Nano Banana 2 Lite)

Fast, cost-efficient image generation and editing from the Nano Banana family

About model

On Together AI, Gemini 3.1 Flash-Lite Image (Nano Banana 2 Lite) costs $0.069 per image.

Gemini 3.1 Flash-Lite Image, also known as Nano Banana 2 Lite, is Google's fastest and most cost-efficient image model in the Nano Banana family, built on Gemini 3.1 Flash-Lite for high-throughput pipelines and rapid iteration. Google reports text-to-image generation roughly 2.7 times faster than Gemini 3.1 Flash Image (Nano Banana 2), while the model keeps the family's reliable prompt adherence, strong character consistency, and legible in-image text. It handles text-to-image generation, prompt-based editing, and multi-image composition through a single interface, with fast multi-turn local edits and optional thinking for more complex prompts. Available on Together AI.

‍

Output Resolution

Optimized for fast 1024px generation

Reference Images

Multi-image composition and editing in one request

Faster Than Nano Banana 2 (Google-Reported)

2.7x

For high-volume and near-real-time workflows

Model key capabilities

Fast Generation: Built for high-throughput pipelines and rapid visual iteration
Editing & Composition: Prompt-based editing, fast multi-turn local edits, and multi-image composition from up to 14 references
Nano Banana Consistency: Keeps the family's prompt adherence, character consistency, and legible in-image text
Available on Together AI: Serverless access through the Together AI API

API usage

cURL
Python
Typescript

Endpoint:

google/flash-image-3.1-lite

curl -X POST "https://api.together.ai/v1/images/generations" \
  -H "Authorization: Bearer $TOGETHER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/flash-image-3.1-lite",
    "prompt": "Draw an anime style version of this image.",
    "width": 1024,
    "height": 768,
    "steps": 28,
    "n": 1,
    "response_format": "url",
    "image_url": "https://huggingface.co/datasets/patrickvonplaten/random_img/resolve/main/yosemite.png"
  }'

from together import Together

client = Together()

imageCompletion = client.images.generate(
    model="google/flash-image-3.1-lite",
    width=1024,
    height=768,
    steps=28,
    prompt="Draw an anime style version of this image.",
    image_url="https://huggingface.co/datasets/patrickvonplaten/random_img/resolve/main/yosemite.png",
)

print(imageCompletion.data[0].url)

import Together from "together-ai";

const together = new Together();

async function main() {
  const response = await together.images.create({
    model: "google/flash-image-3.1-lite",
    width: 1024,
    height: 1024,
    steps: 28,
    prompt: "Draw an anime style version of this image.",
    image_url: "https://huggingface.co/datasets/patrickvonplaten/random_img/resolve/main/yosemite.png",
  });

  console.log(response.data[0].url);
}

main();

Model card
Architecture Overview:
• Image generation and editing model based on Gemini 3.1 Flash-Lite
• Text and image input with image and text output, optimized for 1K (1024px) images
• Multiple aspect ratios from square to ultra-wide and vertical

Training Methodology:
• Evaluated against regression sets built from popular use cases of earlier Nano Banana models to avoid quality regressions
• Outputs carry SynthID watermarking and C2PA provenance

Performance Characteristics:
• Google reports text-to-image generation about 2.7 times faster than Gemini 3.1 Flash Image (Nano Banana 2)
• Supports minimal and high thinking levels for balancing speed and prompt complexity
‍
Prompting
Together AI API Access:
• Access Gemini 3.1 Flash-Lite Image (Nano Banana 2 Lite) via Together AI APIs using the endpoint google/flash-image-3.1-lite
• Authenticate using your Together AI API key in request headers
• Send a text prompt for generation, or include up to 14 reference images for editing and composition
• Choose an aspect ratio and, for complex prompts, a higher thinking level
• Available on Together AI with serverless access
‍
Applications & use cases
High-Volume Creative Pipelines:
• Generate thousands of images quickly for catalogs and campaigns
• Iterate on concepts rapidly before final renders
• Keep per-image cost low in near-real-time apps

Interactive Editing:
• Make fast multi-turn local edits like color swaps and background changes
• Create stickers and assets from existing images
• Compose scenes from multiple reference images

Consistent Characters & Brands:
• Keep characters on model across a series of images
• Render legible labels and short in-image text
• Produce variants across aspect ratios for every placement
‍

Model specifications

Model data

Model provider
Google
Type
Image
Main use cases
Image Generation
Resolution/Duration
1K (1024px)
Deployment
Serverless
Endpoint
google/flash-image-3.1-lite
Price
$0.069 / image
Input modalities
Text
Image
Output modalities
Image

Released
June 29, 2026
Category
Image

Run in Playground

Quickstart docs

Deploy Model

Gemini 3.1 Flash-Lite Image (Nano Banana 2 Lite)

About model

API usage

Model card

Prompting

Applications & use cases