Nano Banana 2 Lite API

google/gemini-3.1-flash-lite-image
Nano Banana 2 Lite is Google's fastest and most cost-efficient multimodal model, combining text intelligence and native image generation at an ultra-low price point.
Output
$39 / 1M tokens
Released
Jun 30, 2026

Overview

What is Nano Banana 2 Lite API?

Nano Banana 2 Lite is the most cost-efficient model in Google's Gemini 3.1 family. The model (google/gemini-3.1-flash-lite-image) handles text understanding, image input, and native image generation in a single unified architecture — without switching between separate models.

It ships under Google's standard commercial terms and is available via AI/ML API with no special tier requirement.

[Model Specifications embed]

[Performance Benchmarks embed]

API Pricing

  • Input (text/image): $0.325 per 1M tokens
  • Output text: $1.95 per 1M tokens
  • Output images: $39.00 per 1M tokens (≈$0.044 per 1K-resolution image)

Where to Use Nano Banana 2 Lite

High-volume image generation pipelines
At approximately $0.044 per image, Nano Banana 2 Lite makes large-scale programmatic image generation economically viable — product visuals, content thumbnails, or automated asset creation at scale.

Multimodal data extraction
Submit documents, screenshots, or mixed-content pages and receive structured text output. The model handles text and image input simultaneously.

Real-time interactive apps
The model's lightweight profile keeps latency low enough for applications where users expect near-instant image generation responses.

Automated content pipelines
Combine text analysis and image creation in a single API call — product descriptions that generate matching visuals, or editorial workflows where written briefs become images automatically.

Nano Banana 2 Lite vs. the Alternatives

  • Nano Banana 2 Lite: Fastest and most affordable multimodal model in the Gemini 3.1 family. Choose this for cost-sensitive, high-throughput production workloads.
  • Nano Banana 2: Higher output quality, slower and more expensive. Choose this when image quality is a hard product requirement.
  • Gemini Omni Flash Preview: Full video generation. Choose this when you need motion output, not static images.

‍

Uptime and performance

  • Uptime (24h): 100%
  • Uptime (7d): 100%
  • Availability (24h): 100%
  • Error rate (24h): 0%

Measured on the AI/ML API gateway across live traffic. Figures are medians unless stated. Last updated 2026-10-12.

Use cases

Rapid prototyping and brainstorming visual ideas are documented use cases for Nano Banana 2 Lite, with Google describing it as ideal for rapid prototyping and brainstorming visual ideas.

Generating large batches of images is another stated use case, especially where high volume and speed matter.

Interactive prototyping and rapid visual drafting are explicitly mentioned, with the model described as well-suited for interactive prototyping and rapid visual drafting.

Contextual scene creation, including accurate contextual scenes and rough data visualizations, is also called out as a fit for the model.

How to use Nano Banana 2 Lite API

Install any OpenAI-compatible SDK, point it at api.aimlapi.com/v1, and set the model to google/gemini-3.1-flash-lite-image.
import requests

r = requests.post(
    "https://api.aimlapi.com/v1/images/generations",
    headers={"Authorization": "Bearer " + AIMLAPI_KEY},
    json={
      "model": "google/gemini-3-1-flash-lite-image",
      "prompt": "A cat holding a sign that says hello"
    },
)
print(r.json())
const r = await fetch("https://api.aimlapi.com/v1/images/generations", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "google/gemini-3-1-flash-lite-image",
    "prompt": "A cat holding a sign that says hello"
  }),
});
console.log(await r.json());
curl -X POST https://api.aimlapi.com/v1/images/generations \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"google/gemini-3-1-flash-lite-image","prompt":"A cat holding a sign that says hello"}'

OpenAI-compatible — swap the base URL and it works with your existing SDK.

Nano Banana 2 Lite API Pricing

TypePrice
Input
$0.325 / 1M tokens
Output
$39 / 1M tokens

Text input $0.325/1M · reasoning $1.95/1M · image output $39/1M.

Nano Banana 2 Lite Benchmarks

BenchmarkScoreWhat it measuresSourceRetrieved
Image Editing Arena
1042
Human preference Elo from blind pairwise comparisons of edited images, measured independently by Artificial AnalysisSourceSeptember 21, 2026

Nano Banana 2 Lite vs other models

ModelInputOutputContextBest for
$0.325 / 1M tokens
$39 / 1M tokens
Image generation at scale
$0.325 / 1M tokens
$78 / 1M tokens
128K tokens
Image generation at scale
$6.5 / 1M tokens
$39 / 1M tokens
Image generation at scale
Image generation at scale
$0.0195 / MP (variable)
Image generation at scale

Frequently asked questions

Nano Banana 2 Lite takes image, text as input and returns image.

Nano Banana 2 Lite is priced at input $0.325 / 1M tokens, output $39 / 1M tokens.

Nano Banana 2 Lite is billed per token, charged separately for input and output.

Yes, Nano Banana 2 Lite accepts image input as well as a text prompt.

Nano Banana 2 Lite was built by Google.

Send a request to https://api.aimlapi.com/v1/images/generations with google/gemini-3.1-flash-lite-image as the model id.

Yes. Nano Banana 2 Lite is served through AI/ML API, so the same key and endpoint format used for other models applies.

Yes, it is a lighter and cheaper variant of Nano Banana 2, built for high-volume image generation.

Start building with Nano Banana 2 Lite

Get API Key
1000+ models, one API.