Google logo

Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)

Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity developer pipelines and rapid-fire visual exploration. It delivers text-to-image generation...

Input Price

$0.30/1M tokens

Output Price

$2.50/1M tokens

Intelligence

22.2

Coding

49.3

Specifications

Technical details and pricing.

ProviderGoogle
Context Window65,536 tokens
Release DateJul 21, 2026
ModalitiesText, Image → Image, Text
CapabilitiesVision
AvailabilityChat only

EU-hosted inference API

Power your AI projects with open-source models.

Drop-in OpenAI-compatible API. No data leaves Europe.

MiniMax

MiniMax M3

$0.50 / $1.90

per M tokens

Z.ai

GLM 5.3 Flash

$0.20 / $0.60

per M tokens

MoonshotAI

Kimi K3

$4.00 / $18.00

per M tokens

DeepSeek

DeepSeek V4.1 Flash

$0.40 / $1.40

per M tokens

Frequently Asked Questions

What is Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) good for?

Use Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) for everyday tasks like writing, summarizing, brainstorming, and getting clear explanations.

How much does Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) cost?

Pricing is based on usage. Current rates are $0.30/1M tokens for input and $2.50/1M tokens for output.

Can I use Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) in LLMBase Chat?

Yes. Use the chat action on this page to open Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) in LLMBase Chat. Access still follows the current plan and model tier.

Does Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) support images or audio?

Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) can understand images.

Where does Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) run?

Processing terms depend on the selected model. Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is not marked as EU-hosted, so it is processed by the company that operates it. LLMBase shows this for every model so you can choose per use case.

Benchmarks and pricing use Artificial Analysis where available. Catalog specs are used as a fallback.