Google logo

Nano Banana Pro (Gemini 3 Pro Image)

Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...

Input Price$2.00/1M tokens
Output Price$12.00/1M tokens
Intelligence40.6
CodingN/A

Specifications

Technical details and pricing.

ProviderGoogle
Context Window65,536 tokens
Release DateNov 18, 2025
ModalitiesText, Image → Image, Text
CapabilitiesFunction Calling, Vision
AvailabilityChat only

Benchmarks

10 benchmark scores from Artificial Analysis.

GPQA90.8%
MMLU Pro89.8%
HLE39.7%
LiveCodeBench91.7%
AIME 202595.7%
SciCode56.1%
LCR73.0%
IFBench70.4%
Tau287.1%
TerminalBench Hard41.7%

Composite Indices

Higher is better; speed and price are normalized

Standard Benchmarks

Only benchmarks with data are shown

EU-Hosted Inference API

Power your AI projects with the best open-source models.

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

Explore Inference API

MiniMax

MiniMax M3

$0.40 / $1.40

per M tokens

Z.ai

GLM 5.2

$1.40 / $4.40

per M tokens

MoonshotAI

Kimi K3

$4.00 / $18.00

per M tokens

DeepSeek

DeepSeek V4 Pro

$1.80 / $3.60

per M tokens

Frequently Asked Questions

What is Nano Banana Pro (Gemini 3 Pro Image) good for?

Use Nano Banana Pro (Gemini 3 Pro Image) for everyday tasks like writing, summarizing, brainstorming, and getting clear explanations.

How much does Nano Banana Pro (Gemini 3 Pro Image) cost?

Pricing is based on usage. Current rates are $2.00/1M tokens for input and $12.00/1M tokens for output.

Can I use Nano Banana Pro (Gemini 3 Pro Image) in LLMBase Chat?

Yes. Use the chat action on this page to open Nano Banana Pro (Gemini 3 Pro Image) in LLMBase Chat. Access still follows the current plan and model tier.

Does Nano Banana Pro (Gemini 3 Pro Image) support images or audio?

Nano Banana Pro (Gemini 3 Pro Image) can understand images.

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