Nano Banana Pro (Gemini 3 Pro Image)

Google · released 18 Jun 2026

Input$2per 1M tokens

Output$12per 1M tokens

Context131Ktokens

WeightsClosed

context on a 1K–2M scale

About

Nano Banana Pro (Gemini 3 Pro Image) is Google’s image-generation and editing model, built on Gemini 3 Pro. Its listed inputs are text and images, and it can return images or text. Google describes it as an extension of the original Nano Banana, with improved multimodal reasoning and real-world grounding. The model accepts up to 131,072 tokens of context and can produce up to 32,768 output tokens. Reasoning, vision and tools are listed as supported capabilities. The model identifier is google/gemini-3-pro-image. Pricing is $2 USD per 1M input tokens and $12 USD per 1M output tokens. Its official listing is on OpenRouter.

Who it is for

It suits teams building image-generation or editing workflows that need text and image inputs, image or text outputs, and reasoning or tool support. The listed token pricing and context limits help frame model selection for a stack.

What is good

Accepts both text and image inputs
Can output images or text
Supports reasoning and tools
131,072-token context window

What to know first

Output tokens cost $12 USD per 1M
Maximum output is 32,768 tokens

Verdict

Nano Banana Pro is oriented toward image generation and editing, with multimodal inputs and image or text outputs. Teams should weigh its $12 USD per 1M output-token price against the available context and output limits.

Details

Lab: Googleopenrouter.ai · 3 Oct 2026
Context: 131Kopenrouter.ai · 3 Oct 2026
Input price: $2 / 1Mopenrouter.ai · 3 Oct 2026
Output price: $12 / 1Mopenrouter.ai · 3 Oct 2026
Max output: 32,768 tokensopenrouter.ai · 3 Oct 2026
Inputs: image, textopenrouter.ai · 3 Oct 2026
Open weights: Noopenrouter.ai · 3 Oct 2026

More longest-context models

See the list

Auto Router 2,000K Context Auto Router (Beta) 2,000K Context Grok 4.20 2,000K Context Grok 4.20 Multi-Agent 2,000K Context Pareto Code Router 2,000K Context Llama 4 Scout 1,311K Context Open source

Listed on Inferse

Longest-Context Models in 2026466 listed
Newest Models in 2026466 listed
Cheapest Language Models in 2026444 listed
Models with Tool Calling in 2026398 listed
Reasoning Models in 2026332 listed
Vision Language Models in 2026295 listed
Google Models: Pricing per 1M Tokens and Context (2026)43 listed
Image Generation Models in 20269 listed

Sources

openrouter.ai/google/gemini-3-pro-image· checked 3 Oct 2026