Can I run Nano Banana Pro locally?

No. The weights are not public and there is no Hugging Face repository; you access it exclusively through Google's API.

What does it cost and how much context does it have?

Input is $2.00 per million tokens and output is $12.00 per million tokens, with a 131,072-token context window.

How does Nano Banana Pro differ from the original Nano Banana?

Pro adds significantly improved multimodal reasoning, real-world Search grounding, finer creative controls like localized edits and camera transformations, and support for higher-resolution outputs.

Nano Banana Pro (Gemini 3 Pro Image)

4594°

#llm #google #vision #reasoning #research

Run this model

Offers / Ads

OpenRouter Terminal / API

Pay per token

Chat with this model in the browser or call it from your code with one API key.

Google | 131,072 token context | $2.00/M input, $12.00/M output. 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 high-fidelity visual synthesis. The model generates context-rich graphics, from infographics and diagrams to cinematic composites, and can incorporate real-time information via Search grounding. It offers industry-leading text rendering in images (including long passages and multilingual layouts), consistent multi-image…Google | 131,072 token context | $2.00/M input, $12.00/M output. 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 high-fidelity visual synthesis. The model generates context-rich graphics, from infographics and diagrams to cinematic composites, and can incorporate real-time information via Search grounding. It offers industry-leading text rendering in images (including long passages and multilingual layouts), consistent multi-image blending, and accurate identity preservation across up to five subjects. Nano Banana Pro adds fine-grained creative controls such as localized edits, lighting and focus adjustments, camera transformations, and support for 2K/4K outputs and flexible aspect ratios. It is designed for professional-grade design, product visualization, storyboarding, and complex multi-element compositions while remaining efficient for general image creation workflows.

Guides for this model

Flat fee vs tokens: why unlimited plans like Graydient.ai are the best value for AI creators in 2026

Open weights vs open source vs API-only: what you are actually allowed to do

The 10 cheapest ChatGPT alternatives in 2026: free local models, free tiers and flat-rate plans

All guides

Captain's notes

Written by Captain, the house editor

Notes from 2026-10-13

Nano Banana Pro is Google's professional-tier image generation and editing model, built on Gemini 3 Pro. It stands out for industry-leading text rendering inside images, identity-consistent multi-subject compositing, and fine-grained controls like localized edits and camera transformations. It suits designers, product teams, and anyone building complex visual workflows who needs more than a basic generation tool.

Known for

Best-in-class text rendering inside images, including multilingual layouts and long passages.
Accurate identity preservation across up to five subjects in a single composition.
Localized edits, lighting, focus, and camera transformation controls.
Search grounding lets it incorporate real-world context into generated visuals.
Supports high-resolution outputs and flexible aspect ratios for production use.

Watch out for

API-only, no open weights — you cannot run this locally or self-host it.
Output pricing at $12.00 per million tokens is steep; complex generation jobs add up quickly.
Context window is 131,072 tokens, which falls short of the 200k threshold for long-context workflows.

Best for

Vision

Reasoning

Research

Prompts to try

Multilingual infographic layout

Create an infographic explaining the water cycle. Include accurate scientific labels in both English and Spanish. Use clear diagram arrows, a clean colour palette, and render all text at high fidelity so it is legible at 4K resolution.

Multi-subject product composite

Generate a product lifestyle image featuring three distinct people — a woman in her 30s, a teenage boy, and an elderly man — each holding the same red water bottle in different outdoor settings. Preserve each person's appearance consistently across the scene.

Localized lighting edit

Take this product photo and apply a warm golden-hour light source from the upper left, affecting only the product and its immediate shadow. Keep the background lighting unchanged. Output at the highest available resolution.

Compare with

Gemma 4 31B
Open-weights model
262,144 token context · $0.20/M input, $0.40/M output
Gemma 4 26B A4B
Open-weights model
262,144 token context · $0.09/M input, $0.30/M output
Gemini 4 Argon
API-only model
1,048,576 token context · $2.00/M input, $10.00/M output
Gemma 3 27B
Open-weights model
131,072 token context · $0.08/M input, $0.45/M output

More text models from google

Questions people ask

Can I run Nano Banana Pro locally?: No. The weights are not public and there is no Hugging Face repository; you access it exclusively through Google's API.
What does it cost and how much context does it have?: Input is $2.00 per million tokens and output is $12.00 per million tokens, with a 131,072-token context window.
How does Nano Banana Pro differ from the original Nano Banana?: Pro adds significantly improved multimodal reasoning, real-world Search grounding, finer creative controls like localized edits and camera transformations, and support for higher-resolution outputs.

Captain's verdict
The go-to API choice for professional image work that demands precise text, multi-subject consistency, and granular creative control — if you can stomach the output cost.

Captain writes these notes from the model's own description and model card. Prices and context sizes are the provider's at the time of writing and can change.

Ranking badge

Updated Oct 22, 2026

Made this model? Show this badge on your page.

Paste it into your Hugging Face card or Civitai description.

Change colors / personalize / get code

Not this creator?

Get your own badge

How this score adds up

This model has no popularity data from any source yet, so it carries a stand-in number below 7,000° that keeps the lists complete. It never ranks above a model with data. The breakdown appears here as soon as a source reports it.

Glossary: the terms used here

Heat score: One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.
Floor: The 7,000° every model with real data starts from. The scale runs from 0° to 9,999°; the part below the floor is reserved for stand-ins (models without data), so that a model with data always ranks above one without. The floor is the same for everyone and decides nothing; the degrees above it are the measurement.
Download-equivalents: Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.
Log scale: Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.
Likes: Thumbs up and likes from every source, worth half a download each on the log scale.
Adoption rate: How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.
Measured and estimated: Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.
Seeder: Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.
AI Horde: A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.
Generation sites: Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.
OpenRouter tokens: A text model served through an API, such as Claude or GPT, has no weights to download, so its usage is measured in tokens: the pieces of text it read and wrote through OpenRouter, a gateway many apps use, over the last 30 days. Every 10,000,000 tokens count as one download. Source: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
Full model (checkpoint): The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.
LoRA and embedding: Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.
Family and weights: The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.
Age: Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.
Family boost: A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.
Stand-in score: A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.
New! (grace period): A model less than 7 days old shows New! instead of a score and holds no place in the rankings. Its score is computed from day one, but a model one day old grows faster than anything, so without the wait the week's #1 would always be whatever came out yesterday rather than what held up for a week.
Trend: How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.
Typical model: The middle of the catalog: half the models with a figure grew faster over the period, half slower.

Similar Models

Llama 3.2 3B Instruct

TEXT / LLM

Qwen3 Coder 30B A3B Instruct

TEXT / LLM

Nemotron 3 Nano 30B A3B

TEXT / LLM

Laguna XS 2.1

TEXT / LLM

AI Models for Image, Video & Text Generation

Nano Banana Pro (Gemini 3 Pro Image) is a text model for the Text / LLM family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Text / LLM models and check its heat score to see how it is trending.

More Text / LLM models llm google vision reasoning research

Browse by Model Family