# Nano Banana Pro

> Gemini 3 Pro with image generation capabilities. Combines advanced reasoning with the ability to generate and edit images.

## Quick Reference

- Model ID: gemini-3-pro-image-preview
- Creator: Google
- Status: active
- Family: gemini-3
- Base URL: https://api.lumenfall.ai/openai/v1

## Specifications

- Context Window: 1048576 tokens
- Max Input Images: 900
- Max Output Tokens: 65536
- Input Modalities: text, image, audio, video, file
- Output Modalities: text, image
- Capabilities: function_calling, structured_output, batch, streaming, system_prompt, tool_use, grounding, thinking, code_execution, json_mode

## Model Identifiers

- Primary Slug: gemini-3-pro-image-preview
- Aliases: gemini-3-pro-image
- Alternative Names: Nano Banana Pro

## Dates

- Released: November 2025

## Tags

multimodal, reasoning, image-generation, long-context

## Available Providers

### Gemini API

- Config Key: gemini/gemini-3-pro-image-preview
- Provider Model ID: gemini-3-pro-image-preview
- Regions: global
- Pricing:
  - notes: ["$0.0011 per input image (560 tokens)", "$0.134 per output image from 1024x1024px (1K) and up to 2048x2048px (2K) (1120 tokens)", "$0.24 per output image up to 4096x4096px (4K) (2000 tokens)"]
  - source: official
  - currency: USD
  - components: [{"type" => "input", "metric" => "token", "unit_size" => 1000000, "unit_price" => 2}, {"type" => "input", "metric" => "token", "unit_size" => 1000000, "conditions" => {"cached" => true}, "unit_price" => 0.2}, {"type" => "output", "metric" => "token_text", "unit_size" => 1000000, "unit_price" => 12}, {"type" => "output", "metric" => "token_image", "unit_size" => 1000000, "unit_price" => 120}, {"type" => "input", "metric" => "token", "unit_size" => 1000000, "conditions" => {"batch" => true}, "unit_price" => 1}, {"type" => "output", "metric" => "token", "unit_size" => 1000000, "conditions" => {"batch" => true}, "unit_price" => 6}, {"type" => "output", "metric" => "image", "conditions" => {"batch" => true, "resolution" => "1K/2K"}, "unit_price" => 0.067}, {"type" => "output", "metric" => "image", "conditions" => {"batch" => true, "resolution" => "4K"}, "unit_price" => 0.12}]
  - source_url: https://ai.google.dev/gemini-api/docs/pricing#gemini-3-pro-image-preview
  - effective_at: 2025-11-18

### Replicate

- Config Key: replicate/gemini-3-pro-image-preview
- Provider Model ID: google/nano-banana-pro
- Pricing:
  - notes: ["Also known as Nano Banana Pro", "$0.15 per image for 1K-2K resolution", "$0.30 per image for 4K resolution", "Supports up to 14 reference images"]
  - source: official
  - currency: USD
  - components: [{"type" => "output", "metric" => "image", "unit_price" => 0.15}, {"type" => "output", "metric" => "image", "conditions" => {"resolution" => "2K"}, "unit_price" => 0.15}, {"type" => "output", "metric" => "image", "conditions" => {"resolution" => "4K"}, "unit_price" => 0.3}]
  - source_url: https://replicate.com/google/nano-banana-pro
  - effective_at: 2026-01-26

### fal.ai

- Config Key: fal/gemini-3-pro-image-preview
- Provider Model ID: fal-ai/gemini-3-pro-image-preview
- Pricing:
  - notes: ["Also known as Nano Banana Pro", "$0.15 per image for 1K-2K resolution", "$0.30 per image for 4K resolution (2x standard rate)", "Supports up to 2 reference images simultaneously"]
  - source: official
  - currency: USD
  - components: [{"type" => "output", "metric" => "image", "unit_price" => 0.15}, {"type" => "output", "metric" => "image", "conditions" => {"resolution" => "4K"}, "unit_price" => 0.3}]
  - source_url: https://fal.ai/models/fal-ai/gemini-3-pro-image-preview/edit
  - effective_at: 2026-01-26

### Vertex AI

- Config Key: vertex/gemini-3-pro-image-preview
- Provider Model ID: gemini-3-pro-image-preview
- Regions: global
- Pricing:
  - notes: ["$0.0011 per input image (560 tokens)", "$0.134 per output image from 1024x1024px (1K) and up to 2048x2048px (2K) (1120 tokens)", "$0.24 per output image up to 4096x4096px (4K) (2000 tokens)"]
  - source: official
  - currency: USD
  - components: [{"type" => "input", "metric" => "token", "unit_size" => 1000000, "unit_price" => 2}, {"type" => "input", "metric" => "token", "unit_size" => 1000000, "conditions" => {"cached" => true}, "unit_price" => 0.2}, {"type" => "output", "metric" => "token_text", "unit_size" => 1000000, "unit_price" => 12}, {"type" => "output", "metric" => "token_image", "unit_size" => 1000000, "unit_price" => 120}, {"type" => "input", "metric" => "token", "unit_size" => 1000000, "conditions" => {"batch" => true}, "unit_price" => 1}, {"type" => "output", "metric" => "token", "unit_size" => 1000000, "conditions" => {"batch" => true}, "unit_price" => 6}, {"type" => "output", "metric" => "image", "conditions" => {"batch" => true, "resolution" => "1K/2K"}, "unit_price" => 0.067}, {"type" => "output", "metric" => "image", "conditions" => {"batch" => true, "resolution" => "4K"}, "unit_price" => 0.12}]
  - source_url: https://cloud.google.com/vertex-ai/generative-ai/pricing
  - effective_at: 2025-11-18


## Performance Metrics

Provider performance over the last 30 days.

### gemini

- Median Generation Time (p50): 19586ms
- 95th Percentile Generation Time (p95): 35647ms
- Average Generation Time: 21403ms
- Success Rate: 93.0%
- Total Requests: 128
- Time to First Byte (p50): 19405ms
- Time to First Byte (p95): 35302ms

### vertex

- Median Generation Time (p50): 25988ms
- 95th Percentile Generation Time (p95): 102922ms
- Average Generation Time: 38231ms
- Success Rate: 67.4%
- Total Requests: 46
- Time to First Byte (p50): 25614ms
- Time to First Byte (p95): 113357ms

### fal

- Median Generation Time (p50): 42967ms
- 95th Percentile Generation Time (p95): 83370ms
- Average Generation Time: 45290ms
- Success Rate: 36.2%
- Total Requests: 47
- Time to First Byte (p50): 42967ms
- Time to First Byte (p95): 80688ms


## Arena Benchmarks

### Man and Car in California

- Elo: 1292
- Record: 53W / 26L / 1T (80 battles)
- Rank: #1 of 13

### Victorian Greenhouse Oasis

- Elo: 1285
- Record: 9W / 6L / 1T (16 battles)
- Rank: #1 of 17

### Isometric Miniature Diorama Scenes

- Elo: 1249
- Record: 13W / 2L / 2T (17 battles)
- Rank: #1 of 19

### Golden Hour Stroll

- Elo: 1247
- Record: 24W / 6L / 1T (31 battles)
- Rank: #3 of 12

### Modern Clean Menu

- Elo: 1234
- Record: 13W / 1L / 0T (14 battles)
- Rank: #5 of 19

### Bald man challenge

- Elo: 1224
- Record: 13W / 3L / 3T (19 battles)
- Rank: #1 of 14

### Fantasy Warrior

- Elo: 1222
- Record: 12W / 3L / 0T (15 battles)
- Rank: #4 of 19

### Candid Street Photography

- Elo: 1218
- Record: 10W / 3L / 0T (13 battles)
- Rank: #1 of 22

### Neutral Expression to Genuine Smile

- Elo: 1216
- Record: 18W / 9L / 4T (31 battles)
- Rank: #4 of 12

### Night Sky Transformation

- Elo: 1213
- Record: 20W / 4L / 4T (28 battles)
- Rank: #1 of 15

### Over-the-top cartoon caricature

- Elo: 1207
- Record: 17W / 14L / 2T (33 battles)
- Rank: #3 of 13

### Apollo 11: Journey to Tranquility

- Elo: 1206
- Record: 14W / 6L / 0T (20 battles)
- Rank: #4 of 19

### Studio Ghibli Anime Style

- Elo: 1183
- Record: 7W / 8L / 2T (17 battles)
- Rank: #7 of 13

### Heroic Super Hero Portrait

- Elo: 1181
- Record: 16W / 7L / 1T (24 battles)
- Rank: #8 of 19

### Vintage Cafe Logo

- Elo: 1152
- Record: 10W / 14L / 2T (26 battles)
- Rank: #10 of 19

### Selective Object Swap

- Elo: 1151
- Record: 4W / 0L / 0T (4 battles)
- Rank: #1 of 12

### Geometric Composition

- Elo: 1148
- Record: 10W / 6L / 4T (20 battles)
- Rank: #15 of 22

### Adorable Baby Animals in Sunny Meadow

- Elo: 1127
- Record: 5W / 2L / 1T (8 battles)
- Rank: #17 of 23


## Use Cases & Category Performance

### Photorealism (Image Editing)

- Rank: #1 of 16
- Elo: 1265
- Record: 128W / 48L / 13T (189 battles)
- Win Rate: 67.7%

### Portrait (Text-to-Image)

- Rank: #2 of 19
- Elo: 1241
- Record: 12W / 3L / 0T (15 battles)
- Win Rate: 80.0%

### Photorealism (Text-to-Image)

- Rank: #4 of 22
- Elo: 1232
- Record: 10W / 3L / 0T (13 battles)
- Win Rate: 76.9%

### Text Rendering (Text-to-Image)

- Rank: #5 of 21
- Elo: 1242
- Record: 37W / 21L / 2T (60 battles)
- Win Rate: 61.7%

### Portrait (Image Editing)

- Rank: #4 of 14
- Elo: 1250
- Record: 31W / 12L / 7T (50 battles)
- Win Rate: 62.0%

### Anime (Image Editing)

- Rank: #9 of 13
- Elo: 1186
- Record: 7W / 8L / 2T (17 battles)
- Win Rate: 41.2%

### Product, Branding & Commercial (Text-to-Image)

- Rank: #16 of 19
- Elo: 1155
- Record: 10W / 14L / 2T (26 battles)
- Win Rate: 38.5%


## Image Gallery

23 images available for this model.
- Curated examples: 5
  - "Create an image of an ape, eating a banana, walking trough the streets of new york city and taking capybara for a wal..."
  - "Create an image of an ape, eating a banana, walking trough the streets of new york city and taking capybara for a wal..."
  - "A medium-shot portrait of a master watchmaker at an antique wooden workbench, illuminated by the warm, directional gl..."
  - "A hyper-realistic close-up of an elderly artisan's weathered hands meticulously assembling a complex, vintage brass o..."
  - "A cozy indie bookstore storefront with a large glass window displaying a hand-painted sign that reads "LOVELY STORIES..."
- Competition results: 18
  - Man and Car in California: #1 of 13 (Elo 1292)
  - Victorian Greenhouse Oasis: #1 of 17 (Elo 1285)
  - Isometric Miniature Diorama Scenes: #1 of 19 (Elo 1249)
  - Golden Hour Stroll: #3 of 12 (Elo 1247)
  - Modern Clean Menu: #5 of 19 (Elo 1234)
  - Bald man challenge: #1 of 14 (Elo 1224)
  - Fantasy Warrior: #4 of 19 (Elo 1222)
  - Candid Street Photography: #1 of 22 (Elo 1218)
  - Neutral Expression to Genuine Smile: #4 of 12 (Elo 1216)
  - Night Sky Transformation: #1 of 15 (Elo 1213)
  - Over-the-top cartoon caricature: #3 of 13 (Elo 1207)
  - Apollo 11: Journey to Tranquility: #4 of 19 (Elo 1206)
  - Studio Ghibli Anime Style: #7 of 13 (Elo 1183)
  - Heroic Super Hero Portrait: #8 of 19 (Elo 1181)
  - Vintage Cafe Logo: #10 of 19 (Elo 1152)
  - Selective Object Swap: #1 of 12 (Elo 1151)
  - Geometric Composition: #15 of 22 (Elo 1148)
  - Adorable Baby Animals in Sunny Meadow: #17 of 23 (Elo 1127)

## Example Prompt

The following prompt was used to generate an example image in our playground:

A cozy indie bookstore storefront with a large glass window displaying a hand-painted sign that reads "LOVELY STORIES FOUND HERE" in elegant gold leaf calligraphy. A small capybara sits quietly on the sidewalk nearby, reading a tiny newspaper.

## Code Examples

### Text to Image (Generation)

#### cURL

curl -X POST \
  https://api.lumenfall.ai/openai/v1/images/generations \
  -H "Authorization: Bearer $LUMENFALL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3-pro-image-preview",
    "prompt": "A serene mountain landscape at sunset",
    "size": "1024x1024"
  }'

# Response:
# { "created": 1234567890, "data": [{ "url": "https://...", "revised_prompt": "..." }] }

#### JavaScript

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'YOUR_API_KEY',
  baseURL: 'https://api.lumenfall.ai/openai/v1'
});

const response = await client.images.generate({
  model: 'gemini-3-pro-image-preview',
  prompt: 'A serene mountain landscape at sunset',
  size: '1024x1024'
});

// { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }
console.log(response.data[0].url);

#### Python

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.lumenfall.ai/openai/v1"
)

response = client.images.generate(
    model="gemini-3-pro-image-preview",
    prompt="A serene mountain landscape at sunset",
    size="1024x1024"
)

# { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }
print(response.data[0].url)

### Image Editing

#### cURL

curl -X POST \
  https://api.lumenfall.ai/openai/v1/images/edits \
  -H "Authorization: Bearer $LUMENFALL_API_KEY" \
  -F "model=gemini-3-pro-image-preview" \
  -F "image=@source.png" \
  -F "prompt=Add a starry night sky to this image" \
  -F "size=1024x1024"

# Response:
# { "created": 1234567890, "data": [{ "url": "https://...", "revised_prompt": "..." }] }

#### JavaScript

import OpenAI from 'openai';
import fs from 'fs';

const client = new OpenAI({
  apiKey: 'YOUR_API_KEY',
  baseURL: 'https://api.lumenfall.ai/openai/v1'
});

const response = await client.images.edit({
  model: 'gemini-3-pro-image-preview',
  image: fs.createReadStream('source.png'),
  prompt: 'Add a starry night sky to this image',
  size: '1024x1024'
});

// { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }
console.log(response.data[0].url);

#### Python

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.lumenfall.ai/openai/v1"
)

response = client.images.edit(
    model="gemini-3-pro-image-preview",
    image=open("source.png", "rb"),
    prompt="Add a starry night sky to this image",
    size="1024x1024"
)

# { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }
print(response.data[0].url)


## About

## Overview
Gemini 3 Pro Image Preview is a multimodal model developed by Google that integrates advanced reasoning capabilities with native image generation and editing. Specifically designed to bridge the gap between complex cognitive tasks and visual synthesis, this model allows users to perform interleaved text-and-image workflows within a single session. It is distinctive for its high-density reasoning performance and its ability to process diverse inputs—including audio, video, and files—while outputting both descriptive text and high-fidelity images.

## Strengths
*   **Interleaved Reasoning and Synthesis:** Unlike models that treat image generation as a separate tool, this model can reason about a prompt's context and generate images that reflect complex logic or multi-step instructions.
*   **Comprehensive Modality Support:** The model accepts a wide array of input types, including video and audio, allowing for "visual-to-visual" workflows such as generating a static image based on a specific scene from a video file.
*   **Structured Output and Tool Use:** It excels at generating valid JSON schemas and executing function calls, making it highly effective for automation pipelines where image generation must be triggered by specific data conditions.
*   **Long-Context Reasoning:** Inheriting the Gemini family's strength in context window management, it can maintain consistency across large amounts of input data before producing a visual or textual response.

## Limitations
*   **Preview Stability:** As a "Preview" release, the model may exhibit inconsistencies in image composition or adherence to highly granular spatial constraints compared to specialized, single-purpose diffusion models.
*   **Output Latency:** Due to the computational overhead of combined reasoning and image synthesis, response times may be higher than text-only or small-scale generative models.
*   **Specialized Artistic Control:** While capable of high-quality generation, it may lack some of the fine-grained aesthetic control (such as specific seed-based styling or LoRA support) found in dedicated image generation frameworks.

## Technical Background
Gemini 3 Pro is built on a transformer-based multimodal architecture designed for native cross-modal understanding. Rather than using a separate text-to-image "wrapper," the model leverages integrated training objectives that allow visual and textual tokens to be processed in a unified latent space. Key technical features include a "thinking" mode for enhanced chain-of-thought processing and built-in code execution for validating logic before generating final outputs.

## Best For
This model is ideal for building sophisticated creative assistants that require deep context, such as storyboard generators that analyze scripts (text or PDF) to create visual frames, or marketing tools that generate ad copy and matching imagery simultaneously. It is also well-suited for developers needing structured data extraction from images coupled with automated visual editing. 

Gemini 3 Pro Image Preview is available through **Lumenfall’s unified API and playground**, allowing for easy integration into existing multimodal applications.

## Frequently Asked Questions

### How much does Nano Banana Pro cost?

Nano Banana Pro starts at $0.067 per image through Lumenfall. Pricing varies by provider. Lumenfall does not add any markup to provider pricing.

### What can Nano Banana Pro do?

Nano Banana Pro supports Function calling, Structured output, Batch, Streaming, System prompt, Tool use, Grounding, Thinking, Code execution, and Json mode. It accepts text, image, audio, video, and file input and produces text and image output.

### How do I use Nano Banana Pro via API?

You can use Nano Banana Pro through Lumenfall's OpenAI-compatible API. Send requests to the unified endpoint with model ID "gemini-3-pro-image-preview". Code examples are available in Python, JavaScript, and cURL.

### Which providers offer Nano Banana Pro?

Nano Banana Pro is available through Gemini API, Replicate, fal.ai, and Vertex AI on Lumenfall. Lumenfall automatically routes requests to the best available provider.

## Links

- Model Page: https://lumenfall.ai/models/google/gemini-3-pro-image-preview
- About: https://lumenfall.ai/models/google/gemini-3-pro-image-preview/about
- Providers, Pricing & Performance: https://lumenfall.ai/models/google/gemini-3-pro-image-preview/providers
- API Reference: https://lumenfall.ai/models/google/gemini-3-pro-image-preview/api
- Benchmarks: https://lumenfall.ai/models/google/gemini-3-pro-image-preview/benchmarks
- Use Cases: https://lumenfall.ai/models/google/gemini-3-pro-image-preview/use-cases
- Gallery: https://lumenfall.ai/models/google/gemini-3-pro-image-preview/gallery
- Playground: https://lumenfall.ai/playground?model=gemini-3-pro-image-preview
- API Documentation: https://docs.lumenfall.ai