Skip to main content
Endpoint: POST https://fal.run/fal-ai/gemini-3-pro-image-preview Endpoint ID: fal-ai/gemini-3-pro-image-preview

Try it in the Playground

Run this model interactively with your own prompts.

​
Quick Start

import fal_client

def on_queue_update(update):
    if isinstance(update, fal_client.InProgress):
        for log in update.logs:
           print(log["message"])

result = fal_client.subscribe(
    "fal-ai/gemini-3-pro-image-preview",
    arguments={
        "prompt": "An action shot of a black lab swimming in an inground suburban swimming pool. The camera is placed meticulously on the water line, dividing the image in half, revealing both the dogs head above water holding a tennis ball in it's mouth, and it's paws paddling underwater."
    },
    with_logs=True,
    on_queue_update=on_queue_update,
)
print(result)

​
Input Schema

​
prompt
string
required
The text prompt to generate an image from.
​
num_images
integer
default:"1"
The number of images to generate. Default value: 1Range: 1 to 4
​
seed
integer
The seed for the random number generator.
​
aspect_ratio
Enum
default:"1:1"
The aspect ratio of the generated image. Default value: 1:1Possible values: auto, 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16
​
output_format
OutputFormatEnum
default:"png"
The format of the generated image. Default value: "png"Possible values: jpeg, png, webp
​
safety_tolerance
SafetyToleranceEnum
default:"4"
The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict. Default value: "4"Possible values: 1, 2, 3, 4, 5, 6
​
sync_mode
boolean
default:"false"
If True, the media will be returned as a data URI and the output data won’t be available in the request history.
​
resolution
ResolutionEnum
default:"1K"
The resolution of the image to generate. Default value: "1K"Possible values: 1K, 2K, 4K
​
limit_generations
boolean
default:"false"
Experimental parameter to limit the number of generations from each round of prompting to 1. Set to True to to disregard any instructions in the prompt regarding the number of images to generate.
​
enable_web_search
boolean
default:"false"
Enable web search for the image generation task. This will allow the model to use the latest information from the web to generate the image.

​
Output Schema

​
images
list<ImageFile>
required
The generated images.
​
description
string
required
The description of the generated images.

​
Input Example

{
  "prompt": "An action shot of a black lab swimming in an inground suburban swimming pool. The camera is placed meticulously on the water line, dividing the image in half, revealing both the dogs head above water holding a tennis ball in it's mouth, and it's paws paddling underwater.",
  "num_images": 1,
  "aspect_ratio": "1:1",
  "output_format": "png",
  "safety_tolerance": "4",
  "sync_mode": false,
  "resolution": "1K",
  "limit_generations": false,
  "enable_web_search": false
}

​
Output Example

{
  "images": [
    {
      "content_type": "image/png",
      "file_name": "nano-banana-pro-t2i-output.png",
      "url": "https://storage.googleapis.com/falserverless/example_outputs/nano-banana-pro-t2i-output.png"
    }
  ],
  "description": ""
}
Google’s Nano Banana Pro (2) Preview delivers state-of-the-art image generation at $0.15 per image, trading cost efficiency for advanced reasoning capabilities and prompt understanding. Built on Gemini 3 Pro’s multimodal architecture, it handles complex natural language instructions that would trip up traditional diffusion models. Use Cases: Complex Scene Composition | Typography-Heavy Designs | Natural Language-Driven Editing

​
Performance

Nano Banana Pro prioritizes semantic understanding over raw speed, making it ideal for projects where prompt accuracy matters more than generation volume.
MetricResultContext
Resolution RangeUp to 4K (4096px)4K outputs charged at 2x standard rate
Cost per Image$0.156-7 generations per $1.00 on fal
Batch Generation1-4 imagesPer request via num_images parameter
Web Search IntegrationOptionalEnable via enable_web_search for current information

​
Advanced Prompt Understanding Through Gemini 3 Architecture

Gemini 3 Pro Image leverages Google’s latest foundation model to interpret complex, conversational prompts rather than requiring carefully crafted keyword strings. What this means for you:
  • Natural Language Processing: Describe scenes conversationally (“meticulously placed camera on the water line, dividing the image in half”) instead of keyword stuffing
  • Typography Excellence: Tagged for realism and typography, making it particularly strong for text-heavy designs where letter accuracy matters
  • Flexible Output Control: Generate up to 4 images per request with selectable aspect ratios (21:9 to 9:16) and formats (JPEG, PNG, WebP)
  • Resolution Scaling: Choose 1K, 2K, or 4K output based on your quality-versus-cost tradeoff, with transparent 2x pricing for 4K

​
Technical Specifications

SpecDetails
ArchitectureGemini 3 Pro Image
Input FormatsText prompts with optional web search grounding
Output FormatsJPEG, PNG, WebP
Resolution Options1K, 2K, 4K (4K at 2x cost)
LicenseCommercial use via partnership
API Documentation | Quickstart Guide | Enterprise Pricing

​
How It Stacks Up

Gemini 2.5 Flash Image – Nano Banana Pro trades speed and cost efficiency for advanced reasoning and complex instruction following at 4x the cost (0.15vs0.15 vs 0.039). Gemini 2.5 Flash Image remains ideal for high-volume workflows where rapid iteration matters more than nuanced prompt interpretation. **AuraFlow (0.012)∗∗–NanoBananaProprioritizessemanticunderstandingandtypographyaccuracyat12.5xthecost(0.012)** – Nano Banana Pro prioritizes semantic understanding and typography accuracy at 12.5x the cost (0.15 vs $0.012). AuraFlow offers maximum cost efficiency for straightforward text-to-image generation where natural language complexity isn’t critical.

​
Limitations

  • num_images range: 1 to 4
  • output_format restricted to: jpeg, png, webp
  • safety_tolerance restricted to: 1, 2, 3, 4, 5, 6
  • resolution restricted to: 1K, 2K, 4K