Models
Google
Nano Banana Pro

Google

Nano Banana Pro

Name: Nano Banana Pro
Brand: Google
Price: 0.067 USD
Availability: InStock

AI Image Editing Model

Mode:

Image Featured #3 Text-to-Image #1 Image-to-Image

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

Nano Banana Pro generated image of A medium-shot portrait of a master watchmaker at an antique wooden workbench,...

Nano Banana Pro generated image of A hyper-realistic close-up of an elderly artisan's weathered hands meticulous...

Try Model Benchmark examples

1.0M

Context Window

Supported Modes

Text to Image Image Edit

Active

Capabilities

Function calling Structured output Batch Streaming System prompt Tool use Grounding Thinking Code execution Json mode

Details

Model ID

gemini-3-pro-image-preview

Also known as: gemini-3-pro-image

Creator

Google

Family

gemini-3

Released

November 2025

Max Input Images

900

Max Output Tokens

65,536

Ready to integrate?

Access gemini-3-pro-image-preview via our unified API.

Create Account

Available at 4 providers

Starting from

$0.150 /image via fal.ai, Replicate · +2 more

Batch from $0.067/image via Gemini API, Vertex AI

Popular formats

2K (2048×2048)

~$0.150

4K (4096×4096)

~$0.300

Prices shown are in USD · Some prices estimated from per-megapixel or per-token pricing

See all providers

Provider Performance

Fastest generation through gemini at 28,408ms median latency with 88.8% success rate.

Aggregated from real API requests over the last 30 days.

Generation Time

gemini

p95: 55,633ms

fal

p95: 99,302ms

replicate

p95: 46,303ms

vertex

p95: 91,299ms

Success Rate

gemini

88.8%

452 / 509 requests

fal

75.9%

22 / 29 requests

replicate

55.0%

11 / 20 requests

vertex

64.4%

105 / 163 requests

Time to First Byte

gemini

26,552ms

p95: 49,021ms

fal

34,356ms

p95: 100,521ms

replicate

35,595ms

p95: 48,991ms

vertex

43,017ms

p95: 87,705ms

Provider Rankings

#	Provider	p50 Gen Time	p95 Gen Time	Success Rate	TTFB (p50)
1	gemini	28,408ms	55,633ms	88.8%	26,552ms
2	fal	33,502ms	99,302ms	75.9%	34,356ms
3	replicate	35,595ms	46,303ms	55.0%	35,595ms
4	vertex	43,605ms	91,299ms	64.4%	43,017ms

Data updated every 15 minutes. Based on all API requests through Lumenfall over the last 30 days.

Providers & Pricing (4)

Nano Banana Pro is available from 4 providers, with per-image pricing starting at $0.067 through fal.ai.

fal.ai

Image Edit

fal/gemini-3-pro-image-preview-edit

Provider Model ID: fal-ai/gemini-3-pro-image-preview/edit

Output

Image

$0.150 per image

Image 4K

$0.300 per image

Pricing Notes (4)

• 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

View official pricing • As of Jan 26, 2026

Replicate

Text to Image Image Edit

replicate/gemini-3-pro-image-preview

Provider Model ID: google/nano-banana-pro

Output

Image

$0.150 per image

Image 2K

$0.150 per image

Image 4K

$0.300 per image

Pricing Notes (4)

• 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

View official pricing • As of Jan 26, 2026

Gemini API

Text to Image Image Edit

gemini/gemini-3-pro-image-preview

Provider Model ID: gemini-3-pro-image-preview

Input

Token

$2.00 per 1M

Token Cached

$0.200 per 1M

Output

Token text

$12.00 per 1M

Token image

$120.00 per 1M

Pricing Notes (3)

• $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)

View official pricing • As of Nov 18, 2025

Vertex AI

Text to Image Image Edit

vertex/gemini-3-pro-image-preview

Provider Model ID: gemini-3-pro-image-preview

Input

Token

$2.00 per 1M

Token Cached

$0.200 per 1M

Output

Token text

$12.00 per 1M

Token image

$120.00 per 1M

Pricing Notes (3)

• $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)

View official pricing • As of Nov 18, 2025

gemini-3-pro-image API OpenAI-compatible

Access Nano Banana Pro via Lumenfall’s OpenAI-compatible API to integrate advanced text-to-image generation and complex image editing capabilities into any application.

Base URL

https://api.lumenfall.ai/openai/v1

Model

gemini-3-pro-image-preview

Code Examples

Image Edit

/v1/images/edits

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 "[email protected]" \

  -F "prompt=Add a starry night sky to this image" \

  -F "size=1024x1024"

# Response:

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

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);

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)

Parameter Reference

Required Supported Not available

Core Parameters

Parameter	Type	Description	Modes
`prompt`	string	Required. Text prompt for image generation	T2I Edit
`seed`	integer	Random seed for reproducibility	T2I Edit

Size & Layout

Parameter	Type	Description	Modes
`size`	string	Image dimensions as WxH pixels (e.g. "1024x1024") or aspect ratio (e.g. "16:9") WxH determines both shape and scale (aspect_ratio and resolution are ignored when size is provided). W:H format is equivalent to aspect_ratio.	T2I Edit
`aspect_ratio`	string	Aspect ratio of the output image (e.g. "16:9", "1:1") Controls shape independently of scale. Use with resolution to control both. If size is also provided, size takes precedence. Any ratio is accepted and mapped to the nearest supported value.	T2I Edit
`resolution`	string	Output resolution tier (e.g. "1K", "4K") `auto` `1K` `2K` `4K` Controls scale independently of shape. Higher tiers produce larger images and cost more. If size is also provided, size takes precedence for scale. Any tier is accepted and mapped to the nearest supported value.	T2I Edit

Output	`size`		`aspect_ratio` + `resolution`
Flexible
Auto	`"auto"`	—	Model chooses optimal dimensions

1K 10 sizes

Output	`size`		`aspect_ratio` + `resolution`
1183 × 887	`"1183x887"`	or	`"4:3"` + `"1K"`
916 × 1145	`"916x1145"`	or	`"4:5"` + `"1K"`
1145 × 916	`"1145x916"`	or	`"5:4"` + `"1K"`
1024 × 1024	`"1024x1024"`	or	`"1:1"` + `"1K"`
887 × 1182	`"887x1182"`	or	`"3:4"` + `"1K"`
836 × 1254	`"836x1254"`	or	`"2:3"` + `"1K"`
1254 × 836	`"1254x836"`	or	`"3:2"` + `"1K"`
768 × 1365	`"768x1365"`	or	`"9:16"` + `"1K"`
1365 × 768	`"1365x768"`	or	`"16:9"` + `"1K"`
1563 × 670	`"1563x670"`	or	`"21:9"` + `"1K"`

2K 10 sizes

Output	`size`		`aspect_ratio` + `resolution`
3129 × 1341	`"3129x1341"`	or	`"21:9"` + `"2K"`
1774 × 2365	`"1774x2365"`	or	`"3:4"` + `"2K"`
2365 × 1774	`"2365x1774"`	or	`"4:3"` + `"2K"`
1832 × 2290	`"1832x2290"`	or	`"4:5"` + `"2K"`
2290 × 1832	`"2290x1832"`	or	`"5:4"` + `"2K"`
1536 × 2731	`"1536x2731"`	or	`"9:16"` + `"2K"`
2731 × 1536	`"2731x1536"`	or	`"16:9"` + `"2K"`
2048 × 2048	`"2048x2048"`	or	`"1:1"` + `"2K"`
1672 × 2508	`"1672x2508"`	or	`"2:3"` + `"2K"`
2508 × 1672	`"2508x1672"`	or	`"3:2"` + `"2K"`

4K 10 sizes

Output	`size`		`aspect_ratio` + `resolution`
3548 × 4730	`"3548x4730"`	or	`"3:4"` + `"4K"`
3345 × 5017	`"3345x5017"`	or	`"2:3"` + `"4K"`
4580 × 3664	`"4580x3664"`	or	`"5:4"` + `"4K"`
4096 × 4096	`"4096x4096"`	or	`"1:1"` + `"4K"`
3072 × 5461	`"3072x5461"`	or	`"9:16"` + `"4K"`
5461 × 3072	`"5461x3072"`	or	`"16:9"` + `"4K"`
4729 × 3547	`"4729x3547"`	or	`"4:3"` + `"4K"`
5016 × 3344	`"5016x3344"`	or	`"3:2"` + `"4K"`
3663 × 4579	`"3663x4579"`	or	`"4:5"` + `"4K"`
6256 × 2681	`"6256x2681"`	or	`"21:9"` + `"4K"`

How these parameters work

size

Exact pixel dimensions

"1920x1080"

aspect_ratio

Shape only, default scale

"16:9"

resolution

Scale tier, preserves shape

"1K"

Priority when combined

size › aspect_ratio + resolution › aspect_ratio › resolution

size is most specific and always wins. aspect_ratio and resolution control shape and scale independently.

How matching works

Shape matching – we pick the closest supported ratio. Ask for 7:1 on a model with 4:1 and 8:1, you get 8:1.

Scale matching – providers use different tier formats: K tiers (0.5K 1K 2K 4K) or megapixel tiers (0.25 1). If the exact tier isn't available, you get the nearest one.

Dimension clamping – if a model has pixel limits, we clamp dimensions to fit and keep the aspect ratio intact.

Media Inputs

Parameter	Type	Description	Modes
`image`	file	Required. Input image(s) to edit Supports PNG, JPEG, WebP. Up to 900 images per request.	T2I Edit

Output & Format

Parameter	Type	Description	Modes
`response_format`	string	How to return the image `url` `b64_json` Default: `"url"`	T2I Edit
`output_format`	string	Output image format `png` `jpeg` `gif` `webp` `avif` Gateway converts to requested format if provider doesn't support it natively.	T2I Edit
`output_compression`	integer	Compression level for lossy formats (JPEG, WebP, AVIF)	T2I Edit
`n`	integer	Number of images to generate Default: `1` Gateway generates multiple images in parallel even if provider only supports 1.	T2I Edit

Additional Parameters

Provider-specific passthrough fields, available only when the request is routed to the listed provider.

Parameter	Type	Description	Modes
fal
`enable_web_search`	boolean	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.	T2I Edit
`limit_generations`	boolean	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.	T2I Edit
`safety_tolerance`	string	The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict. `1` `2` `3` `4` `5` `6`	T2I Edit
`sync_mode`	boolean	If `True`, the media will be returned as a data URI and the output data won't be available in the request history.	T2I Edit
replicate
`allow_fallback_model`	boolean	Fallback to another model (currently bytedance/seedream-5) if Nano Banana Pro is at capacity.	T2I Edit
`safety_filter_level`	string	block_low_and_above is strictest, block_medium_and_above blocks some prompts, block_only_high is most permissive but some prompts will still be blocked `block_low_and_above` `block_medium_and_above` `block_only_high`	T2I Edit

Parameter Normalization

How we handle parameters across different providers

Not every provider speaks the same language. When you send a parameter, we handle it in one of four ways depending on what the model supports:

Behavior	What happens	Example
`passthrough`	Sent as-is to the provider	style, quality
`renamed`	Same value, mapped to the field name the provider expects	prompt
`converted`	Transformed to the provider's native format	size
`emulated`	Works even if the provider has no concept of it	n, response_format

Parameters we don't recognize pass straight through to the upstream API, so provider-specific options still work.

Full API Reference Authentication, endpoints, and more

Nano Banana Pro Benchmarks

Nano Banana Pro leads the industry in image editing with a #1 ranking and 1244 Elo score. In text-to-image generation, it maintains a top-tier position at rank #3 with a 1273 Elo rating, demonstrating superior competitive performance.

Lumenfall Arena

Text-to-Image

1279 Elo

Lumenfall Arena

Image Editing

1241 Elo

Image Editing Landscape

Elo vs Cost

1 model without pricing omitted

Elo vs Speed

1 model waiting for enough speed data

Competition Results

Image Editing

Photorealism

View leaderboard

Man and Car in California

13 models

Image Editing

Source

Edit instruction

“Make a photo of the man driving the car down the California coastline”

Nano Banana Pro edited result for Bald man challenge

Original image before Nano Banana Pro editing

Before After

Bald man challenge

15 models

Image Editing

Edit instruction

“Give the person a full, thick head of natural hair with realistic texture, density, and a natural hairline. Preserve facial features and lighting.”

Nano Banana Pro edited result for Golden Hour Stroll

Before After

Golden Hour Stroll

13 models

Image Editing

Edit instruction

“Add dynamic motion to this photo: make hair blow in the wind, add leaves flying, energetic and lively feel.”

Nano Banana Pro edited result for Neutral Expression to Genuine Smile

Before After

Neutral Expression to Genuine Smile

14 models

Image Editing

Edit instruction

{
  "action": "image_edit",
  "reference": "uploaded neutral portrait",
  "change": "Warm genuine Duchenne smile: lips curved up, slight natural teeth, soft eye crinkles, subtle cheek raise",
  "details": "Realistic smiling skin (dimples if present, soft cheek shadows), slightly brighter eyes; keep exact eye shape/color/iris",
  "preserve_exact": "Face identity/structure, eyes/nose/lips/eyebrows, hair, skin texture/pores/freckles, makeup, clothing, head pose, background, lighting, shadows, framing",
  "no_changes": "No face shape change, no new features, no gaze shift, no hair/clothing/lighting/background edits",
  "style": "Ultra-photorealistic 8K portrait, sharp face focus, natural soft lighting, realistic skin glow"
}

3 attempts – showing best result

Nano Banana Pro edited result for Night Sky Transformation

Before After

Night Sky Transformation

16 models

Image Editing

Edit instruction

“Change the scene to night: a deep, dark sky with subtle, glistening stars visible behind the mountain.”

3 attempts – showing best result

Image Editing

Anime

View leaderboard

Studio Ghibli Anime Style

14 models

Image Editing

Source

Edit instruction

“Transform this photo into a Studio Ghibli–inspired illustration. Use soft pastel colors, hand-painted textures, gentle lighting, dreamy backgrounds, and a warm, nostalgic mood”

Image Editing

Portrait

View leaderboard

Before After

Bald man challenge

15 models

Image Editing

Edit instruction

“Give the person a full, thick head of natural hair with realistic texture, density, and a natural hairline. Preserve facial features and lighting.”

Before After

Neutral Expression to Genuine Smile

14 models

Image Editing

Edit instruction

{
  "action": "image_edit",
  "reference": "uploaded neutral portrait",
  "change": "Warm genuine Duchenne smile: lips curved up, slight natural teeth, soft eye crinkles, subtle cheek raise",
  "details": "Realistic smiling skin (dimples if present, soft cheek shadows), slightly brighter eyes; keep exact eye shape/color/iris",
  "preserve_exact": "Face identity/structure, eyes/nose/lips/eyebrows, hair, skin texture/pores/freckles, makeup, clothing, head pose, background, lighting, shadows, framing",
  "no_changes": "No face shape change, no new features, no gaze shift, no hair/clothing/lighting/background edits",
  "style": "Ultra-photorealistic 8K portrait, sharp face focus, natural soft lighting, realistic skin glow"
}

3 attempts – showing best result

Uncategorized

Over-the-top cartoon caricature

13 models

Image Editing

Source

Edit instruction

“Create a caricature of me and my job. Make it exaggerated and humorous, incorporating my profession as a tv show anchor and my love for dogs and hockey.”

Nano Banana Pro edited result for Selective Object Swap

Before After

Selective Object Swap

12 models

Image Editing

Edit instruction

“Swap the positions of the blue and yellow blocks”

2 attempts – showing best result

Top Matchups

See how Nano Banana Pro performs head-to-head against other AI models, ranked by community votes in blind comparisons.

vs Nano Banana 2

Challenge: Over-the-top cartoon caricature

50% W · 50% L

vs Nano Banana

Challenge: Bald man challenge

25% W · 25% L · 50% T

vs GPT Image 1.5

Challenge: Vintage Cafe Logo

0% W · 100% L

vs Wan 2.6

Challenge: Golden Hour Stroll

33% W · 67% L

vs FLUX.2 [max]

Challenge: Studio Ghibli Anime Style

33% W · 33% L · 33% T

Nano Banana Pro is best for

See all Use Cases

This model excels in photorealism and portraiture, achieving a #1 rank for photorealistic output with a 67.6% win rate and an 80% win rate in portrait categories. While it performs strongly in text rendering at rank #5, it shows lower efficiency for product, branding, and commercial applications where it ranks #15.

#1 of 17

Photorealism

Edit · 68.4% win rate

#4 of 15

Portrait

Edit · 70.1% win rate

Gallery

View all 8 images

Nano Banana Pro FAQ

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

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.

Try Nano Banana Pro in Playground

Generate images with custom prompts — no API key needed.

Open Playground