“Make a photo of the man driving the car down the California coastline”
Gemini 3 Pro with image generation capabilities. Combines advanced reasoning with the ability to generate and edit images.
Capabilities
Details
gemini-3-pro-image-preview
Ready to integrate?
Access gemini-3-pro-image-preview via our unified API.
Starting from
Batch from $0.067/image via Gemini API, Vertex AI
Popular formats
Prices shown are in USD · Some prices estimated from per-megapixel or per-token pricing
See all providersProvider Performance
Fastest generation through gemini at 21,949ms median latency with 69.2% success rate.
Aggregated from real API requests over the last 30 days.
Generation Time
Success Rate
Time to First Byte
Provider Rankings
| # | Provider | p50 Gen Time | p95 Gen Time | Success Rate | TTFB (p50) |
|---|---|---|---|---|---|
| 1 | gemini | 21,949ms | 32,966ms | 69.2% | 20,033ms |
| 2 | vertex | 40,746ms | 69,512ms | 48.2% | 40,083ms |
| 3 | replicate | 41,822ms | 97,656ms | 84.0% | 41,822ms |
| 4 | fal | 42,435ms | 89,951ms | 78.4% | 42,435ms |
Providers & Pricing (5)
Nano Banana Pro is available from 5 providers, with per-image pricing starting at $0.067 through fal.ai.
All modes
fal/gemini-3-pro-image-preview
Output
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
fal/gemini-3-pro-image-preview-edit
Output
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
replicate/gemini-3-pro-image-preview
Output
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
gemini/gemini-3-pro-image-preview
Input
Output
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)
vertex/gemini-3-pro-image-preview
Input
Output
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)
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.
https://api.lumenfall.ai/openai/v1
gemini-3-pro-image-preview
Code Examples
Text to Image
/v1/images/generationscurl -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": "",
"size": "1024x1024"
}'
# Response:
# { "created": 1234567890, "data": [{ "url": "https://...", "revised_prompt": "..." }] }
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: '',
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.generate(
model="gemini-3-pro-image-preview",
prompt="",
size="1024x1024"
)
# { created: 1234567890, data: [{ url: "https://...", revised_prompt: "..." }] }
print(response.data[0].url)
Image Edit
/v1/images/editsParameter Reference
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 is most specific and always wins. aspect_ratio and resolution control shape and scale independently.
How matching works
7:1 on a model with
4:1 and 8:1,
you get 8:1.
0.5K 1K 2K 4K)
or megapixel tiers (0.25 1).
If the exact tier isn't available, you get the nearest one.
Media Inputs
| Parameter | Type | Description | Modes |
|---|---|---|---|
image
|
file |
Required.
Input image(s) to edit
Supports PNG, JPEG, WebP.
|
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:
1Gateway generates multiple images in parallel even if provider only supports 1.
|
T2I
Edit
|
Additional Parameters
| Parameter | Type | Description | Modes |
|---|---|---|---|
allow_fallback_model
replicate
|
boolean | Fallback to another model (currently bytedance/seedream-5) if Nano Banana Pro is at capacity. |
T2I
Edit
|
enable_web_search
fal
|
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
fal
|
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_filter_level
replicate
|
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
|
safety_tolerance
fal
|
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
fal
|
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
|
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.
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.
Image Editing Landscape
Elo vs Cost
Elo vs Speed
1 without speed data omitted.
Text-to-Image Landscape
Elo vs Cost
Elo vs Speed
10 without speed data omitted.
Competition Results
{
"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"
}
“Give the person a full, thick head of natural hair with realistic texture, density, and a natural hairline. Preserve facial features and lighting.”
“Change the scene to night: a deep, dark sky with subtle, glistening stars visible behind the mountain.”
“Add dynamic motion to this photo: make hair blow in the wind, add leaves flying, energetic and lively feel.”
“Create a clean, modern vector infographic poster about the Apollo 11 mission. NASA-inspired palette (navy, white, muted red, light gray). Flat-vector style, crisp lines, consistent iconography, subtle gradients only. Steps (stop at landing): 1. Launch (Saturn Vicon) 2. Earth Orbit (Earth + orbit ring icon) 3. Translunar (trajectory arc icon) 4. Lunar Orbit (Moon + orbit ring icon) 5. Descent (lunar module descending icon) 6. Landing (lunar module on the surface icon) Small supporting elements (minimal text): • Crew strip: three silhouette icons with only last names: Armstrong, Aldrin, Collins. • Landing site marker: Moon pin labeled "Tranquility" only. Layout constraints: generous margins, large readable labels, clean background with subtle stars. Vector-only, print-poster look, high resolution.”
“Modern minimalist restaurant menu design, white background with colorful food photos in grid, sections for appetizers/pizza/mains, bold sans-serif fonts, vibrant accents, clean professional layout for casual dining.”
“Vintage minimalist restaurant logo for "Caffè Florian", retro cloche dome with steam and "Est. 1720" banner, classic typography, warm brown and cream tones, subtle texture on light background, vector emblem style.”
“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”
{
"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"
}
“Give the person a full, thick head of natural hair with realistic texture, density, and a natural hairline. Preserve facial features and lighting.”
“A candid street photo of an elderly Japanese man repairing a red bicycle in light rain, reflections on wet pavement, shallow depth of field, 50mm lens, natural skin texture, imperfect framing, motion blur from passing cars, cinematic but realistic, no stylization.”
“Vintage minimalist restaurant logo for "Caffè Florian", retro cloche dome with steam and "Est. 1720" banner, classic typography, warm brown and cream tones, subtle texture on light background, vector emblem style.”
“Close portrait of a battle-worn paladin in ornate engraved plate armor, hair braided with small beads, faint scars and dirt on the skin, warm torchlight reflecting off metal, shallow depth of field, bokeh sparks, lifelike eyes, highly detailed texture on leather straps and cloth underlayer.”
Uncategorized
“Hyper-photorealistic interior of a lush Victorian glass greenhouse filled with exotic tropical plants, vibrant blooming orchids, tall ferns, colorful butterflies in flight, sunlight filtering through ornate glass roof creating realistic caustics and dew on leaves, intricate iron framework visible, misty atmosphere, 8K masterpiece.”
“Create a clear, 45° top-down isometric miniature 3D cartoon scene of Japan's signature dish: sushi, with soft refined textures, realistic PBR materials, gentle lighting, on a small raised diorama base with minimal garnish and plate. Solid light blue background. At top-center: 'JAPAN' in large bold text, 'SUSHI' below it, small flag icon. Perfectly centered, ultra-clean, high-clarity, square format.”
“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.”
“Hyper-photorealistic full-body portrait of a female superhero standing triumphantly on a New York skyscraper rooftop at golden sunset, wearing a classic modest superhero costume with flowing cape, chest emblem, gloves, and boots in red and blue colors, practical design, short hair, strong determined heroic expression looking into the distance, powerful confident stance with hands on hips and cape billowing dramatically in the wind, detailed urban cityscape background, warm natural sunlight with sharp shadows and fabric highlights, ultra-sharp textures on suit, hair, and concrete, 8K masterpiece, empowering family-friendly style.”
“A glass cube on a wooden table. Inside the cube is a small blue sphere. On top of the cube sits a red book. A green plant is behind the cube, partially visible through the glass. Soft window light from the left.”
“Hyper-photorealistic scene of fluffy baby animals—a golden retriever puppy, tabby kitten, baby bunny, and red fox kit—with big expressive eyes and ultra-detailed soft fur, playfully chasing butterflies and tumbling together in a lush wildflower meadow, warm golden sunrise light with god rays and dew sparkles, joyful wholesome vibe, 8K masterpiece.”
“Swap the positions of the blue and yellow blocks”
Top Matchups
See how Nano Banana Pro performs head-to-head against other AI models, ranked by community votes in blind comparisons.
vs Stable Diffusion 3.5 Large
Challenge: Apollo 11: Journey to Tranquility
40% W · 60% L
vs Nano Banana 2
Challenge: Over-the-top cartoon caricature
50% W · 50% L
vs FLUX.2 [dev] Turbo
Challenge: Geometric Composition
0% W · 33% L · 67% T
vs Nano Banana
Challenge: Neutral Expression to Genuine Smile
67% W · 33% L
vs GPT Image 1.5
Challenge: Vintage Cafe Logo
0% W · 100% L
Nano Banana Pro is best for
See all Use CasesThis 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.
Gallery
View all 23 imagesNano 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 Vertex AI, fal.ai, Replicate, and Gemini API 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.