Nano Banana Pro (Gemini 3 Pro Image) API

Most advanced image generation with accurate visuals and clarity

Try Now
Nano Banana Pro

This model is not currently supported on Together AI.

Visit our Models page to view all the latest models.

Introducing Nano Banana Pro

Nano Banana Pro is Google DeepMind's most advanced image generation and editing model, built on Gemini 3 Pro for state-of-the-art text rendering and visual accuracy. Delivering dramatically cleaner details and far more accurate visuals than previous generation models, Nano Banana Pro excels at creating infographics, slides, and layouts with exceptional clarity while maintaining consistency across 14 input images and up to 5 people — now available on Together AI with 2K and 4K resolution output for professional-grade results.

SOTA
Text Rendering
Accurate, legible text in multiple languages
14
Image Composition
Blend multiple inputs with 5-person consistency
4K
Resolution Output
Studio-quality 2K and 4K generation
Key Capabilities
Dramatically Better Text Rendering: SOTA accuracy for infographics, slides, and layouts with legible multi-language text from taglines to paragraphs
Cleaner, More Accurate Visuals: Far greater clarity and detail refinement compared to previous generation image models
Advanced Composition Control: Maintain consistency across 14 input images with up to 5-person identity preservation in complex scenes
Precise Creative Controls: Professional-grade adjustments to color, composition, camera angles, and lighting at 2K/4K resolution on Together AI

Nano Banana Pro (Gemini 3 Pro Image) API Usage

Endpoint

curl -X POST "https://api.together.xyz/v1/chat/completions" \
  -H "Authorization: Bearer $TOGETHER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemini-3-pro-image",
    "messages": [
      {
        "role": "user",
        "content": "What are some fun things to do in New York?"
      }
    ]
}'
curl -X POST "https://api.together.xyz/v1/images/generations" \
  -H "Authorization: Bearer $TOGETHER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemini-3-pro-image",
    "prompt": "Draw an anime style version of this image.",
    "width": 1024,
    "height": 768,
    "steps": 28,
    "n": 1,
    "response_format": "url",
    "image_url": "https://huggingface.co/datasets/patrickvonplaten/random_img/resolve/main/yosemite.png"
  }'
curl -X POST https://api.together.xyz/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $TOGETHER_API_KEY" \
  -d '{
    "model": "google/gemini-3-pro-image",
    "messages": [{
      "role": "user",
      "content": [
        {"type": "text", "text": "Describe what you see in this image."},
        {"type": "image_url", "image_url": {"url": "https://huggingface.co/datasets/patrickvonplaten/random_img/resolve/main/yosemite.png"}}
      ]
    }],
    "max_tokens": 512
  }'
curl -X POST https://api.together.xyz/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $TOGETHER_API_KEY" \
  -d '{
    "model": "google/gemini-3-pro-image",
    "messages": [{
      "role": "user",
      "content": "Given two binary strings `a` and `b`, return their sum as a binary string"
    }]
  }'
curl -X POST https://api.together.xyz/v1/rerank \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $TOGETHER_API_KEY" \
  -d '{
    "model": "google/gemini-3-pro-image",
    "query": "What animals can I find near Peru?",
    "documents": [
      "The giant panda (Ailuropoda melanoleuca), also known as the panda bear or simply panda, is a bear species endemic to China.",
      "The llama is a domesticated South American camelid, widely used as a meat and pack animal by Andean cultures since the pre-Columbian era.",
      "The wild Bactrian camel (Camelus ferus) is an endangered species of camel endemic to Northwest China and southwestern Mongolia.",
      "The guanaco is a camelid native to South America, closely related to the llama. Guanacos are one of two wild South American camelids; the other species is the vicuña, which lives at higher elevations."
    ],
    "top_n": 2
  }'
curl -X POST https://api.together.xyz/v1/embeddings \
  -H "Authorization: Bearer $TOGETHER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "input": "Our solar system orbits the Milky Way galaxy at about 515,000 mph.",
    "model": "google/gemini-3-pro-image"
  }'
curl -X POST https://api.together.xyz/v1/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $TOGETHER_API_KEY" \
  -d '{
    "model": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
    "prompt": "A horse is a horse",
    "max_tokens": 32,
    "temperature": 0.1,
    "safety_model": "google/gemini-3-pro-image"
  }'
curl --location 'https://api.together.ai/v1/audio/generations' \
  --header 'Content-Type: application/json' \
  --header 'Authorization: Bearer $TOGETHER_API_KEY' \
  --output speech.mp3 \
  --data '{
    "input": "Today is a wonderful day to build something people love!",
    "voice": "helpful woman",
    "response_format": "mp3",
    "sample_rate": 44100,
    "stream": false,
    "model": "google/gemini-3-pro-image"
  }'
curl -X POST "https://api.together.xyz/v1/audio/transcriptions" \
  -H "Authorization: Bearer $TOGETHER_API_KEY" \
  -F "model=google/gemini-3-pro-image" \
  -F "language=en" \
  -F "response_format=json" \
  -F "timestamp_granularities=segment"
curl --request POST \
  --url https://api.together.xyz/v2/videos \
  --header "Authorization: Bearer $TOGETHER_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
    "model": "google/gemini-3-pro-image",
    "prompt": "some penguins building a snowman"
  }'
curl --request POST \
  --url https://api.together.xyz/v2/videos \
  --header "Authorization: Bearer $TOGETHER_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
    "model": "google/gemini-3-pro-image",
    "frame_images": [{"input_image": "https://cdn.pixabay.com/photo/2020/05/20/08/27/cat-5195431_1280.jpg"}]
  }'

from together import Together

client = Together()

response = client.chat.completions.create(
  model="google/gemini-3-pro-image",
  messages=[
    {
      "role": "user",
      "content": "What are some fun things to do in New York?"
    }
  ]
)
print(response.choices[0].message.content)
from together import Together

client = Together()

imageCompletion = client.images.generate(
    model="google/gemini-3-pro-image",
    width=1024,
    height=768,
    steps=28,
    prompt="Draw an anime style version of this image.",
    image_url="https://huggingface.co/datasets/patrickvonplaten/random_img/resolve/main/yosemite.png",
)

print(imageCompletion.data[0].url)


from together import Together

client = Together()

response = client.chat.completions.create(
    model="google/gemini-3-pro-image",
    messages=[{
    	"role": "user",
      "content": [
        {"type": "text", "text": "Describe what you see in this image."},
        {"type": "image_url", "image_url": {"url": "https://huggingface.co/datasets/patrickvonplaten/random_img/resolve/main/yosemite.png"}}
      ]
    }]
)
print(response.choices[0].message.content)

from together import Together

client = Together()
response = client.chat.completions.create(
  model="google/gemini-3-pro-image",
  messages=[
  	{
	    "role": "user", 
      "content": "Given two binary strings `a` and `b`, return their sum as a binary string"
    }
 ],
)

print(response.choices[0].message.content)

from together import Together

client = Together()

query = "What animals can I find near Peru?"

documents = [
  "The giant panda (Ailuropoda melanoleuca), also known as the panda bear or simply panda, is a bear species endemic to China.",
  "The llama is a domesticated South American camelid, widely used as a meat and pack animal by Andean cultures since the pre-Columbian era.",
  "The wild Bactrian camel (Camelus ferus) is an endangered species of camel endemic to Northwest China and southwestern Mongolia.",
  "The guanaco is a camelid native to South America, closely related to the llama. Guanacos are one of two wild South American camelids; the other species is the vicuña, which lives at higher elevations.",
]

response = client.rerank.create(
  model="google/gemini-3-pro-image",
  query=query,
  documents=documents,
  top_n=2
)

for result in response.results:
    print(f"Relevance Score: {result.relevance_score}")

from together import Together

client = Together()

response = client.embeddings.create(
  model = "google/gemini-3-pro-image",
  input = "Our solar system orbits the Milky Way galaxy at about 515,000 mph"
)

from together import Together

client = Together()

response = client.completions.create(
  model="meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
  prompt="A horse is a horse",
  max_tokens=32,
  temperature=0.1,
  safety_model="google/gemini-3-pro-image",
)

print(response.choices[0].text)

from together import Together

client = Together()

speech_file_path = "speech.mp3"

response = client.audio.speech.create(
  model="google/gemini-3-pro-image",
  input="Today is a wonderful day to build something people love!",
  voice="helpful woman",
)
    
response.stream_to_file(speech_file_path)

from together import Together

client = Together()
response = client.audio.transcribe(
    model="google/gemini-3-pro-image",
    language="en",
    response_format="json",
    timestamp_granularities="segment"
)
print(response.text)
from together import Together

client = Together()

# Create a video generation job
job = client.videos.create(
    prompt="A serene sunset over the ocean with gentle waves",
    model="google/gemini-3-pro-image"
)
from together import Together

client = Together()

job = client.videos.create(
    model="google/gemini-3-pro-image",
    frame_images=[
        {
            "input_image": "https://cdn.pixabay.com/photo/2020/05/20/08/27/cat-5195431_1280.jpg",
        }
    ]
)
import Together from 'together-ai';
const together = new Together();

const completion = await together.chat.completions.create({
  model: 'google/gemini-3-pro-image',
  messages: [
    {
      role: 'user',
      content: 'What are some fun things to do in New York?'
     }
  ],
});

console.log(completion.choices[0].message.content);
import Together from "together-ai";

const together = new Together();

async function main() {
  const response = await together.images.create({
    model: "google/gemini-3-pro-image",
    width: 1024,
    height: 1024,
    steps: 28,
    prompt: "Draw an anime style version of this image.",
    image_url: "https://huggingface.co/datasets/patrickvonplaten/random_img/resolve/main/yosemite.png",
  });

  console.log(response.data[0].url);
}

main();

import Together from "together-ai";

const together = new Together();
const imageUrl = "https://huggingface.co/datasets/patrickvonplaten/random_img/resolve/main/yosemite.png";

async function main() {
  const response = await together.chat.completions.create({
    model: "google/gemini-3-pro-image",
    messages: [{
      role: "user",
      content: [
        { type: "text", text: "Describe what you see in this image." },
        { type: "image_url", image_url: { url: imageUrl } }
      ]
    }]
  });
  
  console.log(response.choices[0]?.message?.content);
}

main();

import Together from "together-ai";

const together = new Together();

async function main() {
  const response = await together.chat.completions.create({
    model: "google/gemini-3-pro-image",
    messages: [{
      role: "user",
      content: "Given two binary strings `a` and `b`, return their sum as a binary string"
    }]
  });
  
  console.log(response.choices[0]?.message?.content);
}

main();

import Together from "together-ai";

const together = new Together();

const query = "What animals can I find near Peru?";
const documents = [
  "The giant panda (Ailuropoda melanoleuca), also known as the panda bear or simply panda, is a bear species endemic to China.",
  "The llama is a domesticated South American camelid, widely used as a meat and pack animal by Andean cultures since the pre-Columbian era.",
  "The wild Bactrian camel (Camelus ferus) is an endangered species of camel endemic to Northwest China and southwestern Mongolia.",
  "The guanaco is a camelid native to South America, closely related to the llama. Guanacos are one of two wild South American camelids; the other species is the vicuña, which lives at higher elevations."
];

async function main() {
  const response = await together.rerank.create({
    model: "google/gemini-3-pro-image",
    query: query,
    documents: documents,
    top_n: 2
  });
  
  for (const result of response.results) {
    console.log(`Relevance Score: ${result.relevance_score}`);
  }
}

main();


import Together from "together-ai";

const together = new Together();

const response = await client.embeddings.create({
  model: 'google/gemini-3-pro-image',
  input: 'Our solar system orbits the Milky Way galaxy at about 515,000 mph',
});

import Together from "together-ai";

const together = new Together();

async function main() {
  const response = await together.completions.create({
    model: "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
    prompt: "A horse is a horse",
    max_tokens: 32,
    temperature: 0.1,
    safety_model: "google/gemini-3-pro-image"
  });
  
  console.log(response.choices[0]?.text);
}

main();

import Together from 'together-ai';

const together = new Together();

async function generateAudio() {
   const res = await together.audio.create({
    input: 'Today is a wonderful day to build something people love!',
    voice: 'helpful woman',
    response_format: 'mp3',
    sample_rate: 44100,
    stream: false,
    model: 'google/gemini-3-pro-image',
  });

  if (res.body) {
    console.log(res.body);
    const nodeStream = Readable.from(res.body as ReadableStream);
    const fileStream = createWriteStream('./speech.mp3');

    nodeStream.pipe(fileStream);
  }
}

generateAudio();

import Together from "together-ai";

const together = new Together();

const response = await together.audio.transcriptions.create(
  model: "google/gemini-3-pro-image",
  language: "en",
  response_format: "json",
  timestamp_granularities: "segment"
});
console.log(response)
import Together from "together-ai";

const together = new Together();

async function main() {
  // Create a video generation job
  const job = await together.videos.create({
    prompt: "A serene sunset over the ocean with gentle waves",
    model: "google/gemini-3-pro-image"
  });
import Together from "together-ai";

const together = new Together();

const job = await together.videos.create({
  model: "google/gemini-3-pro-image",
  frame_images: [
    {
      input_image: "https://cdn.pixabay.com/photo/2020/05/20/08/27/cat-5195431_1280.jpg",
    }
  ]
});

How to use Nano Banana Pro (Gemini 3 Pro Image)

Model details

Architecture Overview:
• Built on Gemini 3 Pro foundation model with enhanced reasoning and real-world knowledge
• State-of-the-art text rendering engine delivering dramatically better accuracy and legibility across multiple languages
• Multi-modal composition system supporting up to 14 input images with consistency maintenance across up to 5 distinct people
• Advanced creative control framework for precise adjustments to color, composition, and camera angles
• High-resolution output capabilities supporting 2K and 4K generation for professional-grade results
• Optimized for deployment on Together AI's serverless infrastructure

Key Capabilities:
• SOTA Text Rendering: Industry-leading text generation with accurate details, proper spacing, and legible fonts
• Cleaner Details: Far more accurate visuals with improved clarity and refinement across all elements
• Enhanced Multilingual Support: Generate and localize text content across multiple languages with cultural context
• Infographic Excellence: Purpose-built for creating clear, professional infographics, slides, and layouts
• Real-Time Knowledge Integration: Access to Google Search knowledge base for current information visualization
• SynthID Watermarking: Imperceptible digital watermarks embedded for transparency and content verification

Performance Characteristics:
• Text Quality: Best-in-class rendering from short taglines to long paragraphs with consistent accuracy
• Composition Complexity: Maintains visual consistency across 14+ input elements simultaneously
• Character Consistency: Preserves identity and resemblance of up to 5 people across scenes
• Resolution Range: Studio-quality outputs from standard to 4K resolution
• Detail Fidelity: Dramatically cleaner details compared to previous generation image models
• Creative Precision: Advanced localized editing for targeted region transformations

Prompting Nano Banana Pro (Gemini 3 Pro Image)

Applications & Use Cases

Professional Design & Marketing:
• Infographic Creation: Generate data visualizations, educational explainers, and information graphics with exceptional clarity
• Presentation Design: Create professional slide layouts with clean text rendering and visual hierarchy
• Marketing Materials: Produce posters, social media graphics, and campaign assets with precise branding
• Product Mockups: Transform sketches into photorealistic products with accurate text labels and details
• Advertising Creative: Studio-quality assets with advanced composition and color control

Enterprise & Business Applications:
• Data Visualization: Transform complex data into compelling visual formats with clear labels and legends
• Corporate Communications: Maintain brand consistency across visual touchpoints with up to 14-image composition
• Educational Content: Context-rich diagrams and explainers with accurate text and detailed illustrations
• Report Generation: Professional charts, graphs, and visual summaries at 2K/4K resolution
• Training Materials: Create instructional graphics and documentation with legible multi-language text

Content Creation at Scale:
• Social Media: Generate platform-optimized visuals with correct aspect ratios and high engagement potential
• Blog & Article Graphics: Featured images, inline graphics, and visual explanations with clarity
• E-commerce: Product visualization, lifestyle shots, and catalog imagery at professional quality
• Localization: Generate region-specific content with culturally appropriate text and imagery
• A/B Testing: Rapid variation generation for optimization and performance analysis

Technical & Developer Use Cases:
• API Integration: Build custom image generation into applications via Together AI
• Workflow Automation: Programmatic image creation for publishing and marketing pipelines
• Batch Processing: Scale visual content production for large catalogs and documentation
• Dynamic Content: Real-time image generation for personalized user experiences
• Multi-Platform Publishing: Generate assets optimized for web, print, and mobile simultaneously

Unique Advantages:
• SOTA Text Rendering: Industry-leading text accuracy eliminates manual text overlay work
• Cleaner Details: Dramatically improved visual fidelity across all generated elements
• 14-Image Composition: Unmatched ability to blend multiple inputs while maintaining consistency
• 5-Person Consistency: Preserve character identity across complex scenes and narratives
• Precise Creative Control: Professional-grade adjustments to color, composition, lighting, and camera angles
• Production-Ready Resolution: 2K and 4K output suitable for professional printing and large displays
• Serverless on Together AI: Pay-per-use pricing with automatic scaling and reliable inference

Looking for production scale? Deploy on a dedicated endpoint

Deploy Nano Banana Pro (Gemini 3 Pro Image) on a dedicated endpoint with custom hardware configuration, as many instances as you need, and auto-scaling.

Get started