Text that reads correctly
Renders legible, styled text in many languages, so headlines, labels and menus come out usable instead of garbled.
Google
OperationalNano Banana Pro API
The Nano Banana Pro API: 1K, 2K and 4K images, 74% below Google's price.
Price per image74%off
- 1K
- $0.035
$0.134 - 2K
- $0.035
$0.134 - 4K
- $0.065
$0.24
Model ID
nano-banana-progenerate.py
from openai import OpenAIclient = OpenAI( base_url="https://api.zurelay.com/v1", api_key="YOUR_ZURELAY_KEY",)image = client.images.generate( model="nano-banana-pro", prompt="A red fox sitting in fresh snow at dawn, photo", size="2K", extra_body={"aspect_ratio": "16:9"},)print(image.data[0].url)Base URL https://api.zurelay.com/v1. Works with any OpenAI SDK.
- Resolutions
- 1K · 2K · 4K
- Aspect ratios
- 1:1 to 21:9
- Input
- Text, Image
- Output
- Image, Text
- Released
- Nov 20, 2025
- Uptime, 7 days
- New
Examples
Made with Nano Banana Pro. Straight from the API.
Every image here is a single API call with the prompt underneath it, not retouched or upscaled. They're shown as compressed WebP; the API returns full-quality PNG.
Portrait of a smiling spice vendor at a Marrakech market, deep laugh lines, a woven cap, pyramids of saffron, paprika and turmeric in front of him, warm afternoon light through a canvas awning, 85mm lens, shallow depth of field, photorealistic documentary photography. Close-up of a steaming bowl of tonkotsu ramen on a dark wooden counter, glossy chashu pork slices, a jammy soft-boiled egg cut in half, nori, scallions, sesame seeds, visible steam, moody side lighting, food photography, photorealistic. Product photograph of a glass jar of golden honey on a rustic wooden table, the kraft paper label clearly reads "Wildflower Honey" with a small bee illustration and "Blue Ridge Apiary" underneath, a wooden honey dipper dripping honey beside it, warm morning window light, shallow depth of field, commercial food photography. A lighthouse on a rocky cliff during a winter storm, huge waves crashing and exploding into white spray, the beam cutting through heavy rain, dramatic dark clouds, long exposure seascape photograph, ultra detailed, photorealistic. A mint green 1960s convertible parked on a coastal road in Amalfi, chrome details gleaming, pastel houses on the cliff behind, turquoise sea, bright midday Mediterranean sun, 35mm travel photography, photorealistic. A New York subway platform, a large printed poster on the tiled wall reads "Summer Jazz Nights, Every Friday in Central Park" with a saxophone photo, commuters blurred in motion, fluorescent lighting, 35mm street photography, photorealistic.
Pricing
Nano Banana Pro API pricing. A fraction of the list price.
Pay as you go from prepaid credit, with no subscription and no minimum. Requests that fail are never billed.
| Rate | zurelay | Google list | You save |
|---|---|---|---|
1K image per image | $0.035 | 74%off | |
2K image per image | $0.035 | 74%off | |
4K image per image | $0.065 | 73%off |
Every image is checked against the resolution and aspect ratio you asked for before it's delivered.
Savings calculator
Move the sliders to your monthly usage.
Images per month1,000
Resolution
zurelay
$35.00
Google list price
$134.00
You save every month$99.00
$1,188 a year
Overview
What is Nano Banana Pro?
Nano Banana Pro is Google DeepMind's image generation model, built on Gemini 3 Pro and served in the Gemini API as Gemini 3 Pro Image. The zurelay Nano Banana Pro API turns a text prompt into 1K, 2K or 4K images through an OpenAI-style images endpoint, for developers who need legible text, diagrams and production assets at a lower price per image.
Google announced Nano Banana Pro on November 20, 2025. Its API name is Gemini 3 Pro Image. Google describes it as a professional design engine with a reasoning core, aimed at studio-quality 4K visuals, complex layouts and precise text rendering. On zurelay, the Nano Banana Pro API uses the model ID nano-banana-pro and costs $0.035 per 1K or 2K image and $0.065 per 4K image.
Two things set it apart from lighter image models. The first is text: it renders clear, legible text in many languages, so it works for posters, menus, infographics and UI mockups. The second is knowledge: it draws on Gemini's reasoning and real-world knowledge, which helps with prompts that depend on facts, such as infographics, labeled diagrams and historical scenes. Thinking is built in and always on, so the model works through the composition before it renders the final image.
Output comes in three resolutions (1K, 2K and 4K) and ten aspect ratios: 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9 and 21:9. Every image carries Google's invisible SynthID watermark, which identifies it as AI-generated.
On zurelay, send a prompt to POST /v1/images/generations with size set to 1K, 2K or 4K and an optional aspect_ratio. You get up to 4 images per request, as a URL or as base64. zurelay checks every image's pixel dimensions against Google's official size for the resolution and ratio you asked for. An image that doesn't match counts as a failed attempt, and failed attempts are not billed.
Strengths
Where Nano Banana Pro shines. And what teams build with it.
Knowledge-aware visuals
Uses Gemini's reasoning and world knowledge to lay out infographics, diagrams and fact-dependent scenes.
Up to 4K resolution
Generates at 1K, 2K or 4K. Use 4K for print, hero banners and large displays, priced separately at $0.065.
The right shape from the start
Ten aspect ratios, from 21:9 banners to 9:16 stories, so you generate at the target format instead of cropping.
Use cases
Infographics and diagrams
Turn a data summary or process description into a labeled infographic or diagram with readable text.
Ads and marketing creatives
Produce posters, banners and social posts with the headline rendered in the image, in the exact aspect ratio each placement needs.
Localized assets
Generate the same layout with text in each target language for different markets.
Print and large-format 4K
Create posters, packaging mockups and hero images at 4K for print or high-density screens.
Get started
Call Nano Banana Pro in three steps.
No waitlist and no new SDK. If your code already talks to OpenAI, it already talks to zurelay.
- 1
Create a key
Sign up, add credit and create an API key. Set a monthly budget or a rate limit per key if you like.
- 2
Point your SDK at zurelay
Change the base URL. Everything else in your code stays the same.
https://api.zurelay.com/v1 - 3
Use nano-banana-pro
Send a prompt to /v1/images/generations with a size and aspect ratio, and get back a link to your image.
nano-banana-pro
Works with the tools you already use
Compare
Similar models. All on the same key.
65%off
Claude Opus 5.5
$1.40 / $7.00 per 1M tokens
Use Claude Opus 5.5 to plan layouts, write detailed image prompts or review generated images; it reads images but does not create them.
Claude Opus 5.5 API60%off
Claude Sonnet 5.5
$0.80 / $4.00 per 1M tokens
Use Claude Sonnet 5.5 for faster, lower-cost prompt writing and captioning around your image pipeline.
Claude Sonnet 5.5 API63%off
Nano Banana 2
from $0.025 per image
Nano Banana 2 by Google, 63% below list price.
Nano Banana 2 APIFAQ
Nano Banana Pro API questions.
Anything else, write to sales@zurelay.com and an engineer will answer.
What is the Nano Banana Pro API price on zurelay?
zurelay charges $0.035 per image at 1K or 2K and $0.065 per image at 4K. Google's list price is $0.134 and $0.24, so you save 74%. You pay per image generated, and failed attempts are not billed.
Is there a cheaper Nano Banana Pro API than Google's?
Yes. zurelay serves nano-banana-pro at 74% below Google's list price per image. It is the same model, and each image is checked against Google's official output size for your request. One key covers Nano Banana Pro and the text models in the catalog.
How do I generate a Nano Banana Pro 4K image?
POST to https://api.zurelay.com/v1/images/generations with model set to nano-banana-pro, your prompt, size set to 4K and an aspect_ratio such as 16:9. size also accepts pixel sizes like 1024x1536, which map to the nearest resolution and ratio. 4K images are billed at $0.065.
Can I call the Nano Banana Pro API with the OpenAI SDK?
Yes. Point the OpenAI SDK at https://api.zurelay.com/v1 and call images.generate with model nano-banana-pro and size 1K, 2K or 4K. aspect_ratio is not an OpenAI field, so pass it through extra_body in the Python SDK or as an extra body property in Node.
Which resolutions and aspect ratios does Nano Banana Pro support?
Three resolutions: 1K, 2K and 4K. Ten aspect ratios: 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9 and 21:9. If you leave size out, you get 1K, and if you leave aspect_ratio out, the model picks the shape.
What is Nano Banana Pro best at?
Images that need readable text or real-world accuracy: infographics, diagrams, posters, menus, ads and UI mockups. Google positions it as its premium choice for the most complex visual tasks, where world knowledge, localization and brand consistency matter.
What are the Nano Banana Pro limits per request?
Google lists a 65,536-token input limit and a 32,768-token output limit for the model. On zurelay's images endpoint, prompts can be up to 32,000 characters and n can be 1 to 4 images. You can also set your own requests-per-minute cap and spend limit on each key.
How are Nano Banana Pro images returned?
By default you get a signed URL for each image. Set response_format to b64_json to get base64 data in the response instead. Images are returned directly, not streamed.
Are Nano Banana Pro images on zurelay the same as from Google's API?
Yes, they come from the same model, and zurelay rejects any image that doesn't match Google's official size for your request. Every image carries Google's SynthID watermark. Generation is sampled, so the same prompt gives a different image each time on any API. zurelay is an independent service and is not affiliated with or endorsed by Google.
More models on zurelay
All models- Claude Opus 5.5 API$1.40 / $7.00 per 1M tokens−65%
- GPT-6 Astra API$2.50 / $12.50 per 1M tokens−75%
- Nano Banana 2 APIfrom $0.025 per image−63%
- Claude Sonnet 5.5 API$0.80 / $4.00 per 1M tokens−60%
- GPT-6.1 Sol API$0.50 / $2.50 per 1M tokens−75%
- GPT-6 Sol API$0.50 / $2.50 per 1M tokens−75%
- GPT-6 Luna API$0.025 / $0.125 per 1M tokens−75%
- Grok 4.7 API$0.70 / $2.10 per 1M tokens−65%
- MiMo V2.6 Pro API$0.18 / $0.36 per 1M tokens−59%
- MiMo V2.6 Flash API$0.06 / $0.12 per 1M tokens−57%
- DeepSeek V4.1 Flash API$0.037 / $0.15 per 1M tokens−88%
- DeepSeek V4 Flash API$0.045 / $0.18 per 1M tokens−85%
- DeepSeek V4 Flash 0731 API$0.022 / $0.06 per 1M tokens−61%
- DeepSeek V4 Pro 0813 API$0.23 / $0.62 per 1M tokens−84%
- Claude Fable 5.1 API$3.50 / $17.50 per 1M tokens−65%
- Claude Fable 5 API$3.50 / $17.50 per 1M tokens−65%
- Claude Opus 5 API$1.75 / $8.75 per 1M tokens−65%
- Claude Opus 4.8 API$1.75 / $8.75 per 1M tokens−65%
- Claude Opus 4.7 API$1.78 / $8.93 per 1M tokens−64%
- Claude Opus 4.6 API$1.75 / $8.75 per 1M tokens−65%
- Claude Haiku 4.5 API$0.38 / $1.90 per 1M tokens−62%
- GPT-5.6 Sol API$1.14 / $5.70 per 1M tokens−72%
- GPT-5.6 Terra API$0.54 / $3.26 per 1M tokens−73%
- GPT-5.6 Luna API$0.08 / $0.49 per 1M tokens−59%
- Gemini 3.7 Flash API$0.32 / $1.59 per 1M tokens−58%
- Gemini 3.5 Flash-Lite API$0.12 / $1.04 per 1M tokens−58%
- Gemini 3.1 Flash-Lite API$0.10 / $0.59 per 1M tokens−61%
- GLM-5.3 API$0.38 / $1.21 per 1M tokens−73%
- GLM-5.2 API$0.38 / $1.21 per 1M tokens−73%
- Kimi K3 API$1.27 / $6.37 per 1M tokens−58%
- Qwen 3.8 Max API$1.20 / $3.60 per 1M tokens−40%
- Qwen 3.8 Flash API$0.07 / $0.22 per 1M tokens−53%
- Qwen 3.8 Omni Flash API$0.075 / $0.235 per 1M tokens−50%
- HY4 Preview API$0.40 / $1.20 per 1M tokens−52%
- MiniMax M2.7 API$0.13 / $0.51 per 1M tokens−57%
- GPT Image 2.5 Flare API$0.02 per image−62%
- GPT Image 2.5 Sunburst API$0.02 per image−62%
- GPT Image 2 API$0.02 per image−62%
- Seedance 2.5 APIfrom $0.14 per secondVideo
- Seedance 2.0 APIfrom $0.097 per secondVideo
- Seedance 2.0 Fast APIfrom $0.074 per secondVideo
- Seedance 2.0 Mini APIfrom $0.047 per secondVideo
Stop paying list price.
Start saving today.
Create a key in seconds, point the SDK you already use at zurelay, and every request costs up to 85% less from the first token.