Image

Nano Banana Pro API

Reasoning-driven images, up to 4K.

Generate and edit images with Google's Nano Banana Pro through one unified API. A single REST endpoint, async jobs, and webhooks, with no Google Cloud setup to manage.

Get API key Read the docs

4K
Max resolution: ~20s
Avg. generation: Search
Google grounding: 19 credits
From

Nano Banana Pro 4K product hero of the MERIDIAN mechanical wristwatch on dark slate

Playground

Try Nano Banana Pro right here.

model: nano-banana-pro

Prompt

Aspect ratio Resolution

Media inputs

Reference image

Advanced settings

Output format Google search grounding Image search grounding

Estimated cost 19–38 credits · $0.19–$0.38 Generate in Studio

Output Example

Nano Banana Pro infographic titled HOW A MECHANICAL WATCH WORKS with labeled mainspring, escapement, balance wheel, and gear train — A clean infographic titled HOW A MECHANICAL WATCH WORKS, labeled mainspring, escapement, balance wheel, and gear train, English labels only, navy and cream editorial layout.

Capabilities

What's new in Nano Banana Pro.

Reasoning-driven, studio quality

Built on Gemini 3 Pro, it brings advanced reasoning to image work, making it the strongest option for complex, multi-turn creation and editing.

Up to 4K resolution

It generates natively at 1K, 2K, and 4K, giving the detail needed for print, large-format, and high-end marketing assets.

Best-in-class text rendering

It produces legible, stylized, and multilingual text, which suits infographics, menus, diagrams, and detailed marketing layouts.

Grounding with Google Search

It can use Search as a tool to pull in real-time data, generating imagery from current weather, stock charts, or recent events, and verifying facts as it goes.

Studio-level creative controls

It adjusts camera angle, focus and depth of field, color grading, and scene lighting, including shifts like day to night or adding a bokeh effect.

Reasoning-based editing and consistency

It edits through a joint reasoning-generation process that preserves everything you did not ask it to change, and it holds character consistency well, with SynthID watermarking on every output.

Showcase

See what Nano Banana Pro can create.

Real outputs generated with Nano Banana Pro on Apiframe, each with the prompt behind it.

Try Nano Banana Pro

Nano Banana Pro bilingual MERIDIAN poster reading KEEP TIME and 時を刻む in gold on navy — A bilingual poster for MERIDIAN, English headline KEEP TIME and Japanese 時を刻む beneath, watch silhouette, navy and gold, print-ready.

Nano Banana Pro five-step MERIDIAN watchmaking flowchart: Design, Machine, Assemble, Regulate, Case — Turn handwritten watchmaker notes into a clean five-step flowchart: Design, Machine, Assemble, Regulate, Case. MERIDIAN wordmark small at top.

Nano Banana Pro edit of the MERIDIAN watch restaged from a daylight product still into a night scene with warm bokeh — Change this daytime product photo of the MERIDIAN watch to a moody night scene with warm city bokeh behind the watch, keeping the watch identical.

Nano Banana Pro lifestyle wrist shot of the MERIDIAN watch in daytime cafe window light — The same MERIDIAN wristwatch on a wrist, daytime cafe window light, photoreal, navy dial, cream numerals.

Nano Banana Pro MERIDIAN fox mascot character sheet across six labeled poses on cream paper — A consistent character sheet of the MERIDIAN fox mascot across six scenes: waving, sitting at a bench, holding a watch, walking, reading, and sleeping.

Pricing

Simple per-generation pricing.

19–38 credits per generation ≈ $0.19–$0.38

The rate depends on the resolution and options you pick.

You only pay for successful generations. Failed jobs are refunded automatically.
One credit balance across every model on Apiframe, no per-model plans.
Start with free credits. No subscription required.
Volume discounts on larger plans.

See plans and credit packs API pricing Nano Banana Pro credit cost and rates

Specs

At a glance.

Provider Google

Model ID nano-banana-pro

Aspect ratios 1:1, 3:4, 4:3, 9:16, 16:9

Resolutions 1K, 2K, 4K

Image input Supported

Avg. time ~30s

Comparison

Nano Banana Pro vs Nano Banana 2 vs Seedream 5.0 Pro

Nano Banana Pro against the sibling that undercuts it and the ByteDance flagship.

Feature	Nano Banana Pro	Nano Banana 2	Seedream 5.0 Pro
Max resolution	4K	4K	2K
Avg. generation	~20s	~12s	~20s
Signature strength	Deepest reasoning + search grounding	Pro quality at Flash speed	Up to 10 reference images
Price per image	19–38 credits (≈$0.19–$0.38)	8–19 credits (≈$0.08–$0.19)	6–11 credits (≈$0.06–$0.11)
Best for	Complex briefs and 4K finals	Everyday production work	Reference-pinned composition

Specs reflect what each model supports on Apiframe today, from the live catalog.

Quickstart

How to call the Nano Banana Pro API.

Send one POST /v2/images/generate request with your API key. The call returns a jobId you can poll, or pass a webhook_url and the result is pushed to you the moment it's ready.

Swap nano-banana-pro for any other model and nothing else changes.

Get API key Read the docs

generate.js

const response = await fetch("https://api.apiframe.ai/v2/images/generate", {
  method: "POST",
  headers: {
    "X-API-Key": "afk_your_api_key_here",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "prompt": "a sleek silver sports car on a coastal highway at sunset, hyper-realistic",
    "model": "nano-banana-pro",
    "nanoBananaParams": {
      "resolution": "1K",
      "image_input": "https://example.com/input.jpg",
      "output_format": "jpg",
      "google_search": false
    }
  }),
});
const { jobId } = await response.json();
console.log(jobId);

import requests

response = requests.post(
    "https://api.apiframe.ai/v2/images/generate",
    headers={
        "X-API-Key": "afk_your_api_key_here",
        "Content-Type": "application/json",
    },
    json={
        "prompt": "a sleek silver sports car on a coastal highway at sunset, hyper-realistic",
        "model": "nano-banana-pro",
        "nanoBananaParams": {
            "resolution": "1K",
            "image_input": "https://example.com/input.jpg",
            "output_format": "jpg",
            "google_search": False
        }
    },
)
print(response.json())  # { "jobId": "...", "status": "QUEUED" }

curl -X POST https://api.apiframe.ai/v2/images/generate \
  -H "X-API-Key: afk_your_api_key_here" \
  -H "Content-Type: application/json" \
  -d '{
        "prompt": "a sleek silver sports car on a coastal highway at sunset, hyper-realistic",
        "model": "nano-banana-pro",
        "nanoBananaParams": {
            "resolution": "1K",
            "image_input": "https://example.com/input.jpg",
            "output_format": "jpg",
            "google_search": false
        }
    }'

let job;
do {
  await new Promise((r) => setTimeout(r, 2000));
  job = await fetch("https://api.apiframe.ai/v2/jobs/JOB_ID", {
    headers: { "X-API-Key": "afk_your_api_key_here" },
  }).then((r) => r.json());
} while (job.status !== "COMPLETED" && job.status !== "FAILED");
console.log(job.result);

import requests, time

while True:
    job = requests.get(
        "https://api.apiframe.ai/v2/jobs/JOB_ID",
        headers={"X-API-Key": "afk_your_api_key_here"},
    ).json()
    if job["status"] in ("COMPLETED", "FAILED"):
        break
    time.sleep(2)
print(job["result"])

curl https://api.apiframe.ai/v2/jobs/JOB_ID \
  -H "X-API-Key: afk_your_api_key_here"

Input schema

Every field Nano Banana Pro accepts, with types and defaults. The full reference lives in the docs.

Field	Type	Description
prompt required	string	Text description of what to generate.
model required	string	The model identifier for this endpoint. Default:"nano-banana-pro" · "nano-banana-pro"
nanoBananaParams.resolution	string	Resolution Default:"1K" · "512px", "1K", "2K", "4K"
nanoBananaParams.image_input	string (URL)	Compose with or edit a reference image.
nanoBananaParams.output_format	string	Output format Default:"jpg" · "jpg", "png", "webp"
nanoBananaParams.google_search	boolean	Google search grounding Default:false
nanoBananaParams.image_search	boolean	Image search grounding Default:false

Nano Banana versions

Every Nano Banana image model on Apiframe. Switch with one parameter.

Use cases

What teams build with Nano Banana Pro.

Studio-grade finals

The reasoning-driven tier: it plans the composition before rendering, and outputs up to 4K for assets that will be inspected closely.

Fact-grounded imagery

Google Search grounding pulls real-world knowledge into the frame, current products, places, and events rendered accurately.

Text-heavy creative

Best-in-class text rendering in the family: dense copy, multilingual labels, and brand lockups come out clean.

Reasoning-based edits

Complex, multi-step edit instructions are interpreted rather than pattern-matched, keeping consistency across the change.

Reviews

9,800+ developers. One API.

Real Apiframe reviews from Trustpilot and G2.

Speeds up our ad creative iteration

The API integrates directly into my existing pipeline, so I can generate and iterate on image variations for Meta ads without jumping between tools. We can go from concept to a testable ad in the same day instead of spreading it across a week.

Ethan M. July 2026 G2

Fast, reliable, easy to integrate

Image generation requests are processed quickly, and the results are consistently high quality. Customer support has also been responsive whenever I had questions. It has saved me a lot of development time.

Nana Arianto July 2026 Trustpilot

Seamless integrations, effortless setup

Generating ad creatives for Facebook and Google ads is more streamlined now since we use APIFRAME to manage the workflow, which used to require a lot of time with official APIs. The initial setup was very easy, just a matter of using curl.

Bean A. July 2026 G2

Nano Banana Pro questions

What teams ask before shipping with Nano Banana Pro. Everything else lives in the docs.

What is Nano Banana Pro?

Google's Gemini 3 Pro Image, a higher-fidelity, reasoning-driven image generation and editing model, positioned as the quality tier above the original Nano Banana.

How is it different from Nano Banana?

Pro focuses on quality, detail, and reasoning, adding up to 4K output, Search grounding, and studio controls, while the original is the faster, cheaper, more casual option.

What resolution does it produce?

Up to 4K, with native 1K, 2K, and 4K options.

What is grounding with Google Search?

It lets the model bring real-time data into images, such as current weather or recent events, and check facts while generating.

How much does it cost?

On Apiframe, 19 credits ($0.19) per 1K or 2K image and 38 credits ($0.38) for 4K, and every output carries a SynthID watermark.

Where can you access it?

Through Apiframe, as well as the Gemini app, Google AI Studio, the Gemini API, and Vertex AI.