モデル料金エンタープライズ
500以上のAI Model API、オールインワンAPI。CometAPIで。
モデルAPI
開発者
クイックスタートドキュメントAPI ダッシュボード
会社
会社概要エンタープライズ
リソース
AIモデルブログ変更履歴サポート
利用規約プライバシーポリシー
© 2026 CometAPI · All rights reserved
Home/Models/Google/Nano Banana Pro
G

Nano Banana Pro

入力:$1.952/M
出力:$11.712/M
Nano Banana Pro is an AI model for general-purpose assistance in text-centric workflows. It is suitable for instruction-style prompting to generate, transform, and analyze content with controllable structure. Typical uses include chat assistants, document summarization, knowledge QA, and workflow automation. Public technical details are limited; integration aligns with common AI assistant patterns such as structured outputs, retrieval-augmented prompts, and tool or function calling.
新着
商用利用
Playground
概要
機能
料金プラン
API
バージョン

Basic features

  • Text → Image: full prompt-driven generation with strong prompt adherence.
  • Image → Image (edits): fine, targeted edits with maintained subject/character consistency across multiple edits.
  • Maximum output resolution: up to 4K (examples and supported exact pixel sizes depend on aspect ratio; the API exposes 1K/2K/4K presets)
  • Iterative planning & self-correction: an internal “multi-stage” pipeline that detects and corrects common visual mistakes (perspective, text, fine geometry).
  • Advanced in-image text rendering: clear, legible multi-language text (short captions to long paragraphs) suitable for posters, mockups, and infographics.
  • 5 characters and fidelity for up to 14 objects/reference images in a single workflow.
  • Watermarking / provenance: all generated images include a SynthID watermark; model embeds C2PA metadata for provenance in some product integrations.

Gemini 3 Pro Image versions & naming

  • gemini-3-pro-image-preview
  • gemini-3-pro-image

Technical details

Architecture

  • Lineage / backbone: Nano Banana Pro be built on Google’s evolving Gemini image stack — specifically the new Gemini 3 Pro Image / GEMPIX 2 architecture (a higher-capacity multimodal image+text framework). That is an evolution from Gemini 2.5 Flash Image (the original “nano-banana”) into a natively multimodal image model with expanded vision-language reasoning capabilities.
  • Model behavior: native multimodality (image + text + world knowledge), explicit pipelines for multi-image fusion, and an internal staged planner that refines outputs over multiple passes rather than producing a single static sample. Early reports indicate stronger geometric/optical reasoning (glass, refraction) versus prior versions.
  • Thinking / internal refinement: The model uses a visible “thinking” process internally to refine composition (the API documents this behavior and notes those internal steps are not charged as final image tokens).
  • Grounding & tools: Supports Search grounding (can incorporate web facts into diagram/infographic generation). It also supports system instructions for more deterministic control.

Key API parameters:

  • thinking_level (low / high) to trade latency vs reasoning depth;
  • media_resolution (low/medium/high) to control image OCR/detail reading tokens;
  • generationConfig.imageConfig to control aspect ratio/resolution in image outputs.

Image limits:

  • Input modalities supported: Text and images (the model does not accept audio or video as image-generation inputs).
  • Max images per prompt: 14 (for the Gemini 3 Pro Image preview).
  • Max image size (upload): 7 MB per input image.
  • Supported aspect ratios: 1:1, 3:2, 16:9, 9:16, 21:9, etc.

Output images / tokens: high limits, with 4K/4096px supported.

Benchmark performance

Short summary: public/early benchmarks so far are mostly qualitative / community-driven, but consistently report substantial improvements in resolution, artifact reduction, and physical fidelity versus the original nano-banana (Gemini 2.5 Flash Image). Specific named “challenges” have shown clear visual gains, but there are not yet (public) standardized numeric benchmark tables from Google comparing v1 → v2 across standard image-generation metrics.

  • Qualitative community tests: Cleaner edges, sharper micro-details, truer colors, and more faithful prompt adherence (fewer hallucinated props, more consistent characters). Popular informal tests include the so-called “Wine Glass Test” and “Glass Burger Challenge”, where GEMPIX2 (Nano Banana Pro) handles transparency and refraction markedly better than earlier builds.
  • Text handling: Nano Banana Pro shows visibly improved typography and text placement inside images (a persistent weakness for many image models). Community comparisons indicate fewer garbled rendered glyphs.
  • Throughput / UX: faster iteration speed and a UX that performs multi-stage refinement on the back end so users see more reliable first-pass results (reducing manual re-rolls).

Limitations & risks

  • Content filters & detection: Platforms integrating the model (e.g., Whisk/third-party apps) may enable strict celebrity or likeness detection and block certain outputs, which affects creative workflows that rely on realistic celebrity likenesses.
  • Hallucination / reasoning edge cases: while improved, the model can still produce physically unrealistic artifacts, especially with dense symbolic text inside images or highly technical diagrams — though NB2 appears to reduce these errors versus earlier versions.
  • Safety & misuse: generative image models can be used to create problematic or harmful content. Google applies constraints, content filters, and the SynthID watermark to help with provenance; nevertheless, misuse has occurred (high-profile controversy tied to a Nano Banana generated image in a politically sensitive setting).

How Nano Banana Pro stacks up vs other models

  • Nano Banana Pro (GEMPIX 2 / Gemini 3 Pro Image) — strong mobile integration, multi-image fusion, iterative self-correction, 2K native/4K upscaling, tightly integrated into Google apps (Search, Photos, Workspace/Gemini). Best for workflows that need reliable edits, continuity, and integration with Google services.
  • Midjourney — excels at stylized artistic outputs and community-driven prompt engineering; not typically targeted at photo-accurate multi-image fusion or deep multimodal editing pipelines.
  • Stable Diffusion / open weights — fully open, highly customizable, and hostable locally; ecosystem of checkpoints and fine-tuning is a decisive advantage for research and offline usage. Less “one-click” mobile integration and less consistent multi-image editing coherence out-of-the-box than Nano Banana Pro.
  • Seedream 4.0 (ByteDance) — recently positioned explicitly as a Nano Banana competitor, emphasizing ultra-fast rendering, 2K output, and support for many reference images (up to six). Positioned as a pro/creator alternative.

(These comparisons are high level; pick a winner by matching the tool to your workflow: openness/customizability → Stable Diffusion; stylized art → Midjourney; integrated, consistent mobile editing with aggressive iteration → Nano Banana Pro/ Gemini 3 Pro image family.)

Real-world use cases

  • Mobile photo editing & creative filters (Google Photos integrations — restyling, background fusion, portrait recomposition).
  • Marketing & ad assets — fast concept generation, consistent brand characters across multiple frames/angles.
  • Concept art & storyboarding — multi-image fusion helps keep character continuity across panels.
  • E-commerce / product mockups — generate consistent product shots in different contexts/lighting conditions.
  • Rapid prototyping for AR/VR assets — high quality 2K/4K outputs that can be upscaled for immersive uses.
  • How to accessl gemini-3-pro-image(Nano Banana Pro) API

Required Steps

  • Log in to cometapi.com. If you are not our user yet, please register first
  • Get the access credential API key of the interface. Click “Add Token” at the API token in the personal center, get the token key: sk-xxxxx and submit.
  • Get the url of this site: https://api.cometapi.com/

Use Method

  1. Select the “gemini-3-pro-image” endpoint to send the API request and set the request body. The request method and request body are obtained from our website API doc. Our website also provides Apifox test for your convenience.
  2. Replace <YOUR_API_KEY> with your actual CometAPI key from your account.
  3. Insert your question or request into the content field—this is what the model will respond to.
  4. . Process the API response to get the generated answer.

CometAPI provides a fully compatible REST API—for seamless migration. Key details :

  • Base URL: https://api.cometapi.com/v1beta/models/gemini-3-pro-image-preview:generateContent
  • Model Names: gemini-3-pro-image
  • Authentication: Bearer YOUR_CometAPI_API_KEY header
  • Content-Type: application/json .

Nano Banana Proの機能

Nano Banana Proのパフォーマンスと使いやすさを向上させるために設計された主要機能をご紹介します。これらの機能がプロジェクトにどのようなメリットをもたらし、ユーザーエクスペリエンスを改善するかをご確認ください。

Nano Banana Proの料金

Nano Banana Proの競争力のある価格設定をご確認ください。さまざまな予算や利用ニーズに対応できるよう設計されています。柔軟なプランにより、使用した分だけお支払いいただけるため、要件の拡大に合わせて簡単にスケールアップできます。Nano Banana Proがコストを管理しながら、お客様のプロジェクトをどのように強化できるかをご覧ください。
コメット価格 (USD / M Tokens)公式価格 (USD / M Tokens)割引
入力:$1.952/M
出力:$11.712/M
入力:$2.44/M
出力:$14.64/M
-20%

Nano Banana ProのサンプルコードとAPI

Nano Banana Proの包括的なサンプルコードとAPIリソースにアクセスして、統合プロセスを効率化しましょう。詳細なドキュメントでは段階的なガイダンスを提供し、プロジェクトでNano Banana Proの潜在能力を最大限に活用できるよう支援します。
POST
/v1beta/models/{model}:generateContent
Python
JavaScript
Curl
from google import genai
from google.genai import types
import os

# Get your CometAPI key from https://api.cometapi.com/console/token, and paste it here
COMETAPI_KEY = os.environ.get("COMETAPI_KEY") or "<YOUR_COMETAPI_KEY>"
BASE_URL = "https://api.cometapi.com"

client = genai.Client(
    http_options={"api_version": "v1beta", "base_url": BASE_URL, "timeout": 600000},
    api_key=COMETAPI_KEY,
)

prompt = "Da Vinci style anatomical sketch of a dissected Monarch butterfly. Detailed drawings of the head, wings, and legs on textured parchment with notes in English."
aspect_ratio = "1:1"  # "1:1","2:3","3:2","3:4","4:3","4:5","5:4","9:16","16:9","21:9"
resolution = "4K"  # "1K", "2K", "4K"

response = client.models.generate_content(
    model="gemini-3-pro-image-preview",
    contents=prompt,
    config=types.GenerateContentConfig(
        response_modalities=["TEXT", "IMAGE"],
        image_config=types.ImageConfig(
            aspect_ratio=aspect_ratio,
            image_size=resolution,
        ),
    ),
)

# Output directory
OUTPUT_DIR = os.path.join(os.path.dirname(__file__), "..", "output")
os.makedirs(OUTPUT_DIR, exist_ok=True)

for part in response.parts:
    if part.text is not None:
        print(part.text)
    elif image := part.as_image():
        output_path = os.path.join(OUTPUT_DIR, "butterfly_4k.png")
        image.save(output_path)
        print(f"Image saved to: {output_path}")

Python Code Example

from google import genai
from google.genai import types
import os

# Get your CometAPI key from https://api.cometapi.com/console/token, and paste it here
COMETAPI_KEY = os.environ.get("COMETAPI_KEY") or "<YOUR_COMETAPI_KEY>"
BASE_URL = "https://api.cometapi.com"

client = genai.Client(
    http_options={"api_version": "v1beta", "base_url": BASE_URL, "timeout": 600000},
    api_key=COMETAPI_KEY,
)

prompt = "Da Vinci style anatomical sketch of a dissected Monarch butterfly. Detailed drawings of the head, wings, and legs on textured parchment with notes in English."
aspect_ratio = "1:1"  # "1:1","2:3","3:2","3:4","4:3","4:5","5:4","9:16","16:9","21:9"
resolution = "4K"  # "1K", "2K", "4K"

response = client.models.generate_content(
    model="gemini-3-pro-image-preview",
    contents=prompt,
    config=types.GenerateContentConfig(
        response_modalities=["TEXT", "IMAGE"],
        image_config=types.ImageConfig(
            aspect_ratio=aspect_ratio,
            image_size=resolution,
        ),
    ),
)

# Output directory
OUTPUT_DIR = os.path.join(os.path.dirname(__file__), "..", "output")
os.makedirs(OUTPUT_DIR, exist_ok=True)

for part in response.parts:
    if part.text is not None:
        print(part.text)
    elif image := part.as_image():
        output_path = os.path.join(OUTPUT_DIR, "butterfly_4k.png")
        image.save(output_path)
        print(f"Image saved to: {output_path}")

JavaScript Code Example

import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";
import * as path from "node:path";
import { fileURLToPath } from "node:url";

// Get your CometAPI key from https://api.cometapi.com/console/token, and paste it here
const COMETAPI_KEY = process.env.COMETAPI_KEY || "<YOUR_COMETAPI_KEY>";
const BASE_URL = "https://api.cometapi.com";

const __filename = fileURLToPath(import.meta.url);
const __dirname = path.dirname(__filename);

async function main() {
  const ai = new GoogleGenAI({
    apiKey: COMETAPI_KEY,
    httpOptions: { baseUrl: BASE_URL },
  });

  const prompt =
    "Da Vinci style anatomical sketch of a dissected Monarch butterfly. Detailed drawings of the head, wings, and legs on textured parchment with notes in English.";
  const aspectRatio = "1:1"; // "1:1","2:3","3:2","3:4","4:3","4:5","5:4","9:16","16:9","21:9"
  const resolution = "4K"; // "1K", "2K", "4K"

  const response = await ai.models.generateContent({
    model: "gemini-3-pro-image-preview",
    contents: prompt,
    config: {
      responseModalities: ["TEXT", "IMAGE"],
      imageConfig: {
        aspectRatio: aspectRatio,
        imageSize: resolution,
      },
    },
  });

  // Output directory
  const outputDir = path.join(__dirname, "..", "output");
  if (!fs.existsSync(outputDir)) {
    fs.mkdirSync(outputDir, { recursive: true });
  }

  for (const part of response.candidates[0].content.parts) {
    if (part.text) {
      console.log(part.text);
    } else if (part.inlineData) {
      const imageData = part.inlineData.data;
      const outputPath = path.join(outputDir, "butterfly_4k.png");
      const buffer = Buffer.from(imageData, "base64");
      fs.writeFileSync(outputPath, buffer);
      console.log(`Image saved to: ${outputPath}`);
    }
  }
}

main();

Curl Code Example

#!/bin/bash
# Get your CometAPI key from https://api.cometapi.com/console/token, and paste it here

# Output directory
SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
OUTPUT_DIR="$SCRIPT_DIR/../output"
mkdir -p "$OUTPUT_DIR"

curl -s -X POST \
  "https://api.cometapi.com/v1beta/models/gemini-3-pro-image-preview:generateContent" \
  -H "x-goog-api-key: $COMETAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [{"parts": [{"text": "Da Vinci style anatomical sketch of a dissected Monarch butterfly. Detailed drawings of the head, wings, and legs on textured parchment with notes in English."}]}],
    "generationConfig": {
      "responseModalities": ["TEXT", "IMAGE"],
      "imageConfig": {"aspectRatio": "1:1", "imageSize": "4K"}
    }
  }' | jq -r '.candidates[0].content.parts[] | select(.inlineData) | .inlineData.data' | head -1 | base64 --decode > "$OUTPUT_DIR/butterfly_4k.png"

echo "Image saved to: $OUTPUT_DIR/butterfly_4k.png"

Nano Banana Proのバージョン

Nano Banana Proに複数のスナップショットが存在する理由としては、アップデート後の出力変動により旧版スナップショットの一貫性維持が必要な場合、開発者に適応・移行期間を提供するため、グローバル/リージョナルエンドポイントに対応する異なるスナップショットによるユーザー体験最適化などが考えられます。各バージョンの詳細な差異については、公式ドキュメントをご参照ください。
version
gemini-3-pro-image

その他のモデル

D

Doubao Seedream 4-5

D

Doubao Seedream 4-5

リクエストごと:$0.04
Seedream 4.5 is ByteDance/Seed’s multimodal image model (text→image + image editing) that focuses on production-grade image fidelity, stronger prompt adherence, and much-improved editing consistency (subject preservation, text/typography rendering, and facial realism).
F

FLUX 2 PRO

F

FLUX 2 PRO

無料
リクエストごと:$0.1
FLUX 2 PRO is the flagship commercial model in the FLUX 2 series, delivering state-of-the-art image generation with unprecedented quality and detail. Built for professional and enterprise applications, it offers superior prompt adherence, photorealistic outputs, and exceptional artistic capabilities. This model represents the cutting edge of AI image synthesis technology.
F

FLUX 2 FLEX

F

FLUX 2 FLEX

無料
リクエストごと:$0.01
FLUX 2 FLEX is the versatile, adaptable model designed for flexible deployment across various use cases and hardware configurations. It offers scalable performance with adjustable quality settings, making it ideal for applications requiring dynamic resource allocation. This model provides the best balance between quality, speed, and resource efficiency.
R

Black Forest Labs/FLUX 2 PRO

R

Black Forest Labs/FLUX 2 PRO

リクエストごと:$0.075
FLUX 2 PRO is the flagship commercial model in the FLUX 2 series, delivering state-of-the-art image generation with unprecedented quality and detail. Built for professional and enterprise applications, it offers superior prompt adherence, photorealistic outputs, and exceptional artistic capabilities. This model represents the cutting edge of AI image synthesis technology.
R

Black Forest Labs/FLUX 2 FLEX

R

Black Forest Labs/FLUX 2 FLEX

リクエストごと:$0.24
FLUX 2 FLEX is the versatile, adaptable model designed for flexible deployment across various use cases and hardware configurations. It offers scalable performance with adjustable quality settings, making it ideal for applications requiring dynamic resource allocation. This model provides the best balance between quality, speed, and resource efficiency.
R

Black Forest Labs/FLUX 2 DEV

R

Black Forest Labs/FLUX 2 DEV

リクエストごと:$0.075
FLUX 2 DEV is the development-friendly version optimized for research, experimentation, and non-commercial applications. It provides developers with powerful image generation capabilities while maintaining a balance between quality and computational efficiency. Perfect for prototyping, academic research, and personal creative projects.

関連ブログ

7 Nano Banana Pro Prompts that You Should to Try!
Dec 9, 2025
gemini-3-pro-image
nano-banana-pro

7 Nano Banana Pro Prompts that You Should to Try!

Google’s Nano Banana Pro (the marketing name for the Gemini 3 Pro Image family) landed as a major step forward in image generation and editing tools. It’s