Annual Plan SavingsSave 50% with an annual plan
View plans
Nano Banana Pro
Nano Banana Series
Nano Banana 2.1
RECOMMENDED

Sharper visuals · Accurate text · Consistent subjects

Nano Banana Pro

Generate high-quality images from text descriptions

Nano Banana 2

Next-gen · Google Search · 14 Input Images

Nano Banana 2 Lite

Lightweight and fast version of Nano Banana 2

GPT Image Series
GPT Image 2.6
RECOMMENDED

Generate images, edit with references, or create GIFs with GPT Image 2.6.

GPT Image 2.5

Natural lighting · Rich textures · Fine detail

GPT Image 2

Photoreal quality, precise text, pixel-level editing

GPT Image 1.5

Latest GPT 5.2 powered image generation

Seedream SeriesRELAXED
Seedream 5.5
NEW

Stable multi-round editing, transparent PNG and layer separation

Seedream 5 Pro

Rivals Nano Banana 2, precise editing with layer control

Seedream 5 Lite

Latest Seedream model, 4K quality, 8 aspect ratios

Seedream 4.0

4K support, relaxed content policy, batch generation

Qwen Image
Qwen Image 3.0

Complex layouts · Clear text rendering · Fine realism

MiniMax
MiniMax H3 Image
NEW

Faster renders · Lifelike texture · Consistent subjects

Z-Image
Z-Image

Fast photorealistic generation with relaxed content policy

Seedance Series
Seedance 2.5
NEW

30-second 4K video generation with native audio and advanced controls

Seedance 2
HOT

Cinema-quality video with native audio, up to 15s, text & image to video

Seedance 2 Mini
HOT

High-value Seedance 2 with native audio, 4-15s, 720p/1080p

Seedance 1.5 Pro

Supports first/last frame, text-to-video/image-to-video modes, cost-effective

Kling Series
Kling 4.0
NEW

Keyframes and omni reference, up to 30 seconds with native audio

Kling 3
HOT

Cinematic 4K generation with native audio

Kling o3

Omni model with first/last-frame control

Kling 2.6

Cinematic quality with native audio generation

Wan Series
Wan 3.0
NEW

Standard and high-speed Prime in one workspace

Wan 2.7
HOT

Text, image, reference, and video edit modes

Wan 2.6

Relaxed content policy

Wan 2.5

Relaxed content policy with high creative freedom

Google Series
Gemini Omni

Multimodal input × native audio, cinematic-level controllable video

Veo 3.1

Supports first/last frame video, multi-image reference video generation

Grok Series
Grok Imagine 1.5

Image-to-video by xAI Grok, flexible aspect ratios, up to 15s

Grok

Faster generation, weaker prompt adherence, supports spicy mode

Hailuo AI Series
H3 Max / Turbo

A cost-efficient MiniMax H3 Max studio for text-to-video, image-to-video and reference-led creation with native audio.

MiniMax H3 (Hailuo 03)

Hailuo 03 with text, first/last frame, and multimodal reference video modes

Hailuo AI

MiniMax Hailuo video: text/image to video, excellent first/last frame effects

Claude Opus 5.5
NEW

Newest Opus flagship for complex reasoning and coding

GPT-5.5

OpenAI flagship for coding and analysis

Enhance
Image Enhancement

Enhance image resolution, refine details

Video Upscale

Choose a higher output resolution for an existing clip.

Creative Tools
E-commerce Image Suite

Upload a product image and generate a complete set for major marketplaces

Nano Banana Pro Combo

Generate multi-card grid sheets in one call

GPT Image 2 Combo

Multi-card grid sheets powered by GPT Image 2

Audio
AI Audio
NEW

Generate dialogue, ambience, sound effects, and background music

AI Music

Generate original songs with custom lyrics and styles

Digital Humans
OmniHuman 1.5

Single image and audio to digital human video

V2V Lip Sync

Sync an existing video mouth motion to target audio

CreationsCreations
PricingPricing
Prompts
Nano Banana Prompt Examples

Explore high-quality prompt examples for Nano Banana Pro

GPT Image 2 Prompt Examples
NEW

Browse GPT Image 2 prompts for social posts, posters, and product visuals

Seedance 2.0 Video Prompt Examples

Browse curated Seedance 2.0 video prompt examples with videos, authors, publish dates, and engagement metrics.

Seedance 2 Prompt Guide

Dive deep into advanced features and best practices

AI Image Prompt Builder
NEW

Easily build complex prompts through a visual interface

Developers
API

Integrate Nano Banana Pro capabilities into your applications

MCP
NEW

Generate from Claude, Cursor and other AI assistants

In use
Nano Banana Pro
AI ImageAI Video

Nano Banana Pro

Nano Banana Pro is the revolutionary AI-powered image generation and editing platform that delivers consistent character editing and scene preservation with superior performance.

Email: support@nanobananapro.site

  • Email

Product

  • Home
  • Features
  • Showcases
  • Ecommerce
  • Pricing

Other Services

  • AI Image Upscaler
  • AI video upscaler
  • Grok
  • Veo 3.1
  • Wan 2.5
  • Kling 4.0

Other

  • Blog
  • About Us
  • Climate Action Plan

© 2026 bananapro.site. All rights reserved.

  • Privacy Policy
  • Terms of Service
  • Refund Policy
  • Referral Program
  • Invoice Management
🇺🇸 English🇨🇳 中文🇰🇷 한국어🇯🇵 日本語🇪🇸 Español🇩🇪 Deutsch🇫🇷 Français🇷🇺 Русский🇸🇦 العربية🇧🇷 Português🇮🇹 Italiano
PricingCreate

For developers

Nano Banana Pro MCP server

Let your AI assistant create images and videos on your behalf. Add one server address to a client that supports the Model Context Protocol, sign in to your account in the browser, and describe what you need in plain language.

How it works

  1. 1

    Add the server address

    Paste the address below into your client, using its command, its configuration file or its custom connector field.

    MCP server address

    https://preview.bananapro.site/api/mcp
  2. 2

    Sign in and allow access

    The client opens a browser window. Sign in to your Nano Banana Pro account and press Allow. No API key has to be typed.

  3. 3

    Describe what you need

    Ask for an image or a video in the conversation. The assistant chooses a tool, starts the task and returns the result links.

Manage connectionsAPI documentation

Setup by client

Choose your client. Menu names can differ slightly between versions.

Claude Code

  1. 1Run the command below in a terminal to add the server.
  2. 2In Claude Code, open /mcp, select nanobanana and finish the sign-in in the browser.
claude mcp add --transport http nanobanana https://preview.bananapro.site/api/mcp

Codex

  1. 1Run the first command in a terminal to add the server.
  2. 2Run the second command. A browser window opens.
  3. 3Sign in to your account and press Allow.
codex mcp add nanobanana --url https://preview.bananapro.site/api/mcp
codex mcp login nanobanana

Cursor and JSON clients

  1. 1Add the following to the MCP configuration file of the client, for example mcp.json in Cursor.
  2. 2Restart the client if needed. On first use it opens a browser window: sign in and press Allow.
{ "mcpServers": { "nanobanana": { "url": "https://preview.bananapro.site/api/mcp" } } }

Custom connector

  1. 1Open the client's settings and find the field for a custom connector or a remote MCP server.
  2. 2Paste the server address shown below and save.
  3. 3Choose Connect, sign in to your account and press Allow.
https://preview.bananapro.site/api/mcp

API key

  1. 1Use this method only for clients that cannot open a browser.
  2. 2Create a key on the API keys page. Send it in the header shown first, or add it under headers in a JSON configuration as in the second field.
  3. 3Store the key in the credential settings of the client and never share it.
Authorization: Bearer YOUR_API_KEY
{ "mcpServers": { "nanobanana": { "url": "https://preview.bananapro.site/api/mcp", "headers": { "Authorization": "Bearer YOUR_API_KEY" } } } }

What the assistant can do

The server exposes six tools. Four only read information and cost nothing; two start a generation and use credits.

ToolWhat it doesUses credits
list_modelsLists the image and video models available to your account and the request types each one accepts.No
get_balanceShows how many credits the account has left.No
generate_imageStarts an image generation or an image edit from a prompt and optional reference images.Yes
generate_videoStarts a video generation from a prompt, images or other reference media.Yes
get_taskChecks a generation and returns the result links once it has finished.No
list_tasksLists recent generations, which helps when a task id was lost.No

Command line tool

The nanobanana command creates images and videos from a terminal, from scripts and from AI apps that can run commands on your computer.

Requires Node.js 22 or later on macOS or Linux.

  1. 1

    Install the CLI

    Install the package @nanobanana-pro/cli with npm.

    npm install -g @nanobanana-pro/cli
  2. 2

    Sign in

    Run the command, then sign in to your account in the browser window and press Allow.

    nanobanana auth login
  3. 3

    Check the account and the models

    This command shows your credit balance. The command nanobanana models lists the available models.

    nanobanana account
  4. 4

    Create

    Save a request with the model and the prompt in request.json, then run the command. The option --wait keeps it running until the task is finished.

    nanobanana create --input request.json --wait
  5. 5

    Download the result

    Replace TASK_ID with the task ID returned by the previous command.

    nanobanana download TASK_ID --output result.png

See it run

Ask for a picture in one sentence. Your AI app writes the request, creates the image and saves the file.

You

Make an image of a paper boat drifting down a rainy street at night.

request.json

{ "model": "MODEL_ID", "prompt": "A paper boat drifting down a rainy street" }

$ nanobanana create --input request.json --wait

Task TASK_ID submitted; waiting for the result…

{ "status": "completed" }

$ nanobanana download TASK_ID --output result.png

{ "files": ["result.png"] }

AI app

Done. The image is saved as result.png.

Models

The assistant can use the image and video models that your account can use on the website and in the API.

  • Ask the assistant to call list_models for the current list of models and the kinds of request each one accepts.
  • Each model offers the same options as on the website. A setting that a model does not support is declined with an explanation.
  • Reference images and videos must be public https links. Files cannot be uploaded through MCP.

Credits and billing

  • Signing in and the free tools (list_models, get_balance, get_task, list_tasks) cost nothing.
  • generate_image and generate_video use the same credits as the website and the API, taken from your account balance.
  • A task that fails is refunded automatically.
  • Your subscription to the AI assistant itself is separate and is billed by that assistant.

Example requests

Once the server is connected, try asking your assistant something like this.

  • Which image and video models can I use? Show them as a short list.
  • Create a 16:9 product photo of a ceramic mug on a wooden table.
  • Turn this landscape photo into a five-second video: https://example.com/photo.jpg
  • Check the status of my latest task and send me the result link.

Frequently asked questions

Do I need an API key?

Not for clients that can open a browser. Signing in and pressing Allow is enough. A key is needed only for clients that cannot, as described under API key.

Where do I see or remove a connection?

Open the API keys page. Each connection appears there under the name of its client, and removing it ends that client's access.

What does a generation cost?

The same credits as on the website and in the API. A task that fails is refunded automatically.

Can I use my own images or videos as references?

Yes, as public https links. There is no file upload, so place the file where it can be reached and pass its address.

The connection works but the tools do not appear. What should I do?

Check that the sign-in was completed and that the client lists the server as connected. Then start a new conversation, because some clients load tools only at the start.

Where do I find the results?

The assistant returns the result links in the conversation. Earlier tasks can be listed again with list_tasks.

Prefer to call the API yourself?

The MCP server is built on the public API. The documentation lists every endpoint, parameter and model.

Read the API documentation