Why does this model use `generateText` instead of `generateImage`?

Nano Banana Pro (Gemini 3 Pro Image) is a multimodal model, not a dedicated image generation API. It returns both text and image files in a single response. In the AI SDK, you call `generateText` and then iterate over `result.files` to access the generated images.

What types of diagrams can this model generate with accurate labels?

The model handles architectural schematics, data flow charts, and similar technical visualizations where text annotations must be precisely placed and readable.

How does web search integration work for image generation?

The model can query Google's index at generation time to retrieve current visual reference data. This helps render lesser-known landmarks, recent events, or real-world objects accurately rather than relying solely on training data.

What resolution does Nano Banana Pro (Gemini 3 Pro Image) support?

Nano Banana Pro (Gemini 3 Pro Image) generates higher resolution images compared to the base Nano Banana model. Check the model specs on this page for current resolution and pricing details.

Can I use this model with multiple input images for compositing?

Yes. Nano Banana Pro (Gemini 3 Pro Image) introduces higher multi-image input limits specifically to support compositing workflows where multiple reference images must be combined into a single generated output.

Do I need a Google account to use this model on AI Gateway?

No. AI Gateway manages all provider credentials. You authenticate via a Vercel API key or OIDC token and AI Gateway routes requests to the appropriate provider automatically.

How is Nano Banana Pro (Gemini 3 Pro Image) different from the base Nano Banana model?

Nano Banana Pro (Gemini 3 Pro Image) targets advanced and professional use cases. It adds diagram labeling accuracy, web-search grounding for up-to-date imagery, higher resolution output, and higher multi-image input limits. These capabilities are not available in the base flash-tier image model.

Can I receive both text and image output in the same request?

Yes. Because this is a multimodal model using `generateText`, a single request returns `result.text` for any written content and `result.files` containing the generated images, allowing mixed-media responses in one API call.

Google

Nano Banana Pro (Gemini 3 Pro Image)

Nano Banana Pro (Gemini 3 Pro Image) (Nano Banana Pro) is Google's advanced native image generation model built for professional and creative workflows, with accurate diagram labeling, web-search-grounded imagery, and higher resolution output.

View API reference

Input and output price: Prices from: Input $2, Output $12, Per 1M tokens
24h uptime: Loading AI Gateway uptime

Get API key Read the docs

import { generateText } from 'ai'

const result = await generateText({
  model: 'google/gemini-3-pro-image',
  prompt: 'Render a picture of a red balloon.',
});

Read docs

Overview Playground Providers Uptime Status Throughput Latency API Similar About FAQ

Copy link to headingPlayground

Try out Nano Banana Pro (Gemini 3 Pro Image) by Google. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.

Nano Banana Pro (Gemini 3 Pro Image)

Prompt

Describe what you want the model to generate.

Reference images(optional)

Add up to 4 images

Images to generate

Aspect ratio

Resolution

Your generated image will appear here

Copy link to headingProviders

Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.

Provider

Input	Output	Cache	Web Search	Capabilities	ZDR	No Training	Free Tier	Release Date

Google Legal:Terms•Privacy	$2/M+2 more	$12/M+2 more $0.13/img+3 more	Read$0.20/M	$14/K	+1				09/01/2025
Google Vertex AI Legal:Terms•Privacy	$2/M+1 more	$12/M+1 more $0.13/img+3 more	Read$0.20/M	$14/K+1 more					09/01/2025

Getting started

Call Nano Banana Pro (Gemini 3 Pro Image) through AI Gateway with the AI SDK generateText and streamText functions, or through the OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages APIs by changing the base URL. AI Gateway authenticates the request and routes it to an available provider.

Install the AI SDK (pnpm add ai dotenv), create an API key from the API Keys page, and set it as AI_GATEWAY_API_KEY in your environment. Full setup is covered in the text generation quickstart.

index.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'google/gemini-3-pro-image',
    prompt: 'Why is the sky blue?',
  });

  console.log(result.text);
}

main().catch(console.error);

Top-level parameters

The same Nano Banana Pro (Gemini 3 Pro Image) request in each API format AI Gateway supports.

top-level-params.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'google/gemini-3-pro-image',
    system: 'You are a concise technical assistant.',
    prompt: 'Summarize the tradeoffs between static generation and SSR.',
    maxOutputTokens: 1024,
    temperature: 0.5,
  });

  console.log(result.text);
}

main().catch(console.error);

Standard parameters like prompt, messages, temperature, and tools work as documented in the AI SDK docs. These are the parameters with model-specific behavior.

Parameter	Type	Required	Description
`model`	`string`	Yes	Model ID in the form `creator/model`, e.g. `google/gemini-3-pro-image`. AI Gateway routes the request to an available provider.
`maxOutputTokens`	`number`	No	Hard cap on generated tokens. Nano Banana Pro (Gemini 3 Pro Image) supports up to `32,768` output tokens.
`providerOptions`	`Record<string, JSONValue>`	No	AI Gateway routing options under `gateway`, plus any provider-native options under the provider’s own namespace — see the table below.

Input limits

Input	Formats	Sources	Max count	Max size	Limits
Text	—	—	—	—	Prompt and response share the 66K-token context window
Image	—	URL, base64, Uint8Array	—	—	Sent as image parts in messages; counts as input tokens

Provider options

Set AI Gateway routing options under providerOptions.gateway. For provider-specific options, pass them under the provider’s namespace as documented by the AI SDK.

Learn more in the AI SDK google provider docs.

provider-options.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'google/gemini-3-pro-image',
    prompt: 'Why is the sky blue?',
    providerOptions: {
      gateway: {
        only: ['google', 'vertex'],
      },
    },
  });

  console.log(result.text);
}

main().catch(console.error);

These AI Gateway routing options apply to every model. Provider-specific options pass through under the provider’s own namespace (for example providerOptions.anthropic) exactly as documented by the AI SDK.

Parameter	Type	Required	Description
`providerOptions.gateway.only`	`string[]`	No	Restrict routing to these provider slugs. Requests fail over only within the listed providers.
`providerOptions.gateway.order`	`string[]`	No	Preferred provider order. Listed providers are tried first; unlisted providers remain available as fallbacks.
`providerOptions.gateway.sort`	`'cost' \| 'ttft' \| 'tps'`	No	Rank candidate providers by price, time to first token, or tokens per second instead of the default routing order.
`providerOptions.gateway.zeroDataRetention`	`boolean`	No	Route only to providers with a zero-data-retention policy for this model.

Routing across providers

AI Gateway serves the same model through multiple providers and fails over automatically. order expresses a preference while keeping every provider eligible; only is a hard allowlist — if none of the listed providers are available the request fails instead of falling back.

Options under a provider's own namespace (for example providerOptions.anthropic) are forwarded to that provider with the request. Providers ignore option namespaces that don't apply to them, so it is safe to set provider options alongside gateway routing options.

Image input

Send images alongside text as message parts. Images count as input tokens.

image-input.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'google/gemini-3-pro-image',
    messages: [
      {
        role: 'user',
        content: [
          { type: 'text', text: 'Describe this image.' },
          { type: 'image', image: 'https://example.com/photo.jpg' },
        ],
      },
    ],
  });

  console.log(result.text);
}

main().catch(console.error);

Copy link to headingMore models by Google

Model

Context	Latency	Throughput	Input	Output	Cache	Web Search	Capabilities	Providers	ZDR	No Training	Free Tier	Release Date

google/gemini-3.8-flash

1.9 s

417 tps

$0.75/M

$3.75/M

Read$0.08/M

$14/K+1 more

09/02/2026

google/gemini-3.7-flash

0.9 s

279 tps

$0.75/M

$3.75/M

Read$0.08/M

$14/K+1 more

08/13/2026

google/gemini-3.5-flash-lite

0.5 s

307 tps

$0.30/M

$2.50/M

Read$0.03/M

$14/K+1 more

07/21/2026

google/gemini-3.1-flash-lite

0.6 s

255 tps

$0.25/M

$1.50/M

Read$0.03/M

$14/K+1 more

05/07/2026

google/gemini-3-flash

0.6 s

199 tps

$0.50/M+1 more

$3/M+1 more

Read$0.05/M

$14/K+1 more

12/17/2025

google/gemini-2.5-flash-lite

0.3 s

271 tps

$0.10/M

$0.40/M

Read$0.01/M

$35/K+1 more

06/17/2025

Copy link to headingAbout Nano Banana Pro (Gemini 3 Pro Image)

Nano Banana Pro (Gemini 3 Pro Image) (internally codenamed Nano Banana Pro) is Google's image generation model for professional and creative use cases that demand more than basic image synthesis. It has three headline capabilities: accurate label generation in diagrams and charts, integration of Google web search to ground images in up-to-date real-world information, and higher resolution output with higher multi-image input limits for complex compositing.

The diagram and labeling capability is particularly significant for technical teams. Generating an architectural diagram, data pipeline schematic, or annotated system map with accurate text labels has historically been a weak point for image models. Nano Banana Pro (Gemini 3 Pro Image) handles these workflows directly.

Unlike dedicated image generation APIs, Nano Banana Pro (Gemini 3 Pro Image) is a multimodal model that outputs both text and images through generateText. A single request can return a written description, a diagram, and explanatory annotations together. This makes it suitable for documentation generation, creative briefing, and technical illustration workflows where you need mixed-media output.

Copy link to headingWhat To Consider When Choosing a Provider

Configuration: Because this is a multimodal model that uses generateText (not generateImage) for image output, ensure your integration handles both result.text and result.files in the response when processing generated images.
Zero Data Retention: Zero Data Retention is available for this model. It is offered on a per-provider and model basis. See the documentation for details.
Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.

Copy link to headingWhen to Use Nano Banana Pro (Gemini 3 Pro Image)

Best for

Labeled technical diagrams: Generating architecture charts and data flow visualizations with accurate labeling
High-resolution creative workflows: Requiring higher resolution images and multi-image compositing
Web-search-grounded imagery: Applications that need image generation grounded in current real-world information via web search
Mixed-media pipelines: A single request should return both explanatory text and accompanying images
Professional design and documentation: Workflows where image quality must match that of prior-generation flagship models

Consider alternatives when

Pure image generation: You need images without text output (consider google/imagen-4.0-generate-001 or google/imagen-4.0-ultra-generate-001)
Language-only reasoning: Your use case has no image generation requirement (consider google/gemini-3-pro-preview)
Flash-tier speed and cost: Generation speed matters more than pro-level quality (consider google/gemini-3.1-flash-image-preview)
Video output required: Still images are not sufficient (consider the Veo model family)

Copy link to headingConclusion

Nano Banana Pro (Gemini 3 Pro Image) fills a gap in AI-assisted technical documentation and professional creative production. It generates accurately labeled diagrams and web-search-grounded imagery at higher resolutions. For teams building tools that produce technical illustrations, enriched visual content, or composite image workflows, it exposes capabilities that simpler image-generation models do not.

Copy link to headingFrequently Asked Questions

Why does this model use generateText instead of generateImage?
Nano Banana Pro (Gemini 3 Pro Image) is a multimodal model, not a dedicated image generation API. It returns both text and image files in a single response. In the AI SDK, you call generateText and then iterate over result.files to access the generated images.
What types of diagrams can this model generate with accurate labels?
The model handles architectural schematics, data flow charts, and similar technical visualizations where text annotations must be precisely placed and readable.
How does web search integration work for image generation?
The model can query Google's index at generation time to retrieve current visual reference data. This helps render lesser-known landmarks, recent events, or real-world objects accurately rather than relying solely on training data.
What resolution does Nano Banana Pro (Gemini 3 Pro Image) support?
Nano Banana Pro (Gemini 3 Pro Image) generates higher resolution images compared to the base Nano Banana model. Check the model specs on this page for current resolution and pricing details.
Can I use this model with multiple input images for compositing?
Yes. Nano Banana Pro (Gemini 3 Pro Image) introduces higher multi-image input limits specifically to support compositing workflows where multiple reference images must be combined into a single generated output.
Do I need a Google account to use this model on AI Gateway?
No. AI Gateway manages all provider credentials. You authenticate via a Vercel API key or OIDC token and AI Gateway routes requests to the appropriate provider automatically.
How is Nano Banana Pro (Gemini 3 Pro Image) different from the base Nano Banana model?
Nano Banana Pro (Gemini 3 Pro Image) targets advanced and professional use cases. It adds diagram labeling accuracy, web-search grounding for up-to-date imagery, higher resolution output, and higher multi-image input limits. These capabilities are not available in the base flash-tier image model.
Can I receive both text and image output in the same request?
Yes. Because this is a multimodal model using generateText, a single request returns result.text for any written content and result.files containing the generated images, allowing mixed-media responses in one API call.

Your use is subject to Google's Terms & Privacy Policies.

Agent Stack

Core Platform

Tools

Learn

Build

Explore

Nano Banana Pro (Gemini 3 Pro Image)

Copy link to headingPlayground

Copy link to headingProviders

Copy link to headingUptime24 hours

Copy link to headingThroughput24 hours

Copy link to headingLatency24 hours

Getting started

Top-level parameters

Input limits

Provider options

Routing across providers

Image input

Copy link to headingMore models by Google

Copy link to headingAbout Nano Banana Pro (Gemini 3 Pro Image)

Copy link to headingWhat To Consider When Choosing a Provider

Copy link to headingWhen to Use Nano Banana Pro (Gemini 3 Pro Image)

Best for

Consider alternatives when

Copy link to headingConclusion

Copy link to headingFrequently Asked Questions