How do I call Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) on AI Gateway?

Set the model to `google/gemini-3.1-flash-lite-image` in the AI SDK, call `generateText` or `streamText`, and include `responseModalities: ['TEXT', 'IMAGE']` in `providerOptions.google`. AI Gateway handles provider routing, retries, and failover automatically.

What resolution does Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) generate?

1K resolution. That cap is part of what keeps Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) fast and inexpensive. For 2K or 4K output, use `google/gemini-3.1-flash-image` or `google/gemini-3-pro-image`.

How is Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) different from Gemini 3.1 Flash Image?

Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) is the speed tier: lower latency and cost in exchange for the higher resolutions, video input, and search grounding of Gemini 3.1 Flash Image. Choose Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) for volume and iteration speed rather than maximum output fidelity.

Should I migrate from Gemini 2.5 Flash Image?

Google recommends that `google/gemini-2.5-flash-image` users move to Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) for better quality, faster generation, and lower cost. The original Nano Banana is now the legacy model in the family.

Does Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) support image editing?

Yes. Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) handles prompt-based edits and multi-image composition alongside text-to-image generation. Complex masked edits, major lighting changes, and heavy multi-image blending can produce artifacts, so route those jobs to a higher tier in the family.

Are generated images watermarked?

Yes. Every image carries an invisible SynthID watermark that identifies the output as AI-generated.

How fast is Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite)?

Google positions Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) as its fastest image generation model, built for rapid creation and iteration. See the live latency metrics on this page for current performance through AI Gateway.

How does Zero Data Retention work with Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) through AI Gateway?

Yes, Zero Data Retention is available for this model. Zero Data Retention is offered on a per-provider basis. See https://vercel.com/docs/ai-gateway/capabilities/zdr for details.

Google

Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite)

Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) is the fastest, most cost-efficient image model in the Nano Banana family, generating and editing 1K images with reliable prompt adherence, strong character consistency, and legible in-image text for high-volume production workloads.

View API reference

Input and output price: Prices from: Input $0.25, Output $1.50, 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-3.1-flash-lite-image',
  prompt: 'Render a picture of a red balloon.',
});

Read docs

Overview Playground Providers Uptime Status Latency API Similar About FAQ

Copy link to headingPlayground

Try out Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) 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.

Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite)

Prompt

Describe what you want the model to generate.

Reference images(optional)

Add up to 4 images

Images to generate

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	$0.25/M	$1.50/M $0.03/img+1 more	Read$0.03/M	$14/K+1 more	+2				06/30/2026
Google Vertex AI Legal:Terms•Privacy	$0.25/M	$1.50/M $0.03/img+1 more	Read$0.03/M	$14/K+1 more	+2				06/30/2026

Getting started

Call Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) 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-3.1-flash-lite-image',
    prompt: 'Why is the sky blue?',
  });

  console.log(result.text);
}

main().catch(console.error);

Top-level parameters

The same Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) 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-3.1-flash-lite-image',
    system: 'You are a concise technical assistant.',
    prompt: 'Summarize the tradeoffs between static generation and SSR.',
    maxOutputTokens: 1024,
  });

  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-3.1-flash-lite-image`. AI Gateway routes the request to an available provider.
`maxOutputTokens`	`number`	No	Hard cap on generated tokens. Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) supports up to `4,096` output tokens. Reasoning tokens count toward this limit.
`reasoning`	`'provider-default' \| 'none' \| 'minimal' \| 'low' \| 'medium' \| 'high' \| 'xhigh'`	No	Provider-agnostic reasoning effort, available in AI SDK 7 or later. Maps to the provider’s native reasoning configuration; reasoning settings under `providerOptions` take precedence when both are set. See the Reasoning section below.
`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-3.1-flash-lite-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.

Reasoning

AI Gateway bridges reasoning across every API format. The AI SDK exposes a provider-agnostic top-level reasoning level (none, minimal, low, medium, high, or xhigh); the Chat Completions and Responses formats take the same effort under reasoning.effort; and the Anthropic Messages format uses a native thinking token budget. Whichever you send, the gateway maps it to the target model’s native configuration, converting between effort levels and token budgets as needed. Reasoning-related settings under providerOptions take full precedence over the top-level reasoning value and are never merged. Reasoning tokens typically count toward your output-token usage, though how they’re reported and billed varies by provider.

Learn more in the AI Gateway reasoning guide.

reasoning.ts

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

async function main() {
  const result = await generateText({
    model: 'google/gemini-3.1-flash-lite-image',
    prompt: 'Explain the Monty Hall problem step by step.',
    reasoning: 'high',
  });

  console.log(result.text);
}

main().catch(console.error);

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-3.1-flash-lite-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

412 tps

$0.75/M

$3.75/M

Read$0.08/M

$14/K+1 more

09/02/2026

google/gemini-3.7-flash

0.8 s

280 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

302 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

257 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

197 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

0.2 s

392 tps

$0.10/M

$0.40/M

Read$0.01/M

$35/K+1 more

06/17/2025

Copy link to headingAbout Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite)

Google released Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) on June 30, 2026 as the fastest, most cost-efficient image model in the Nano Banana family. Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) is built for high-throughput pipelines where teams generate thousands of images and iterate quickly, keeping per-image cost low enough for near-real-time and high-volume workflows.

Despite the speed focus, Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) retains the traits the Nano Banana family is known for: reliable prompt adherence, strong character consistency, and legible in-image text rendering. Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) handles text-to-image generation, prompt-based editing, and multi-image composition through a single multimodal interface, so a generation pipeline and an editing pipeline can share one model.

The main tradeoff is resolution. Output is capped at 1K, while other models in the family generate at 2K and 4K. Google positions the lineup in three tiers: Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) for speed and scale, Gemini 3.1 Flash Image as the generalist, and Gemini 3 Pro Image for complex professional work. Google also recommends Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) as the upgrade path from the original Nano Banana, google/gemini-2.5-flash-image, citing better quality, faster generation, and lower cost.

Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) accepts prompts within a context window of 65.5K tokens and returns text and images in the same response. Every generated image carries an invisible SynthID watermark for downstream identification of AI-generated content.

Copy link to headingWhat To Consider When Choosing a Provider

Configuration: Output resolution is capped at 1K; other models in the family generate at 2K and 4K. This is a multimodal model: call Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) with generateText or streamText and set responseModalities: ['TEXT', 'IMAGE'] in providerOptions.google to receive image output. Google notes that Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) can struggle with small faces, fine text detail, and complex masked edits, so route those jobs to a higher tier in the family.
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 Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite)

Best for

High-Volume Image Pipelines: Catalog imagery, thumbnails, and previews generated at scale where per-image cost dominates
Rapid Creative Iteration: Fast generation loops that let users explore many variations before a final render
Interactive Product Features: Low-latency image creation inside user-facing apps and tools
Cost-Sensitive Editing Workflows: Prompt-based edits and multi-image composition at the lowest cost in the family
Readable In-Image Text: Marketing cards, banners, and simple graphics that need legible rendered text

Consider alternatives when

Higher Resolution Required: 2K and 4K output need google/gemini-3.1-flash-image or google/gemini-3-pro-image
Complex Professional Compositing: Fine-detail work and heavy multi-image blending land better on google/gemini-3-pro-image
Video Input or Search Grounding: google/gemini-3.1-flash-image adds video-to-image and Google Image Search grounding
Text-Only Workloads: A text model like google/gemini-3.1-flash-lite avoids per-image billing entirely
Video Output Required: Generated clips need the Veo model family rather than still images

Copy link to headingConclusion

Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) makes image generation cheap and fast enough to treat as a high-volume primitive rather than a premium call. Keep Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) on the hot path for generation, iteration, and routine edits, and step up to Gemini 3.1 Flash Image or Gemini 3 Pro Image when a job needs higher resolution or heavier compositing.

Copy link to headingFrequently Asked Questions

How do I call Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) on AI Gateway?
Set the model to google/gemini-3.1-flash-lite-image in the AI SDK, call generateText or streamText, and include responseModalities: ['TEXT', 'IMAGE'] in providerOptions.google. AI Gateway handles provider routing, retries, and failover automatically.
What resolution does Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) generate?
1K resolution. That cap is part of what keeps Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) fast and inexpensive. For 2K or 4K output, use google/gemini-3.1-flash-image or google/gemini-3-pro-image.
How is Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) different from Gemini 3.1 Flash Image?
Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) is the speed tier: lower latency and cost in exchange for the higher resolutions, video input, and search grounding of Gemini 3.1 Flash Image. Choose Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) for volume and iteration speed rather than maximum output fidelity.
Should I migrate from Gemini 2.5 Flash Image?
Google recommends that google/gemini-2.5-flash-image users move to Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) for better quality, faster generation, and lower cost. The original Nano Banana is now the legacy model in the family.
Does Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) support image editing?
Yes. Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) handles prompt-based edits and multi-image composition alongside text-to-image generation. Complex masked edits, major lighting changes, and heavy multi-image blending can produce artifacts, so route those jobs to a higher tier in the family.
Are generated images watermarked?
Yes. Every image carries an invisible SynthID watermark that identifies the output as AI-generated.
How fast is Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite)?
Google positions Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) as its fastest image generation model, built for rapid creation and iteration. See the live latency metrics on this page for current performance through AI Gateway.
How does Zero Data Retention work with Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) through AI Gateway?
Yes, Zero Data Retention is available for this model. Zero Data Retention is offered on a per-provider basis. See https://vercel.com/docs/ai-gateway/capabilities/zdr for details.

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

Agent Stack

Core Platform

Tools

Learn

Build

Explore

Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite)

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

Reasoning

Image input

Copy link to headingMore models by Google

Copy link to headingAbout Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite)

Copy link to headingWhat To Consider When Choosing a Provider

Copy link to headingWhen to Use Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite)

Best for

Consider alternatives when

Copy link to headingConclusion

Copy link to headingFrequently Asked Questions