← Models

Nano Banana 2 Lite

Google · Nano Banana

Google's fastest and cheapest Gemini 3.1 Flash image route for high-volume 1K generation.

Type
image
Context
N/A
Max Output
N/A
Status
current
Input
$0.25/1M tok
Output
$1.5/1M tok
API Access
Yes
License
proprietary
image-generation image-editing google low-latency cost-efficient stable batch
Released June 2026 · Updated July 6, 2026

Overview

Freshness note: Image-model capabilities, pricing, and lifecycle details can change quickly. This profile is a point-in-time snapshot last verified on July 6, 2026.

Nano Banana 2 Lite is Google’s efficiency-focused Gemini image model. The Gemini API model ID is gemini-3.1-flash-lite-image, and Google positions it as the fastest and cheapest member of the current Nano Banana family.

This is not the “best quality” route in the family. That job belongs to Nano Banana Pro. Nano Banana 2 Lite exists for high-volume interactive workflows where latency, price, and straightforward image edits matter more than multi-reference composition, rich grounding, or 4K asset production.

Capabilities

Google describes Nano Banana 2 Lite as a sub-2 second image generation and editing model for developer and consumer applications that need scale. It supports text and image inputs, text and image outputs, image generation, image editing, function calling, Batch API, and thinking at minimal and high levels.

The practical constraints are just as important. Lite only supports 1K output, does not support Search grounding, and is not optimized for multiple reference inputs or multi-turn sequential editing in the way the heavier Nano Banana 2 and Pro routes are. It does add a broad set of aspect ratios and is useful for fast local edits such as color swaps, stickers, and background changes.

Technical Details

This is an image-native model, so Signal Lens stores contextWindow and maxOutput as 0 and treats them as N/A in UI comparisons. Google’s current model card lists:

  • Model ID: gemini-3.1-flash-lite-image
  • Inputs: text and image
  • Outputs: image and text
  • Input token limit: 65,536
  • Output token limit: 4,096
  • Latest update: June 2026
  • Supported output size: 1K / 1024px
  • Watermarking: SynthID always on plus C2PA watermarking

Google’s image-generation docs describe Nano Banana as a four-route family: Nano Banana 2 Lite, Nano Banana 2, Nano Banana Pro, and legacy Nano Banana based on Gemini 2.5 Flash Image.

Pricing & Access

Nano Banana 2 Lite is available through the Gemini API and Google AI Studio. Current paid-tier standard pricing is:

  • Input: $0.25 per 1M text/image/video tokens
  • Output text and thinking: $1.50 per 1M tokens
  • Output images: $30 per 1M image-output tokens
  • Effective 1K image price: about $0.0336 per image

Batch pricing halves those rates to 0.125input,0.125 input, 0.75 text/thinking output, 15imageoutputper1Mtokens,orabout15 image output per 1M tokens, or about 0.0168 per 1K image.

Best Use Cases

Choose Nano Banana 2 Lite for high-volume thumbnails, simple visual variants, UI placeholders, lightweight image edits, internal tooling, and consumer experiences where speed and cost dominate.

Avoid it when the task needs grounded factual imagery, 2K/4K output, complex brand layouts, many reference images, or careful text rendering. Use Nano Banana 2 or Nano Banana Pro for those.

Comparisons

  • Nano Banana 2: Better generalist workhorse with larger limits, grounding, stronger editing, and up to 4K output.
  • Nano Banana Pro: Better for professional asset production, complex layouts, and higher-fidelity text or brand control.
  • Gemini 2.5 Flash Image: Legacy Nano Banana route; Google now recommends newer Nano Banana routes for fresh work.