ZMIME
Google · image model · Released Aug 26, 2025

Nano Banana

Nano Banana image model for fast generation, edits, and character-consistent assets.

  • Image model
  • Proprietary
  • Text to image
  • Image editing
  • Deprecated
Arena score
1,291#33 of 61 · image editing
Starting price
—Not published
Largest size
—Not published
References
Yesinput images for editing
Quality & price

How it rates and what it costs

Text to image arena
1,149 ±2#36 of 82 · 907,282 votes
Image editing arena
1,291 ±2#33 of 61 · 11,448,539 votes

Arena scores come from blind, side-by-side human votes on the same prompts (higher is better; ± is the 95% range). Boards updated Oct 26, 2026 and Oct 27, 2026.

Specifications

The details

Lab
Google
Type
Image model
Released
Aug 26, 2025
Inputs
Text prompts, Reference images
Output
Images
Can do
Text to image, Image editing
Weights
Proprietary
Official price
$0.30 / $30.00input / output per million tokens, on Google
API model ID
gemini-2.5-flash-imageon Google
Availability
12 API hosts
Status
Deprecated by the provider

Google documentation

Same lab

More image models from Google

Questions

About Nano Banana

How good is Nano Banana?

In blind side-by-side votes, Nano Banana scores 1,149 for text to image (#36 of 82) and 1,291 for image editing (#33 of 61). Higher is better; scores within about 4 points of each other are effectively tied.

Who makes Nano Banana?

Nano Banana is an image model from Google, released Aug 26, 2025.

What can Nano Banana do?

Nano Banana accepts text prompts and reference images and produces images. In practice: text to image and image editing.

Is Nano Banana open source?

No. Nano Banana is proprietary; you use it through Google’s API or partner apps.

Where can I use Nano Banana?

It is listed by 12 API hosts we track; the model ID on Google is gemini-2.5-flash-image. The lab bills it per token: $0.30 input and $30.00 output per million tokens.

What are the alternatives to Nano Banana?

The closest image models from other labs, by release date, are Seedream 4.0 (ByteDance Seed, Sep 9, 2025), Qwen-Image (Alibaba (Qwen), Aug 7, 2025), GPT-5 Image (OpenAI, Oct 14, 2025) and Lucid Origin (Leonardo.Ai, Jun 1, 2025).