whatmodel.sh / image / Nano Banana 2.1

Nano Banana 2.1

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Nano Banana 2.1 is a closed-weights image model from Google, released October 2026. Licence: proprietary.

Catalogue identity notes

Google's Gemini Nano Banana 2.1, API model gemini-nano-banana-2.1, released generally available on the Gemini API on 6 Oct 2026 as 'An update to Nano Banana 2 (gemini-3.1-flash-image)'; the same release note deprecates gemini-3.1-flash-image. The Arena entry 'gemini-nano-banana-2.1' (organization google, licence column Proprietary) is the exact API model id; first listed in image_edit on 2026-10-06 and in text_to_image on 2026-10-06/07. Distinct from nano-banana-2 (gemini-3.1-flash-image) and nano-banana-2-lite.

Model information sources

Release date ↗

80.7±2.2#4 of 144 image modelsfrom 2 benchmark results across 1 source* thinly tested, treat the rank as provisional

Score within the LMArena text-to-image comparison set only.

$ how it compares

The image models ranked either side of Nano Banana 2.1, out of 197 with a score, then more from Google.

#modelscorewhereRAMreleased
3GPT Image 2 OpenAI85±1api $0.053/image2026-04
4MAI-Image-2.6 Microsoft AI81±2comparison only2026-08
5Nano Banana 2.1 Google81±2api $0.034/image2026-10
6Grok Imagine Image 2.0 SpaceXAI79±2api $0.040/image2026-08
7Reve 2.1 Reve78±2api $0.25/image2026-07
more from Google
9Nano Banana 2 (Gemini 3.1 Flash Image) Google76±1api $0.067/image2026-02
10Nano Banana Pro (Gemini 3 Pro Image) Google76±1api $0.13/image2025-11
16Nano Banana 2 Lite (Gemini 3.1 Flash-Lite Image) Google73±2api $0.034/image2026-06

see all image models · find the ones that fit your machine

$ what it's good at

text to image▂▅▅▃▄▄█▃▁▂▃▁ #4 of 126 * · 71% of its score · 1 test
testresultvs the others in its rundifficultycountswhy
LMArena text-to-image1327.8 ✎▂▂▃▄▇█▄▂▄▃·▂ beats 71/75avg 1027▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 71%typical
image to image / editing▁▁·▃▂▃█▃▃▄▃▁ #4 of 62 * · 27% of its score · 1 test
testresultvs the others in its rundifficultycountswhy
Arena image edit1428.1 ✎▂▁▁▂▆▇█▄▆▅▁▂ beats 49/53avg 1153▇▇▇▇▇▇▇▇▇▇▇ 27%typical

$ where to run it

Through an API

api · $0.034/image · ai.google.dev ↗ · price sourceUSD per 1K (1024x1024) generated image on the Gemini Developer API Standard paid tier: image output is $30.00 per 1M tokens and Google states that 1K output images consume 1,120 tokens and are 'equivalent to $0.0336 per image' (2K $0.0504, 4K $0.113; Batch $0.0168 per 1K image). Input ($1.50 per 1M text/image/video) and text/thinking output ($7.50 per 1M) are additional; free tier 'Not available'. Product: Gemini Developer API. API model: gemini-nano-banana-2.1. Settings: tier=Standard paid, resolution=1K, batch=no, n=1. Price basis: provider-published per-image equivalent of the image-output rate. Currency: USD. Google Gemini API official pricing page (page footer 'Last updated 2026-10-07 UTC'), observed 2026-10-09.

$ how the score was worked out · LMArena leaderboard dataset 98%

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

sourceresultsshare of the scorelicence
LMArena leaderboard dataset2▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 98%CC BY 4.0
prior · pull toward the middle▇ 2%
weighted average= 80.7

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json