Nano Banana 2.1
Near-top image quality for about 3 cents an image, free to try in Gemini. Skip only if you need the very best edits.
Should you use it?
Pick it if
People and app developers who want strong images cheaply, or free in the Gemini app.
Best for: Strong images cheaply, or free to try in the Gemini app (Image models Top 20)
Skip it if
You need the best possible edit accuracy and cost is no issue; GPT Image 2.5 Sunburst leads every edit board.
You give up: Behind both GPT Image 2.5 models on every board, most clearly on edits
The short version
- What this is
- Google's fast image model for making and editing pictures, in the Gemini app and the Gemini API since October 2026.
- Why it matters
- It gets you close to the best image quality available for a small fraction of the price, or free in the app.
- Top 6 on arena.ai and 4th on Artificial Analysis for images.
- About $0.034 per 1K image in the API, against about $0.21 for GPT Image 2.5 at max.
- Turn off Keep Activity in the Gemini app if you don't want uploads used for training.
Good at
Our take
Nano Banana 2.1 is one of the best-value image models. It sits in the top 6 on all four boards we checked, and fourth on Artificial Analysis, at $0.0336 per 1K image in the API s1 s3 s5. The two GPT Image 2.5 models score higher but cost about six times as much per image s3. Muse Image is cheaper per image but scores lower, 59 against 73; see its review.
You can also try it in the Gemini app for free, though Google doesn't say which image model each plan gets s6. In the app, uploads can be used for training while Keep Activity is on; the paid API does not use your data to improve products s5 s7.
Score
A score from 0 to 100 per job, against everything available today. Overall 73 across 1 job, the average of the job scores.
New to this? What the scores and labels mean
- 0 to 100
- Our score for one job, like writing or coding, compared with everything else out today. 100 is the best available today. For AI models we build it from public data, such as Arena's blind votes and Epoch AI's independent tests; apps and tools are scored on our own checklist. The same tool can score differently for different jobs, and where two likely ranges overlap, we call it a tie.
- Our verdict
- Use it: a top choice for most people. Worth trying: good, and worth a go. Depends: good for some people or one kind of job. Wait: too early to tell, or not out for everyone yet. Skip: something else does the job better.
- First look
- Just released. We say what it is and whether to bother, and give it a score once public results exist.
- No score yet
- None of the public sources we use covers it yet, or the only evidence is from a source whose numbers we can't use, so we describe it in words instead.
- Best buy
- Nothing cheaper scores as well for that job.
- Best free
- The best score for that job that costs nothing, through a free plan or by running on your own computer.
- Pay as you go
- No monthly plan: you pay for each use, usually through a developer account.
- Checked
- The day we last confirmed the score and the price against the sources. Prices change often, so check the date.
- AI model
- The engine underneath, like GPT or Claude. You use it through an app or, if you code, directly.
- Open source
- Free to download and run on your own computer, so nothing leaves your machine.
#3 of the 5 we have scored for this job.
From blind votes (Arena) · Arena data, CC BY 4.0
Early, few votesData read 20 Oct
Alternatives
Better or cheaper for images, from our scores, then the ones we'd also look at. The same kind of product comes first.
- GPT Image 2.5 SunburstBetterImage model100Pay as you goScores 100 in images, against 73 here; price not checked. The top scorer on every board, for about six times the price per image. Side by side
- Qwen-Image-2.1Image model48FreeOpen weights you run yourself, for research and personal use only. Side by side
- Muse ImageImage model59FreeScores 59 for images against 73 here, at $10 per 1,000 images against $33.6 s3. Side by side
Value for money
Where it sits in images: higher is a better score, further left is cheaper to run. Green dots are the best value.
Evidence
Everything behind the call and the scores, folded so the page stays short. Spotted a wrong price, score or link? Report a mistake.
How we scored this
The images score is our own, built from public data: blind votes on Arena and, where they cover the job, Epoch AI's independent tests. How we combine them is our method and we don't publish it.
Public leaderboard
Reviews are drafted with help from AI models, including Anthropic's Claude. Model scores come only from outside leaderboards and independent evaluations, by a written rule.
No one paid for this review or gave us free access, and we earn nothing if you sign up. How we score
Sources 9
- s1arena.ai Text to Image leaderboard
- s2arena.ai Image Edit leaderboard (Single Image Edit)
- s3Artificial Analysis text-to-image leaderboard
- s4Artificial Analysis image editing leaderboard
- s5Gemini API pricing
- s6Google AI plans (Gemini subscriptions)
- s7Gemini Apps Privacy Hub
- s8Google DeepMind: Nano Banana (Gemini Image Flash)
- s9Gemini API changelog
Something here out of date or wrong? Report a mistake and we will check it against the source.
History 2 changes
Every change to a rating, the price or our call, with the reason. Scores are against what exists on the day, so they drift down as better things ship. Older entries come from before we moved to scores.
- New: Images ratedReviewed: images (rank 6, preliminary).
- Audit: replaced the Nano Banana 2 Lite alternative (skipped, and the page itself said not to pick it) with Muse Image, a cheaper option. Rating re-derived, unchanged.
Use it well 4 guides on this site
Pages on this site that help with the jobs above.