Google releases Nano Banana 2.1 image model at roughly half the price

Google releases Nano Banana 2.1 image model at roughly half the price

Google has released Nano Banana 2.1, a new model for image generation and editing. It replaces Nano Banana 2, which came out in February 2026, and Google says it improves on previous versions "across the board." The model is built on Gemini 3.6 Flash.

Prices fall by roughly half compared with Nano Banana 2. A 1K image now costs 3.36 cents, down from 6.70 cents. A 4K image drops from 15.10 to 7.56 cents. For comparison, Nano Banana Pro costs considerably more at 13.40 cents per 1K image.

According to Google, version 2.1 improves visual quality, text rendering, character consistency across conversation turns, wide panoramas and infographics. It can process up to 14 reference images at once, keeping up to four characters and ten objects consistent. The model also connects to Google Search and offers minimal, medium and high thinking levels that affect image quality. It runs at Flash-tier speed and supports 1K, 2K and 4K resolutions.

The source is careful about how 2.1 stacks up against Pro. Nano Banana Pro likely remains Google's best image model, since it uses the most recent Pro model, 3.1, while 2.1 uses Gemini 3.6 Flash. In benchmarks, 2.1 sometimes beats Pro by a wide margin, but Nano Banana 2 also matched Pro in those tests. In practice, Pro often still produces noticeably better images. Google itself calls 2.1 "the more efficient counterpart" to Pro. The next major gain in image quality could come with Google's announced Pro model, Gemini 4 Argon, according to The Decoder.

The model is already rolling out across Google's products: the Gemini app, AI Mode in Google Search, Google AI Studio, Flow by Google, Stitch by Google, Google Ads and the Gemini Enterprise Platform. More details are in the model card. Google will shut down the previous model, "gemini-3.1-flash-image," on October 29, 2026.

Key facts

  • Nano Banana 2.1 replaces Nano Banana 2 (February 2026) and runs on Gemini 3.6 Flash; Google says it improves on earlier versions "across the board."
  • A 1K image costs 3.36 cents, down from 6.70 cents; a 4K image falls from 15.10 to 7.56 cents. Nano Banana Pro costs 13.40 cents per 1K image.
  • Claimed gains: visual quality, text rendering, character consistency across turns, wide panoramas and infographics, with up to 14 reference images, four characters and ten objects kept consistent.
  • The model is rolling out in the Gemini app, AI Mode in Google Search, Google AI Studio, Flow, Stitch, Google Ads and the Gemini Enterprise Platform.
  • The previous model, "gemini-3.1-flash-image," will be shut down on October 29, 2026.

Why it matters

This is an iterative upgrade, not a leap. The headline change is cost: image prices drop by roughly half at both 1K and 4K while Google claims quality improves. That moves a Flash-speed model closer to the quality of Nano Banana Pro at a fraction of Pro's price (3.36 cents against 13.40 cents per 1K image). The Decoder adds that the next big quality jump could come with Google's announced Pro model, Gemini 4 Argon.

Who it affects

Anyone generating images through Google's stack: users of the Gemini app and AI Mode in Google Search, developers in Google AI Studio, creators using Flow and Stitch, advertisers in Google Ads, and enterprise customers on the Gemini Enterprise Platform. Teams still running "gemini-3.1-flash-image" are affected most directly, because that model is shut down on October 29, 2026.

How to use it

The model is already rolling out across the Gemini app, AI Mode in Google Search, Google AI Studio, Flow by Google, Stitch by Google, Google Ads and the Gemini Enterprise Platform. It supports 1K, 2K and 4K output, accepts up to 14 reference images, connects to Google Search, and offers minimal, medium and high thinking levels that affect image quality. Anyone on "gemini-3.1-flash-image" should switch before October 29, 2026. Google points to the model card for further details.

How solid is it

The improvement claims come from Google, including the "across the board" line and the list of gains in text rendering, character consistency, panoramas and infographics. The source does not give benchmark names or scores, only that 2.1 sometimes beats Pro by a wide margin in benchmarks. It also notes that Nano Banana 2 matched Pro in those same tests. The price figures are stated precisely, for 1K and 4K images.

Risks and caveats

Benchmarks and real use diverge here: Nano Banana Pro often still produces noticeably better images, and likely remains Google's best image model because it uses the more recent Pro model, 3.1. The cheaper model is positioned as the efficient option, not the top-quality one. Prices for 2K images are not given. The old model's shutdown date leaves a fixed deadline for anyone who has not migrated.

“the more efficient counterpart”

— Google, describing Nano Banana 2.1 relative to Nano Banana Pro (as reported by The Decoder)