Updated

Nano Banana 2.1

Google’s Nano Banana 2.1 is an image-generation and editing model in the Gemini 3 family. Its model card lists text and image inputs, image and text outputs, and distribution through Gemini, Google AI Studio, the Gemini API, Search AI Mode, Ads, Flow, and Stitch.

By No Code MBA · Facts checked

Provider
Google
Announcement date
Status at last check
Generally available
Model family
Gemini 3
Preceding model
Nano Banana 2
Capabilities
Text, Image

What changed

Nano Banana 2.1 is an image generation and editing model built on Gemini 3.6 Flash. It takes text and image input with up to a 1M-token context and outputs images plus text (up to 64K text tokens), with optional thinking. In Google's human evaluations, the thinking mode scored 1050 Elo on text-to-image preference versus 990 for Nano Banana 2, and infographic factuality rose from 0.179 to 0.521. Google also reports gains in multi-character editing consistency.

Access and availability

Call gemini-nano-banana-2.1 through the Gemini API or Google AI Studio (paid tier only, with a Batch tier at half price). It is also in the Gemini app, Search AI Mode, Google Ads, Flow and Stitch.

Official access documentation

Pricing

$1.50 per million input tokens, $7.50 per million text and thinking output tokens, and $30 per million image output tokens (about $0.0336 per 1K image, $0.0504 per 2K and $0.113 per 4K)

Official pricing

What you can build

Compare it with your current image model on a small set of prompts that test text rendering, image edits, and multi-reference consistency; review outputs for fidelity and instruction-following errors.

Limitations

Google's model card lists weak rendering of small or long text, imperfect character consistency, spatial left/right confusion, limited 3D reasoning and world knowledge, and occasional slowness or timeouts. There is no free API tier.

Sources and release history