Breaking

Google Releases Nano Banana 2.1 as Design Arena Adds the Image Model

October 6, 2026 at 13:09 EDT

Media Generation
Foundation Models

Google has released Gemini Nano Banana 2.1, a new high-efficiency image generation and conversational editing model, and Design Arena says it is now available for creators to test. The update targets sharper visual design, more reliable edits and stronger subject consistency while keeping the model in Google's Flash-style efficiency tier.

Oct. 6, 2026 · Google

Nano Banana 2.1 moves into image workflows

The new Gemini image model targets more natural visuals, stronger multi-turn consistency and cheaper high-resolution output for generation and editing.

reference images per prompt

highest listed output resolution

$0.0756

standard 4K image-output price

Image-output cost scales with resolution

Standard image prices rise with token consumption: $0.0336 at 1K, $0.0504 at 2K and $0.0756 at 4K.

1K$0.0336

2K$0.0504

4K$0.0756

A design edit loop, not a general agent runtime

Prompt→References→Grounding→Edited image

The strongest story is controllability: repeated edits, consistent subjects and legible text inside designed images.

What improves

Lower listed image-output prices, support for 14 reference images, 4K output and stronger consistency targets for characters and objects.

What stays constrained

No seed, temperature, topP or topK controls, and no function calling, structured outputs or Live API support.

Continue reading

The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.