AI Research Atlas

Nano Banana 2.1

Google DeepMind · 6 October 2026

Google released Nano Banana 2.1, a Flash-tier image generation and editing model with better mask and ink editing, product recontextualization and factual accuracy, now on OpenRouter.

Nano Banana 2.1 succeeds Nano Banana 2 and Nano Banana Pro. OpenRouter's listing says it improves product recontextualization, mask and ink-based editing and factual accuracy, and supports 1K, 2K and 4K output with extended aspect ratios. Firstpost reports character consistency and control over lighting, camera angle and aspect ratio. NPowerUser reports better prompt adherence and text rendering, and rollout in Google Flow and Gemini apps.

Date
Tuesday, 6 October 2026
Lab
Google DeepMind
Kind
model
Access
closed API
Price
$1.50 in / $7.50 out per M tokens, image output $30 per M tokens (OpenRouter)

Figures

MeasureValueMeasured by
API input price per 1M tokens$1.50
OpenRouter listing
OpenRouter
API output price per 1M tokens$7.50
image output listed separately at $30 per 1M tokens
OpenRouter
Context window65,536 tokens
OpenRouter listing
OpenRouter

No Google primary page was read. The claim of generating up to twice as fast as GPT Image 2.5 comes from early community tests reported by NPowerUser and is unconfirmed.

Sources

  1. openrouter.ai/google/gemini-nano-banana-2.1
  2. www.firstpost.com/tech/google-unveils-nano-banana-2-1-with-subject-consistency-and-mask-ba
  3. nokiapoweruser.com/google-quietly-launches-nano-banana-2-1-image-model/

This record was checked against its sources on 6 October 2026. How we check

Read the daily brief for 6 October 2026