Post-Cutoff

Google DeepMindGemini Image familyCurrentImage generationReleased 6 Oct 2026

Nano Banana 2.1 (Gemini Nano Banana 2.1)

Google’s default fast image generation/editing model from Oct 2026, successor to Nano Banana 2 (gemini-3.1-flash-image).

Model idgemini-nano-banana-2.1

Price$1.50 in, $7.50 out per 1M tokens

Checked7 October 2026

Where it stands

6newer image generation models since its release

The 5 newest are listed. All image generation models

Before it from Google
Nano Banana 2 Lite (Gemini 3.1 Flash-Lite Image)30 Jun 2026
Weights
Closed weights; access is hosted only.

How to call it

4 ways to use Nano Banana 2.1 (Gemini Nano Banana 2.1), with the model id each provider expects.

Providers, model ids, endpoints and docs for Nano Banana 2.1 (Gemini Nano Banana 2.1)
ProviderModel idEndpointDocs
Gemini API gemini-nano-banana-2.1 https://generativelanguage.googleapis.com/v1beta/models/gemini-nano-banana-2.1:generateContent ai.google.dev
Google AI Studio aistudio.google.com
OpenRouter google/gemini-nano-banana-2.1
Web app gemini.google.com

Pricing

Prices for Nano Banana 2.1 (Gemini Nano Banana 2.1)
Input$1.50 per 1M tokens
Output$7.50 per 1M tokens
Per 1K image$0.0336
Per 2K image$0.0504
Per 4K image$0.113

As published: “per 1M tokens: $1.50 input (text/image/video), $7.50 text+thinking output, $30 image output (= $0.0336 per 1K, $0.0504 per 2K, $0.113 per 4K image); Batch is half price; no free tier”.

Source: ai.google.dev, checked 7 October 2026.

Specs

Input
Text, images, video and PDF
Output
Images and text
Context window
131,072 tokens
Max output
32,768 tokens
Open weights
No
Licence
Proprietary
Training cutoff
March 2026
Released
6 October 2026
Status
Current
Type
Image generation

What stands out

What its maker marketed at launch, and what people found later, each with its source.

  • Half the per-image price of Nano Banana 2

    Image output is $30 per 1M tokens versus $60 for gemini-3.1-flash-image: a 1K image costs $0.0336 instead of $0.067. Input is pricier ($1.50 vs $0.50 per 1M).

    Source: ai.google.dev

  • Built on Gemini 3.6 Flash

    Model card: ‘Nano Banana 2.1 is based on Gemini 3.6 Flash’, with a March 2026 knowledge cutoff.

    Source: deepmind.google

  • Configurable thinking and search grounding

    Thinking levels minimal / medium (default) / high; grounding with Google Web and Image Search; up to 14 reference images (4 consistent characters, 10 objects).

    Source: ai.google.dev

  • Fixed panorama tiling

    Fixes tiling artifacts at 1:4, 4:1, 1:8 and 8:1 aspect ratios at 2K and 4K, and improves text and infographic layout.

    Source: ai.google.dev

Notes

GA on the Gemini API on 2026-10-06 (stable id only, no preview id). Also rolled out in the Gemini app, AI Mode in Search, Flow, Stitch, Google Ads and Gemini Enterprise (per The Decoder). It deprecates gemini-3.1-flash-image (no shutdown date yet). No caching, function calling or structured outputs. The Decoder quotes a $0.0756 4K price; the official pricing page says $0.113 (3,780 tokens), which is the figure used here.

curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-nano-banana-2.1:generateContent" \
  -H "x-goog-api-key: $GEMINI_API_KEY" -H "Content-Type: application/json" \
  -d '{"contents":[{"parts":[{"text":"An infographic about the water cycle"}]}]}'

Sources: model page, pricing, Gemini API changelog, Oct 6 2026, model card, The Decoder.