Post-Cutoff
Search For AI agents

Google DeepMindGemini Image familyCurrentImage generationReleased 20 Nov 2025

Nano Banana Pro (Gemini 3 Pro Image)

Studio-quality image generation built on Gemini 3 Pro reasoning; best for complex graphic design and text-heavy images.

Model idgemini-3-pro-image

Price$2 in, $12 out per 1M tokens

Checked29 September 2026

Where it stands

25newer image generation models since its release

The 5 newest are listed. All image generation models

Before it from Google
Nano Banana (Gemini 2.5 Flash Image)2 Oct 2025
After it from Google
Nano Banana 2 (Gemini 3.1 Flash Image)26 Feb 2026
Weights
Closed weights; access is hosted only.

How to call it

4 ways to use Nano Banana Pro (Gemini 3 Pro Image), with the model id each provider expects.

Providers, model ids, endpoints and docs for Nano Banana Pro (Gemini 3 Pro Image)
ProviderModel idEndpointDocs
Gemini API gemini-3-pro-image https://generativelanguage.googleapis.com/v1beta/models/gemini-3-pro-image:generateContent ai.google.dev
Google Cloud Gemini Enterprise Agent Platform (Vertex AI) docs.cloud.google.com
OpenRouter google/gemini-3-pro-image
Web app gemini.google.com

Pricing

Prices for Nano Banana Pro (Gemini 3 Pro Image)
Input$2 per 1M tokens
Output$12 per 1M tokens
Per 1K or 2K image$0.134
Per 4K image$0.24

As published: “per 1M tokens text/image input and text output; image output $120 per 1M tokens = $0.134 per 1K/2K image, $0.24 per 4K image”.

Source: ai.google.dev, checked 29 September 2026.

Specs

Input
Text and images
Output
Images and text
Context window
65,536 tokens
Max output
32,768 tokens
Open weights
No
Licence
Proprietary
Released
20 November 2025
Status
Current
Type
Image generation

What stands out

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

  • Accurate multilingual text in images

    Correct, legible text rendering in many languages, fonts and calligraphy; suited to infographics and mockups.

    Source: blog.google

  • Search-grounded visuals

    Uses Google Search to visualize real-time info (weather, sports, recipes) and factual data visualizations.

    Source: blog.google

  • Multi-image composition

    Blends up to 14 images while keeping resemblance of up to 5 people; up to 4K with lighting/depth-of-field edits.

    Source: blog.google

Notes

Launched 2025-11-20 as gemini-3-pro-image-preview (still on OpenRouter); stable id GA 2026-05-28. Highest-quality but priciest Gemini image model.

curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-3-pro-image:generateContent" \
  -H "x-goog-api-key: $GEMINI_API_KEY" -H "Content-Type: application/json" \
  -d '{"contents":[{"parts":[{"text":"Infographic explaining photosynthesis, labeled"}]}]}'

Sources: model page, pricing, launch blog.