Gemini 3 Pro Image (Nano Banana Pro)vsGPT-Image-2

Both image models, compared at each maker’s own API list prices. Every figure links to its source.

Where each stands among all scored models

Each line runs from the lowest to the highest score on the board; the tick is the median.

LMArena Text-to-Image#11 vs #5 of 37GPT-Image-2: 1,382Gemini 3 Pro Image (Nano Banana Pro): 1,246LMArena Image Edit#9 vs #5 of 33GPT-Image-2: 1,460Gemini 3 Pro Image (Nano Banana Pro): 1,390
  • Gemini 3 Pro Image (Nano Banana Pro)
  • GPT-Image-2

Key differences

Output modalities
Text, Image Gemini 3 Pro Image (Nano Banana Pro) model · as of Nov 1, 2026
Image GPT-Image-2 · as of Nov 3, 2026
OutputMaker’s official API · global · USD · Image tokens
$120.00 / 1M tokens Gemini API pricing · as of Nov 1, 2026
$30.00 / 1M tokens OpenAI API pricing · as of Nov 2, 2026

These differences use verified vendor specifications or each maker’s official API on the same region, currency, meter and billing conditions. Different conditions remain side by side in the full table; they do not establish which model is cheaper. Declared features describe support, not measured quality or a recommendation. Missing evidence does not mean a feature is unsupported.

Full comparison

Gemini 3 Pro Image (Nano Banana Pro) Google GPT-Image-2 OpenAI
Overview
ReleasedMay 28, 2026 Apr 21, 2026
Specs
Input modalitiesText, Image Text, Image
Output modalitiesText, Image Image
Max resolution6336 × 5504 3840 × 3840
EditingYes Yes
Reference images14 Not stated
Context65.54K Not stated
Max output32.77K Not stated
Pricing
Price per imagefrom $0.134Also priced under other conditions: 2K, 4K, Input1K from $0.005Also priced under other conditions: 1024×1024, 1536×1024, Medium quality, High quality1024×1536, Low quality
Cited scores
LMArena Text-to-Image1,246 2K thinking budget1,382 medium quality
LMArena Image Edit1,390 2K thinking budget1,460 medium quality

Headline prices may come from different channels, regions or tiers. Check each source before choosing a model; missing facts stay blank.

Model details and sources

Cited scores