MODEL Google/DeepMind Last updated:

Nano Banana Pro / Gemini 3 Pro Image

4K Text-Native Image

Google DeepMind's image model integrated into Gemini 3 — internally "Nano Banana" — outputs 4K with industry-leading text rendering and strict SynthID watermarking on every pixel. The Gemini 3.1 Flash Image variant (Nano Banana 2) launched soon after as a cheap / fast tier.

Cost
High
$2.00 in / $12.00 out
How are Intelligence, Speed & Cost bucketed?
Intelligence and Speed buckets are percentile ranks on Artificial Analysis. Cost buckets are fixed dollar thresholds keyed off output-token price ($/M out).
Intelligence
  • Top 1%≤ 1%
  • Top 5%≤ 5%
  • Top 10%≤ 10%
  • Good≤ 25%
  • Medium≤ 50%
  • Below avg> 50%
Speed
  • Top 1%≥ 345 tok/s
  • Top 5%≥ 237 tok/s
  • Top 10%≥ 196 tok/s
  • Good≥ 146 tok/s
  • Medium≥ 90 tok/s
  • Slow< 90 tok/s
Cost
  • Freeopen weights · self-host
  • Low< $1 / M out
  • Moderate$1–5 / M out
  • High≥ $5 / M out

Why it matters

Combined with Gemini 3's native omni-modal architecture, Nano Banana made image generation a baseline LLM feature rather than a specialized tool. Closed the prompt-adherence + text-rendering gap with GPT Image 1.5 at the top of the leaderboards.

Core Capabilities

Generative
Produces images, video, audio, or other media.
Multimodal
Combines text, vision, and audio in one model.
Vision
Understands images, scenes, and visual context.

Context Window

Context window not disclosed.

Availability

API
Available
Product / App
Available
Open Source
Not released
Enterprise
Contact sales

Pricing Model

Pay per token
Input and output billed separately.
Pay-per-token

Capability / Performance

Where this model sits relative to the middle 60% of models in the tree. All scores are 0–10 (higher is better).

Lower 20% Upper 80% This model
Lower 20% 20th percentile — 20% of models score below this This model Where the current model lands Upper 80% 80th percentile — only 20% of models score above this Percentile boundaries are computed across every model in the tree that reports the underlying benchmark for each capability.

What it feels like

  • Vision-language model from Google DeepMind — see the linked sources below for benchmark and review coverage
  • Vision and multimodal tasks are the typical fit per the published model card

Best use cases

  • Vision tasks (charts, documents, images) per the model card
  • See the model spec and sources block for benchmarked use cases

Tools to try

Not ideal for

  • Tasks far outside the modalities listed in this model's spec
  • Workflows where a more recent successor in the same family scores higher

Model Evolution

View full evolution tree →