Skip to content
Tier B — Production
Runs in:USMade in:United States
Google Gemini

Nano Banana 2

Tier B — Production · 66K tokens

Tokonomix Editorial Team·Reviewed by Mes Kalkan·
Section 01

Pricing

What one image costs you on Tokonomix, per size and quality.

Price per image — Nano Banana 2

from $0.1035 per image

Billed per image. The price depends on size and quality; your prompt is included.

SizeQualityPer image
Every image$0.1035

Editing an image: $0.1035 per image

Section 02

Capabilities

source: seed-gemini-ga-imagevisionjson modejson schemaimage editingprompt cachingimage generationoutputTokenLimit: 65536max output tokens: 32768
Section 03

Availability

Availability

No measurements yet

We haven't recorded enough API calls to show availability stats for this model. Data appears once the model starts receiving live traffic.

Section 04

Tokonomix benchmark verdicts

● 2026-11-22

Nano Banana 2 shifts to image output with multimodal input support

Nano Banana 2 represents a significant architectural pivot from its predecessor, transitioning to an image-output modality while adding vision input capabilities. The model now supports both visual understanding and image generation, alongside structured output formats including JSON mode and JSON schema. Image editing functionality has also been introduced, enabling manipulation of existing visual content. This configuration suggests the model is positioned for creative and visual design workflows rather than traditional text-based tasks. Users should note that this version cannot be evaluated against standard text intelligence benchmarks due to its output modality. The addition of vision input means the model can process both text and image prompts to generate visual outputs. Without performance data from previous versions, baseline comparisons are unavailable, but the feature set indicates a focus on multimodal creative applications. Users requiring text-based outputs should consider alternative models in the Gemini family.

Quality

—

Latency p50

—

Test runs

0

✓ Vision input capability added✓ Image generation and editing enabled✓ Structured output formats supported
Last automated test
— · Benchmark
P50 latency
—
P95 latency
—
Errors
0 / 0 runs
Last reviewed by Tokonomix Team·September 30, 2026