IMAGEgoogle

Google: Nano Banana Pro (Gemini 3 Pro Image)

Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...

Anyone in the Project can @-mention Google: Nano Banana Pro (Gemini 3 Pro Image) with the team's shared context - pooled credits, one chat, one memory.

All models

Starter is free forever - 1 Project, 100 credits/month, 1 MCP. No card.

Verdict

Nano Banana Pro delivers Google's multimodal capabilities at a mid-tier price point with a generous 65K context window. The $2/$12 per Mtok pricing sits between budget and premium tiers, making it viable for moderate-volume image analysis workflows. Best for teams that need reliable vision understanding without the cost of Gemini Pro or the limitations of free-tier models. The lack of public benchmarks means you're betting on Google's track record rather than proven performance data.

Best for

Screenshot analysis and UI documentation
Receipt and invoice data extraction
Moderate-volume image captioning workflows
Visual QA for customer support
Document layout understanding tasks

Strengths

The 65K context window handles multi-image analysis and long conversations without truncation, useful for comparing screenshots or processing document sequences. Google's vision models historically perform well on OCR and structured data extraction from images. The $2 input pricing makes it economical for batch processing compared to premium alternatives. Multimodal support means you can mix text and image inputs in a single request without preprocessing.

Trade-offs

No public benchmark data makes performance claims unverifiable — you'll need to test on your own data before committing. The $12 output pricing adds up quickly for verbose responses or batch jobs with detailed captions. Google's proprietary license limits deployment flexibility compared to open-weight alternatives. Falls into an awkward middle ground: costs more than budget models without the proven performance of Gemini Pro or Claude Sonnet.

Specifications

Provider: google
Category: image
Context length: 65,536 tokens
Max output: 32,768 tokens
Modalities: image, text
License: proprietary
Released: 2026-06-18

Pricing

Input: $2.00/Mtok
Output: $12.00/Mtok
Model ID: google/gemini-3-pro-image

Per-token prices show what the model costs upstream. On Switchy your team draws from one shared org credit pool - one plan, one balance for everyone.

Team cost calculator

Seats5 peopleMessages / seat / day80Avg turn size2 ktokOutput share30 %

Estimated monthly spend

$88.00

17.6M tokens / month
5 seats · 80 msgs/day

Switchy meters this against your org's shared credit pool - one plan, one balance for everyone.

Providers

Provider	Context	Input	Output	P50 latency	Throughput	30d uptime
google	66k	$2.00/Mtok	$12.00/Mtok	—	—	—

Performance

Performance snapshots are collected daily. Check back after the next ingestion run.

Benchmarks

Public benchmark scores are not available yet for this model. Check back after the next ingestion run.

Works well with

Top MCPs

Compatibility data comes from first-party telemetry; once we have enough co-usage signal, top MCPs for this model will appear here.

How Switchy teams use it

Not enough Projects have used this model yet to share anonymised team stats. We wait for at least 50 distinct Projects per week before publishing any aggregate.

Starter prompts

Extract Invoice Line Items

Extract all line items from this invoice image as a JSON array. Include item name, quantity, unit price, and total for each entry. Return only valid JSON with no additional commentary.

Open in a Project →

Compare UI Screenshots

I'm attaching before and after screenshots of a UI redesign. List the 5 most significant visual changes you observe, focusing on layout, color, and component placement. Be specific about locations.

Open in a Project →

Generate Alt Text

Write a concise alt text description for this image, 15-25 words. Focus on the main subject and any text visible in the image. Optimize for screen reader users.

Open in a Project →

Analyze Document Layout

Describe the layout structure of this document page. Identify headers, body text regions, tables, images, and their relative positions. Output as a hierarchical list.

Open in a Project →

Visual QA for Support

A user submitted this screenshot reporting an error. What error message or issue is visible? Describe the UI state and suggest what might have caused this problem based on what you see.

Open in a Project →

Compare with

Compare Google: Nano Banana Pro (Gemini 3 Pro Image) with…

More image models

See all image models →