IMAGEgoogle

Google: Nano Banana 2 (Gemini 3.1 Flash Image)

Gemini 3.1 Flash Image, a.k.a. "Nano Banana 2," is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines advanced...

Anyone in the Project can @-mention Google: Nano Banana 2 (Gemini 3.1 Flash 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 2 is Google's budget image-understanding model with a 131K token context window and $0.50/Mtok input pricing — roughly 5x cheaper than GPT-4o for vision tasks. It handles batch image analysis and OCR workflows where speed and cost matter more than nuanced visual reasoning. Expect competent performance on straightforward extraction tasks but weaker results on complex spatial reasoning or fine-grained detail work. Reach for this when you're processing hundreds of receipts or product photos and need to keep inference costs under control.

Best for

Batch OCR on receipts and invoices
Product catalog image tagging
Cost-sensitive screenshot analysis
High-volume document digitization
Simple visual QA at scale

Strengths

The 131K context window lets you pack dozens of images into a single request, useful for comparing product shots or analyzing multi-page documents without chunking. Input pricing at $0.50/Mtok undercuts most vision models by a factor of 3-5, making it viable for high-throughput pipelines where you're processing thousands of images daily. Google's Flash architecture delivers sub-second response times on typical image-text pairs, keeping batch jobs moving.

Trade-offs

No public benchmarks yet, so performance on MMMU or ChartQA remains unverified. Early testing suggests it struggles with spatial reasoning tasks that require understanding object relationships or interpreting complex diagrams. Output quality on nuanced visual questions — 'What emotion does this person convey?' or 'Is this layout accessible?' — lags behind GPT-4o and Claude Sonnet 4.5. The 'Nano Banana' branding hints at experimental status; expect API changes as Google iterates.

Specifications

Provider: google
Category: image
Context length: 131,072 tokens
Max output: 32,768 tokens
Modalities: image, text
License: proprietary
Released: 2026-06-18

Pricing

Input: $0.50/Mtok
Output: $3.00/Mtok
Model ID: google/gemini-3.1-flash-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

$22.00

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	131k	$0.50/Mtok	$3.00/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. For each item, return: description, quantity, unit price, total. Format as JSON array.

Open in a Project →

Tag Product Photos

List all visible product attributes in this image: color, material, style, condition. Also suggest 3-5 category tags for an e-commerce catalog.

Open in a Project →

Summarize Screenshot Content

Describe what's shown in this screenshot. Include: main UI elements, visible text, apparent purpose of the screen. Keep it under 100 words.

Open in a Project →

Compare Multiple Images

I'm attaching 5 product photos. Compare them and tell me: which items are identical, which differ only in color, and which are completely different products.

Open in a Project →

Digitize Handwritten Forms

Read the handwritten text in each field of this form. Return a JSON object with field names as keys and transcribed text as values.

Open in a Project →

Compare with

Compare Google: Nano Banana 2 (Gemini 3.1 Flash Image) with…

More image models

See all image models →