IMAGEgoogle

Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)

Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity developer pipelines and rapid-fire visual exploration. It delivers text-to-image generation...

Anyone in the Space can @-mention Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) with the team's shared context - pooled credits, one chat, one memory.

All models

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

Verdict

Nano Banana 2 Lite targets cost-conscious image analysis at $0.25/Mtok input, undercutting most vision models by 60-80%. The 65K context window handles multi-image batches comfortably. Trade-off: no public benchmarks yet, so accuracy against GPT-4V or Claude Sonnet remains unproven. Reach for this when budget trumps bleeding-edge vision performance, especially for high-volume OCR, receipt parsing, or screenshot annotation where good-enough beats perfect.

Best for

High-volume receipt and invoice OCR
Screenshot annotation and UI analysis
Multi-image batch processing workflows
Cost-sensitive document digitization
Prototyping vision features before production

Strengths

Input pricing at $0.25/Mtok makes this the cheapest vision model in the Switchy catalog, enabling economics that were impossible six months ago. The 65K context window supports 20-30 images per request depending on resolution, streamlining batch workflows. Flash architecture suggests sub-second response times for single-image tasks. Gemini lineage implies solid instruction-following and structured output generation, critical for parsing invoices or forms into JSON.

Trade-offs

Zero public benchmarks means you're flying blind on accuracy versus GPT-4V, Claude 3.5 Sonnet, or even Gemini 1.5 Flash. Expect weaker performance on complex visual reasoning, fine-grained OCR in challenging fonts, or nuanced image interpretation. Output pricing at $1.50/Mtok climbs fast if you request verbose descriptions. The 'Lite' suffix and rock-bottom input cost signal a model optimized for speed and cost, not state-of-the-art vision understanding.

Specifications

Provider: google
Category: image
Context length: 65,536 tokens
Max output: 66,000 tokens
Modalities: image, text
License: proprietary
Released: 2026-06-30

Pricing

Input: $0.25/Mtok
Output: $1.50/Mtok
Model ID: google/gemini-3.1-flash-lite-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

$11.00

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	$0.25/Mtok	$1.50/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 Spaces have used this model yet to share anonymised team stats. We wait for at least 50 distinct Spaces per week before publishing any aggregate.

Starter prompts

Extract Receipt Line Items

Extract all line items from this receipt image. Return a JSON array with fields: item_name, quantity, unit_price, total_price. Include the receipt total and date at the top level.

Open in a Space →

Annotate UI Screenshot

Describe every interactive element in this screenshot: buttons, input fields, dropdowns, links. For each, provide the label text, element type, and approximate position (top-left, center, etc.).

Open in a Space →

Batch Image Categorization

I'm providing 15 product images. For each, return: image number, primary category (electronics/clothing/home goods/other), condition (new/used/damaged), and a one-sentence description.

Open in a Space →

Form Field Extraction

Extract all filled form fields from this document image. Return a JSON object where keys are field labels and values are the handwritten or printed entries. Mark any illegible fields as null.

Open in a Space →

Visual QA for E-commerce

Answer these questions about the product in this image: 1) What color is it? 2) Are there visible brand logos or text? 3) Does it show signs of wear or damage? 4) Estimated size category (small/medium/large).

Open in a Space →