Skip to content

Google · Image

Gemini 3.1 Flash Image

Google 🇺🇸ImageGemini familyOne of its sources says the weights aren't publicly available.
From Netmind's listing:
Gemini 3.1 Flash Image is a fast, cost-efficient image generation and editing model from Google. It generates high-quality images from text prompts and can edit or compose from reference images when input image URLs are supplied.
llminfo IQ
115.7
Maker's price
$0.045 /image
Max context
1M
Listings
41

Evidence and sources

llminfo IQ 115.7, ranked among image generation models. From 40 benchmarks. A fair amount of data behind it.How llminfo IQ is computedMaker HQ: US (according to Google's own website)
All rankings: #228 on OpenRouter today #247 on OpenRouter this week #258 on OpenRouter this month #359 on OpenRouter today #374 on OpenRouter this week #400 on OpenRouter this monthSources: Google Generative AI API data docs, LMArena data, Writer Pricing, Models.dev data, AI/ML API data, NetMind.AIPrimary data from Google Generative AI API from LMArena: name from Writer Pricing: variant from Models.dev: weights availability from AI/ML API: primary mode from NetMind.AI: description

Advantages and trade-offs

Compared with 10 image generation models, picked mainly by popularity and IQ

Advantages

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 04:34 UTC.

Input & output

as stated by the model's providers
Text
Images
Video
Files
Text
Images

Capabilities

Supported operations and provider-stated features

VisionReasoningFunction callingStructured outputPrompt cachingPDF inputWeb searchBatch API

Listings

 Googlemodels/gemini-3.1-flash-imageSources: Google Generative AI API data docs, LiteLLM data, Models.dev data131K$0.50cache read $0.05batch $0.25$3.00batch $1.50$60.00$0.045$0.00056
 Tokensmindgemini-3.1-flash-image-previewSource: TokensMindNot published by the provider$0.175$42.00———
 302aigemini-3.1-flash-image-previewSource: Models.dev data131K$0.50$60.00———
 Aihubmixgemini-3.1-flash-imageSource: AIHubMix data docs131K$0.50cache read $0.05$3.00———
 Atlascloudgoogle/gemini-3.1-flash-imageSource: AtlasCloud data131K$0.50$3.00———
 Cometapigemini-3.1-flash-imageSources: CometAPI data, CometAPI Pricing dataNot published by the provider$0.50$3.00———
 Eden AIInference by Googlegoogle/gemini-3.1-flash-imageSource: Models.dev data66K$0.50$3.00———
 Fastroutergoogle/gemini-3.1-flash-image-previewSources: FastRouter data, Models.dev data66K$0.50$3.00———
 Flowdotgemini-3.1-flash-imageSource: FlowDot data66K$0.50$3.00———
 Kilogoogle/gemini-3.1-flash-imageSources: Kilo AI Gateway data, Models.dev data131K$0.50cache read $0.05$3.00———
Show all 32 listings

Showing 10 of 32: the maker's own listing first, then the cheapest per 1M input tokens from each provider.

Also sold by Abacus, Databricks, fal.ai, Llmgateway, Meganova, Merge Gateway, NanoGPT, Netmind, OpenRouter, Replicate, Requesty, Together AI, Tokenmix, Vercel, Writer.

9 listings without a price are hidden.

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Image generation

Human preference

Agentic

Data credits: LMArena, CC BY 4.0 (licence)

Also known as: databricks/databricks-gemini-3-1-flash-image, fal-ai/gemini-3.1-flash-image-preview, fal-ai/gemini-3.1-flash-image-preview/edit, fal-ai/nano-banana-2, fal-ai/nano-banana-2/edit, flash-image-3.1, gemini-3.1-flash-image-nano-banana-2, gemini-3.1-flash-image-nano-banana-2-web-search, gemini-3.1-flash-image-preview, gemini/gemini-3.1-flash-image, gemini/gemini-3.1-flash-image-preview, google-gemini-3.1-flash-image-nano-banana-2, google/flash-image-3.1, google/gemini-3.1-flash-image, google/gemini-3.1-flash-image-preview, google/nano-banana-2, nano banana 2, nano-banana-2, nano-banana-2-beta, nano-banana-2-edit, replicate/google/nano-banana-2, together_ai/google/flash-image-3.1, vertex/gemini-3.1-flash-image, vertex_ai/gemini-3.1-flash-image, vertex_ai/gemini-3.1-flash-image-preview

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works