Google: Gemini 3.1 Flash Image

Gemini 3.1 Flash Image combines image generation with instruction-led editing. Its range of aspect ratios and output sizes makes it useful for adapting a visual idea to a banner, portrait layout, or detailed standalone image.

Compare models

gemini-3.1-flash-image

AvailableGoogleImageSync / Async

Input / Output-50%: $0.50 / $3.00$0.25 / $1.50
Context: 1M
Released: May 28, 2026
Max output: 64K
Modalities: ImageVision

About Gemini 3.1 Flash Image

Gemini 3.1 Flash Image, marketed by Google as Nano Banana 2, is a Flash-tier model for generating and editing images. Google positions it for high-efficiency, production-scale visual creation. It takes text prompts and reference pictures, outputs at 1K, 2K, or 4K, and offers fourteen aspect ratios including very wide and very tall banners such as 8:1 and 1:8.

Where it works well

Fourteen aspect ratios include 4:1, 8:1, 1:4, and 1:8 strips that most image models skip.
Instruction-led editing changes a supplied image without regenerating it from nothing.
Three output sizes, up to 4K, let one model serve thumbnails and larger assets.
As a Flash-tier model it is meant for steady, high-volume generation work.

When to choose another model

Nano Banana Pro gives more design control and fidelity on detailed, text-heavy compositions.
It returns still images only, with no layers, vectors, or transparent cutouts as a native output.

Getting started

Create API key
Create a key in Console, then use it with every model on the platform.

Send your first request

Copy the example for your language and run it against the endpoint.

Image editingImage to imageText to imageTokenLab endpoint

POST/v1/images/generations

API format:

curl -X POST "https://api.tokenlab.sh/v1/images/generations" \
  -H "Authorization: Bearer sk-xxx" \
  -H "Content-Type: application/json" \
  -d '{
  "aspect_ratio": "1:1",
  "operation": "text-to-image",
  "resolution": "1k",
  "model": "gemini-3.1-flash-image",
  "prompt": "A minimalist product photo of matte black headphones on a soft blue background."
}'

Pricing

The Verified price applies to Verified, which costs less on most models. The Official price is the model maker's published price and applies to the more reliable Official route. Auto bills the route that completes the request.

Text

per 1M tokens

Official price: Input $0.50 / Output $3.00 / Text Input $0.50 / Image Input $0.50 / Text Output $3.00
Verified price: Input $0.25 / Output $1.50 / Text Input $0.25 / Image Input $0.25 / Text Output $1.50
Discount: -50%

Image

per 1M tokens

Official price: Input $0.50 / Output $60.00 / Text Input $0.50 / Image Input $0.50 / Text Output $3.00 / Image Output $60.00
Verified price: Input $0.25 / Output $30.00 / Text Input $0.25 / Image Input $0.25 / Text Output $1.50 / Image Output $30.00
Discount: -50%

	Official priceper 1M tokens	Verified priceper 1M tokens	Discount
Text	Input $0.50 / Output $3.00 / Text Input $0.50 / Image Input $0.50 / Text Output $3.00	Input $0.25 / Output $1.50 / Text Input $0.25 / Image Input $0.25 / Text Output $1.50	-50%
Image	Input $0.50 / Output $60.00 / Text Input $0.50 / Image Input $0.50 / Text Output $3.00 / Image Output $60.00	Input $0.25 / Output $30.00 / Text Input $0.25 / Image Input $0.25 / Text Output $1.50 / Image Output $30.00	-50%

Usage & activity

Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.

Usage & availability

Last 24 hours

Requests
Success rate
P95 latency
Total tokens

Model performance

Last updated Oct 10, 2026, 09:00 PM UTC

Metrics appear once privacy and data volume thresholds are met.

Data is based on aggregate user requests, excluding status checks.

Open in Console

Open Gemini 3.1 Flash Image in Console with a prompt ready to edit or send.

Help me create an image with gemini-3.1-flash-image using text-to-image at /v1/images/generations. Show the result, cost, and any limits I should know.

Use cases

Best for

Text to Image
Vision

Banner adaptation
Turn one visual idea into a leaderboard strip, a story format, and a square tile in separate calls.
Product image editing
Swap backgrounds or change colors on product photos by describing the change in words.
Social content batches
Generate a week of consistent post images from a template prompt with small variations.
Concept exploration
Try ten directions for a campaign quickly before choosing one to finish in a heavier model.

Prompt examples

An ultra-wide 8:1 website header showing a calm mountain lake at dawn, soft mist, no people.

Change the sneaker in this photo from white to forest green, keep the lighting and the shadow on the floor.

A vertical 9:16 story frame with a sliced mango on a pink background and space for a headline at the top.

This model has conditional pricing. Monthly token totals alone cannot produce a reliable estimate; use the detailed pricing for the request specification, cache, and applicable time window.

FAQ

What is Gemini 3.1 Flash Image?

It is Google's Flash-tier image model, also called Nano Banana 2. It generates images from text, builds new images from reference pictures, and edits supplied images from written instructions, with 1K, 2K, and 4K output.

Which aspect ratios does it support?

Fourteen: 1:1, 1:4, 1:8, 2:3, 3:2, 3:4, 4:1, 4:3, 4:5, 5:4, 8:1, 9:16, 16:9, and 21:9. The extreme strips are the main difference from Nano Banana Pro.

Is Gemini 3.1 Flash Image the same as Nano Banana 2?

Yes. Google lists gemini-3.1-flash-image under the product name Nano Banana 2, so both names point to one model. Prompts, aspect ratios, and sizes you tested under either name carry over without changes.

When should I choose Nano Banana Pro instead?

Choose Pro when a single image must be as polished as possible, for example text-rich posters or 4K print work. Stay with this model for volume, variety, and unusual banner shapes.

How much does Gemini 3.1 Flash Image cost?

On TokenLab, Gemini 3.1 Flash Image costs Input $0.25 / Output $1.50 per 1M tokens. The pricing table above shows the full breakdown. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.

Which endpoint should Gemini 3.1 Flash Image use?

Use https://api.tokenlab.sh/v1/images/generations for Gemini 3.1 Flash Image. The request example below shows the matching code shape.

Which operations does Gemini 3.1 Flash Image support?

Gemini 3.1 Flash Image supports Image editing, Image to image, Text to image. Select an operation above to see its endpoint and request example.