Google: Gemini 3.1 Flash-Lite Image

Fastest, most cost-efficient Gemini image model for high-volume 1K generation and editing

gemini-3.1-flash-lite-image

AvailableGoogleImageSync / Async

Input / Output-50%: $0.25 / $1.50$0.125 / $0.75
Context: 64K
Max output: 4K
Modalities: ImageVision
Capabilities: Tool use

About Gemini 3.1 Flash-Lite Image

Gemini 3.1 Flash-Lite Image, called Nano Banana 2 Lite by Google, is the smallest model in the Nano Banana line. Google describes it as ultra-low latency and cost-effective image generation. It makes and edits images at 1K only, so it suits drafts, thumbnails, and layout checks rather than large final art, which belongs to Nano Banana 2 and Pro.

Where it works well

Generation is built for low latency, so many variants can be produced in one sitting.
Text-to-image, image-to-image, and image editing are all available through the same model.
Output is fixed at 1K, which keeps results predictable for previews and thumbnails.
Structured output and tool support help when an app wraps the model in a larger flow.

When to choose another model

Resolution stops at 1K; use Nano Banana 2 or Pro when a 2K or 4K deliverable is required.
Lite-tier fidelity is lower on dense text and fine detail than the larger image models.

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 '{
  "operation": "text-to-image",
  "resolution": "1k",
  "model": "gemini-3.1-flash-lite-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 $0.25 / Output $1.50 / Text Input $0.25 / Image Input $0.25 / Text Output $1.50
Verified price: Input $0.125 / Output $0.75 / Text Input $0.125 / Image Input $0.125 / Text Output $0.75
Discount: -50%

Image

per 1M tokens

Official price: Input $0.25 / Output $30.00 / Text Input $0.25 / Image Input $0.25 / Text Output $1.50 / Image Output $30.00
Verified price: Input $0.125 / Output $15.00 / Text Input $0.125 / Image Input $0.125 / Text Output $0.75 / Image Output $15.00
Discount: -50%

	Official priceper 1M tokens	Verified priceper 1M tokens	Discount
Text	Input $0.25 / Output $1.50 / Text Input $0.25 / Image Input $0.25 / Text Output $1.50	Input $0.125 / Output $0.75 / Text Input $0.125 / Image Input $0.125 / Text Output $0.75	-50%
Image	Input $0.25 / Output $30.00 / Text Input $0.25 / Image Input $0.25 / Text Output $1.50 / Image Output $30.00	Input $0.125 / Output $15.00 / Text Input $0.125 / Image Input $0.125 / Text Output $0.75 / Image Output $15.00	-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, 02:24 AM 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-Lite Image in Console with a prompt ready to edit or send.

Help me create an image with gemini-3.1-flash-lite-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

Draft layouts
Check composition and color direction on dozens of quick renders before spending effort on a final.
Thumbnail generation
Create small preview images for articles, listings, or video covers, where a 1K frame is already larger than the slot it fills.
Edit previews
Show a user a fast preview of an instruction-based change before applying it at full size.
Prompt testing
Try prompt wording cheaply to learn what the larger image models are likely to do.

Prompt examples

A flat vector-style icon of a paper plane over a blue gradient, centered, plenty of margin.

Make the sky in this photo a sunset orange, leave the buildings as they are.

Four different thumbnail ideas for an article titled 'Why bread goes stale', warm kitchen colors.

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-Lite Image?

It is Google's fastest and most economical Gemini image model, also named Nano Banana 2 Lite. It produces new images and edits supplied ones, always at 1K resolution.

Which sizes can it output?

Only 1K. The resolution option has a single value, while aspect ratio offers fifteen choices including 1:8, 8:1, and auto. Use a larger Nano Banana model for 2K or 4K.

Can it edit images?

Yes. It accepts an image plus a written instruction and returns the edited result, in addition to text-to-image and image-to-image generation. Describe what should stay unchanged as well as what to change.

Is it good enough for final assets?

For web thumbnails and drafts, often yes. For print, hero banners, or text-heavy graphics, compare it against Nano Banana 2 first, since the Lite tier gives up fidelity for speed.

How much does Gemini 3.1 Flash-Lite Image cost?

On TokenLab, Gemini 3.1 Flash-Lite Image costs Input $0.125 / Output $0.75 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-Lite Image use?

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

Which operations does Gemini 3.1 Flash-Lite Image support?

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