Google: Nano Banana 2 Lite

Nano Banana 2 Lite offers image generation and editing at 1K resolution. It fits layout experiments and draft visual assets when a fixed output size is sufficient to judge composition and the direction of a change.

Compare models

nano-banana-2-lite

AvailableGoogleImageSync / Async

Price: From $0.0168
Modalities: Image

About Nano Banana 2 Lite

Nano Banana 2 Lite is the economy member of Google's Nano Banana 2 family, aimed at ultra-low latency and cost-effective image generation. It supports text-to-image, image-to-image, and image editing at 1K only, with fifteen aspect-ratio choices including auto. It fits layout experiments and draft assets where a fixed small size is enough to judge composition.

Where it works well

An auto aspect-ratio option lets the model pick the frame from the prompt or reference.
Image-to-image support means a supplied picture can be changed by instruction.
Fixed 1K output keeps drafts light.
Fourteen explicit ratios plus auto cover most layouts.

When to choose another model

It cannot output 2K or 4K; Nano Banana 2 or Pro is needed for larger files.
Fine text and small details are less reliable than on the full-size 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

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": "nano-banana-2-lite",
  "prompt": "A minimalist product photo of matte black headphones on a soft blue background."
}'

Parameters

Image editing

Parameter	Values and limits	Default	Notes
`aspect_ratio`	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, 21:9	Not provided	Not provided
`async`	Not provided	Not provided	Not provided
`image`	Not provided	Not provided	This operation accepts image inputs. The maximum total source-image count is not yet verified for this public operation.
`image_url`	Not provided	Not provided	Not provided
`image_urls`	Not provided	Not provided	Not provided
`operation`	Not provided	Not provided	Not provided
`prompt`	Not provided	Not provided	Not provided
`resolution`	1k	Not provided	Not provided
`size`	Not provided	Not provided	Use the declared resolution and aspect_ratio to select the corresponding output size. size follows the model-specific resolution table; arbitrary pixel dimensions are not declared as a public control.

Image to image

Parameter	Values and limits	Default	Notes
`aspect_ratio`	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, 21:9	Not provided	Not provided
`async`	Not provided	Not provided	Not provided
`image`	Not provided	Not provided	This operation accepts image inputs. The maximum total source-image count is not yet verified for this public operation.
`image_url`	Not provided	Not provided	Not provided
`image_urls`	Not provided	Not provided	Not provided
`operation`	Not provided	Not provided	Not provided
`prompt`	Not provided	Not provided	Not provided
`resolution`	1k	Not provided	Not provided
`size`	Not provided	Not provided	Use the declared resolution and aspect_ratio to select the corresponding output size. size follows the model-specific resolution table; arbitrary pixel dimensions are not declared as a public control.

Text to image

Parameter	Values and limits	Default	Notes
`aspect_ratio`	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, 21:9	Not provided	Not provided
`async`	Not provided	Not provided	Not provided
`operation`	Not provided	Not provided	Not provided
`prompt`	Not provided	Not provided	Not provided
`resolution`	1k	Not provided	Not provided
`size`	Not provided	Not provided	Use the declared resolution and aspect_ratio to select the corresponding output size. size follows the model-specific resolution table; arbitrary pixel dimensions are not declared as a public control.

TokenLab treats requests with source images as image-to-image generation.

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 to image / Image to image / Image editing · 1k

per image

Official price: $0.0336
Verified price: $0.0168
Discount: -50%

	Official priceper image	Verified priceper image	Discount
Text to image / Image to image / Image editing · 1k	$0.0336	$0.0168	-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 Nov 1, 2026, 8:09 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 Nano Banana 2 Lite in Console with a prompt ready to edit or send.

Help me create an image with nano-banana-2-lite 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

Layout experiments
Test several compositions quickly, comparing centered, offset, and diagonal arrangements before committing to one direction.
Draft assets
Produce placeholder visuals for a design review, where the team judges layout and tone rather than final detail.
Reference tweaks
Try a change on a supplied image before running it at full size.
Prompt tuning
Learn which wording works before moving the same prompts to a larger model, saving effort on the final high-resolution run.

Prompt examples

Same product on a plain background, three arrangements: centered, left-aligned, diagonal.

Take this photo and make it look like late afternoon, otherwise unchanged.

A minimalist poster for a bike race, bold shapes, two colors.

FAQ

What is Nano Banana 2 Lite?

It is the smallest, cheapest-to-run member of the Nano Banana 2 family, made for fast drafts at 1K resolution with text-to-image, image-to-image, and image-edit operations.

Does it support auto aspect ratio?

Yes, 'auto' is offered next to fourteen fixed ratios running from 1:8 to 21:9, so the frame can follow the prompt or the supplied reference picture.

Can it use reference images?

Yes. Image-to-image and image editing are listed alongside text-to-image, so you can send a picture with a written instruction and receive a changed 1K version of that picture.

Is it the same as Gemini 3.1 Flash-Lite Image?

Google names gemini-3.1-flash-lite-image as Nano Banana 2 Lite, so they appear to be the same product; the listing here is separate and shows different options.

How much does Nano Banana 2 Lite cost?

On TokenLab, Nano Banana 2 Lite costs $0.0168 per image. 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 Nano Banana 2 Lite use?

Use https://api.tokenlab.sh/v1/images/generations for Nano Banana 2 Lite. The request example below shows the matching code shape.

Which operations does Nano Banana 2 Lite support?

Nano Banana 2 Lite supports Image editing, Image to image, Text to image. Select an operation above to see its endpoint and request example.