Google: Nano Banana Pro

Nano Banana Pro is an image creation and editing model with output choices up to 4K. It is a candidate for detailed artwork and reference-led revisions that need to progress from a concept to a larger finished visual.

Compare models

nano-banana-pro

AvailableGoogleImageAsync

Price: From $0.067
Modalities: Image

About Nano Banana Pro

Nano Banana Pro is Google's top model in the Nano Banana line, described as a professional design engine with a reasoning core for studio-quality 4K visuals. It generates from text and edits from reference images at 1K, 2K, or 4K in ten aspect ratios. It is meant for detailed artwork that moves from concept to a larger finished image.

Where it works well

4K output for finished artwork.
A reasoning step helps with prompts that set several constraints.
Reference-led image-to-image revisions keep the subject while the scene changes.
Ten common aspect ratios for ads and web.

When to choose another model

Extreme 1:8 and 8:1 strips are only on Nano Banana 2.
It costs more effort per image than Nano Banana 2 for bulk drafts.

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-pro",
  "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, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 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, 2k, 4k	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, 2:3, 3:2, 3:4, 4:3, 9:16, 16:9	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, 2k, 4k	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.

Use resolution=1k, 2k, or 4k for image-to-image generation.

Text to image

Parameter	Values and limits	Default	Notes
`aspect_ratio`	1:1, 2:3, 3:2, 3:4, 4:3, 9:16, 16:9	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, 2k, 4k	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 supports prompt-only and reference-guided image generation through /v1/images/generations.

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 image

Official price: $2.00/image
Verified price: $1.00/image
Discount: -50%

Text to image / Image to image / Image editing · 1k / 2k

per image

Official price: $0.134
Verified price: $0.067
Discount: -50%

Text to image / Image to image / Image editing · 4k

per image

Official price: $0.24
Verified price: $0.12
Discount: -50%

	Official priceper image	Verified priceper image	Discount
Text	$2.00/image	$1.00/image	-50%
Text to image / Image to image / Image editing · 1k / 2k	$0.134	$0.067	-50%
Text to image / Image to image / Image editing · 4k	$0.24	$0.12	-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, 3:12 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 Nano Banana Pro in Console with a prompt ready to edit or send.

Help me create an image with nano-banana-pro 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

Final artwork
Produce hero images and print-ready drafts at 4K, where the finished file goes straight to a layout or a printer.
Brand visuals
Revise a reference image into a new scene, such as moving a product onto a different surface while its look stays the same.
Detailed illustrations
Render scenes with many specified elements, such as an illustration where each character, object, and background detail is named.
Concept to finish
Refine a Nano Banana 2 draft at larger size once the composition is approved and only fidelity remains to be raised.

Prompt examples

Editorial illustration of a lighthouse in a storm, ink and gouache look, 3:2, dramatic sky.

Place this watch photo on a marble counter with a blurred cafe behind it.

Fantasy map of an island with five named regions, aged paper texture, 16:9.

FAQ

What is Nano Banana Pro?

It is Google's highest-fidelity Nano Banana image model, used for generating and editing detailed images, with a reasoning step aimed at studio-quality results in design work.

Does it accept reference images?

Yes, image-to-image is listed beside text-to-image, so a reference picture plus a written instruction returns a revised version of that picture with the requested changes.

How big can outputs be?

Output goes up to 4K, with 1K and 2K also selectable, and ten aspect ratios from 9:16 portrait to 21:9 ultra-wide are offered for different placements.

Is it the same as gemini-3-pro-image?

Yes. Google lists gemini-3-pro-image as Nano Banana Pro, and this entry is the Nano Banana-branded listing of that same model, with its own options shown.

How much does Nano Banana Pro cost?

On TokenLab, Nano Banana Pro costs $0.067-$0.12 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 Pro use?

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

Which operations does Nano Banana Pro support?

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