Google: Gemini 3 Pro Image

Nano Banana Pro for higher-fidelity image generation and design-heavy edits

gemini-3-pro-image

AvailableGoogleImageSync / Async

Input / Output-50%: $2.00 / $12.00$1.00 / $6.00
Context: 1M
Released: May 28, 2026
Max output: 64K
Modalities: ImageVision

About Gemini 3 Pro Image

Nano Banana Pro is the name Google gives to Gemini 3 Pro Image, its image generation and editing model aimed at design work. Google describes it as a professional design engine with a reasoning core for studio-quality 4K visuals. It generates from text and edits from reference images, with 1K, 2K, and 4K output and ten aspect ratios from square to ultra-wide.

Where it works well

Output reaches 4K, enough for print mockups and large hero images.
A reasoning step before rendering helps with prompts that specify layout, text placement, or several constraints at once.
Image-edit requests change a supplied picture according to written instructions.
Ten aspect ratios, from 9:16 portrait to 21:9 ultra-wide, cover most ad and web formats.

When to choose another model

The Flash-based Nano Banana 2 models are the lighter choice when you generate many drafts and do not need top fidelity.
It is built for single stills; it produces no video, audio, or layered files.

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-pro-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 $2.00 / Output $12.00 / Text Input $2.00 / Image Input $2.00 / Text Output $12.00
Verified price: Input $1.00 / Output $6.00 / Text Input $1.00 / Image Input $1.00 / Text Output $6.00
Discount: -50%

Image

per 1M tokens

Official price: Input $2.00 / Output $120.00 / Text Input $2.00 / Image Input $2.00 / Text Output $12.00 / Image Output $120.00
Verified price: Input $1.00 / Output $60.00 / Text Input $1.00 / Image Input $1.00 / Text Output $6.00 / Image Output $60.00
Discount: -50%

	Official priceper 1M tokens	Verified priceper 1M tokens	Discount
Text	Input $2.00 / Output $12.00 / Text Input $2.00 / Image Input $2.00 / Text Output $12.00	Input $1.00 / Output $6.00 / Text Input $1.00 / Image Input $1.00 / Text Output $6.00	-50%
Image	Input $2.00 / Output $120.00 / Text Input $2.00 / Image Input $2.00 / Text Output $12.00 / Image Output $120.00	Input $1.00 / Output $60.00 / Text Input $1.00 / Image Input $1.00 / Text Output $6.00 / Image Output $60.00	-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 11, 2026, 05:05 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 Pro Image in Console with a prompt ready to edit or send.

Help me create an image with gemini-3-pro-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

Design comps
Produce poster, packaging, or landing-page visuals with specific text and layout instructions, then refine them by edit.
Large-format artwork
Generate a 4K master image and crop it into several banner shapes.
Reference-led revisions
Upload a product photo and ask for a new background or lighting while the product stays recognizable.
Infographic drafts
Describe a diagram with labels and hierarchy and review a rendered first version before a designer takes over.

Prompt examples

A 4:5 poster for a jazz night: dark teal background, a brass trumpet in warm light, the title 'Blue Hour Sessions' in bold serif letters at the top.

Edit this product photo so the bottle stands on wet black stone with soft rim lighting; keep the label unchanged.

Isometric infographic of a coffee supply chain from farm to cup, five labeled stages, flat 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 Nano Banana Pro?

It is Google's name for the gemini-3-pro-image model: a higher-end image generator and editor in the Nano Banana family, built for detailed design work and studio-quality results up to 4K.

Which resolutions and shapes can I request?

You can choose 1K, 2K, or 4K output and one of ten aspect ratios: 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, and 21:9. Pick the size to match the final placement.

Can it edit an existing image?

Yes. It supports image editing as well as text-to-image and image-to-image: send a picture with an instruction and it returns a changed version. Keep the instruction specific about what must stay the same.

How does it differ from Nano Banana 2?

Pro targets maximum fidelity and design control with 4K output; Nano Banana 2 is the Flash-based option for faster, higher-volume production and offers more extreme aspect ratios such as 1:8 and 8:1.

How much does Gemini 3 Pro Image cost?

On TokenLab, Gemini 3 Pro Image costs Input $1.00 / Output $6.00 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 Pro Image use?

Use https://api.tokenlab.sh/v1/images/generations for Gemini 3 Pro Image. The request example below shows the matching code shape.

Which operations does Gemini 3 Pro Image support?

Gemini 3 Pro Image supports Image editing, Image to image, Text to image. Select an operation above to see its endpoint and request example.