Nano Banana Pro. Gemini 3 Pro Image, up to 4K.
Google's pro-tier image model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, renders at 1K, 2K, or 4K, and composes from up to 10 reference images on a Treza node.
- Text and image input
- 1K, 2K, or 4K output
- 10 aspect ratios, 9:16 to 21:9
- Up to 10 reference images
Nano Banana Pro is Google's name for Gemini 3 Pro Image, the image generation and editing model built on Gemini 3 Pro. It extends the original Nano Banana, Gemini 2.5 Flash Image, with significantly improved multimodal reasoning. It also takes more in and puts more out: up to 10 reference images on a node where the original takes 3, and a resolution setting of 1K, 2K, or 4K where the original has none.
On Treza it sits in the Image Generation node's picker as Nano Banana Pro (Gemini 3 Pro Image), next to Gemini 2.5 Flash Image and Gemini 3.1 Flash Image. A pattern that works well is draft on flash, finish on Pro: iterate compositions on a flash-tier model, then swap the node to Nano Banana Pro and render the chosen direction at 2K or 4K. The pipeline around it publishes as one API.
Built on Gemini 3 Pro
Significantly improved multimodal reasoning over the original Nano Banana, with text, images, and instructions arriving together in one request.
1K, 2K, or 4K output
Pick the resolution on the node. Draft at 1K, then deliver at 2K or 4K from the same prompt and the same pipeline.
Up to 10 references at once
Wire product, character, style, and scene images into one node and compose a single image from all of them. The original Nano Banana takes 3.
Edits, carried over
Image input and instruction-based editing work the way the Nano Banana line established: attach a photo, describe the change, get the edit back.
What to make with Nano Banana Pro
Real prompts, and what comes back. Each one runs on an Image Generation node with Nano Banana Pro picked in the model menu.
“A 4K key visual for a coffee launch: this can (attached) on a sunlit marble counter”
Your product in a deliverable-resolution still.
“Build one scene from these five references: the character, the jacket, the street, the lighting, the palette”
A single composition that draws on every reference.
“Same image, but move the scene to golden hour and keep the pose”
A targeted edit that changes the light, not the subject.
“A 21:9 website hero of a greenhouse cafe, morning light, calm and airy”
A wide hero image rendered at 2K or 4K.
“Re-render this flash draft (attached) at 4K, same composition”
The approved draft, finished at full resolution.
“Our mascot (attached) as a chef, a pilot, and a gardener, one image each”
Your character on model across a set of scenes.
Nano Banana Pro is one node on a canvas
Chain it with language, image, and video models, then publish the whole pipeline as an API. See how a full AI video pipeline fits together.
- Step 01
Draft the brief
A language model node expands a one-line idea into a detailed, on-brand prompt before it ever reaches the model.
- Step 02
Generate with Nano Banana Pro
Run variants in parallel, compare against other models on the same prompt, and keep every result in run history.
- Step 03
Publish it as an API
The pipeline becomes a versioned endpoint. Your product calls it with the typed /invoke API or any OpenAI SDK.
Nano Banana Pro as an API, priced per image
The Nano Banana Pro API
Build a pipeline with Nano Banana Pro on a node and publish it. It becomes a versioned HTTP endpoint: the typed /invoke route enqueues a run and returns a run id to poll, and an OpenAI-compatible route works with SDKs you already use. Agents connect over MCP the same way. Your prompt engineering ships inside the pipeline, so every caller gets your quality, and swapping the model later does not change the API your product calls.
Nano Banana Pro pricing
Prepaid credits, no subscription. Each image is charged at Nano Banana Pro's own rate from your balance, shown before you run, and only successful generations are charged, so a failed run costs nothing. Credit packs start at $5 and never expire, which suits spiky production schedules. Run history records the cost of every generation, per node, so spend is auditable rather than a surprise.
Nano Banana Pro, answered
Is Nano Banana Pro the same as Gemini 3 Pro Image?
Yes. Nano Banana Pro is Google's name for Gemini 3 Pro Image, the image model built on Gemini 3 Pro. On Treza it is listed in the model picker as Nano Banana Pro (Gemini 3 Pro Image). The original Nano Banana is Gemini 2.5 Flash Image, and it is in the picker too.
Should I use Nano Banana Pro or a flash model?
Use Gemini 2.5 or 3.1 Flash Image for fast iteration and volume. Use Nano Banana Pro for the final: the reasoning of Gemini 3 Pro, output at up to 4K, and up to 10 references in one request. A pipeline can do both, drafting on flash and then swapping the node to Pro, with no other edits.
What resolutions and aspect ratios does Nano Banana Pro support?
1K, 2K, or 4K, chosen on the node, across ten aspect ratios from 9:16 vertical to 21:9 wide, including 1:1, 4:5, and 16:9. It accepts text and image input, with up to 10 reference images per node.
How much does Nano Banana Pro cost on Treza?
Treza uses prepaid credits with no subscription. Each image is charged at Nano Banana Pro's rate from your balance, and only successful generations are charged. Credit packs start at $5 and never expire.
Can I call Nano Banana Pro through an API?
Yes. Build a pipeline that uses Nano Banana Pro and publish it as a versioned HTTP endpoint. Call the typed /invoke API from your product, or point any OpenAI SDK at the OpenAI-compatible endpoint. If a better model ships later, swap it on the node without changing the API your product calls.
Your first video is one prompt away.
Generate your first video, image, or draft today. Prepaid credits, no subscription.