Nano Banana 2.1. Google's flash-tier image model, newest generation.
The successor to Nano Banana 2 on the Flash tier. Make an image from a prompt, or edit and compose from up to 14 reference images, in fourteen aspect ratios with a 1K, 2K or 4K setting.
- Text and image input
- 1K, 2K or 4K setting
- 14 aspect ratios, 1:8 to 8:1
- Up to 14 reference images
Nano Banana 2.1 is Google's image generation and editing model on the Flash tier, listed on OpenRouter on 2026-10-06 as the successor to Nano Banana 2. One model handles text-to-image and image-to-image: give it a prompt, or a prompt plus up to 14 reference images, and pick a resolution of 1K, 2K or 4K. In our tests a square came back at 1024, 2048 or 4096 pixels to match the setting, and 1024 with no setting at all.
On Treza it sits in the Image Generation node's picker and in chat. Renders took 8 seconds at 1K, 13 at 2K and 25 at 4K, and an edit with one reference also took 8. The edit kept the product and moved it into the new scene as asked. OpenRouter bills it per output image token; we measured $0.036 an image at 1K, $0.053 at 2K and $0.116 at 4K. It bills from prepaid credits, and a failed generation costs nothing.
Up to 14 references
Carry a product, a character and a setting into one image. In our test a reference edit kept the shirt and put it on the counter the prompt described, for about a fifth of a cent more.
Three resolution settings
1K, 2K or 4K. A square rendered at 1024, 2048 and 4096 pixels for the three settings, and 1024 with none set.
Fast at every size
8 seconds at 1K and 13 at 2K in our tests, so it fits inside a chat turn. 4K took 25 seconds.
Fourteen aspect ratios
From 1:8 and 9:16 portraits to 16:9, 21:9 and 8:1 banners, plus 4:5 and 5:4 for feeds.
What to make with Nano Banana 2.1
Prompts to try, and what to expect back. Each runs on an Image Generation node with Nano Banana 2.1 picked in the model menu.
“A ceramic cup of coffee on a sunlit wooden cafe table, steam rising, shallow depth of field”
A warm product-style still, our benchmark image.
“The same folded shirt (attached) on a white marble counter in a bright studio”
Your product moved into a new set.
“This sofa (attached) in this living room (attached), afternoon light”
Two references composed into one scene.
“An 8:1 banner of a coastal road at golden hour for a website header”
A wide still at the ratio you asked for.
“Keep this character (attached) and show her at a market, a station and a rooftop”
One character across a series.
“A 4K still of a lighthouse on a cliff in a storm”
A 4096-pixel square for print or crop.
Nano Banana 2.1 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 2.1
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 2.1 as an API, priced per image
The Nano Banana 2.1 API
Build a pipeline with Nano Banana 2.1 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 2.1 pricing
Prepaid credits, no subscription. Each image is charged at Nano Banana 2.1's own rate from your balance, shown before you run, and a failed generation 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 2.1, answered
What does Nano Banana 2.1 cost per image?
OpenRouter lists it per output image token. In our tests a 1K image billed 1,120 image tokens, $0.036; 2K billed 1,680, $0.053; 4K billed 3,780, $0.116; and a reference image added about $0.002. Treza quotes those measured amounts, plus its credit markup, before a run.
How is Nano Banana 2.1 different from Nano Banana 2 and Nano Banana Pro?
It is the newer Flash-tier model, listed as the successor to both. On Treza all three sit in the same picker, so run the same prompt on each and let the output decide. In our tests 2.1 was fast at every size and followed a reference edit closely.
Can I use it in chat?
Yes. Ask for Nano Banana 2.1 by name in chat, attach reference images if you have them, and the image comes back in the conversation.
How much does Nano Banana 2.1 cost on Treza?
Treza uses prepaid credits with no subscription. Each image is charged at Nano Banana 2.1's rate from your balance, and only successful generations are charged. Credit packs start at $5 and never expire.
Can I call Nano Banana 2.1 through an API?
Yes. Build a pipeline that uses Nano Banana 2.1 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.