Nano Banana 2

Nano Banana 2 is the name Google uses for Gemini 3.1 Flash Image, out since February 2026. Its strength is speed with choice: one request can return four takes on the same idea, so you pick a direction in seconds instead of rerunning the prompt over and over. A 1K picture usually arrives within 10 to 30 seconds.

What you can make

• Four concept options for a campaign visual in a single run.
• Long website banners and vertical strips at 4:1, 8:1, 1:4 or 1:8.
• One visual in several sizes: a 0.5K layout check, then the same prompt at 4K.
• A character series that keeps the same face thanks to reference photos.

Settings that matter

• Images per request: set num_images up to 4 to compare interpretations side by side.
• Resolution: 0.5K, 1K, 2K or 4K. The 0.5K tier is meant for layout drafts.
• Aspect ratio: 14 shapes, including the very long 8:1 and 1:8.
• References: up to 14 in total; Google suggests up to 10 object images and up to 4 character images.
• Grounding: Google offers web and image search grounding for this model, but Kadraris does not pass it through yet.

Starter prompt

Wide 8:1 web banner, left to right: small green leaf logo, bold headline "Fresh every morning", basket of bread on a wooden counter, soft daylight

On long formats, describe the layout along the long side in order, and change the headline in quotes to your own copy.

Questions

How is Nano Banana 2 priced?

from $0.07 per image, charged from your prepaid balance, with the rate depending on resolution. When a generation fails, you are not charged.

Can I get the image back in the same API call?

Yes for short jobs. Call /v1/generate?wait=60 and the finished picture comes in the response; the generate docs show the details.

When is Nano Banana Pro the better choice?

For heavy multi-reference composites and polished key art, try Nano Banana Pro. The comparison shows where each one wins.

Nano Banana 2 in your code

curl https://kadraris.com/v1/generate?wait=60 \
  -H "Authorization: Bearer $KADRARIS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "nano-banana-2",
  "input": {
    "prompt": "Packshot of a white linen sneaker on a concrete block, hard midday sun, crisp shadow, 85mm",
    "aspect_ratio": "1:1",
    "resolution": "1k"
  }
}'

import os, time, requests

API = "https://kadraris.com/v1"
H = {"Authorization": f"Bearer {os.environ['KADRARIS_API_KEY']}"}

task = requests.post(f"{API}/generate", headers=H, json={
    "model": "nano-banana-2",
    "input": {
        "prompt": "Packshot of a white linen sneaker on a concrete block, hard midday sun, crisp shadow, 85mm",
        "aspect_ratio": "1:1",
        "resolution": "1k"
    }
}).json()
while task["status"] in ("queued", "running"):
    time.sleep(3)
    task = requests.get(f"{API}/tasks/{task['id']}", headers=H).json()

print(task["status"], task["cost"], [o["url"] for o in task["output"]])

const API = "https://kadraris.com/v1";
const headers = { Authorization: `Bearer ${process.env.KADRARIS_API_KEY}`, "Content-Type": "application/json" };

let task = await (await fetch(`${API}/generate`, {
  method: "POST",
  headers,
  body: JSON.stringify({
    "model": "nano-banana-2",
    "input": {
      "prompt": "Packshot of a white linen sneaker on a concrete block, hard midday sun, crisp shadow, 85mm",
      "aspect_ratio": "1:1",
      "resolution": "1k"
    }
  }),
})).json();

while (task.status === "queued" || task.status === "running") {
  await new Promise((r) => setTimeout(r, 3000));
  task = await (await fetch(`${API}/tasks/${task.id}`, { headers })).json();
}
console.log(task.status, task.cost, task.output.map((o) => o.url));

Input fields

Fetch this list as JSON with GET /v1/models/nano-banana-2.