32:9 super ultrawide wallpaper from a 4:1 image: crop 11% of width

A 32:9 super ultrawide screen is 3.56:1. The widest ratio GPT Image 2.5 takes on Sume is 3:1, and Nano Banana 2.1 lists 4:1, so a 4:1 image at 4K for $0.20 can be cropped to 32:9 by keeping 88.9% of its width.

Which ratio can get there

Why 4:1, not 8:1

Both reach 32:9, but 8:1 would throw away more than half the width you paid for. 4:1 keeps 3.556 / 4 = 88.9% of the width, so almost every pixel stays in the wallpaper.

import os, requests

body = {
    "model": "google/nano-banana-2.1",
    "prompt": "Ultra-wide desktop wallpaper, calm mountain lake at dusk, no text, no people",
    "aspect_ratio": "4:1",
    "resolution": "4K",
}
r = requests.post(
    "https://api.sume.com/v1/images",
    headers={"Authorization": f"Bearer {os.environ['SUME_API_KEY']}"},
    json=body, timeout=60,
)
print(r.status_code)  # 200 = image body, 202 = job envelope
if r.status_code == 200:
    out = r.json()
    print(out["data"][0]["url"], out["usage"]["cost"])

Gotchas

• Crop evenly from both edges so the focal point stays on the middle of the screen.
• A 4K call can take longer than the 30-second sync window; on a 202, poll the job and read the result.
• Check the returned file's dimensions before you decide the crop box.