AI blueprint-style poster: Ideogram 4.5 at $0.0375, $0.075 or $0.275
Ideogram 4.5 bills $0.0375, $0.075 or $0.275 per image on Sume by quality (list $0.03, $0.06, $0.22), the same at 1K and 2K; draft low, finish high.

For an AI blueprint-style poster, call ideogram/ideogram-v4.5 and pick the cost with quality: low, medium or high bill at $0.0375, $0.075 and $0.275 per image on Sume, which are the list prices of $0.03, $0.06 and $0.22 times 1.25. The price follows quality, not size, so resolution: "2K" costs the same as 1K; draft at low, then finish the keeper at high.
Blueprint posters are line art with small labels, which is a good test of how a model handles thin lines and short words. The figures are from Sume's Image API page and the catalog source, read on 2026-10-05, and nothing here claims how well a tier draws labels: run the draft and look.
What does each quality tier cost?
If you omit quality, Sume sends medium. Ideogram 4.5 takes 1K or 2K output and a long ratio list that includes 3:2, 4:5 and 3:1. Sume does not accept output_format for this model: the provider chooses it.
| `quality` | List per image | Billed per image | Ten posters |
|---|---|---|---|
| low | $0.03 | $0.0375 | $0.375 |
| medium (default) | $0.06 | $0.075 | $0.75 |
| high | $0.22 | $0.275 | $2.75 |
| Draft low, finish one high | - | $0.0375 + $0.275 | $0.3125 per poster |
How do I draft and then finish?
Run the draft at low and 1K, read it, then rerun the same prompt at high and 2K. Reruns are not identical because the catalog has no seed, so pick a draft for composition and expect the finish to differ in detail.
import os, requests
body = {
"model": "ideogram/ideogram-v4.5",
"prompt": "Blueprint-style poster of a lighthouse in white line art on deep blue paper, grid lines, dimension arrows, small label \"LANTERN ROOM\" and \"GALLERY\"",
"aspect_ratio": "3:2",
"quality": "low",
"resolution": "1K"
}
r = requests.post(
"https://api.sume.com/v1/images",
headers={"Authorization": f"Bearer {os.environ['SUME_API_KEY']}"},
json=body,
timeout=60,
)
if r.status_code == 200:
out = r.json()
for img in out["data"]:
print(img["url"])
print("billed USD:", out["usage"]["cost"])
elif r.status_code == 202:
print("still running, poll:", r.json()["data"]["status_url"])
else:
print(r.status_code, r.text)What should I proof?
- Check every label for spelling, since the model sets text itself.
- Compare line weight between low and high on the same prompt before deciding the high tier is worth 7 times the cost.
- Never send
very_low: it is outside the public quality vocabulary. - For a print size, check the pixel count of the result against the print size you need.
Sources
Related posts
More in Models
- AI book cover mockup on Nano Banana Pro: 4:5 and four resolutions
Nano Banana Pro lists at $0.15 at 1K and default quality and bills $0.1875 on Sume; it takes 0.5K, 1K, 2K or 4K and 4:5, so read usage.cost for larger tiers.
- AI Christmas ornament renders on Recraft V4: text only, $0.05
Recraft V4 on Sume is text-to-image only and bills $0.05 per image ($0.04 list x 1.25); twelve ornament designs cost $0.60 in 1:1, 4:5, 3:2 and more.
- AI cocktail menu photos: four 4:5 takes per drink on Sume
Eight cocktails at four takes each is 32 images: $3.20 on Nano Banana 2 at $0.10 each, 4:5 ratio, one call per drink with n=4.
- AI digital planner cover art on Seedream 5 Lite: $0.04375 each
Seedream 5 Lite lists at $0.035 and bills $0.04375 on Sume; six planner cover options in 3:4 or 4:5 cost $0.2625 and read like one set.
Written by Sume