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.

To render Christmas ornament designs on Recraft V4, call recraft/recraft-v4 with a text prompt: it is text-to-image only on Sume, and it bills $0.05 per image, which is the $0.04 catalog list times 1.25. Twelve ornament designs cost $0.60.
Ornaments are small objects with a clear silhouette, a good use for a model that renders clean illustrated shapes. Facts are from Sume's Image API page and the catalog source, read on 2026-10-05. Because Recraft V4 takes no reference image, you cannot start from a photo of your real ornament; use it for concept art, and use an edit-capable model for pictures of a real product. Check GET /v1/images/models for the output formats the row lists before you assume one.
What are Recraft V4's limits on Sume?
Recraft V4 maps to a text-to-image endpoint, so a request with input_references has nothing to edit. Parameters outside the model's catalog descriptor return 400 unsupported_parameter, so read the descriptor first.
| Item | Value | Source |
|---|---|---|
| Model id | recraft/recraft-v4 | Image API page |
| Input | Text only | Text-to-image endpoint in the repo |
| Billed price per image | $0.05 | $0.04 list x 1.25 |
| Twelve designs | $0.60 | 12 x $0.05 |
| Ratios | 1:1, 16:9, 9:16, 4:3, 3:4, 4:5, 5:4, 3:2, 2:3, 21:9, 9:21, 1:2, 2:1 | Catalog aspect list |
| Custom pixels | image_size takes priority over aspect_ratio | Image API page |
How do I request an ornament?
Ask for one ornament per call on a plain background. The four takes of a call are variations of one brief.
import os, requests
body = {
"model": "recraft/recraft-v4",
"prompt": "A single hand-painted glass Christmas ornament, deep green with gold snowflakes, hanging on a thin ribbon, plain cream background, studio light",
"aspect_ratio": "1:1"
}
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 check?
- Do not pass
input_references: the row is text-only. - Keep concept art labelled as a concept until a real ornament matches it.
- Sum
usage.costacross the set to confirm it matches 12 x $0.05. - Look at the file type of the returned URL before wiring it into a listing template.
Sources
Related posts
More in Models
- 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.
- AI flat lay product photos on Imagen 4 Ultra: $0.075, 1K or 2K
Imagen 4 Ultra bills $0.075 per image on Sume ($0.06 list x 1.25) at 1K or 2K, in 1:1 and 4:3: a top-down flat lay concept for five products costs $0.375.
- AI flower bouquet photos for a florist: Seedream 4.5 reference edit
A florist can keep a real arrangement and change only the backdrop on Seedream 4.5: $0.04 list, $0.05 billed on Sume, 4:5 ratio, up to 10 references.
Written by Sume