Higgsfield Soul on Sume: half a cent per image, batches of 1 or 4
higgsfield-soul costs $0.005 at 720p and $0.0075 at 1080p on Sume. It takes batch sizes 1 or 4, no references. Price table and a four-image call.

higgsfield-soul is the cheapest image row in Sume's catalog: $0.005 at 720p and $0.0075 at 1080p per image. It is text-to-image only (zero input_references), and the number of images per request is 1 or 4, not a free 1 to 4 range.
Price by tier and batch
| Resolution | 1 image | 4 images | 1,000 images |
|---|---|---|---|
| 720p | $0.005 | $0.02 | $5.00 |
| 1080p | $0.0075 | $0.03 | $7.50 |
A four-image call
Ask for four when you want a spread, since a batch of four costs four singles.
import os, requests
r = requests.post(
"https://api.sume.com/v1/images",
headers={"Authorization": f"Bearer {os.environ['SUME_API_KEY']}"},
json={
"model": "higgsfield/soul",
"prompt": "Portrait of a skateboarder in golden hour light, film grain",
"n": 4,
"resolution": "720p",
},
timeout=60,
)
print(r.status_code)
body = r.json()
if r.status_code == 200:
for item in body["data"]:
print(item["url"])
else:
print(body)Where it fits
Use Soul for mood boards, prompt exploration and thumbnails you will not edit. When you need to edit a photo, keep text legible, or return a transparent PNG, switch to a row that lists references, quality tiers or the background field.
Sizes depend on the tier; read the live resolution descriptor from GET /v1/images/models rather than hard-coding it.
Budget view
- 10,000 images at 720p cost $50.00.
- The same 10,000 at 1080p cost $75.00.
- Use
n: 4for a spread andn: 1for a single; other counts are not listed for this row. - Read
GET /v1/images/models/{model_id}/endpointsfor the livepricingline before a large run: prices are catalog data and can change.
Sources
Related posts
More in Models
- How long can a Sume agent run take? Timeouts for slow models
Format runs are finalized at 90 minutes, or after 10 silent minutes once past 25. Agent Completions publish no deadline. Webhooks time out at 10 s per attempt.
- How many aspect ratios each Sume image model lists, vs Hy's 14
Hy Image 3.5 Preview lists 14 aspect ratios. On Sume, Nano Banana 2.1 and Ideogram list 15, Grok and Flux 13, GPT Image 2.5 only 9. Full counts by row.
- HunyuanVideo VRAM: 45 GB at 544p, 60 GB at 720p, 80 GB advised
The HunyuanVideo README lists 45 GB for 544x960 and 60 GB for 720x1280 at 129 frames, tested on one 80 GB GPU. FP8 saves about 10 GB. Table and hosted route.
- HunyuanVideo 720p: 1,904 s on one GPU, 338 s on eight
README latency for a 1280x720, 129-frame, 50-step clip: 1,904 s on 1 GPU and 338 s on 8. The GPU-seconds each setup burns, and what it means for hosted jobs.
Written by Sume