Higgsfield Soul on Sume: 1080p portrait covers at $0.0075 each
Soul bills $0.005 at 720p and $0.0075 at 1080p on Sume, makes 1 or 4 images, and lists 3:4 and 9:16. Fine for cover drafts, text-to-image only.

Higgsfield Soul is the cheapest image row on Sume: $0.005 per image at 720p and $0.0075 at 1080p, after the 1.25 margin on a $0.004 and $0.006 list. It generates 1 or 4 images per call, takes text only (no reference photos), and lists seven aspect ratios including 3:4 and 9:16, the shapes of a portrait cover.
The row
| Field | Value |
|---|---|
| API id | higgsfield/soul |
| List per image | $0.004 at 720p, $0.006 at 1080p |
| Billed per image | $0.005 at 720p, $0.0075 at 1080p |
| Images per call | 1 or 4 |
| Aspect ratios | 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3 |
| Reference images | No (text-to-image only) |
| Output format | Provider-selected (PNG) |
A cover-drafting batch
Four 1080p portrait options in one call (n: 4) cost 4 x $0.0075 = $0.03. A hundred 720p drafts cost $0.50. Those are the cheapest drafts in the catalog, so Soul fits a first pass where you pick a direction before paying for a finish on another model.
One caveat on price
The catalog marks Soul's list rate as the authenticated Higgsfield estimate for Sume's account, not a published tariff. The rate in the repo was verified on 2026-09-17. Treat it as the number Sume bills today and check pricing on the endpoint route before a large run.
Use it for
- Reels and TikTok cover drafts at 9:16, and grid-friendly 3:4 tiles.
- Mood boards and look tests before a finish on Nano Banana or GPT Image 2.5.
- Any job where you want many cheap variants and do not need exact text in the image.
Moving from draft to final
A practical flow is Soul for fifty cheap looks, then a finish on a row that can follow a reference. Soul cannot take a reference image, so the handoff is manual: pick the best draft, describe it in the final prompt (or pass the draft as input_references to an edit-capable row), and render the final at the ratio you will publish. Fifty 720p drafts cost $0.25, and a final on Nano Banana 2.1 at 2K adds $0.15.
For a series, keep the style words and the ratio fixed across drafts so that the set looks like one family. Consistency comes from your prompt text and fixed ratio.
Do not use it for
Edits of a real photo, since references return 400 unsupported_parameter; and text-heavy covers, where you should test a model with a quality knob such as GPT Image 2.5 or Ideogram 4.5. Request fields are on the Image API page: set resolution to 720p or 1080p and n to 1 or 4.
Sources
Related posts
More in Models
- Ideogram 4.5 edits: first reference is the source, 4 more allowed
On Sume, the first Ideogram 4.5 input reference is the image being edited and up to 4 more are references: 5 total. Order them or the wrong photo gets edited.
- Ideogram 4.5 API cost: $0.0375 to $0.275 per image on Sume
Ideogram 4.5 via Sume is $0.0375, $0.075 or $0.275 per image (low, medium, high): $3.75, $7.50 or $27.50 per 100. Draft-then-upgrade: $6.50.
- Image-to-video prompt: write the motion, not the photo
When a photo is already pinned as the first frame, spend the prompt on motion, camera and sound, not on describing what the picture shows. A worked rewrite.
- Imagen 4 Fast vs Ultra on Sume: $0.025 vs $0.075, text-to-image only
Imagen 4 Fast bills $0.025 and Ultra $0.075 on Sume. Both are text-to-image only with five ratios and no 4:5. Ultra adds 1K and 2K tiers. What that means.
Written by Sume