200-image mood board for $1: Soul at half a cent on Sume

Answer

Higgsfield Soul (higgsfield/soul) is Sume's cheapest image row at $0.005 per image, so 200 mood board images cost $1.00 when you send 50 calls with n: 4. It is text-to-image only, and its n is 1 or 4, so you cannot ask for two or three.

Soul accepts seven aspect ratios (1:1, 16:9, 9:16, 4:3, 3:4, 3:2 and 2:3) and a resolution of 720p or 1080p. Its output format is chosen by the provider, and the catalog notes PNG.

Caveats

• The catalog says the list price is the authenticated Higgsfield estimate for the Sume account, not a published tariff. Read pricing from the endpoints call before you scale up.
• No reference photos. If a mood board must start from a product shot, use Grok Imagine or Qwen Image at $0.025.
• Quality values do not apply to Soul. A request that sets quality returns a 400.
• Mood boards are idea sheets. Pick a direction, then regenerate finals on a higher-end row.

Request

curl -X POST https://api.sume.com/v1/images \
  -H "Authorization: Bearer $SUME_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"higgsfield/soul","prompt":"mood board frame: quiet cafe at dawn, film grain, muted greens","aspect_ratio":"3:2","n":4,"resolution":"720p"}'

Use mode: "async" for large runs, since each sync wait ends after 30 seconds with a 202. A failed call is not billed. Docs: Sume Image API.

Before a large run

Prices and descriptors change when the catalog changes, so confirm them before you spend. Call GET /v1/images/models/{id}/endpoints for the row you plan to use and read its pricing line and supported_parameters; both come back in one response.

Then run a pilot of three to five images and read usage.cost on each response. Multiply by your planned count for a forecast you can trust. Completed generations are billed in full and failed or cancelled ones are not, so a pilot that errors costs nothing.

For big batches, use mode: "async" or mode: "webhook" with a public HTTPS webhook_url, so no request waits on the 30-second sync limit. Poll GET /v1/jobs/{id}/status and fetch GET /v1/jobs/{id}/result when the job completes.