Ideogram dry_run price quote vs Sume image pricing lines

On Ideogram's v2 endpoints, dry_run=true validates and prices the request without generating or billing, and returns a PriceQuote. The Sume images docs and OpenAPI entry for POST /v1/images list no dry_run parameter. To price an image first, read the model's pricing lines from GET /v1/images/models/{model_id}/endpoints and multiply by n.

Ideogram facts are from its API reference; Sume facts from Image generation, read 2026-10-01.

What does Ideogram's dry_run do?

It is a boolean query parameter, default false. When true, the request is validated and priced but not run: nothing is generated, stored or billed, and no safety review is performed. Ideogram says to send exactly the request you would send to generate, so the quote reflects the same options.

How do I price an image on Sume before calling?

Call the per-endpoint record and read pricing, which holds billable lines such as output_image with a unit and cost_usd. The docs state that these lines are the amount charged to your wallet, with Sume's margin already applied, so cost_usd × n is what you pay.

curl "https://api.sume.com/v1/images/models/bytedance-seed/seedream-4.5/endpoints" \
  -H "Authorization: Bearer $SUME_API_KEY"

How do the two approaches compare?

Do I need to know what parameters a model supports?

Yes. Capability descriptors in the catalog list what each model accepts, and a request that sets an unlisted parameter is rejected rather than dropped. Reading supported_parameters and pricing together gives you a check before spending anything. See also Replicate estimates versus Sume previews.