Ideogram 4.5 quality: very_low needs a source image
Ideogram 4.5 quality defaults to medium with source images and high without, and very_low needs sources. Sume's quality enum is catalog-gated.
Ideogram 4.5's quality defaults to medium when you send source images and high when you do not, and very_low, its fastest and cheapest setting, requires source images. Sume has a quality field too, but its values are auto, low, medium, high, xhigh or max, gated per model by the catalog, so very_low is not a Sume value.
Ideogram facts are from its Ideogram 4.5 reference; Sume facts from the Image API and catalog code, read 2026-10-01.
What are Ideogram 4.5's quality rules?
The reference says higher quality takes longer and costs more. The default depends on the request: medium with source images, high without. The snapshot names very_low, medium and high; it does not list the other enum values, so check the page for the full set. A text-only request that sets very_low breaks the stated rule.
What does quality mean on Sume?
The request table describes quality as a string that is auto, low, medium, high, xhigh or max (catalog-gated). A request that sets a parameter the selected model does not list is rejected with 400 unsupported_parameter, so read the model's descriptors first. In the catalog code, the Ideogram entry is Ideogram V3, with the constraint that quality maps to a rendering speed upstream, not to a general quality scale.
| Item | Ideogram 4.5 | Sume Image API |
|---|---|---|
| Values named | very_low, medium, high | auto, low, medium, high, xhigh, max |
| Default | medium with sources, high without | Not stated for every model |
| Lowest tier | very_low (needs sources) | low |
| Who limits values | The endpoint | The model's catalog descriptors |
| Ideogram on Sume | Not applicable | Ideogram V3 only |
How should I translate a request?
Do not pass very_low through; the nearest Sume value for a quick draft is low, if the model lists it. Read supported_parameters for the model, send one of its values, and leave the field out when you want the default. Sume does not say the two scales line up, so test the output rather than assuming a match.
For a side-by-side of the older tiers, see Ideogram V3 quality tiers.
Does quality change what I pay?
On Ideogram, the reference says higher quality costs more. On Sume, the image docs list quality among the high-cost configurations that can push a request past the 30-second wait into a 202 job envelope, and the price you pay is the endpoint pricing line from GET /v1/images/models. Check that line for the model and settings you use.
Sources
Related posts
More in Developers
- Ideogram 4.5 size source: keep dimensions, and Sume aspect auto
Ideogram 4.5 size takes auto, source or WIDTHxHEIGHT; source needs source images. Sume's size is a tier shorthand; use aspect_ratio auto to match a reference.
- Ideogram 4.5 edit images: 5 sources, first is edited, vs Sume
Ideogram 4.5 takes up to 5 source images, 25 MB each; the first is edited and multipart is required. Sume takes public HTTPS URLs as input_references.
- Ideogram 4 describe image to JSON prompt vs Sume reference input
Ideogram's describe endpoint returns a structured json_prompt with optional bounding boxes. The Sume docs list no such route; pass the image as a reference.
- Ideogram ad localizer API: exact_copy vs a Sume edit prompt
Ideogram's ad-localizer takes one language per call and an exact_copy mapping. On Sume you send the ad as a reference and spell out the copy in the prompt.
Written by Sume