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.

On Sume, Ideogram 4.5 is ideogram/ideogram-v4.5. Without references it generates from text. With references, the first input_references item is the image that gets edited and up to four more are style or content references, five in total. Put the photo you want changed first, or the wrong image becomes the edit source.
One id, two modes
Sume's docs say the request switches mode by whether you send references. No references runs a text-to-image generation. Any references run an edit. An edit without aspect_ratio keeps the shape of the source image, so you do not need to restate its dimensions.
| Mode | input_references | Quality values | List price per image |
|---|---|---|---|
| Text to image | none | low, medium, high | $0.03, $0.06, $0.22 |
| Edit | 1 source + up to 4 more | low, medium, high | $0.03, $0.06, $0.22 |
| Default quality | omitted | medium | $0.06 |
| Resolution | any | 1K or 2K | same price at any size |
Order matters
Reference 1 is the source. Reference 2 might be a logo, 3 a colour palette image. In the prompt, name each by position: change the text on image 1 using the logo in image 2. If you swap the order, Sume does not warn you, because it cannot know which photo you meant.
curl -X POST "https://api.sume.com/v1/images" \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"ideogram/ideogram-v4.5","prompt":"Edit image 1: replace the headline with SUMMER SALE. Use the logo from image 2 in the top left. Change nothing else.","quality":"medium","input_references":[{"type":"image_url","image_url":{"url":"https://media.sume.com/uploads/banner.png"}},{"type":"image_url","image_url":{"url":"https://media.sume.com/uploads/logo.png"}}]}'What the docs rule out
The Ideogram section of the Image API docs lists only input_references, quality, resolution and aspect_ratio for this model, so do not count on mask_url for a region edit; check the capabilities from GET /v1/images/models before relying on any other parameter. The quality names are Sume's low, medium and high.
Budget
The prices above are list prices and exclude Sume's pricing, so read cost_usd from GET /v1/images/models/ideogram/ideogram-v4.5/endpoints before you plan a run.The Sume docs give one per-quality list price for the model and do not add a per-reference charge.
Edit checklist
Before sending an Ideogram edit:
- Source image first in
input_references. - At most four more references after it.
- Leave
aspect_ratioout to keep the source shape. - Name each image by position in the prompt.
Sources
Related posts
More in Models
- 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 shut down Aug 17: Nano Banana 2.1 is the named replacement
Google lists gemini-nano-banana-2.1 as the Imagen 4 replacement. Imagen rows on Sume take no reference photos, while Nano Banana 2.1 takes up to 10.
- Lip-sync and motion control cost per clip: H3 Max, Fabric, Kling
Sume prices H3 Max lip-sync at $0.0625 to $0.20 per audio second, Fabric at $0.1875 and Kling 3.0 Motion Control at $0.1575. A 10-second clip is $0.63 to $2.00.
Written by Sume