Image 1.0: text, reference or masked edit - which fields to send
Image 1.0 uses prompt only for text-to-image, prompt plus image_urls for edits or references, and adds mask_image_url for masked edits. Fields and URL rules.

On Image 1.0, send only prompt for text-to-image, add image_urls for an edit or reference, and add mask_image_url on top for a masked edit. All image URLs must be public HTTPS.
From Sume's Image 1.0 docs, read 2026-09-30. Image 1.0 is retiring soon and returns job.model: "sume/auto".
Which goal needs which fields?
The docs give a three-row table.
| Goal | Approach |
|---|---|
| Text to image | prompt only |
| Edit or reference | prompt plus image_urls (1 to 10 public HTTPS URLs) |
| Masked edit | Add mask_image_url with image_urls |
What does an edit prompt look like?
The docs' own example keeps the product and swaps the background:
curl -X POST https://api.sume.com/v1/image-1.0/generate \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: image-edit-001" \
-d '{
"prompt": "Keep the product identical; swap the background to a soft daylight studio",
"image_urls": ["https://media.sume.com/artifacts/artf_demo/product.png"],
"quality": "medium",
"aspect_ratio": "4:3"
}'What are the URL rules?
Use public HTTPS image URLs only. Localhost, private-network and non-HTTPS URLs are rejected before submission.
How do I get the result?
Submit responses include status_url, result_url and events_url. Poll until the job is terminal, then read result.artifacts[], which holds Sume-hosted media. Raw provider URLs are not part of the public result contract.
How do I check this myself?
Because Image 1.0 uses Auto model selection, the family that ran is not disclosed and job.model stays sume/auto. If you need a specific family for edits, use POST /v1/images with a catalog id. The linked docs pages and the catalog endpoint show the current values, and this post reflects them as of 2026-09-30.
Sources
Related posts
More in Developers
- mask_image_url or mask_url? Masked edits on Sume's image APIs
Image 1.0 takes mask_image_url with image_urls; POST /v1/images takes mask_url with input_references for GPT Image 2.5. Field names, models and limits.
- Image job metadata on Sume: stored on the job, not sent upstream
The metadata field on Image 1.0 and POST /v1/images is stored on the job and not sent to the provider. Use it to tie jobs to your own records.
- Image 1.0 mode vs POST /v1/images: default wait and 202 explained
POST /v1/images defaults to sync and blocks up to 30 seconds; Image 1.0 lists async, sync, subscribe and webhook. Compare defaults and wait_timeout_seconds.
- num_images 1-4 or n 1-10? Images per call on Sume's image APIs
Image 1.0 takes num_images 1 to 4. POST /v1/images takes n up to 10, with lower per-model ceilings. Which to use and how to read the real limit.
Written by Sume