POST /v1/image-router/generate deprecated: what to call instead
Sume's legacy /v1/image-router/generate and /v1/image-router/models routes still work but gain no new parameters. Use POST /v1/images and GET /v1/images/models.
Sume's legacy POST /v1/image-router/generate and GET /v1/image-router/models still work and are unchanged, but they are deprecated and will not gain new parameters. Move to POST /v1/images and GET /v1/images/models.
From Sume's Image API docs, read 2026-09-30.
What maps to what?
The replacement surface covers generation and discovery.
| Legacy | Replacement |
|---|---|
POST /v1/image-router/generate | POST /v1/images |
GET /v1/image-router/models | GET /v1/images/models |
Bare ids such as gpt-image-2 | openai/gpt-image-2 |
Will old code keep working?
The docs say the legacy routes still work. Bare Image Router ids like gpt-image-2 and nano-banana-2 are accepted as aliases for their org/slug equivalents. Anything new, such as mask_url or background for ChatGPT Image 2.5, is documented on the newer surface.
What changes in the response?
POST /v1/images returns Sume-hosted data[].url with usage.cost, and a 202 job envelope for slow runs. Check the status code, not the body shape, and read the n, quality and input_references descriptors for each model.
curl "https://api.sume.com/v1/images/models" \
-H "Authorization: Bearer $SUME_API_KEY"What about Image 1.0?
Image 1.0 is a separate compatibility alias for Auto that is retiring soon. For new integrations use POST /v1/images with model: "sume/auto" or a catalog id.
How do I check this myself?
Plan the move in two steps: switch the URL and model id first, then adopt the newer fields. Keep the legacy call working in a branch until the new one matches your outputs. 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
- size vs image_size on Sume's Image API: where custom pixels go
On POST /v1/images, size is a resolution-tier shorthand and explicit pixels on size return 400. Custom pixels go in image_size or aspect_ratio.
- Image API usage shows 0 tokens: where the cost is on Sume
POST /v1/images returns usage.prompt_tokens, completion_tokens and total_tokens as 0 in v1. The billed amount is usage.cost in USD, metered per image.
- Lambda 90-minute timeout: does it change AI video jobs?
AWS raised Lambda's async timeout to 90 minutes on Managed Instances. A Sume job still fits best as submit, then poll or webhook, and sync waits stay 30 s.
- List music models by API: GET /v1/music-router/models
The Music Router catalog endpoints list routable music model ids and a provider list price. Routable ids today: sume/music-auto, lyria-3.5, lyria-3-pro.
Written by Sume