google/veo-3.1 style ids vs Sume: bare video model ids
OpenRouter names video models org/slug, such as google/veo-3.1. Sume uses bare catalog ids like seedance-2 and never a provider prefix. How to port an id.

Sume video models use bare catalog ids such as seedance-2, never an org/slug id like OpenRouter's google/veo-3.1 example. A prefixed id is not a valid Sume model, so look up the bare id in the catalog.
How do the two id styles differ?
OpenRouter's page gives google/veo-3.1 as its example model. Sume's differences table says its published contract never carries a provider-org prefix.
| Side | Example |
|---|---|
| OpenRouter page | google/veo-3.1 |
| Sume | seedance-2 |
| Sume auto pick | sume/auto |
What is sume/auto then?
It is the one prefixed value in the docs: a Sume-only addition that lets Sume pick the family. It is not a provider prefix.
How do I find the right id?
List the catalog and read the id field of each entry. The example returns seedance-2 with name Seedance 2.0.
curl "https://api.sume.com/v1/videos/models" \
-H "Authorization: Bearer $SUME_API_KEY"What if the model I want is not listed?
The docs' troubleshooting notes for a model-not-found error say to use the model list and to verify the id is a bare catalog id. For Veo, see Veo 3.1 access and catalog alternatives and the video docs.
What else changes when I port a request?
Base URL, key and id are the main edits. size, seed and non-empty provider.options are rejected, and the webhook envelope is Sume's, signed with x-sume-webhook-signature.
Auto routing is a Sume addition: model: "sume/auto" lets Sume pick the family, and the response echoes sume/auto.
Sources
Related posts
More in Developers
- GPT Image 2.5 1080x1350: why the size fails and what to send
1080x1350 breaks GPT Image 2.5's multiple-of-16 size rule. 1080 is not a multiple of 16. 1088x1360 (exact 4:5) meets the listed rules. Per OpenAI and Sume docs.
- GPT Image 2.5 Batch API: not supported, so fan out jobs
OpenAI's model page lists Batch as unsupported for GPT Image 2.5. On Sume, submit many async or webhook jobs to /v1/images and collect the results.
- GPT Image 2.5 mask edit: does the mask need an alpha channel?
OpenAI's API says the mask must contain an alpha channel. Sume's docs list a public HTTPS mask_url for GPT Image 2.5 edits but state no mask format rule.
- GPT Image 2.5 moderation low: can you send it through Sume?
OpenAI lists a moderation parameter (auto or low) for GPT Image 2.5. Sume's request table does not list it, so check the catalog before sending it.
Written by Sume