OpenRouter video client on Sume: six documented differences
Sume says /v1/videos matches the OpenRouter Video Generation API except six items: base path, auth, model ids, auto routing, size and provider.options.
A video client written from the OpenRouter Video Generation docs should work on Sume after you change the base URL and the API key, with six documented differences. They cover the base path, auth, model ids, auto routing, the size field and provider.options. Everything else on the surface is described as field-for-field the same.
The differences
This table restates the "Sume differences" section of the Videos docs.
| Area | OpenRouter | Sume |
|---|---|---|
| Base path | https://openrouter.ai/api/v1/videos | https://api.sume.com/v1/videos, no /api segment |
| Auth | Bearer OPENROUTER_API_KEY | Bearer SUME_API_KEY |
| Model ids | org/slug, for example google/veo-3.1 | Bare catalog ids, for example seedance-2 |
| Auto routing | No generate-time auto | model sume/auto; responses show sume/auto |
| size | Accepted when the model shows supported_sizes | Every v1 model reports null, so 400 unsupported_parameter |
| provider.options | Forwarded to the matched provider | Non-empty value returns 400 unsupported_parameter |
What this means for a port
Most ports are two edits and a search. Change the URL and key, then search for slash-prefixed model ids and drop the prefix, since Sume does not publish an org prefix on video ids. Replace size with resolution and aspect_ratio, and delete any provider.options. Your model choice must also exist in the Sume catalog; read GET /v1/videos/models, because the lists are not the same.
What this does not tell you
The docs claim API agreement, not output parity. Durations, resolutions, audio and prices are set per model and differ from what another router shows for a similar name, so re-test with a few real prompts before moving traffic.
Sources
Related posts
More in Comparisons
- Pick an image model by job: product photo, poster text, edit
Five new image releases in a month. A job-first table for Sume: GPT Image 2.5, Ideogram 4.5, Nano Banana 2.1, FLUX.2 and Qwen, with the limits that decide.
- Sora API shutdown report: which claims Sume docs can answer
Pondero's Sora API shutdown report names Runway, Kling and Seedance. Sort its claims from what Sume's docs list, so you do not assume a model is there.
- Precise image editing on Sume: what it has and what it lacks
A plain list of what Sume offers for precise edits after Flux 3 Image and Ideogram 4.5: no Flux 3, no box field, mask_url on one model, Ideogram 4.5 present.
- Real-time or async avatar: six questions to ask before you choose
Need an avatar that talks live, or a finished clip? Six yes/no questions decide it, with what Sume's async avatar jobs cover and what they do not.
Written by Sume