POST /v1/videos or /v1/video-router/generate for a new build?
Sume recommends POST /v1/videos for new integrations. Video Router stays unchanged with the same models and jobs but a different wire. The differences.
Use POST /v1/videos for a new Sume video integration. Sume's docs recommend it over the Video Router and say it has the same catalog and the same jobs, behind an OpenRouter-compatible wire. POST /v1/video-router/generate stays available and does not change, so existing code on it does not need to move.
Side by side
Both create the same jobs with the same model ids. What differs is the request and response shape, per the Sume docs read 2026-10-09.
| Area | POST /v1/videos | POST /v1/video-router/generate |
|---|---|---|
| Status in docs | Recommended for new integrations | Legacy, unchanged, still works |
| Wire | OpenRouter-compatible video generation | Sume { "data": ... } job envelope |
| Image inputs | OpenRouter-style frame and reference fields | Flat image_url and reference_image_urls |
| Auto model | model: "sume/auto" | Video Router Auto, same pipe |
| Idempotency | Idempotency-Key header, replay returns the original job | Idempotency-Key header shown in the docs example |
| Polling | Polling URL, or GET /v1/jobs/{id}/status and /result | Jobs API |
Why it matters in practice
A client written from OpenRouter's video docs works on /v1/videos after changing the base URL and the key, since Sume's differences are listed in one table: no /api segment, bare model ids with no org prefix, size rejected in favor of resolution plus aspect_ratio, no seed, no provider.options, and a USD workspace balance instead of credits. The reservation at submit is the provider list price times 1.25.
If you already have Video Router code with the flat image_url fields, there is no deadline in the docs. Migrate when you next touch it, not before.
Auto, and what to pin
sume/auto lets Sume pick the model family and never discloses which family ran. The Auto create controls default to 720p and 8 seconds, with 3 to 10 second clips at 16:9 or 9:16. If you need a fixed price per second or a duration above 10 seconds, pin a model from GET /v1/videos/models instead.
See the Video generation page and the Video Router page for the full fields, and the catalog for prices.
- New code:
/v1/videos. - Existing Video Router code: leave it.
- Need 30-second clips: pin Seedance 2.5 or Wan 3.0, not Auto.
Reproduce the numbers
Every Sume price on this page comes from the public catalog at https://api.sume.com/v1/catalog, which needs no API key. Fetch it, find the row for the job or model named in the table, and multiply by your own seconds, characters or image count. Sume bills the list price shown in that row, so the catalog figure is the one that applies to your balance.
All figures on this page are Sume's own, as of 2026-10-09. Prices and limits can change, so re-read the catalog and the linked docs before a large run, and keep the arithmetic in a spreadsheet so you can update it in a minute.
Sources
Related posts
More in Comparisons
- Veo 3.1 takes 3 reference images; Omni on Sume takes 10 plus 3 clips
How many reference images does Veo 3.1 accept, and how many does Gemini Omni Flash take on Sume? Limits, tag syntax and a request example.
- Max AI video length: Runway Gen-4.5 10 s vs Sume's 30-second rows
Runway's Gen-4.5 runs 2 to 10 seconds and Omni 3 to 10. Sume's Wan 3.0 and Seedance 2.5 reach 30. Longest single clip by model, with the sources.
- YouTube AI label: three auto-detection signals and Sume outputs
YouTube may label video automatically for its GenAI tools, C2PA metadata or internal detection. Sume docs do not mention C2PA, so here is what to check.
- Which audiobook stores accept AI narration? ACX, Apple, KDP, Spotify
ACX bans unauthorized AI narration, Apple narrates for you, KDP is an invite beta, Spotify wants a disclosure. Read 2026-10-10, plus where Sume TTS audio fits.
Written by Sume