Kling 4 or Vidu Q4 on Sume: model_not_found and what to call
Sume has no kling-4 or vidu-q4 row, so a submit with those ids fails with 404 model_not_found. Call kling-3, wan-3.0 or sume/auto. Read 2026-10-13.

If you send kling-4 or vidu-q4 to Sume today, expect a 404 model_not_found: those ids are not in the catalog. The closest rows that are listed are kling-3 (1080p, 4-15 s, first and end frame, no references) and, for long or budget text-to-video, wan-3.0 (2-30 s). sume/auto is the safe default when you only need a good clip and not a particular family.
Check before you submit
A cheap catalog check avoids a wasted job and a confusing error. The code below prints whether each id is listed; it only reads the catalog and does not create a job.
import os, requests
H = {"Authorization": f"Bearer {os.environ['SUME_API_KEY']}"}
r = requests.get("https://api.sume.com/v1/videos/models", headers=H, timeout=30)
r.raise_for_status()
ids = {m["id"] for m in (r.json().get("data") or [])}
for want in ("kling-4", "vidu-q4", "kling-3"):
print(want, "listed" if want in ids else "not listed")What changes in your client?
Nothing, if the id comes from config. Keep the model id in an environment variable or setting, test it against GET /v1/videos/models at startup, and fall back to a listed id when it is missing. A fallback that silently changes family should be logged, because limits differ: kling-3 is always 1080p, wan-3.0 has three tiers, and Omni is 16:9 or 9:16 only.
| Need | Fallback row | Why |
|---|---|---|
| Kling family, first and end frame | kling-3 | Listed, 1080p, 4-15 s |
| Longest text-to-video clip at a low rate | wan-3.0 at 480p | Tiered rate, 2-30 s |
| No preference | sume/auto | Router picks, default is Omni Flash 1.1 |
Sources
Related posts
More in Developers
- LinkedIn Posts API video post body: the fields and a Python builder
A LinkedIn video post needs author, commentary, visibility, distribution, a urn:li:video media id and lifecycleState PUBLISHED. Version 202510 sunsets Oct 15.
- LinkedIn video post stuck in processing: two status ladders to poll
LinkedIn tracks a video asset (PROCESSING, AVAILABLE) and a post (PUBLISH_REQUESTED, PUBLISHED) separately. Poll both, then compare with a Sume job poll.
- MAI-Transcribe-2 on OpenRouter: wav, base64, transcript JSON
OpenRouter exposes microsoft/mai-transcribe-2 at POST /api/v1/audio/transcriptions with base64 audio and returns JSON with transcript and usage.
- MAI-Voice-2.1 on OpenRouter: audio/speech call, mp3 or pcm
OpenRouter serves microsoft/mai-voice-2.1 at POST /api/v1/audio/speech and returns raw audio bytes, mp3 or pcm. Here is the call and how Sume jobs differ.
Written by Sume