Why a video model is missing from your Sume model list
A documented video id can be absent from the model list: Veo needs Google Cloud, Tencent rows need the Tencent switch. Absent ids 404. Read 2026-10-13.

Because some rows are conditional. The Video Router doc marks Veo as Google Cloud only, the WAND-Vega, Mingmou, Hunyuan and H3 Regen rows as Tencent VOD only, and Genjutsu as listed only when configured. If your environment lacks that provider, the row is not in GET /v1/videos/models, and submitting its id fails with 404 model_not_found.
Which rows depend on what
Use this table to find the cause quickly.
| Row | Condition |
|---|---|
veo-3.1, -fast, -lite | Google Cloud serves them |
wand-vega-*, mingmou-1, hunyuan-1.5, hailuo-h3-regen | Tencent VOD switch |
higgsfield-genjutsu | Provider configured |
heygen-video-1 | OpenRouter route only |
kling-4, vidu-q4 | not in the catalog at all |
How to handle it in code
Read the list at startup and never hardcode the assumption that a documented id exists. Choose a fallback from the always-listed rows (Seedance, Kling 3, Wan 3.0, H3, H3 Max, Omni), or send sume/auto. Log the id that served each job so a missing row shows up as a config question rather than a bug.
Sources
Related posts
More in Developers
- X media upload: how many APPEND calls a Sume MP4 needs at 5 MB
X's chunked upload keeps each segment at or below 5 MB, with an 8 MB server limit. Divide your MP4's byte size by 5 MB, rounded up, to count APPEND calls.
- Year-in-review videos for 250 customers: bulk queues of 100, 100, 50
A Sume bulk run takes at most 100 items, so 250 year-in-review runs need three queues. Set concurrency 1 to 16, a spend cap per item and a new key per queue.
- Which MCP server lets Claude Code or Cursor generate video and images?
MCP servers that let Claude Code and Cursor make video and images: Sume, fal, Replicate, Runway, Higgsfield. Endpoints, sign-in, billing, setup.
- Idempotency keys for AI video APIs: retry without paying twice
An idempotency key makes a retried create return the original run or job instead of a second paid one. How Sume's Idempotency-Key works on each API.
Written by Sume