Runway Model Router vs sume/auto: how each picks a video model
Runway's Model Router saves a cost, latency or quality config and reuses it by configId. Sume's sume/auto picks the family and never says which. Differences.
Runway's changelog says Model Router became available on Runway Dev on July 23, 2026: you create a saved routing configuration once and reference it by configId, filtering models by cost, latency or quality (Runway changelog, read 2026-10-09). Sume's equivalent is a model id, sume/auto: you send the request and Sume selects the family. The difference is control. Runway lets you set the filter; Sume sets the choice and hides it.
What does sume/auto promise?
These come from the video generation docs and the Video Router docs.
- Resolution is a pure function of the normalized request and the catalog version, so an idempotent replay gets the same price and the same route.
- The poll response reports
"model": "sume/auto"; Sume does not disclose which family served the request. - Defaults are 720p and 8 seconds, with 3 to 10 second clips at 16:9 or 9:16.
- Responses show
sume/auto, and you should not infer the family from the output.
What does a saved config give you that Auto does not?
A Runway config is something you can review and change: prefer cost today, quality tomorrow. With Sume Auto there is no such knob in the request, and the Video Router's routing_preset values (cost, speed, quality) are ignored on the legacy Video 1.0 URL. If you need to control the model, pin a catalog id.
| Need | Runway | Sume |
|---|---|---|
| Let the service choose | Model Router with a saved config | model: "sume/auto" |
| Bias toward cost, latency or quality | Config filters | Not available on Auto |
| Choose a specific model | Name the model | Send a catalog id such as gemini-omni-flash-1.1 |
| Same request, same route | Not stated on the changelog | Yes, by design |
When is Auto the right call?
When the shot is generic and you want a price you can predict. Sume reserves the balance at submit and resolves the same request to the same route, so test your request shape once and check the reserve. If you need a specific model for repeat runs, pin a catalog id.
Sources
Related posts
More in Comparisons
- Runway wait_for_task_output vs a Sume poll loop in Python
Runway's SDK blocks in wait_for_task_output and raises TaskFailedError. On Sume's /v1/videos route you poll a URL yourself; a 10-second loop does it.
- Wan 3 on Runway Dev vs Sume: a 30-second 1080p clip is $6.00 vs $7.50
Runway Dev lists wan3 at 5, 10 and 20 credits per second ($0.01 each). Sume lists wan-3.0 at $0.0625, $0.125 and $0.25. The 30-second totals.
- Runway wan3_prime is 40% above wan3; Sume lists one Wan 3.0 row
Runway lists wan3 at 10 credits a second and wan3_prime at 14. Sume lists wan-3.0 at $0.125 per second at 720p. A 10-second clip: $1.00, $1.40 and $1.25.
- Seedance 2.0 at 1080p or Seedance 2.5 at 720p: 10 seconds on Sume
On Sume a 10-second Seedance 2.0 clip at 1080p costs $8.51 and a Seedance 2.5 clip at 720p costs $5.78. Seedance 2.0 at 720p is $3.78. The full grid.
Written by Sume