gen3a_turbo no longer available on Runway: re-read Sume's model list
Runway now fails requests for gen3a_turbo and gen4_aleph. Avoid the same break on Sume: read /v1/videos/models instead of hard-coding ids.

Runway's changelog says gen3a_turbo and gen4_aleph are no longer available and requests using them fail. On Sume, avoid that failure mode by reading GET /v1/videos/models at startup and choosing an id from the response, rather than baking an id into your code.
Sources: the Runway Dev changelog (July 30, 2026) and Sume's video generation docs, read 2026-10-01.
What did Runway remove?
The entry says Gen-3 Alpha Turbo (gen3a_turbo) and Gen-4 Aleph (gen4_aleph) are no longer available on Runway Dev. It points Gen-3 Alpha Turbo users to Gen-4.5 or Gen-4 Turbo, and Gen-4 Aleph users to Aleph 2.0 (aleph2).
How does Sume's list change?
The docs say some catalog models are listed only when their provider is configured, and that limits are per model: seedance-2.5 accepts 4–30 seconds while most other catalog models top out at 15 seconds (wan-3.0 accepts 2–30). So the set of valid ids and ranges is data, not a constant.
| Situation | Runway Dev | Sume approach |
|---|---|---|
| Removed id | Requests fail | Re-read the model list; drop ids that are gone |
| Conditional id | Not stated | Listed only when its provider is configured |
| Duration limits | Not covered by this entry | Read supported_durations per id |
What should my client do?
Fetch the list, cache it briefly, and validate the chosen id, duration and resolution against the entry before submitting. For an earlier retirement on Sume, see Kling 2.1 sunset.
const res = await fetch("https://api.sume.com/v1/videos/models", {
headers: { Authorization: "Bearer " + process.env.SUME_API_KEY },
});
console.log(await res.json());What happens to a job that fails?
The generation docs say failed jobs and failed queue admission release or refund the reservation where applicable. Resubmitting with a valid id is a new request.
Sources
Related posts
More in Developers
- Runway INTERNAL.BAD_OUTPUT.01: fix the prompt, then resubmit
Runway's INTERNAL.BAD_OUTPUT.01 may succeed after prompt fixes. Sume's equivalent step: inspect job events, fix the input, and send a new request.
- Runway INTERNAL or null failureCode: how long to delay a retry
Runway says to add a delay for INTERNAL or null failure codes but gives no number. Sume's errors carry retryable and retry_after_seconds fields.
- Runway Model Router allow and deny lists vs Sume auto
Runway's Model Router has allow and deny lists plus per-modality credit ceilings. Sume has no lists: pin a catalog id, or send sume/auto and accept its pick.
- Runway per-generation usage export vs the Sume GET /v1/usage ledger
Runway's enterprise usage export lists credits per generation. On Sume, GET /v1/usage returns USD ledger rows per workspace, filterable by job_id.
Written by Sume