Nova Reel EOL September 30, 2026: moving video jobs to Sume
Bedrock lists Nova Reel as Legacy with an EOL date of September 30, 2026. Remap StartAsyncInvoke to a Sume video job and read results from media URLs.
The Bedrock model card lists Nova Reel (amazon.nova-reel-v1:0) with lifecycle Legacy and a model EOL date of September 30, 2026, which is already past on 2026-10-01. On Sume you replace StartAsyncInvoke with a video job: submit, get a job id, poll status_url, then read a media.sume.com URL instead of an S3 object.
Bedrock facts are from the model card; Sume facts from Jobs and results and Video generation.
What does the model card say?
It lists Nova Reel as Amazon's video generation model for short videos from text and image prompts, launched Dec 3, 2024, lifecycle Legacy, EOL September 30, 2026. The APIs column includes StartAsyncInvoke.
What do I remap in a StartAsyncInvoke pipeline?
| Step | Bedrock Nova Reel | Sume video job |
|---|---|---|
| Submit | StartAsyncInvoke | Video request; the first response carries the job id |
| Wait | Check the async invocation | Poll status_url until terminal is true |
| Fetch | Output written to your S3 location | result_url, durable media.sume.com HTTPS URLs |
| Image input | Image prompts | frame_images for first/last frames; input_references for style |
How do results arrive?
The runs docs say media URLs are durable media.sume.com HTTPS URLs that do not expire and are public to anyone holding the link. If your product needs per-customer access control, proxy or copy them.
Will my prompts carry over?
Not necessarily. Models differ in duration, resolution and audio, so test a sample set. A step-by-step comparison is in Nova Reel StartAsyncInvoke vs Sume job results. Use an Idempotency-Key on submits so retries do not create duplicate paid jobs.
Sources
Related posts
More in Models
- Dictation API: AssemblyAI cleaned text vs Sume STT word timings
AssemblyAI's Dictation API returns send-ready text. Sume STT returns a transcript with words[] timings and no cleanup flag, so you do the filler removal.
- AssemblyAI text to speech: coming soon, and what Sume has today
AssemblyAI's product menu lists a Text-to-Speech API as coming soon. Sume TTS is available now: what a call takes, the 20000-character cap, and word timings.
- Cartesia Sonic 2 and Turbo stop October 20: Sume model ids
Cartesia retires sonic-2 and sonic-turbo on October 20, 2026. Sume's TTS Router lists sonic-3.6, 3.5, 3, latest and preview; here is what to send instead.
- Creatify Aurora 2.0 max audio length: 59.7 s, and how to split
Creatify Aurora 2.0 takes up to 59.7 s of audio; Aurora v1 takes 5 minutes. Sume Avatar Video accepts 4-60 s per job, so split longer scripts across jobs.
Written by Sume