sume/video-1.0 and /v1/models/sume/video-1.0/runs: what they are
Video 1.0 is a retiring alias for Video Router Auto. Two URLs take the same body, the public id is sume/video-1.0, and receipts report sume/auto.
sume/video-1.0 is the public id of Video 1.0, a compatibility alias for Video Router Auto that the docs mark as retiring soon. It has two invoke URLs, POST /v1/video-1.0/generate and the model-run alias POST /v1/models/sume/video-1.0/runs, which take the same body.
Which URLs does Video 1.0 have?
The docs list a primary invoke URL and a model-run alias with the same body. Both keep accepting the legacy request shape but use Auto model selection, capability validation and pricing.
| Item | Value |
|---|---|
| Primary URL | POST /v1/video-1.0/generate |
| Model-run alias | POST /v1/models/sume/video-1.0/runs |
| Public model id | sume/video-1.0 |
| Receipt model | sume/auto |
What will my job receipt say?
Completed job receipts report sume/auto, not sume/video-1.0. The docs say Sume does not disclose which family served an Auto request.
Should I start a new integration on it?
No. The page says to use POST /v1/videos with model: "sume/auto" for new integrations. Video 1.0 does not accept a model body field, so to select a family you must move to /v1/videos with a catalog model id.
What do I do with an existing integration?
Nothing breaks today: the legacy URLs keep accepting their shape. When you migrate, follow migrate Video 1.0 to Sume Auto and read the Video 1.0 docs.
How do I read the result of an alias job?
Poll GET /v1/jobs/job_123/status, optionally read /events, then fetch /result. Follow next_action from the submit envelope (poll_status, then fetch_result).
Completed Video 1.0 jobs return Sume-hosted video artifacts with a content_type such as video/mp4. Treat the artifact URLs as opaque and do not parse paths for workspace, job or provider identifiers.
Sources
Related posts
More in Developers
- Join voiceover clips inside one timeline render with audio.parts
Timeline 1.0 takes up to 20 gapless audio.parts slices with source_in and duration. Skip the timeline-audio job when the join is only for one render.
- Timeline 1.0 limits: 200 slots, 1800 s, 20 audio parts, 8 fades
The numbers that cap one Timeline 1.0 render: 1 to 200 video slots, 1 to 1800 s of audio, 20 audio parts, 12-slot single strategy and 8 chained fades.
- Timeline render warnings: padded or looped short sources explained
A Timeline 1.0 slot longer than its source renders with a soft warning, not a failure, and /plan cannot predict it. Read warnings[] and probe clips first.
- Token bucket vs fixed window: what a reset header means
Anthropic says its limits replenish continuously; Sume's docs call ratelimit-reset the seconds until the window resets. How to pace a client for each.
Written by Sume