Wan 3.0 is public after invite-only: check Sume's wan-3.0 id
QwenCloud says Wan 3.0 went from invite-only on August 6 to public. On Sume, wan-3.0 is a catalog id; check the live catalog for limits.

QwenCloud's changelog says Wan 3.0 was initially launched as invite-only on August 6 and is now publicly available. Sume lists wan-3.0 as a public catalog id, so you do not need an invite to name it in a request; to see what your workspace can call today, read the live catalog.
For what Sume hosts of Wan, see Wan 3.0 open source: what is hosted.
What did QwenCloud announce?
The wan3.0-video entry is headed General Availability. It says Wan 3.0 is an All-in-One model for text-to-video, image-to-video, and reference-to-video, initially launched as invite-only on August 6, now publicly available.
| Date | Event (QwenCloud changelog) |
|---|---|
| August 6 | Invite-only launch |
| August 24 | Changelog entry date as noted in the changelog; now publicly available |
Is wan-3.0 available on Sume?
Sume's Video API docs list wan-3.0 among its model ids. The Video Router docs describe a row with text-to-video, image-to-video with an end frame, reference-to-video, and audio, and note a list price dated 2026-08-24.
How do I check what my workspace can call?
Use the model listing endpoint. The docs say to use it to check which resolutions, aspect ratios, and durations are supported by each model before submitting a generation request, and to read capabilities from GET /v1/video-router/models.
Should I rely on a launch post for limits?
No. A vendor announcement tells you when a model opened, not what a given host accepts. Use the catalog for limits such as the 2 to 30 second range for wan-3.0.
Sources
Related posts
More in Models
- Which Sume video models accept an audio reference?
Seven Sume video models take reference audio: the four Seedance 2.x ids, Wan 3.0 and the two MiniMax H3 models. Kling, Grok and Gemini Omni Flash do not.
- Which Sume video models accept a reference video?
Nine Sume video ids take a video input: the four Seedance 2.x ids, Wan 3.0, both MiniMax H3 models, Omni Flash and Genjutsu. Kling and Grok do not.
- YouTube fhd, qhd, uhd thumbnails in the API: a 3840 AI image
YouTube's API notes fhd, qhd and uhd thumbnail keys for some videos. Sume's ChatGPT Image 2.5 image_size accepts a 3840 edge, enough for a 4K image.
- An OpenRouter-compatible video API: sume/auto or a pinned model
Sume's POST /v1/videos follows OpenRouter's video generation API field for field. Let sume/auto pick the model, or pin a catalog id like seedance-2.5.
Written by Sume