Vidu Q4 540p draft to 1080p: Sume video upscale at 2x costs $0.09
A 10-second 960x540 draft upscaled at the default factor 2 gives 1920x1080 for $0.09 on Sume. Sume does not list Vidu; the clip only needs a public HTTPS URL.

Yes. A 10-second Vidu Q4 Preview clip rendered at 960x540 can go to 1920x1080 through Sume Video Upscale 1.0 at the default factor of 2, and the job costs $0.09 (10 seconds x $0.009 per video second). Sume does not list a Vidu model, so you generate the clip with Vidu itself and bring only the file: the upscale route takes any public HTTPS video URL.
Vidu Q4 Preview was announced on October 7, 2026, with output options from 540p to 4K according to the launch coverage. This page quotes no Vidu price: the coverage I could read gives only a starting rate, and other write-ups disagree, so check Vidu's own pricing before you plan a budget.
What the route accepts
The request is POST /v1/video-upscale-1.0/upscale. Per the API reference, the body requires only video_url, a public HTTPS URL. Optional fields are upscale_factor or scale_ratio (1.1 to 4, default 2; scale_ratio wins if both are set), duration_seconds (1 to 30), enhancement_tier (fast, standard, pro; default fast), metadata, and the usual communication options.
{
"video_url": "https://example.com/vidu-q4-draft-540p.mp4",
"upscale_factor": 2,
"duration_seconds": 10
}The arithmetic
Sume's public catalog lists video upscale at $0.009 per video second, with a 30-second input maximum, so the ceiling for one job is $0.27. Send duration_seconds with the real clip length: when you omit it, the admit step reserves 5 seconds, and the hold is $0.045 for a 10-second clip you did not describe.
| Clip length | Arithmetic | Job cost |
|---|---|---|
| 5 s | 5 x $0.009 | $0.045 |
| 10 s | 10 x $0.009 | $0.09 |
| 15 s | 15 x $0.009 | $0.135 |
| 30 s (maximum) | 30 x $0.009 | $0.27 |
What the factor does to a 540p draft
A 960x540 frame at factor 2 becomes 1920x1080, which matches the 1080p tier. At factor 4 the same draft reaches 3840x2160, the top of the allowed range, assuming the ratio multiplies each side. Because the price is per second and not per factor, pick the factor from the delivery size you need, not from cost.
The hosted MCP server exposes the same job as video_upscale_create, listed in the tools and gates page.
- Draft cheaply on the model you like, upscale only the takes you keep.
- Clips longer than 30 seconds need to be cut first; see the video trim docs.
- Check the output dimensions before you deliver; the public contract does not promise more than the requested ratio.
Where this fits in a Vidu workflow
A practical loop is to generate several short drafts at the lowest resolution the vendor offers, pick the ones worth keeping, and only then pay for the larger render or the upscale. With Sume the second step is a fixed per-second price, so you can compare it against the vendor's higher-resolution tier once you have read the vendor's own price page.
Two constraints are worth checking before you send a batch. The clip has to be reachable by a public HTTPS URL when the job runs, so a signed link that expires in minutes is risky for a queued job. And the route accepts at most 30 seconds of video, so a longer Vidu render has to be cut with video trim at $0.02 per job first.
- Ten 10-second keepers upscaled: 10 x $0.09 = $0.90.
- The same ten with a 5-second reservation each, if you omit duration: the hold is 10 x $0.045 = $0.45, which then settles to the real length.
- Reading the finished job: poll the job status and result routes described in the jobs and results docs.
Sources
- Vidu Q4 Preview launch coverage, Yahoo Finance, Oct. 7, 2026 (read 2026-10-09)
- Sume public catalog, api.sume.com/v1/catalog (read 2026-10-09)
- Sume API reference, api.sume.com/reference (read 2026-10-09)
- Sume docs: Video generation models (read 2026-10-09)
- Sume docs: MCP tools and gates (read 2026-10-09)
Related posts
More in Media tools
- Voice greeting on a still photo: TTS first, then H3 Max lip sync
To make a still photo speak, make 5 to 14.8 seconds of TTS audio, then call MiniMax H3 Max lip sync. TTS costs $0.0475 per 1,000 characters.
- Voiceover plus music bed: TTS and Lyria cost, duck_db in Timeline
A 700-character voiceover ($0.03325) and one Lyria bed ($0.125) cost $0.15825 before the render. Timeline duck_db (0 to 20) lowers the bed under speech.
- Which video specs TikTok, LinkedIn, Pinterest and Shorts leave blank
Only TikTok lists a bitrate; only LinkedIn lists a frame rate; Pinterest lists no resolution; the Shorts page lists no size at all. What Sume can set for each.
- X video ad thumbnail: PNG or JPEG under 5 MB, pulled from your own MP4
X accepts a PNG or JPEG thumbnail up to 5 MB that matches the video. Sume video frames returns a still at a time you pick, at source size.
Written by Sume