One finished minute: two 30 s Seedance 2.5 shots plus Timeline
A 60-second video from two 30 s Seedance 2.5 shots plus one Timeline render costs $16.24 at 480p, $34.78 at 720p and $85.40 at 1080p.

A finished 60-second video built from two 30-second Seedance 2.5 shots and one Timeline 1.0 render costs $16.24 at 480p, $34.78 at 720p and $85.40 at 1080p (as of 2026-10-08).
The sum
Timeline 1.0 is $0.10 per ceil(output minute) and runs on worker ffmpeg, with no model inference. Exactly 60 s is one minute, so the render adds $0.10. The two generations are the other cost.
| Resolution | One 30 s shot | Two shots | Plus Timeline $0.10 |
|---|---|---|---|
| 480p | $8.07 | $16.14 | $16.24 |
| 720p | $17.34 | $34.68 | $34.78 |
| 1080p | $42.65 | $85.30 | $85.40 |
What the stitch needs
Timeline takes one audio spine and ordered video slots. For a 60 s result, set audio.duration_seconds to 60, put the first shot at start 0 for 30 s and the second at start 30 for 30 s. You can add a short transition on the second slot; the docs cap a transition at 1 s.
Sources must already be media.sume.com files in the workspace, so import the generated clips first. The unbilled plan endpoint returns billable_minutes and an estimated cost before you spend anything.
Why not one 60 s clip?
No catalog row generates 60 s in one request; Seedance 2.5 and Wan 3.0 stop at 30. Two shots is the minimum, and the join is cheap: the Timeline fee is 0.1 / 34.78 = 0.3% of the 720p total.
The real cost of the join is creative, not financial: the two shots do not share state unless you give them shared references or a first frame from the earlier shot. Plan the seam where a cut is natural.
Scaling to a month
Ten finished minutes a month at 720p cost 10 x $34.78 = $347.80. At 480p they cost $162.40 and at 1080p $854.00. If four of the ten minutes need a second take on one of the two shots, add 4 x $17.34 = $69.36 at 720p.
The Timeline fee, 10 x $0.10 = $1.00, is the smallest line. Your own review time is not in the table and will usually be the larger cost.
Check the number yourself
To confirm the figure behind this post, read the seedance-2.5 entry from GET /v1/video-router/models and check that 30 s and 720p are inside its duration_seconds and resolutions. The grid price for that cell is 1734 cents ($17.34). It is the provider list price times 1.25, rounded up to the next cent for the job, as of 2026-10-08.
Use an Idempotency-Key on every create call so a retry cannot start a second paid job, then poll the job until it is complete and download the file from the result. Media inputs for Timeline or for references must be hosted files, so import them first.
None of the prices here say anything about picture quality, motion or how well a model follows a prompt. Prices can change when a provider changes its list, which is why every table carries a date. Re-read the catalog before you commit a large batch, and run one test job at the exact setting you plan to use.
Sources
Related posts
More in Pricing
- Output tokens in a 3 to 10 second Omni clip: 17,376 to 57,920
Gemini Omni Flash bills 5,792 output tokens per 720p second. A 3 s clip is 17,376 tokens and a 10 s clip 57,920. Dollars at Google and on Sume, per length.
- Qwen-Audio 3.1 price cuts: rebuild your voice bill with three numbers
Qwen-Audio 3.1 cut prices about 70% for TTS, 85% for Realtime and up to 95% for ASR. How to recompute your bill, and where Sume TTS and STT sit.
- Can an API caller raise a Sume schedule's spend cap? No
A run request can lower generation_spend_cap_usd below the schedule cap but never above it. The six cases, including null and 0, in one table.
- A 2,000-word blog post read aloud: MAI-Voice vs Sume TTS cost
A 2,000-word post is about 12,000 characters: $0.264 on MAI-Voice-2.1, $0.18 on Flash, $0.57 on Sume TTS in one request. Arithmetic shown.
Written by Sume