How many generations run at once on SceneMixer
SceneMixer publishes a figure for every tier: three generations at once on a free account, then five, eight, ten, fifteen and twenty on the paid tiers in order. The top three tiers add a priority queue, and anything past the limit waits with its credits held. As of 2026-09-22.
| What is published | As the guide states it |
|---|---|
| Free account | Three generations at once |
| Paid tiers, in order | Five, eight, ten, fifteen and twenty |
| Top three tiers | A priority queue on the site's own queue |
| Past the limit | Jobs wait as queued, credits held, and start as slots free |
Inclusion rule. What the vendor's plan guide states about running generations in parallel. The guide also states what a plan does not change, which is recorded beside it. Order. From the free account to the top tier, then what happens past the limit.
1Where SceneMixer sits in this column
| Channel | Parallel generations |
|---|---|
| HeyGen | Twice as much on one tier, no figures |
| Kling AI | Twenty per package, unlimited on membership |
| SceneMixer | 3 free, then 5, 8, 10, 15 and 20 by tier |
| Vidu | Five free, then $2,080 a month each |
Inclusion rule. Channels whose public pages address how many generations may run at the same time. Silence on the subject is the norm and is recorded on the ledger rather than here. Order. Alphabetical by channel name.
2A figure for every tier, and what it counts
The guide gives a number for each plan and says what it counts: every generation, video segments, sheets, storyboards and composites alike. A production can therefore size a batch before buying, which most channels in this register do not let it do.
It is also explicit about the other side. A plan changes how many jobs run at once, not how long one generation takes, because the same model does the same work on every tier.
3Where concurrency matters most in this kind of product
A tool that turns a script into episodes generates in batches by design: a set of character sheets, then a set of scene plates, then every segment of an episode. At three at a time those batches run in rounds; at ten, an episode's segments can all be in flight together.
The figure therefore decides the wall-clock time of a delivery rather than its cost, which is why it sits in its own column on this ledger.
4A priority queue is not a faster generation
The top three tiers carry a priority queue on the site's own queue. The guide states plainly that it does not reorder anything at the model service and does not make a single generation faster; it decides who waits when the site is busy. That distinction is worth more than the feature, because the two are usually sold as the same thing.
- ConcurrencyA free account runs three generations at once; the paid tiers run five, eight, ten, fifteen and twenty, and the top three add a priority queuea figure for every tier
- Wan 3.0 480P10 credits per second, about $0.06the default tier
- Longest single clip30 seconds on the Wan 3.0 and Seedance 2.5 tiers, 15 seconds on the Seedance 2.0 and MiniMax H3 tiersstated per tier
5Sources
Read from the paid plan guide published at scenemixer.com on 2026-09-22. The rate this column sits beside is on SceneMixer; what the register accepts as published is on the method page. The same column on other channels: HeyGen, Vidu. Every column: what each channel publishes.