Kling motion control: Standard 9 credits, Pro 12, Sume runs Standard
Kling lists 9 credits a second for Standard and 12 for Professional Motion Control. Sume runs the Standard queue at $0.1575 a second, in dollars.

Kling's guide prices Video 3.0 Motion Control at 9 credits per second in Standard mode and 12 credits per second in Professional mode, rounded to whole seconds (read 2026-10-07). Sume does not sell credits for this route. It runs the Kling 3.0 Standard Motion Control queue and bills US dollars: $0.126 list per output second times a 1.25 margin, so $0.1575 per second.
So the question is not 9 versus 12 credits on Sume. It is whether the Standard queue is good enough for your take, because Sume's request body has no field that selects Professional.
The two price lists side by side
Kling prices in credits and Sume prices in dollars, so the table does not convert one into the other. A credit has a different dollar value in each Kling plan, and this post does not guess it.
| Where | Mode | Rate | Rounding |
|---|---|---|---|
| Kling guide | Standard | 9 credits per second | Nearest whole second |
| Kling guide | Professional | 12 credits per second | Nearest whole second |
| Sume | Standard queue | $0.126 list x 1.25 = $0.1575 per second | ceil(duration_seconds) |
| Sume | Professional | Not offered in the documented body | Not applicable |
What a Sume clip costs
The reservation is computed from the duration_seconds you declare, which should match the length of your motion video. The output length follows the motion video, not the field.
At $0.1575 per second, a 5-second clip reserves $0.7875, a 10-second clip $1.575, a 20-second clip $3.15, and a 30-second clip $4.725. Sume reserves the amount at admit, captures it on completion, and refunds it if the job fails.
- Declare the true length: the field is the reservation basis, and Sume never forwards it to the provider.
- Whole seconds up: 10.2 seconds is billed as 11.
- A 402 at submit means the workspace balance cannot cover the reservation; no job starts.
Why the mode matters less than the reference
Most failed takes in motion transfer come from the inputs, not the mode: a still where the body is cropped, or a motion clip that is shaky or has several people. Fix those first, since a better mode cannot repair them. Kling's guide itself puts the emphasis on a visible head and body and on matching the still's framing to the clip.
If you do need a Professional render, Sume cannot give it to you today through this route. Say so in your plan instead of assuming a parameter will appear.
How to budget a run
Take your total motion seconds, round each clip up, and multiply by $0.1575. Seven 12-second clips are 84 seconds, so $13.23. For a cheaper way to compare video prices across vendors, Runway's developer page lists its own video models in credits at $0.01 per credit (read 2026-10-07), which is another reason to compare in dollars, not credits.
Sources
Related posts
More in Pricing
- Lip sync 30 seconds as three 10-second lines: cost by resolution
MiniMax H3 Max lip sync caps audio at 14.8 s, so a 30-second script becomes three jobs. Cost at 480p, 768p and 1080p, with ceil rounding and a split rule.
- LTX-2.5 Fast at 1440p: 19 cents a second, plus 720p, 1080p, 4K
fal lists LTX-2.5 Fast at $0.09, $0.13, $0.19 and $0.30 a second at 720p, 1080p, 1440p and 4K. LTX is not on Sume; here is the nearest comparison.
- LTX-2.5 Pro at 4K: $0.39 a second, 10 s cap, vs Omni 4K on Sume
LTX-2.5 Pro tops out at $0.39 per second for 4K and 10 seconds per clip. A 10-second 4K clip costs $3.90 on LTX and $3.75 on Sume's Omni Flash row.
- MAI-Transcribe-2-Streaming intro rate runs to year end: budget plan
MAI-Transcribe-2-Streaming is $0.54 an hour through year end. How to budget transcription hours against Sume STT at $0.60 an hour (one cent a minute).
Written by Sume