Kling 3.0 in the Sume Videos panel: audio on or off cost per clip
The Videos panel's Create estimate prices Kling 3.0 at $0.14 per second with audio off and $0.21 with audio on: 5 s is $0.70 or $1.05; 10 s is $1.40 or $2.10.

In the Sume Videos panel, a Kling 3.0 clip costs $0.14 per second with audio off and $0.21 per second with audio on, so 5 seconds is $0.70 or $1.05 and 10 seconds is $1.40 or $2.10. Audio adds 50% to the price of every clip.
These figures come from the code behind the panel's Create estimate, which uses the same estimator as API admission: provider list ($0.112 per second without audio, $0.168 with) times 1.25. Kling is not a model id in the Video Router docs, so this is a panel price, not a router quote, and no Kling vendor page was available to read today.
The numbers
Credits are cents, rounded up per job.
| Clip | Audio off | Audio on |
|---|---|---|
| 5 s | $0.70 (70 credits) | $1.05 (105 credits) |
| 10 s | $1.40 (140 credits) | $2.10 (210 credits) |
| 15 s | $2.10 | $3.15 |
Deciding whether audio is worth it
For 20 clips of 10 seconds, audio off is 20 x $1.40 = $28.00 and audio on is 20 x $2.10 = $42.00, so the audio option is worth $14.00 for the test. If you will replace the sound with a voiceover or music anyway, leave it off.
Compare the same 10 seconds on the Video Router: Wan 3.0 at 720p is $1.25 and H3 Max at 768p is $1.00. Gemini Omni Flash 1.1 always includes native synced audio and is $1.25 at 720p (the Video Router docs have the catalog).
Sources
Related posts
More in Models
- 21:9 on kling-3 returns 400: which Sume video ids accept ultrawide
Kling's page lists 21:9 output for Kling 4.0. On Sume, kling-3 accepts only 16:9, 9:16 and 1:1; seedance-2.5 and the MiniMax H3 ids accept 21:9.
- Kling 3.0 dialogue languages: is French or German covered?
Kling lists Chinese, English, Japanese, Korean and Spanish for VIDEO 3.0 dialogue. French and German are not on that list, so test a 720p clip on Sume first.
- Kling 3.0 shot timing prompts: make seconds add up on Sume
Kling's guide writes multi-shot prompts as 'Shot 1, 4s'. On Sume kling-3 has no shot list field, so the timing lives in the prompt and in duration.
- Kling 3.0 square video API: can I request 1:1 on Sume?
Yes: Sume's kling-3 row lists 16:9, 9:16 and 1:1 at 720p or 1080p, 4 to 15 s, with an audio-on rate. What it refuses, what it costs, and a request body.
Written by Sume