50 Kling 3 clips of 10 seconds with audio: $105.00
50 ten-second Kling 3 clips with audio on Sume cost $105.00 ($2.10 each). Without audio each is $1.40.
50 Kling 3 (kling-3) clips of 10 seconds with generated audio cost $105.00 on Sume, $2.10 each. With generate_audio: false each is $1.40.
Prices come from the Sume rate card read on 2026-10-06; the model id and limits are in the video generation docs.
What does audio add?
Audio changes the per-second rate.
| Audio | Per clip | 50 clips |
|---|---|---|
| On | $2.10 | $105.00 |
| Off | $1.40 | $70.00 |
What should I check?
Read the live price in GET /v1/catalog.
- Send
generate_audioexplicitly. - One
Idempotency-Keyper clip. - Run one test clip first.
Sources
Related posts
More in Models
- Accented letters in AI image text: a proof list for Spanish and French
Headlines with é, ñ, ü or ¿ can come back with a wrong accent. Test two Sume models on your real copy, then check every mark against a proof list.
- AI music video with a singer close-up: still plus audio, 5 to 14.8 s
The lip-sync model in Sume's video catalog takes a still and audio of 5 to 14.8 seconds. Split a song to fit, and join the shots on a Timeline.
- AI video ad text in 12 languages: Wan 3.0 or burned-in captions?
Alibaba says Wan 3.0 renders text in 12 languages. Sume lists wan-3.0 at 2 to 30 s. When to let the model draw words and when to add captions yourself.
- AI video API news, October 6 2026: what changed for callers
Kling 4.0 heads to full launch, Seedance 2.5 API pages disagree, Omni 1.1 Flash is Google's default. What to change in a video integration today.
Written by Sume