Muting a Wan 3.0 clip saves nothing; Kling 3 audio off does
Wan 3.0 has no audio price line on Sume, so generate_audio false changes no cost. Kling 3 charges $0.14 off, $0.21 on a second.
If you plan to add your own score, you may be tempted to switch audio off to save money. On Sume that works on one model of the two. Prices are Sume billable rates (provider list x 1.25, rounded up to the cent per job), read 2026-10-07.
Audio on versus off
| Model | Audio on | Audio off |
|---|---|---|
| Wan 3.0 720p | $1.25 | $1.25 |
| Kling 3 | $2.10 | $1.40 |
Wan 3.0 defaults generate_audio to true and has no audio tier, so turn it off only for editing reasons, not price. Kling 3 saves $0.07 a second, or $0.70 on 10 seconds. Over 100 ten-second clips that is $70.00.
Sources
More in Pricing
- Nano Banana 2.1 prices: Google's 1K and 4K list vs Sume's cost
Google launched Nano Banana 2.1 on Oct 6 at $0.0336 per 1K image and $0.0756 at 4K. Here is how to read what Sume bills for google/nano-banana-2.1.
- One 30-second AI ad every day for 30 days: what the month costs
A 30-second ad daily for 30 days is 900 seconds. At Sume's catalog rates that is $56.25 on Wan 480p, $112.50 on Wan 720p, or $189 on Kling 3 with audio.
- One 30-second Wan 3.0 job or four 8-second jobs: which costs less?
One 30-second Wan 3.0 clip at 720p is $3.75; four 8-second clips are $4.00 for 32 seconds. Per second the price is identical, so length is a quality call.
- What does one hour of AI narration cost on Sume, MAI and ElevenLabs?
One hour of finished narration is about 45,000 characters: $2.16 on Sume in three jobs, against $0.99 on MAI-Voice-2.1. Rates read 2026-10-07.
Written by Sume