Waiting for Kling 4.0? Eight Sume video ids by 10-second price
Alternatives you can call today instead of waiting for Kling 4.0: eight Sume video model ids with the price of a 10-second clip, cheapest first.

While Kling 4.0 is only announced, the cheapest id to try on Sume (from an image you supply) is grok-imagine-video-1.5 at $0.125 for 10 seconds, and the most expensive of the eight below is seedance-2.5 at $5.78. kling-3 sits in the middle at $2.10 with sound. Price is the only ranking here: nobody can say from a table which clip will look right for your product.
Ten seconds, cheapest first
Each row is one 10-second request at the resolution shown, billed at the provider list price times 1.25.
| Model id | Setting | 10-second price |
|---|---|---|
| grok-imagine-video-1.5 | 720p | $0.125 |
| minimax-h3 | 768p | $0.75 |
| minimax-h3-max | 768p | $1.00 |
| wan-3.0 | 720p | $1.25 |
| gemini-omni-flash-1.1 | 720p | $1.25 |
| seedance-2-mini | 720p | $1.89 |
| kling-3 | audio on | $2.10 |
| seedance-2.5 | 720p | $5.78 |
Limits that matter before you pick
grok-imagine-video-1.5is image-to-video only, so it needs a first-frame image and takes 4 to 15 seconds.gemini-omni-flash-1.1stops at 10 seconds and always generates audio.minimax-h3andminimax-h3-maxtake 5 to 15 seconds.kling-3takes 4 to 15 seconds;seedance-2.5andwan-3.0go to 30.
A way to choose
Run the same prompt on three ids at the cheapest setting, look at the three clips, and only then spend on the higher tier of the winner.
Reading the ladder
The spread is wide: the top row is 46 times the bottom one. That is why a cheap first pass matters. Ten Grok drafts cost $1.25, which is less than one 10-second kling-3 clip with sound at $2.10.
Resolution moves each row too. Wan 3.0 doubles from 720p to 1080p, MiniMax H3 Max doubles from 768p to 1080p, and Seedance 2.5 more than doubles. Rank by the resolution you will actually publish, not the cheapest setting you can find.
Sume reserves the full price at submit, so the number in the table is also the amount that must be free in the balance when you send the request. If it is not, the call fails with 402 insufficient_credits before any provider work starts.
Sources
Related posts
More in Comparisons
- Walmart 100MB vs Amazon Sponsored Brands 500MB: bitrate each allows
Walmart caps video at 100MB, Amazon Sponsored Brands at 500MB. The average bitrate each allows for 15 to 90 seconds, plus the Sponsored Brands 1 Mbps floor.
- Zoom deepfake risk detection: what it means for avatar video
Zoom lists real-time alerts for synthetic audio or video next to meeting avatars. What the page says, what it leaves open, and how to label a Sume clip.
- Sume vs Argil: AI avatar video and video agents compared
Argil makes AI-avatar and story videos with a chat agent, Director; Sume is a video agent with a multi-model API. Avatars, API, pricing, and limits compared.
- Sume vs fal: a generative media API or a video agent platform
fal runs 1,000+ image, video, and audio models behind one API. Sume adds a video agent, Formats, and avatars to a multi-model API. How the two surfaces differ.
Written by Sume