Luma Ray3.2 or Kling 3 for a start-and-end-frame shot? Sume's option
Ray3.2 takes up to 16 keyframes and 20-second 1080p clips. On Sume, Kling 3 takes a first and a last frame for 4 to 15 seconds; Ray is not in the catalog.

If your shot only needs a start image and an end image, you do not need Luma Ray3.2's 16 keyframes. On Sume, kling-3 takes a first frame and a last frame for 4 to 15 seconds at 720p or 1080p, and wan-3.0, seedance-2.5, minimax-h3-max and gemini-omni-flash-1.1 do the same.
Luma Ray3.2 itself is not in the Sume catalog, so you cannot call it through Sume. This post compares what Luma documents with what Sume rows accept, so you can decide whether a two-frame shot is enough.
What Luma says
Luma's Ray3.2 announcement lists up to 16 keyframes per clip, clips up to 20 seconds at 1080p, native HDR generation, 16-bit EXR export, and an API for developers (read 2026-10-07). The page gives no price, and this post does not quote one.
| Row | Duration | Frame control | Resolution |
|---|---|---|---|
| Luma Ray3.2 (not on Sume) | Up to 20 seconds | Up to 16 keyframes | 1080p, HDR, EXR export |
| kling-3 | 4 to 15 seconds | First and last frame | 720p, 1080p |
| wan-3.0 | 2 to 30 seconds | First and last frame | 480p, 720p, 1080p |
| gemini-omni-flash-1.1 | 3 to 10 seconds | First and end image | 360p to 4K |
Prices for a two-frame, ten-second shot
Sume sells at the provider list per second times 1.25, rounded up to whole cents.
| Row | Setting | Sume per second | 10 seconds |
|---|---|---|---|
| kling-3 | Audio on | $0.21 | $2.10 |
| kling-3 | Audio off | $0.14 | $1.40 |
| wan-3.0 | 720p | $0.125 | $1.25 |
| wan-3.0 | 1080p | $0.25 | $2.50 |
| gemini-omni-flash-1.1 | 1080p | $0.1875 | $1.88 |
Doing a multi-keyframe shot anyway
If the shot needs a middle beat, chain two jobs: generate A to B, take the last frame of the clip as the first frame of B to C, and join the clips on a timeline. That costs two jobs and may show a seam at the cut. Hold B fixed by using the same image as the end of the first job and the start of the second.
Sume does not offer keyframe curves, HDR output or EXR export, so a pipeline that needs those should call Luma directly.
- Two frames, 4 to 15 seconds, optional silence: Kling 3.
- Two frames, 2 to 30 seconds: Wan 3.0.
- More than two frames, HDR or EXR: not on Sume.
Request
A Kling job with both frames:
{
"model": "kling-3",
"prompt": "The product rotates from front to back under soft light",
"duration": 8,
"resolution": "1080p",
"frame_images": [
{"type": "image_url", "image_url": {"url": "https://example.com/front.png"}, "frame_type": "first_frame"},
{"type": "image_url", "image_url": {"url": "https://example.com/back.png"}, "frame_type": "last_frame"}
]
}Sources
Related posts
More in Comparisons
- Luma Ray3.2 face tracking vs Kling motion control: pick by input
Luma Ray3.2 tracks up to eight faces frame by frame; Kling motion control moves a still with a reference clip. Which to use, and what Sume runs today.
- 30-second lyric or music clip with an audio reference: $8.07 vs $1.88
Both seedance-2.5 and wan-3.0 take an audio reference on Sume. A 30-second clip is $8.07 at 480p on Seedance 2.5 and $1.88 at 480p on Wan 3.0.
- MAI-Transcribe-1.5 at $0.36 an hour vs Transcribe-2 and Streaming
Microsoft's own table lists MAI-Transcribe-1.5 at $0.36 per hour and 43 languages. Compare it with Transcribe-2 at $0.10, Streaming at $0.54 and Sume STT.
- MAI-Transcribe-2-Streaming partials vs Sume STT terminal webhook
MAI-Transcribe-2-Streaming sends intermediate and final results as audio streams in. Sume STT sends one signed terminal callback. How to design for each.
Written by Sume