One Sume image upscale costs the same as 22 seconds of video upscale
Sume image upscale is $0.20 per image and video upscale is $0.009 per second, so one image upscale buys 22.2 seconds of video. A cutout is $0.0225.

Image upscale is $0.20 per image and video upscale is $0.009 per second on Sume's rate card. $0.20 / $0.009 = 22.2, so one image upscale costs as much as about 22 seconds of video upscale. At 24 fps, that is 533 frames upscaled for the price of one.
Media tools side by side
The table puts the media-tool rows in one place and normalizes each to a cutout.
| Tool | Rate | Times a cutout |
|---|---|---|
| Remove background | $0.0225 / image | 1.0 |
| Image upscale | $0.20 / image | 8.9 |
| Video upscale | $0.009 / second | 0.4 per second |
| Timeline render | $0.10 / output minute | 4.4 per minute |
A caution on the comparison
The 24 fps figure is arithmetic on a common frame rate, not a statement about how Sume bills: video upscale is billed per second, not per frame. The comparison only says that stills are expensive relative to video seconds.
Worked example and checks
Think of it as a conversion table for mixed projects. A 30-second video upscale at $0.27 is about 1.4 image upscales. A 90-second spot upscaled and 12 stills upscaled cost 90 x 0.009 + 12 x 0.20 = $0.81 + $2.40 = $3.21, and the stills are three-quarters of it.
So the practical rule is to check the stills first. Resizing them to the final canvas size before upscaling does not change the per-image price, but sending only the ones that are below target resolution does.
Practical use
If your video is mostly stills with motion added, upscale the source stills once and animate afterwards, or upscale the final video; compare the two totals for your length. Sume bills model and tool usage at the published rate on top of the plan fee, so the plan price is separate from every number in this post.
Sources
Related posts
More in Comparisons
- OpenAI Image API vs Sume Image API for GPT Image 2.5: what differs
Same model family, different request surface. Moderation, revised_prompt, streaming, output_compression and masks compared between OpenAI direct and Sume.
- OpenRouter video client on Sume: six documented differences
Sume says /v1/videos matches the OpenRouter Video Generation API except six items: base path, auth, model ids, auto routing, size and provider.options.
- Pick an image model by job: product photo, poster text, edit
Five new image releases in a month. A job-first table for Sume: GPT Image 2.5, Ideogram 4.5, Nano Banana 2.1, FLUX.2 and Qwen, with the limits that decide.
- Sora API shutdown report: which claims Sume docs can answer
Pondero's Sora API shutdown report names Runway, Kling and Seedance. Sort its claims from what Sume's docs list, so you do not assume a model is there.
Written by Sume