Grok Imagine Lite upscales to 1080p: what Sume offers instead
xAI describes Grok Imagine Video 1.5 Lite as lowest cost with upscaled 1080p. Sume has no Lite row; it lists grok-imagine-video-1.5 at a flat rate. Compare.

Sume does not list Grok Imagine Video 1.5 Lite. It lists grok-imagine-video-1.5, the full model, and that row needs one start image. xAI's own docs say Lite is the lowest-cost option and that it upscales to 1080p, while 1.5 renders native 1080p (read 2026-10-10).
So if you wanted Lite for the price, you will not find it on Sume by that name. This post shows what xAI and Runway publish for Lite, what Sume's Grok row costs, and when each is the sensible pick.
What xAI says about the three Grok video models
The xAI capabilities page (read 2026-10-10) lists grok-imagine-video-1.5 with native 1080p, -lite as the lowest cost option that upscales to 1080p, and the classic grok-imagine-video up to 720p. Duration is 1 to 15 seconds with a default of 8, and 480p is the default resolution.
The xAI models page (read 2026-10-10) gives the per-second list prices in the table below.
| Model | List price per second | 1080p |
|---|---|---|
| grok-imagine-video-1.5 | $0.080 | Native |
| grok-imagine-video-1.5-lite | $0.020 | Upscaled |
| grok-imagine-video (classic) | $0.050 | Not offered, 720p max |
What Runway charges for Lite
Runway's pricing page (read 2026-10-10) lists grok_imagine_1_5_lite at 2, 3 and 14 credits per second for 480p, 720p and 1080p, plus 1 credit when you start from an image. At $0.01 per credit that is $0.02, $0.03 and $0.14 per second.
The jump at 1080p is the interesting part: a 1080p Lite second costs seven times a 480p one on Runway, even though xAI describes the 1080p as an upscale.
What Sume's Grok row costs
In the pricing code, Sume's grok-imagine-video-1.5 uses a flat $0.01 per second list rate at any resolution, and Sume bills list times 1.25, so $0.0125 per second. A 5-second clip bills $0.0625 and a 15-second clip bills $0.1875 at 480p, 720p or 1080p.
That list rate is not xAI's published $0.080, so the two are different supply paths. Read pricing_skus from GET /v1/videos/models before you budget a large batch, and do not assume the xAI rate card applies to Sume.
| Duration | Any resolution |
|---|---|
| 5 s | $0.0625 |
| 8 s | $0.10 |
| 15 s | $0.1875 |
Worked example: 100 six-second loops from stills
Take 100 product stills and animate each for 6 seconds. The table puts the published rates side by side. The xAI and Runway numbers are list prices from their pages (read 2026-10-10), multiplied by 6 seconds and 100 clips. The Sume number is billed cost, list times 1.25.
The Runway Lite figure uses the 480p rate of 2 credits per second plus 1 credit for the start image, at $0.01 per credit, so $0.13 per clip. The xAI rows add no start-image fee on the page I read.
| Source and model | Per clip | 100 clips |
|---|---|---|
| xAI grok-imagine-video-1.5 | $0.48 | $48.00 |
| xAI grok-imagine-video-1.5-lite | $0.12 | $12.00 |
| Runway grok_imagine_1_5_lite, 480p | $0.13 | $13.00 |
| Sume grok-imagine-video-1.5, billed | $0.075 | $7.50 |
What the numbers do and do not tell you, and which to pick
The Sume row is the lowest figure in the table, but it is not Lite and it is not xAI's endpoint, so output quality and any upscaling behaviour may differ. Run five of your own stills through each option before you commit 100.
Also note what the table leaves out: Lite's 1080p is an upscale per xAI, so for a 1080p deliverable the native 1.5 model may look sharper, and Sume's flat rate means you pay the same at 480p as at 1080p. If you only need 480p previews, you pay for resolution you do not use.
Pick Sume's Grok row when you have a start image and want a cheap loop. It rejects end_image_url, last_frame_url, reference video or audio, and aspect_ratio, so shape the image first. Pick xAI directly for Lite itself. If you need first and last frames, use Kling 3 or Seedance on Sume. The Video Generation docs list the full limits.
Sources
Related posts
More in Comparisons
- Grok Imagine's 3 voice references vs Sume reference-audio rows
xAI's Grok Imagine 1.5 takes up to 3 voice references. Sume's Grok row takes none; Seedance, Wan 3.0 and MiniMax accept reference audio under limits.
- Grok Imagine Lite draft plus Sume upscale: what a 10 s clip totals
xAI lists Lite at $0.020 per second and 1.5 at $0.080. Add Sume video upscale at $0.009 per input second and a 10 s clip totals $0.29. Read 2026-10-10.
- Grok Imagine video edit on xAI vs the video_url error on Sume
xAI edits video with grok-imagine-video; Sume accepts video_url only on Gemini Omni Flash 1.1. The exact error, the edit limits and what to send instead.
- Hedra batch_size 1-8 variations vs Sume's one job per request
Hedra's API returns 1 to 8 variations per request; Sume avatar videos are one job each. How to get variations on Sume with previews and keys (read 2026-10-10).
Written by Sume