14-day holiday countdown from one still: Grok Imagine cost

Fourteen 6-second Grok Imagine Video 1.5 clips cost $1.05 on Sume; joining the 84 seconds adds $0.20. It needs a source image and has no audio.

5 min readSume
All posts

A 14-day countdown made from one product still costs $1.05 for fourteen 6-second clips on Grok Imagine Video 1.5 at $0.0125 per second on Sume, plus $0.20 if you join them into one 84-second file with Timeline (two output minutes at $0.10 each). Grok Imagine Video 1.5 is image-to-video only, 4 to 15 seconds, 480p or 720p, with no audio.

Price by clip length

Per-second figures are the provider list rate times the 1.25 Sume margin that the docs describe, as of 2026-10-08. Read capabilities from GET /v1/video-router/models before you bill a batch, because rates and envelopes can change.

Fourteen daily clips, as of 2026-10-08
Clip lengthPer clip14 clips
4 s$0.05$0.70
6 s$0.075$1.05
10 s$0.125$1.75
15 s$0.1875$2.625

Making each day different

Because there is no audio and no end frame, the variation comes from the still and the prompt. Render day-number overlays separately with your design tool, or burn them into 14 versions of the still, so the model does not need to draw numerals. Then use the same camera prompt for all 14 days for a consistent set.

  • One still per day, or one still with 14 prompts.
  • Add a voiceover or music in Timeline; the clips carry no sound.
  • Join: 14 x 6 s = 84 s, ceil(84/60) = 2 minutes, 2 x $0.10 = $0.20.

Scheduling

You do not need to release the join on the same day. Keep fourteen separate files, and join only the final 'last chance' cut. Submit them in a single wave: on a Pro plan fourteen jobs fit inside the 24 accepted jobs. Amazon's own Prime Big Deal Days page shows how short these windows are: deals drop three times a day, at midnight, 8 a.m. and 1 p.m. PDT (read 2026-10-08), so plan a tiny cutdown, not a long piece.

Keeping the set consistent

Use the same seed-like prompt for each day so that camera movement matches, and change only the still. If you want a voice, TTS costs $0.0475 per 1,000 characters; a 14-word line is about 80 characters, which is under a cent. Music is $0.125 per generation on Lyria 3.5, once for the whole set.

The total for the set is then $1.05 (clips) + $0.20 (join) + $0.125 (music) = $1.375, plus captions at $0.20 per job if you add them.

  • Clips: 14 x 6 x $0.0125 = $1.05.
  • Join: $0.20.
  • Music: $0.125.
  • Total: $1.375.

Before you scale

Confirm the platform side before you schedule 14 posts. Each destination has its own length and ratio limits, which this post does not cover; the Shopify help page, for example, allows video of at least 0.25 seconds and up to 10 minutes, so six-second clips are well within it. Keep the master 9:16 and crop from it for other placements, rather than regenerating.

Sources

Related posts

More in Use cases

All Use cases posts

Written by Sume