TL;DR
- The Grok Imagine 1.5 Lite family (text-to-video
grok-imagine-1.5-lite/text-to-video+ image-to-videogrok-imagine-1.5-lite/image-to-video) bills per second: 480P $0.029, 720P (default) $0.043, 1080P $0.20; the image endpoint adds $0.015 per input image. - A 720P 6-second clip: $0.258 for text-to-video, $0.273 for image-to-video. Treat 1080P separately — $0.20/s means $1.20 for 6 seconds.
- Both endpoints are live: the t2v page and the i2v page. New accounts get 200 free credits. Usage: the t2v guide and the i2v guide.
Price table (same per-second rates; i2v adds the image fee)
| Tier | Per second | t2v 6 s | i2v 6 s (incl. $0.015 fee) | 100 clips (i2v 6 s) |
|---|---|---|---|---|
| 480P | $0.029 | $0.174 | $0.189 | $18.90 |
| 720P (default) | $0.043 | $0.258 | $0.273 | $27.30 |
| 1080P | $0.20 | $1.20 | $1.215 | $121.50 |
HiAPI current prices, checked October 23, 2026. Sound ships with every clip and can't be disabled at no extra cost; failures refund. 1080P at $0.20/s is ~4.65× 720P — budget it separately.
Same prompt, three tiers, real clips (text-to-video)
One balloon prompt across three tiers, all 6 s, 16:9:
A glass hot-air balloon drifts slowly over a misty valley of terraced rice fields at sunrise. Golden light spills across the water-filled terraces, mist rolls between the hills, a flock of white egrets glides beneath the balloon. Smooth aerial tracking shot, gentle wind sounds and distant birdsong, cinematic, natural colors. No text, no logos.
| 480P $0.174 | 720P $0.258 | 1080P $1.20 |
|---|---|---|
| 480P balloon → | 720P balloon → | 1080P balloon → |
grok-imagine-1.5-lite/text-to-video, one prompt, 6 s each, 16:9. Left to right: 480P $0.174, 720P $0.258, 1080P $1.20; sound generates with the picture (the model has no disable switch).
What you can see:
- All three hold the same composition and camera move (aerial follow with egrets passing).
- 480P is loosest in detail; 720P steps up clearly; 1080P renders the sharpest terrace reflections and feather detail — at $1.20 a clip.
- Iterate prompts at 480P, deliver at 720P, reserve 1080P for finals.
Spending less
- Draft at 480P: $0.174 per 6-second clip — 33% below 720P and 85% below 1080P.
- Count the $0.015: bulk budgets = per-second × seconds × clips + $0.015 × clips.
- Sound can't be muted: strip the track in post; the price doesn't move.
- Any integer duration 1–15 s: one action fits 5–6 seconds — don't pay for filler seconds.
Compared with related video models (HiAPI prices, 720p per second)
| Model | Per second | Notes |
|---|---|---|
grok-imagine/text-to-video | $0.0214 | 480p $0.0114; 1080P $0.057142 |
wan2.6-flash/image-to-video | silent $0.029 / audio $0.0575 | 5/10/15 s only |
grok-imagine-1.5-lite/* (this family) | $0.043 | Sound built in; any integer 1–15 s |
ltx-2.5-fast/* | $0.043 | Free audio switch; 1080P $0.086 |
wan2.7-video/image-to-video | $0.1 | 1080P $0.167 |
720P is priced alike across the group — the differences are audio policy, duration granularity, and 1080P pricing; the detailed LTX match-up is here.
Monthly budgets (i2v, 6 s per clip)
| Clips / month | 480P | 720P | 1080P |
|---|---|---|---|
| 100 | $18.90 | $27.30 | $121.50 |
| 500 | $94.50 | $136.50 | $607.50 |
| 1,000 | $189.00 | $273.00 | $1,215.00 |
"480P drafts + 720P finals" is the common mix: 400 six-second 480P image-to-video clips plus 100 six-second 720P image-to-video clips runs about $102.90 a month.
FAQ
- Yes, image-to-video adds $0.015 per clip:
image_urlis required, so the fee always applies; text-to-video has none. - Yes, sound can't be disabled: every clip ships with audio at the same price; cut it in post.
- Yes, duration is any integer 1–15, not fixed steps.
- Yes, 1080P is expensive: $0.20/s — $1.20 for 6 seconds; budget bulk separately.
- Yes, $10 buys about 36 clips (i2v, 720P, 6 s).
Next: take the balloon prompt and run one 480P clip ($0.174) to check composition; full usage is in the t2v guide; the text-to-video model page also lets you try prompts directly.
