TL;DR
- Gemini Omni 1.1 Flash (
gemini-omni-1.1-flash) is billed per clip, not per second, on HiAPI: $0.45 for 4 seconds, $0.60 for 6, $0.75 for 8, $0.90 for 10, and that price covers 360p, 720p and 1080p alike. 4K adds $0.60 to each. - Send a reference video and the price becomes a flat $1.20 per clip at up to 1080p ($1.80 at 4K), whatever the duration.
- Every clip comes with ambient sound. $10 buys about 13 eight-second 1080p clips. Omni 1.1 Flash is live on HiAPI: open the model page and generate in the browser. New accounts get 200 free credits.
Price table
| Duration | 360p / 720p / 1080p | 4K |
|---|---|---|
| 4 s | $0.45 | $1.05 |
| 6 s | $0.60 | $1.20 |
| 8 s (default) | $0.75 | $1.35 |
| 10 s | $0.90 | $1.50 |
| Any duration, with a reference video | $1.20 | $1.80 |
Live HiAPI prices, checked October 16, 2026. duration must be 4, 6, 8 or 10.
Text-to-video, up to 7 reference images, and first/last frame all use the top four rows. Adding a video_list entry moves you to the last row. Failed tasks are refunded.
What a clip looks like
Video-to-video: an 8-second reference clip of a lantern on a lake, re-rendered as night with the same camera move.
Transform the reference video into a refined cinematic night sequence while
preserving the lantern silhouette and smooth camera movement. Shift the
palette from blue hour to deep indigo and warm amber, add slow drifting
firefly-like reflections across the lake, keep the reflection physically
coherent, one continuous shot, no people, no text, no logos, no watermark.
Natural ambient sound: quiet water, soft glass resonance, and distant night
wind.
Generate with this prompt → (upload your reference video, 8 seconds, 720p, 16:9)
gemini-omni-1.1-flash, reference video, 8 seconds, 720p, $1.20.
Per-clip vs per-second: how Omni compares
Most video models bill per second and charge more for higher resolution. Omni's flat clip price changes the math at 1080p:
| Model | 8 s at 1080p | 8 s at 720p | Sound |
|---|---|---|---|
| Gemini Omni 1.1 Flash | $0.75 | $0.75 | Included |
Wan 3.0 wan3.0-video | $1.28 | $0.64 | Included |
| Kling 3.0 Turbo | $1.28 | $1.04 | No |
| Kling 3.0 (with sound) | $1.544 | $1.144 | Yes |
| Seedance 2.5 text-to-video | $4.128 | $1.632 | Yes |
What this means:
- At 1080p with sound, Omni is the cheapest 8-second clip in this table.
- At 720p, Wan 3.0 standard ($0.64) edges it, and Wan goes to 30 seconds where Omni stops at 10.
- There's no price reason to preview below 1080p on Omni, since 360p, 720p and 1080p cost the same.
Monthly budget
| Workload | Clip price | Monthly |
|---|---|---|
| 100 × 8 s, 1080p | $0.75 | $75 |
| 300 × 6 s, 1080p | $0.60 | $180 |
| 100 × 8 s, 4K | $1.35 | $135 |
| 100 video-to-video edits, 1080p | $1.20 | $120 |
Ways to spend less
- Pick the shortest allowed duration that tells the shot: 4 seconds is $0.45, 10 seconds is $0.90.
- Render at 1080p from the start: it costs the same as 360p.
- Reserve 4K for the keeper: it adds $0.60 to every clip.
- With a reference video, length is free: the $1.20 flat rate is the same for 4 or 10 seconds, so request 10.
FAQ
Does resolution change the price?
Only 4K does. 360p, 720p and 1080p share one price per duration.
Does sound cost extra?
No. Clips come with ambient sound at the listed price.
What inputs can I send?
Text; up to 7 reference images (image_urls); a first frame and optional last frame; or one reference video up to 30 seconds (video_list). Reference video switches billing to the $1.20 flat rate.
Am I charged for failed tasks?
No. You pay only for clips that generate successfully.
A ready-made vertical workflow is in Gemini Omni 1.1 Flash for short-form video. Or generate a 4-second 1080p clip for $0.45 on the model page.
