Model
Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
prompt | string | Yes* | - | Text prompt. *Required if no multi_shot |
mode | string | No | "std" | "std" or "pro" |
duration | integer | No | 5 | 3–15 seconds |
aspect_ratio | string | No | "16:9" | "16:9", "9:16", "1:1", "auto" (auto for frames only) |
count | integer | No | 1 | 1–4 |
image_urls | string[] | No | - | Up to 7 reference image URLs, ref as @image_1 in prompt |
elements | ElementInput[] | No | - | Up to 7, IMAGE + VIDEO. Shared pool with image_urls |
start_image_url | string | No | - | Start frame URL |
end_image_url | string | No | - | End frame URL |
video_url | string | No | - | Reference video URL, ref as @video_1 in prompt |
video_mode | string | No | "reference" | "reference" or "transform" |
keep_audio | boolean | No | false | Keep audio from reference video |
multi_shot | Shot[] | No | - | 2–6 shots, total duration 3–15s. Mutually exclusive with prompt |
{ "prompt": string, "duration": int }
Elements
Elements are created automatically from your input, used during generation, then auto-deleted on completion. v3 Omni supports both IMAGE and VIDEO elements.name(required, max 15 chars)description(required, max 100 chars)image_urls(1–4 images) — for IMAGE elementvideo_url(1 mp4, 3–8s) — for VIDEO element- Exactly one of
image_urlsorvideo_urlrequired
@element_1, @element_2, etc.
Example - Basic Generation
Example - With Elements
Example - Multi-Shot
Response
Pricing
| Mode | Price |
|---|---|
std (720p) | $0.075/s |
pro (1080p) | $0.100/s |
