AI Video Models by Google · From Rp975 / second (4 seconds = Rp3,900) · about 60 to 900 seconds · available now
Google Flow audio-native video generation. Fast text-to-video with synchronized dialogue, ambience, and sound effects.
Capabilities
Native audio
4–10 seconds
360p or 720p
Portrait and landscape
Sample output
Sample output from Gemini Omni Flash (Flow), made on GetRun.
Input parameters
Name
Type
Required
seed
integer
no
prompt
string
yes
duration
4 | 6 | 8 | 10
no
resolution
360p | 720p
no
aspect_ratio
16:9 | 9:16
no
The complete schema is published as JSON Schema at GET https://getrun.id/v1/models.
How to call it through the API
Try Gemini Omni Flash (Flow) in Studio, or call it from code: POST https://getrun.id/v1/tasks with body {"model": "google-flow/omni-flash", "input": {…}} and an Idempotency-Key header, then poll GET https://getrun.id/v1/tasks/{task_id}. The details are in the model documentation.
What does Gemini Omni Flash (Flow) cost on GetRun?
Gemini Omni Flash (Flow) is priced at From Rp975 / second (4 seconds = Rp3,900) and billed from a rupiah balance as you use it, with no required subscription. The estimated cost is shown before it runs, and failed tasks are never charged.
How do I call Gemini Omni Flash (Flow) through the API?
Send POST https://getrun.id/v1/tasks with an Authorization: Bearer header and an Idempotency-Key, body {"model": "google-flow/omni-flash", "input": {...}}, then poll GET https://getrun.id/v1/tasks/{task_id} every 2 to 5 seconds until the status is succeeded.
How long does Gemini Omni Flash (Flow) take per request?
Gemini Omni Flash (Flow) typically takes 60 to 900 seconds, depending on load and the input parameters.
Are Gemini Omni Flash (Flow) results stored permanently?
No. Output URLs are served from a CDN and expire after 7 days, so copy the files to your own storage if you need them longer.