Google Omni Flash
Vendor: Google
Video
Create, reference, and edit multimodal video with native audio
- Typical latency
- 60-300s
- Reference inputs
- Up to 6
- toolId
- google-omni-flash
Input modes
text-to-videoimage-to-videoomni-referencevideo-inpaint
Parameters
| Parameter | Type | Default | Values | Notes |
|---|---|---|---|---|
| duration | select | 4 | auto | 4 | 6 | 8 | 10 | Choose the clip length for new video generations. |
| aspect_ratio | select | 9:16 | 16:9 | 9:16 | Output frame shape. Keep one ratio across a series. |
Pricing
Pricing will be published shortly — contact us for early access rates
Prices last updated: —
API example
POST /v1/generations — google-omni-flash
curl -X POST https://api.mukelabs.com/v1/generations \
-H "Authorization: Bearer $MUKE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"toolId": "google-omni-flash",
"inputMode": "text-to-video",
"prompt": "your prompt here",
"params": { "duration": "auto" },
"references": [],
"idempotencyKey": "a-unique-key-per-task",
"subjectId": "your-user-id"
}'FAQ
How do I call Google Omni Flash on Muke Labs?
Submit POST /v1/generations with toolId "google-omni-flash" and one of its input modes (text-to-video, image-to-video, omni-reference, video-inpaint), then poll GET /v1/generations/{jobId} for the result.
What does Google Omni Flash cost?
Public pricing for this model is being finalized — contact us for early access rates. All tasks are billed from your prepaid USD balance and failed tasks refund automatically.
What happens if a task fails?
The job returns status "failed" with a typed error code, and its charge is returned to your balance automatically.
Where do I get an API key?
Create one in the developer portal (https://portal.muke.name), then send it as a Bearer token on every request.
Related models
Text
Gemini 3 Flash Preview
Previous Gemini Flash preview retained for stable workflows
chat
Text
Gemini 3.1 Flash Lite
Low-latency Gemini 3.1 model for high-volume everyday tasks
chat
Text
Gemini 3.1 Pro Preview
Latest Gemini Pro reasoning model for multimodal agent work
chat
Image
Nano Banana 2
Ultra-realistic image creation with multi-reference support
text-to-imageimage-to-image