Video API

Most video models share the same async pattern:

POST create → receive id / task_id
GET poll until success → read the result URL

Host: https://api.omniall.ai · Auth Authorization: Bearer sk-... · models: Model Square.

Family	Create	Poll	Guide
Unified	`/v1/videos` · `/v1/video/generations`	matching `GET`	this page
Google Omni	`/v1/videos`	`/v1/videos/{id}`	text / image / frame / v2v
Veo	`/v1/videos`	`/v1/videos/{id}`	Veo 3.1
Grok video	`/v1/videos`	`/v1/videos/{id}`	Grok Imagine Video
MiniMax-H3	`/v1/videos`	`/v1/videos/{id}`	t2va / i2va / r2va
Seedance	`/v1/video/generations`	matching `GET`	Seedance 2.0 / 2.5
Kling	`/v1/videos`	`/v1/videos/{id}`	text / image / avatar / lip-sync
Runway	`/v1/task/submit` or `/runwayml/v1/*`	matching `GET`	unified + official
Wan	`/v1/video/generations`	matching `GET`	wan2.1 480P/720P/1080P

Quick example

curl -X POST "https://api.omniall.ai/v1/videos" \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "veo-3.1-generate-preview",
    "prompt": "A train crossing a mountain bridge",
    "seconds": "8"
  }'

Full schemas and playground examples: API Reference → Video.