OpenAI-Compatible Video Flow

Method	Path	Use
`POST`	`/v1/video/generations`	Create an OpenAI-compatible video task
`GET`	`/v1/videos/{task_id}`	Poll video task status and result
`GET`	`/v1/videos/{task_id}/content`	Fetch the produced content of a finished video task

This set of endpoints is the platform's standard video protocol: the request uses OpenAI Video-compatible fields, and the platform translates it into the upstream vendor's async video task format.

Create a task

bash

curl https://api.modelgo.ai/v1/video/generations \
  -H "Authorization: Bearer $MODELGO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"<model>","prompt":"a neon city cat","duration":4}'

A successful create returns a task_id. Subsequent polling and content fetches are all keyed by that task_id.

Poll task status

bash

curl https://api.modelgo.ai/v1/videos/task_123 \
  -H "Authorization: Bearer $MODELGO_API_KEY"

json

{
  "id": "task_123",
  "object": "video",
  "status": "completed",
  "progress": 100,
  "metadata": { "url": "https://.../video.mp4", "duration": 4, "resolution": "..." }
}

status is one of queued / in_progress / completed / failed; on completed, the produced asset URL appears in metadata.url.

Fetch the asset

Once the task is done, you can fetch the asset bytes through the content endpoint. The gateway streams the video/mp4 bytes directly (no 302 redirect to object storage), supports Range requests, and only the API key that owns the task (or a console session in the same tenant) may read it:

bash

curl https://api.modelgo.ai/v1/videos/task_123/content \
  -H "Authorization: Bearer $MODELGO_API_KEY" \
  -o video.mp4

Content availability depends on the backend "media delivery" setting:

404 (content_delivery_disabled) when delivery is disabled
409 (task_not_completed) when the task is still running
404 (content_not_available) when the asset has expired or is missing

Key conventions

This is the standard OpenAI-compatible video entrypoint; clients do not need to understand vendor-native protocols.
Whether fields such as duration or size are supported, and which upstream vendor is selected, depends on the logical model referenced by model.
Video generation is asynchronous. Poll with backoff to avoid unnecessary rate-limit pressure.

For the more generic async task entrypoint, see Generic Async Content Generation Tasks. To write against a vendor's own payload style while keeping platform-managed billing and task handling, see the Seedance Video Inbound Protocol and the MiniMax Video Inbound Protocol.