AnyInt Docs
Models

Video Generation

The current published generic video flow is task-based. Use OpenAI-style video routes with a video model ID, or provider-specific media routes when you need provider-native payloads.

The current published generic video flow is task-based. For OpenAI-style video generation, create tasks at /openai/v1/videos with a video model ID available to your account. Provider-specific media routes remain available when you need provider-native payloads.

Published routes

RoutePurpose
POST /dashscope/v1/services/aigc/video-generation/video-synthesisCreate a video from prompt, image, and audio
GET /dashscope/v1/tasks/{task_id}Query video task status and fetch the result
POST /openai/v1/videosCreate an OpenAI-style video task
GET /openai/v1/videos/{video_id}Query an OpenAI-style video task
GET /openai/v1/videos/{video_id}/contentDownload completed video content

Input pattern

The current schema combines:

  • a text prompt
  • an image URL
  • an audio URL
  • generation parameters such as duration and resolution

Task lifecycle

The response returns a task immediately. After that:

  1. store task_id
  2. query the task route
  3. wait for task_status to reach success
  4. consume video_url

In the published examples, the task starts as PENDING and later becomes SUCCEEDED.

Use Models API to discover video model IDs available to your account. For Kling-specific model IDs, fields, polling examples, and native Transtreams routes, see Kling video. Other video models may expose different optional parameters.

Practical advice

  • Design your UI as an async workflow, not a single request-response page
  • Persist the original prompt, task ID, and returned asset URL together
  • Keep polling as a fallback even if you also use webhooks elsewhere in your platform

Where AI Music fits

If you are generating a music video from a song workflow rather than a generic video pipeline, look at Media & Music instead of treating it as a plain video job.

On this page