Skip to main content
XRoute connects developers to leading generative video models for high-definition video synthesis, character motion, and visual storytelling.
Native Asynchronous Task Only: Video generation takes extended compute time (typically 30s–120s). Video models strictly use vendor-native asynchronous task protocols:
  1. Submit Task: POST request returning an initial task_id with status: "PENDING" or "RUNNING".
  2. Poll Status: Periodic GET requests until status: "SUCCEEDED" with generated video download URLs.

Supported Video Models


1. Byteplus Seedance Workflow

Seedance produces cinematic camera dynamics and physics-grounded scene animation.

Step 1: Submit Video Generation Task

  • Endpoint: POST https://api.xroute.ai/Byteplus/contents/generations/tasks
  • Header: Authorization: Bearer $XROUTE_API_KEY

Step 2: Poll Task Status

  • Endpoint: GET https://api.xroute.ai/Byteplus/contents/generations/tasks/{task_id}
cURL
Response (Completed)

Complete Python Polling Script

Python (Byteplus Ark SDK)

2. WAN Video Synthesis Native (DashScope Protocol)

WAN models use Alibaba DashScope’s asynchronous synthesis standard.

Step 1: Submit Synthesis Task

  • Endpoint: POST https://api.xroute.ai/WAN/services/aigc/video-generation/video-synthesis
  • Header:
    • Authorization: Bearer $XROUTE_API_KEY
    • X-DashScope-Async: enable
cURL

Step 2: Poll WAN Task

  • Endpoint: GET https://api.xroute.ai/WAN/tasks/{task_id}
cURL