How do you generate AI videos with Seedance API and check task status?
Updated: 2026-07-05
AI video generation usually returns a task ID first and the final video later. Understanding async task status is essential.
Short answer
Submit the video request, save the task_id, then query https://lizh.ai/v1/images/generations/{task_id} with your own API key in the Authorization header until the task is complete.
Steps
- Submit the video generation request.
- Save the returned task_id.
- Wait a short interval before polling.
- Call the task status endpoint with Authorization: Bearer YOUR_API_KEY.
- Read the video URL or result when the task is complete.
Recommended models
- Seedance for text-to-video and dynamic visuals.
- Seedream for keyframes or supporting images before video generation.
Cost and reliability notes
- Start with short video tests.
- Avoid polling too aggressively.
- Log failed prompts and model settings.
How to do it with lizh.ai
Create an API key in lizh.ai and use it as a Bearer token in clients that support an OpenAI-compatible API.
Use Base URL: https://lizh.ai/v1