Video walkthrough
Start with a minimal request, then add model parameters such as reference images, aspect ratio, and duration.
Prepare your environment
Set API_BASE_URL and LINGJUTA_API_KEY on your server. The platform provides the API service root; do not use the documentation URL as the API URL.
If you have not created a key, open API key management first.
Submit a minimal task
sh
curl --fail-with-body "${API_BASE_URL}/api/v3/contents/generations/tasks" \
-H "Authorization: Bearer ${LINGJUTA_API_KEY}" \
-H 'Content-Type: application/json' \
-d '{
"model": "seedance-2.0-mini",
"content": [{ "type": "text", "text": "A cat runs along the beach" }]
}'Save the id from the successful response in your application records, and use the same ID to query progress.
Understand the task lifecycle
| Status | Meaning | Next step |
|---|---|---|
queued | Waiting in the queue | Query again later |
running | Generating | Query again later |
succeeded | Complete | Retrieve the output URL |
failed | Generation failed | Read the error and correct the request before resubmitting |
cancelled | Cancelled | Stop polling |
expired | Timed out | Stop polling and investigate |
Retrieve the generated result
sh
curl --fail-with-body \
"${API_BASE_URL}/api/v3/contents/generations/tasks/YOUR_TASK_ID" \
-H "Authorization: Bearer ${LINGJUTA_API_KEY}"On success, read content.video_url. Output URLs may expire; save the output promptly if your application needs it. Do not assume example URLs remain accessible indefinitely.
Improve your integration
- Set explicit request timeouts and a maximum polling count.
- Check the original task result after a network timeout to avoid unintended duplicate generation.
- Log task IDs, HTTP statuses, and redacted errors; do not log API keys.
- Refer to the model's official documentation for optional parameter ranges.
For field details, see Create a video task and Query a video task.

