Skip to main content

Documentation Index

Fetch the complete documentation index at: https://chatgpttech.mobi/docs/llms.txt

Use this file to discover all available pages before exploring further.

​
Available models

Use Seedance in the dashboard

Open model page
ModelModel IDDurationAspect ratioPrice
Seedance 2.0doubao/doubao-seedance-2-0-2601285s / 10s16:9 / 9:16 / 1:1$0.28 / generation

​
How it works

Video generation is a two-step async process: submit a task, then poll for the result.
1

Submit a generation task

Send a POST request to /v1/generation/tasks:
curl https://api.chatgpttech.mobi/v1/generation/tasks \
  -H "Authorization: Bearer sk-hub-your-key-here" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "doubao/doubao-seedance-2-0-260128",
    "content": [{"type": "text", "text": "A beautiful sunset over mountains"}],
    "ratio": "16:9",
    "duration": 5
  }'
The response returns a task ID you’ll use to check progress:
{
  "id": "task_abc123",
  "status": "pending",
  "created_at": "2026-05-07T12:00:00Z"
}
2

Poll for the result

Query the task status using the returned id. Poll every 3 seconds until the status is completed or failed:
curl https://api.chatgpttech.mobi/v1/generation/tasks/task_abc123 \
  -H "Authorization: Bearer sk-hub-your-key-here"
Completed response:
{
  "id": "task_abc123",
  "status": "completed",
  "video_url": "https://cdn.example.com/output/abc123.mp4",
  "duration": 5
}

​
Task status reference

StatusDescription
pendingQueued, waiting to be processed
processingGeneration in progress
completedDone — video_url is available
failedGeneration failed — see the error field for details

​
Request parameters

ParameterTypeRequiredDescription
modelstring✓Model ID
contentarray✓Prompt array. Each item has type of text or image_url
ratiostring—Aspect ratio: 16:9 (default), 9:16, or 1:1
durationnumber—Duration in seconds: 5 (default) or 10
resolutionstring—Output resolution: 480p, 720p, or 1080p (default)
Note: Video generation models are not available through /v1/chat/completions. Use /v1/generation/tasks for all video generation requests.

Quickstart

API keys

Text models