WAND-Create โ
This is the API documentation for generating text, images, video, music, and 3D, and for analyzing media. Choose a task type first, then start from the request example of the model you will use.
Choosing a Task โ
| Task | Documentation |
|---|---|
| Text generation and chat | VOD Text / GPT, Gemini, GK, DeepSeek, GLM, Kimi, MiniMax, Hunyuan |
| Image generation and editing | VOD Image, MPS Image, TokenHub Image |
| Video generation | VOD Video, MPS Video |
| Music and sound generation | VOD Music, MPS Music |
| Image and video understanding | Media Understanding / Vega-VL, Gemini |
Call Paths โ
| Category | Endpoint | Authentication | Response mode |
|---|---|---|---|
| VOD Image / Video / Music / 3D | vod.intl.tencentcloudapi.com | TC3-HMAC-SHA256 | Query after the TaskId is accepted |
| MPS Image / Video / Music / 3D | mps.tencentcloudapi.com | TC3-HMAC-SHA256 | Query after the TaskId is accepted |
| VOD Text / Media Understanding | mmu.vod-qcloud.com | VOD AIGC Bearer Token | Complete response or SSE |
| TokenHub Image | tokenhub-intl.tencentcloudmaas.com | TokenHub API Key | Per-model response and query spec |
For VOD generation, specify the output specification with OutputConfig; for MPS generation, with ExtraParameters. The model-specific extra options of VOD use ExtInfo, and MPS is passed to AdditionalParameters as a JSON string.
Vega Models โ
| Task | Model | Call path |
|---|---|---|
| Image generation and editing | WAND-Vega-Image / Lite / Flash / Pro | MPS / VOD / Tokenhub |
| Video generation | WAND-Vega-Video / 1.5-pro / 1.0-pro / 1.0-lite | MPS / VOD |
| Image and video understanding | Vega-VL | VOD multimodal API |
Querying Generation Results โ
- Call the generation action and save
TaskId. - VOD checks
DescribeTaskDetailfor itsStatus=FINISHandErrCode=0, and MPS checks theStatus=DONEof the per-model query action. - Download the file from the result URL, or check the storage specified in the generation request.
Text and Media Understanding do not require querying a generation task. Results are read from the HTTP response or SSE.
Document Structure โ
Each API Reference explains authentication, common request and response formats, and the query and storage specifications. Model documents are organized in the order of basic information, request parameters, request examples, special settings, and response examples. The Image, Video, and Text menus are used to expand the model list.