Wan 2.6 Text to Video

wan2.6-t2v

Wan 2.6 Text to Video uses Alibaba video generation technology to generate high-quality videos from text descriptions.

Endpoints

POST /v1/queue/wan2.6-t2v # Create task

GET /v1/queue/wan2.6-t2v/requests/{request_id}/status # Check status

GET /v1/queue/wan2.6-t2v/requests/{request_id}/response # Get result

PUT /v1/queue/wan2.6-t2v/requests/{request_id}/cancel # Cancel task

Request Parameters

curl --location "https://odirouter.ai/model/v1/queue/wan2.6-t2v" \
  --header "Authorization: Bearer YOUR_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
    "prompt": "A red apple slowly rotating on a white table, clean studio lighting, static camera.",
    "duration": 2,
    "size": "1280*720",
    "prompt_extend": true,
    "watermark": false,
    "seed": 12345
  }'

prompt string Required

Text prompt describing expected elements, motion, and visual characteristics in the generated video. Chinese and English are supported, and content beyond the model limit is truncated automatically.

Maximum length: 1500 characters

negative_prompt string

Negative prompt describing content that should not appear in the generated video. Chinese and English are supported.

duration int

Generated video duration in seconds. This parameter affects cost.

Options: 5, 10, 15

Range: 2 - 15

Default: 5

size string

Output video resolution in explicit width-height format, for example 1280*720.

Use an explicit size when you need a specific 720P or 1080P output dimension.

resolution string

Video resolution tier used to control output clarity. This field affects generation cost.

Example: 720P

For explicit official resolution control, prefer size.

audio_url string

Optional audio URL used to guide video generation when supported by the model workflow.

shot_type string

Shot type used to control video narrative structure.

Options: single, multi

prompt_extend bool

Whether to enable prompt rewriting. When enabled, a large model rewrites the input prompt, often improving short prompts but increasing latency.

Options: true, false

Default: true

seed int

Random seed. When omitted, the system generates a random seed automatically. A fixed seed can improve reproducibility, but identical results are not guaranteed.

Range: 0 - 2147483647

watermark bool

Whether to add a watermark in the lower-right corner of the video.

Options: false, true

Default: false

Response Parameters

{
  "request_id": "mmsu_01hxyz...",
  "response_url": "https://odirouter.ai/model/v1/queue/wan2.6-t2v/requests/mmsu_01hxyz.../response",
  "status_url": "https://odirouter.ai/model/v1/queue/wan2.6-t2v/requests/mmsu_01hxyz.../status",
  "cancel_url": "https://odirouter.ai/model/v1/queue/wan2.6-t2v/requests/mmsu_01hxyz.../cancel",
  "queue_position": 0
}

Field	Type	Description
`request_id`	string	Task ID used for later status checks, result retrieval, and cancellation
`response_url`	string	URL for retrieving the final result
`status_url`	string	URL for checking task status
`cancel_url`	string	URL for canceling the task
`queue_position`	int	Queue position

Next Steps

Check status

Get result

Cancel task

Errors