## Create task
`POST /v1/video/generations`
```bash cURL theme={null}
curl --request POST \
--url https://www.anyfast.ai/v1/video/generations \
--header 'Authorization: Bearer YOUR_API_KEY' \
--header 'Content-Type: application/json' \
--data '{
"model": "wan2.2-t2v-a14b",
"prompt": "A paper lantern floats above a quiet riverside town at dusk. The camera follows from below.",
"duration": 5,
"width": 1280,
"height": 720,
"seed": 42
}'
```
## Request headers
Bearer authentication in the form `Bearer YOUR_API_KEY`.
Request body format.
## Request body
Must be `wan2.2-t2v-a14b`.
Text description of the subject, action, setting, visual style, and camera movement.
Video duration from 3 through 5 seconds.
Output width in pixels.
Output height in pixels.
Optional random seed in `[0, 2147483647]` for more repeatable generation.
Optional extension fields passed to the upstream service.
## Create response
```json 200 theme={null}
{
"id": "asyntask_wan22t2vexample123",
"task_id": "asyntask_wan22t2vexample123",
"object": "video",
"model": "wan2.2-t2v-a14b",
"status": "",
"progress": 0,
"created_at": 1785426400
}
```
Task ID used to query the result.
Task ID, identical to `id`.
Returned object type, `video`.
AnyFast model ID used by the task.
Initial status string. Use the query endpoint for the authoritative task state.
Initial task progress percentage.
Creation time as a Unix timestamp in seconds.
## Create task
`POST /v1/video/generations`
```bash cURL theme={null}
curl --request POST \
--url https://www.anyfast.ai/v1/video/generations \
--header 'Authorization: Bearer YOUR_API_KEY' \
--header 'Content-Type: application/json' \
--data '{
"model": "wan2.2-i2v-a14b",
"prompt": "The cat runs forward through the grass while the camera tracks alongside it.",
"image": "https://cdn.translate.alibaba.com/r/wanx-demo-1.png",
"duration": 5,
"width": 1280,
"height": 720,
"seed": 42
}'
```
## Request headers
Bearer authentication in the form `Bearer YOUR_API_KEY`.
Request body format.
## Request body
Must be `wan2.2-i2v-a14b`.
Text description of the motion and camera behavior.
Public first-frame image URL. Supported upstream formats include JPEG, JPG, PNG without alpha, BMP, and WebP; the Wan2.2 family limit is 10 MB with width and height from 240 through 8,000 pixels.
Video duration from 3 through 5 seconds.
Output width in pixels.
Output height in pixels.
Optional random seed in `[0, 2147483647]` for more repeatable generation.
Optional extension fields passed to the upstream service.
## Create response
```json 200 theme={null}
{
"id": "asyntask_wan22i2vexample123",
"task_id": "asyntask_wan22i2vexample123",
"object": "video",
"model": "wan2.2-i2v-a14b",
"status": "",
"progress": 0,
"created_at": 1785426400
}
```
Task ID used to query the result.
Task ID, identical to `id`.
Returned object type, `video`.
AnyFast model ID used by the task.
Initial status string. Use the query endpoint for the authoritative task state.
Initial task progress percentage.
Creation time as a Unix timestamp in seconds.
## Query task by ID
`GET /v1/video/generations/{task_id}`
```bash cURL theme={null}
curl --request GET \
--url https://www.anyfast.ai/v1/video/generations/asyntask_wan22t2vexample123 \
--header 'Authorization: Bearer YOUR_API_KEY'
```
## Request headers
Bearer authentication in the form `Bearer YOUR_API_KEY`.
## Path parameters
Task ID returned by a Wan2.2 create request.
## Task result
```json 200 theme={null}
{
"code": "success",
"message": "",
"data": {
"task_id": "asyntask_wan22t2vexample123",
"action": "textGenerate",
"status": "SUCCESS",
"fail_reason": "https://example.com/generated-video.mp4",
"result_url": "https://example.com/generated-video.mp4",
"submit_time": 1785426400,
"start_time": 1785426414,
"finish_time": 1785426560,
"progress": "100%",
"request_id": "request_wan22example123",
"data": {
"output": {
"task_id": "upstream_task_wan22example123",
"task_status": "SUCCEEDED",
"video_url": "https://example.com/generated-video.mp4",
"orig_prompt": "A paper lantern floats above a quiet riverside town at dusk.",
"submit_time": "2026-07-30 23:46:53.873",
"scheduled_time": "2026-07-30 23:46:53.900",
"end_time": "2026-07-30 23:49:18.837"
},
"request_id": "upstream_request_wan22example123",
"usage": {
"SR": 720,
"duration": 5,
"input_video_duration": 0,
"output_video_duration": 5,
"ratio": "16:9",
"video_count": 1
}
}
}
}
```
Query-call result. `success` means the query completed; use `data.status` for the generation outcome.
Response message, normally empty for a successful query.
AnyFast task state and result payload.
AnyFast task ID.
Generation workflow, such as `textGenerate` for text-to-video or `generate` for image-to-video.
`NOT_START`, `QUEUED`, or `IN_PROGRESS` means keep polling. On `SUCCESS`, read `result_url`; on `FAILURE`, read `fail_reason`.
Compatibility field. It can repeat `result_url` on success, so use `status` to determine the outcome.
Temporary generated-video URL for a successful task.
Task submission Unix timestamp in seconds.
Task start Unix timestamp in seconds; `0` before processing starts.
Task completion Unix timestamp in seconds; `0` before a terminal state.
Progress from `0%` through `100%`.
AnyFast request trace ID.
Raw upstream response data.
Raw upstream task output.
Upstream task ID.
Upstream status such as `PENDING`, `RUNNING`, `SUCCEEDED`, `FAILED`, `CANCELED`, or `UNKNOWN`.
Generated-video URL in the upstream output.
Prompt received by the upstream service.
Upstream task submission time.
Upstream task scheduling time.
Upstream task completion time.
Upstream request trace ID.
Upstream usage details, normally present after success.
Output resolution value.
Billable duration in seconds.
Input-video duration reported for usage.
Generated output-video duration in seconds.
Generated video aspect ratio when returned.
Number of generated videos.
## Error responses
* `400 Bad Request` - Invalid input or an unsupported parameter.
* `401 Unauthorized` - The API key is missing or invalid.
* `404 Not Found` - The requested task does not exist.
* `429 Rate limit exceeded` - The request rate exceeded the applicable limit.