Wan 3.0 Prime | BeatAPI API Documentation

curl -X POST https://api.beatapi.io/v1/videos/tasks \
     -H "Authorization: Bearer <token>" \
     -H "Content-Type: application/json" \
     -d '{
  "model": "wan-3.0-prime",
  "prompt": "A slow dolly through a neon-lit night market in the rain, steam rising from food stalls.",
  "duration": 8,
  "aspect_ratio": "16:9",
  "resolution": "720p"
}'

{
  "data": {
    "capability_id": "wan-3.0-prime",
    "capability_version": null,
    "completed_at": null,
    "created_at": 1782210000,
    "error_code": null,
    "error_message": null,
    "id": "task_8K2qA",
    "media_type": "video",
    "model": "wan-3.0-prime",
    "object": "task",
    "output": null,
    "request_id": "req_abc123",
    "stage": "queued",
    "status": "queued",
    "task_kind": "video",
    "updated_at": 1782210000,
    "usage": {
      "billable_duration_seconds": 5,
      "credits_charged": 0.63,
      "credits_refunded": 0,
      "credits_reserved": 0.63,
      "credits_settled": 0
    }
  }
}

The priority render tier of Wan 3.0 — the same 2–30 second output at the same price, served from the faster queue.

Supported modes

Mode	Required input	Rules
Text to video	`model`, `prompt`	Omit `images`.
Image to video	`model`, `prompt`, `images`	One image starts the render from that frame.
With references	`model`, `prompt`, `reference_videos` or `reference_audios`	A reference video bills the request at 1.5x.

Async flow: Create the task, save data.id, then poll the Task with GET /v1/tasks/{task_id}. On succeeded, read data.output.media. On failed, read data.error_code and data.error_message, then follow the error and retry policy.

Using a local file? upload a local input first and pass the returned data.url.

The priority render tier of Wan 3.0 — the same 2–30 second output at the same price, served from the faster queue. ### Supported modes | Mode | Required input | Rules | | --- | --- | --- | | Text to video | `model`, `prompt` | Omit `images`. | | Image to video | `model`, `prompt`, `images` | One image starts the render from that frame. | | With references | `model`, `prompt`, `reference_videos` or `reference_audios` | A reference video bills the request at 1.5x. | **Async flow:** Create the task, save `data.id`, then [poll the Task](/quick-guide#get-task-status) with `GET /v1/tasks/{task_id}`. On `succeeded`, read `data.output.media`. On `failed`, read `data.error_code` and `data.error_message`, then follow the [error and retry policy](/quick-guide#errors-and-retry-policy). **Using a local file?** [upload a local input](/quick-guide#upload-an-input-file) first and pass the returned `data.url`.

Authentication

AuthorizationBearer

Send your API key as Authorization: Bearer <BEATAPI_API_KEY>.

Request

This endpoint expects an object.

model"wan-3.0-prime"Required

Must be wan-3.0-prime.

promptstringRequired1-5000 characters

Video generation instructions.

imageslist of stringsOptional

Public HTTPS images. One starts an image-to-video render; more are used as visual references.

reference_videoslist of stringsOptional

Public HTTPS video references. A request that carries one is billed at 1.5x.

reference_audioslist of stringsOptional

Public HTTPS audio references.

durationintegerOptional2-30Defaults to 5

Requested output duration in seconds. Any whole number in range; there is no long-clip surcharge.

aspect_ratioenumOptionalDefaults to 16:9

Output video aspect ratio.

resolutionenumOptionalDefaults to 720p

Output resolution tier. Price scales with it.

Response

Video generation task accepted

Errors

400

Bad Request Error

401

Unauthorized Error

402

Payment Required Error

409

Conflict Error

429

Too Many Requests Error

The priority render tier of Wan 3.0 — the same 2–30 second output at the same price, served from the faster queue.

Supported modes

Mode	Required input	Rules
Text to video	`model`, `prompt`	Omit `images`.
Image to video	`model`, `prompt`, `images`	One image starts the render from that frame.
With references	`model`, `prompt`, `reference_videos` or `reference_audios`	A reference video bills the request at 1.5x.

Using a local file? upload a local input first and pass the returned data.url.

Supported modes

Authentication

Headers

Request

Response

Errors

Supported modes