Kling 3 | BeatAPI API Documentation

curl -X POST https://api.beatapi.io/v1/videos/tasks \
     -H "Authorization: Bearer <token>" \
     -H "Content-Type: application/json" \
     -d '{
  "model": "kling-3",
  "prompt": "A dramatic product reveal with a slow orbiting camera move.",
  "duration": 5,
  "aspect_ratio": "16:9",
  "resolution": "pro",
  "sound": true
}'

{
  "data": {
    "capability_id": "kling-3",
    "capability_version": null,
    "completed_at": null,
    "created_at": 1782210000,
    "error_code": null,
    "error_message": null,
    "id": "task_8K2qA",
    "media_type": "video",
    "model": "kling-3",
    "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": 0.65,
      "credits_refunded": 0,
      "credits_reserved": 0.65,
      "credits_settled": 0
    }
  }
}

Generate 3–15 second videos from text or frames, with optional multi-shot and reusable-element controls up to 4K.

Supported modes

Mode	Required input	Rules
Text to video	`model`, `prompt`	Omit `images`, `multi_prompt`, and `elements`.
First frame	`model`, `prompt`, `images`	Provide one image URL; provide two for first and last frames.
Multi-shot	`model`, `prompt`, `multi_shots`, `multi_prompt`	Set `multi_shots=true`; shot durations must sum to `duration`.
Reusable element	`model`, `prompt`, `elements`	Provide up to three named image or video reference elements.

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.

Generate 3–15 second videos from text or frames, with optional multi-shot and reusable-element controls up to 4K. ### Supported modes | Mode | Required input | Rules | | --- | --- | --- | | Text to video | `model`, `prompt` | Omit `images`, `multi_prompt`, and `elements`. | | First frame | `model`, `prompt`, `images` | Provide one image URL; provide two for first and last frames. | | Multi-shot | `model`, `prompt`, `multi_shots`, `multi_prompt` | Set `multi_shots=true`; shot durations must sum to `duration`. | | Reusable element | `model`, `prompt`, `elements` | Provide up to three named image or video reference elements. | **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`.

身份验证

AuthorizationBearer

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

请求

This endpoint expects an object.

model"kling-3"必需

Must be kling-3.

promptstring必需1-5000 characters

Video generation instructions.

imageslist of strings可选

One first-frame image or first- and last-frame images as public HTTPS URLs. Multi-shot mode accepts exactly one.

durationinteger可选3-15默认为 5

Requested output duration in seconds.

aspect_ratioenum可选

Defaults to 16:9 for text generation. Omit it with frame images to adapt to the input aspect ratio.

resolutionenum可选默认为 pro

Output quality tier.

soundboolean可选

Generate synchronized sound. Defaults to true in multi-shot mode.

multi_shotsboolean可选默认为 false

Enable storyboard-style multi-shot generation.

multi_promptlist of objects可选

Shot definitions required when multi_shots=true.

elementslist of objects可选

Up to three reusable subject or object references.

响应

Video generation task accepted

错误

400

Bad Request Error

401

Unauthorized Error

402

Payment Required Error

409

Conflict Error

429

Too Many Requests Error

Generate 3–15 second videos from text or frames, with optional multi-shot and reusable-element controls up to 4K.

Supported modes

Mode	Required input	Rules
Text to video	`model`, `prompt`	Omit `images`, `multi_prompt`, and `elements`.
First frame	`model`, `prompt`, `images`	Provide one image URL; provide two for first and last frames.
Multi-shot	`model`, `prompt`, `multi_shots`, `multi_prompt`	Set `multi_shots=true`; shot durations must sum to `duration`.
Reusable element	`model`, `prompt`, `elements`	Provide up to three named image or video reference elements.

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

Supported modes

身份验证

请求头

请求

响应

错误

Supported modes