Skip to main content
POST

​
Available models

Pass any video generation model ID in model, for example:

​
Call flow

  1. POST /v1/video/generations — submit task, get task_id
  2. GET /v1/video/generations/{task_id} — poll until status=completed
  3. Read the url field from the response to download the video

​
Image-to-video

Set the image field (URL or Base64) to trigger image-to-video mode. The model will animate the content of the provided image.

​
Extended parameters

For some models, metadata accepts model-specific fields such as negative_prompt, style, or quality_level. Supported fields vary by model — refer to the model’s own documentation.

Authorizations

​
Authorization
string
header
required

Bearer token authentication, format: Authorization: Bearer sk-xxxxxx. Get your API key in the console.

Body

application/json

Generic video generation request body.

​
model
string
required

Model ID. Supports multi-vendor video models such as Kling and Veo. Examples: kling-v2-5-turbo, kling-v2-1-master, veo_3_1, veo_3_1-fast.

Example:

"kling-v2-5-turbo"

​
prompt
string
required

Text prompt describing the video content, scene, camera work, and style.

Example:

"An astronaut walking on the Moon, Earth rising in the background, cinematic shot"

​
image
string

Reference image — URL or Base64 data URI. When set, triggers image-to-video mode and the model animates the image content.

Example:

"https://example.com/image.jpg"

​
duration
number

Video duration in seconds.

Example:

5

​
width
integer

Video width in pixels.

Example:

1280

​
height
integer

Video height in pixels.

Example:

720

​
fps
integer

Video frame rate (fps).

Example:

30

​
seed
integer

Random seed. Using the same seed and parameters tends to produce similar results.

Example:

20231234

​
n
integer

Number of videos to generate. Recommended to keep at 1 for async tasks.

Example:

1

​
response_format
string

Response format. Use url.

Example:

"url"

​
user
string

End-user identifier for auditing and abuse monitoring; not used in generation.

Example:

"user-1234"

​
metadata
object

Extended parameters for model-specific fields such as negative_prompt, style, or quality_level. Supported fields vary by model.

Response

Video generation task created successfully

Response from the generic video generation create endpoint.

​
task_id
string

Task ID — use this to poll for status.

Example:

"abcd1234efgh"

​
status
string

Initial task status, typically queued.

Example:

"queued"