Skip to main content

Video Generation

Create high-quality videos from text prompts using state-of-the-art video generation models. This is an asynchronous endpoint that returns a job ID for status polling.

Endpoint

Request Body

string
required
The model ID to use for video generation.Available models include:
  • veo-3.1 (Google’s latest)
  • sora-2 (OpenAI’s latest)
  • luma-ray-2 (Luma AI’s latest)
  • hailuo-2 (MiniMax’s latest)
  • pika-2.2 (Pika Labs’ latest)
  • kling-v1.5 (Kuaishou’s latest)
string
required
A text description of the desired video. The maximum length is 1000 characters.
string
default:"16:9"
The aspect ratio of the generated video. Options: 16:9, 9:16, 1:1.
integer
default:5
The duration of the generated video in seconds. Options: 5, 10.
string
A unique identifier for the end-user, for abuse monitoring.

Response

string
Unique identifier for the generation job (e.g., vid-abc123)
string
Current status of the job. Always "pending" initially.
string
The URL to poll for the job status.

Polling for Status

Since video generation is an asynchronous process, you must poll the status endpoint until the job is completed.

Endpoint

Response

string
Unique identifier for the generation job
string
Current status of the job. One of: "pending", "processing", "completed", "failed".
object
The result of the generation job (only present when status is "completed").
  • video_url (string): The URL of the generated video
  • thumbnail_url (string): The URL of the video thumbnail
object
Error details (only present when status is "failed").
  • message (string): Description of the error

Examples

Generate Video

Error Responses