Skip to main content
Kling is a video model known for smooth, coherent motion across both text-to-video and image-to-video. A strong default for short clips.

Best for

  • Short text-to-video clips.
  • Animating a still image (image-to-video).
  • Natural motion and camera movement.

Example

Video generation is asynchronous: submit a job, then poll for the result.
1

Submit a job

The response returns a job id, an estimated_cost, and status: "pending".
2

Poll for the result

Poll every 5–10 seconds until status is completed (the response includes the video URL) or failed.

Pricing

Priced per second of output. As a rough guide, expect around $0.10 per second, so a 5-second clip is about $0.50. You’re only charged when a job completes.
Image
Kling sample output: a still frame from a generated clip
The model id and prices above are examples. Confirm the exact id and current price against the live /v1/models list before you rely on them.