Kling AI/kling-2-6
Kling Video 2.6 is Kuaishou's native audio-video generation model for creating synchronized videos from either text prompts or source images.
Output: $0.063 / use or 15 uses / $1
Input
prompt * string
Required positive prompt describing the scene, subject motion, camera behavior, and any desired dialogue, music, sound effects, or ambient audio.
first_frame image
Optional first-frame image. When provided, the task uses image-to-video; otherwise it uses text-to-video. Accepts a URL or base64 for JPG, JPEG, or PNG up to 50 MB, with both dimensions at least 300 px and an aspect ratio from 1:2.5 to 2.5:1.
aspect_ratio enum
Generated frame aspect ratio for text-to-video. Image-to-video derives its framing from the input image.
duration enum
Generated video duration in seconds. Supported values are 5 and 10.
Reset
Output
{
  "task_id": "j2n94b12anrmw0cwdf1bpjde6r",
  "user_id": 1,
  "version": "bb373bc2dfa515e0ef17d07849e8ff37f0450c09fbfb7284c5019d6c027daaf4",
  "error": null,
  "total_time": 549.56,
  "predict_time": 549.55,
  "logs": null,
  "output": [
    "https://vmodel.ai/data/dev/model/kwaivgi/kling-2-6/tmp8xz0xtiw.mp4"
  ],
  "status": "succeeded",
  "create_at": 1771334410,
  "completed_at": 1771334960,
  "input": {
    "prompt": "A cinematic close-up of ocean waves striking dark rocks at sunrise. Seabirds circle above the water while the camera slowly pulls back. Natural surf, distant gull calls, and a gentle coastal breeze.",
    "audio": "native",
    "resolution": "1080p",
    "aspect_ratio": "16:9",
    "duration": 5
  }
}
Generated in: 549.55 seconds
Download
Examples
Pricing
Model pricing for kwaivgi/kling-2-6. Looking for volume pricing? Get in touch.
When
⚙ model variant is no_voice_no_native_audio_720p
$0.063000
per generation at no_voice_no_native_audio_720p
or 15 generations for $1
When
⚙ model variant is no_voice_no_native_audio_1080p
$0.105000
per generation at no_voice_no_native_audio_1080p
or 9 generations for $1
When
⚙ model variant is no_voice_native_audio_1080p
$0.210000
per generation at no_voice_native_audio_1080p
or 4 generations for $1
When
⚙ model variant is voice_native_audio_1080p
$0.252000
per generation at voice_native_audio_1080p
or 3 generations for $1
Readme

Loading...