Video Generationtextimagevideo

Kling 4.0

Kling Video 4.0 is Kuaishou’s native multimodal video creation model, supporting text-to-video, image-to-video, Omni Reference, targeted video editing, up to 10 keyframes, native 3–30 second generation, and two-channel stereo audio.

Entrada

Generation mode

Describe the video with text only—no images required.

Reference image (optional)

Compatible con JPG/JPEG, PNG · se admite arrastrar y soltar

Compatible con JPG/JPEG, PNG · se admite arrastrar y soltar
Duration
330
Resolution
Aspect ratio
Ready to generateReady to generate

Referencia de la API

POSThttps://api.token360.ai/v1/videos
# Step 1: Create video generation task
curl https://api.token360.ai/v1/videos \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-api-key" \
  -d '{
  "model": "kling-4.0",
  "prompt": "A cat walking across a room",
  "duration": 10,
  "watermark": false,
  "resolution": "1080p",
  "aspect_ratio": "16:9"
}'

# Step 2: Poll for completion (replace VIDEO_ID with the id from step 1)
curl https://api.token360.ai/v1/videos/VIDEO_ID \
  -H "Authorization: Bearer your-api-key"

API Documentation

Overview#

Kling Video 4.0 is Kuaishou’s native multimodal video creation model. It supports text-to-video, image-to-video, Omni Reference, video editing, native 3–30 second generation, up to 10 keyframes, and two-channel stereo audio.

Official API endpoints#

  • POST /text-to-video/kling-4.0
  • POST /image-to-video/kling-4.0
  • POST /omni-video/kling-4.0

References#