Kling 2.6 Models

Overview

Vendor: Kling. kling-2-6 generates text- and image-driven video with an optional audio toggle. kling-2-6-motion-control combines a character image and a motion-reference video.

Supported modes

Motion Control requires both image_urls and video_urls. When video_urls is present, send a positive options.source_video_duration_seconds value.

Credit pricing

kling-2-6

The matrix is identical for text-to-video and image-to-video.

kling-2-6-motion-control

For per-second pricing, Vidrush calculates ceil(rate * duration_seconds).

cURL

curl -X POST https://vidrush-ai.com/api/v1/videos \
  -H "Authorization: Bearer $VIDRUSH_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kling-2-6",
    "mode": "text-to-video",
    "prompt": "A slow dolly through a neon-lit night market",
    "options": { "duration": "5s", "audio": true }
  }'

CLI

vidrush generate -m kling-2-6 -p "A slow dolly through a neon-lit night market" \
  --duration 5s --audio --wait

MCP

Use generate_video with model: "kling-2-6"; for Motion Control, provide the required image and video inputs plus the source video duration.

Notes

• Do not send resolution or aspect_ratio for kling-2-6.
• Do not send duration or aspect_ratio for kling-2-6-motion-control.
• The Motion Control rate applies to both of its supported modes.