Kling 2.6 - MixRoute API

Text-to-video, first/last-frame generation and motion control. Standard native-audio and first/last-frame generation require 1080p; image-to-video supports voice references.

Model Specifications

Item	Details
ID	`kling-2.6`
Endpoints	Text to Video / Image to Video / Motion Control
Standard generation resolution	720p / 1080p
Standard generation duration (s)	5 / 10

The duration above does not apply to motion control; media input may impose additional constraints on the linked endpoint pages. Put the model in the path and keep the native body structure, without metadata.

Request Example

Set the MIXROUTE_API_KEY environment variable. Replace example.com media URLs with real, publicly accessible files.

curl --request POST "https://api.mixroute.ai/kling/text-to-video/kling-2.6" \
  --header "Authorization: Bearer $MIXROUTE_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "prompt": "A person gently taps a ceramic mug on a white tabletop. A clear ceramic tapping sound.",
  "settings": {
    "resolution": "1080p",
    "duration": 5,
    "aspect_ratio": "16:9",
    "audio": "native"
  }
}'

Store submission data.id and use Query Kling Task to read status and outputs. For shared options and base pricing, see Kling Overview.