Kling Models Guide

The Kling Unified Format covers 15 video models (kling-*); models differ only in capabilities and parameter ranges. All models go through the same two endpoints — Submit Task → Query & Download. This page introduces each model: what it does, which parameters it supports, and how to call it.

Asset models and routes are series-scoped: each series has its own asset models, and asset IDs are not interchangeable:

Assetkling series (kling-* models)kling-v series (kling-v-* models)
Elementkling-elementkling-v-element
Voicekling-voicekling-v-voice

See Elements & Voices for details.

TIP

If you are using models named kling-video-* (the "Kling Format" that mirrors the vendor's official API structure), see the Kling Format docs. Model names and endpoints of the two lines are not interchangeable.

Model List

Of the 15 models, kling-2.5-turbo ships as a single version; the other seven come in two versions, kling-* and kling-v-*, with identical capabilities per row — the two models on each row share the same resolution, duration, audio and feature set:

kling Serieskling-v SeriesPositioning
kling-2.5-turbo—Entry workhorse: 720p / 1080p, 5 / 10 s
kling-2.6kling-v-2.6Native audio (audio = native)
kling-3.0kling-v-3.0Flagship: 4k, 3–15 s, multi-shot
kling-3.0-turbokling-v-3.0-turboFaster, cheaper v3
kling-3.0-omnikling-v-3.0-omniAll-round: multi-shot + reference video + 4k
kling-o1kling-v-o1Reference-video editing
kling-motion-3.0kling-v-motion-3.0Motion control (accepts 1 element)
kling-motion-2.6kling-v-motion-2.6Motion control (no element)

Creating and referencing element / voice assets: see Elements & Voices.

Capability & Parameter Overview

Supported tiers per model (out-of-range submits return 400 with the legal values):

Model (pair)ResolutionDuration (s)audio valuesNotes
kling-2.5-turbo720p / 1080p5 / 10Not supported (non-off → 400)First-last frame tasks are forced to 1080p
kling-2.6 / kling-v-2.6720p / 1080p5 / 10off / nativeaudio=native is forced to 1080p
kling-3.0 / kling-v-3.0720p / 1080p / 4k3–15off / native / originalMulti-shot; kling-v-3.0 rejects original (400)
kling-3.0-turbo / kling-v-3.0-turbo720p / 1080p3–15Not supported (non-off → 400)—
kling-3.0-omni / kling-v-3.0-omni720p / 1080p / 4k3–15off / native / originalMulti-shot + reference video
kling-o1 / kling-v-o1720p / 1080p3–10 (5 / 10 without reference material)off / originalReference-video editing
kling-motion-3.0 / kling-v-motion-3.0720p / 1080p3–15off / originalExactly one image + one video; element ≤ 1
kling-motion-2.6 / kling-v-motion-2.6720p / 1080p3–15off / originalExactly one image + one video; no element

About audio: off silent (default, cheapest tier) / native generated voice-over / original keep source audio. Omitting the field means silent — pass it explicitly if you want sound.

Material channels (metadata.contents) and where they apply:

typeKeysPurposeApplies to
prompttextPrompt material item, can coexist with top-level promptAll models
first_frameurlFirst-frame imagei2v / omni models
last_frameurlLast-frame image, must come with the first frame; v2.5 / v2.6 last-frame tasks are forced to 1080pi2v / omni models
refer_imageurlReference image (subject reference)i2v / omni models
base_videourlReference videoOmni models only (kling-3.0-omni / kling-o1 series)
feature_videourlReference video (feature)Omni models only
videourlLegacy alias of base_videoOmni models only
imageurlCharacter reference imageMotion-control models only
elementid (optional name; motion tasks also carry element_id)Reference a created element≤ 3 on regular tasks; motion: only kling-motion-3.0, ≤ 1
voiceidReference a created voice≤ 2; audio must not be off when a voice is used

kling-2.5-turbo

Balanced entry workhorse for everyday text-to-video and image-to-video. No audio track — pick kling-2.6 or a v3 model if you need sound.

ParameterValues
resolution720p / 1080p
duration5 / 10 s
audioNot supported (non-off returns 400)
aspect_ratio16:9 / 9:16 / 1:1 / 4:3 / 3:4
FeaturesFirst-last frame tasks forced to 1080p

Image-to-video example (image present means i2v):

cURL
Python
Node.js
# Image-to-video: `image` present means i2v; Chinese prompt works best for the upstream model
curl -X POST https://api-model.shuntianchuang.cn/v1/videos \
  -H "Authorization: Bearer sk-your-token" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kling-2.5-turbo",
    "prompt": "镜头缓缓推进,猫转头看向镜头",
    "resolution": "1080p",
    "image": "https://example.com/first-frame.jpg"
  }'

kling-2.6

Adds native audio: set metadata.audio to native to generate videos with sound (automatically generated and billed at 1080p). Also supports element / voice references — voice tasks are likewise forced to 1080p.

ParameterValues
resolution720p / 1080p
duration5 / 10 s
audiooff / native
aspect_ratio16:9 / 9:16 / 1:1 / 4:3 / 3:4
FeaturesNative audio (auto 1080p); element / voice

Talking image-to-video example:

cURL
Python
Node.js
# Talking i2v: audio=native is billed at 1080p; Chinese prompt works best for the upstream model
curl -X POST https://api-model.shuntianchuang.cn/v1/videos \
  -H "Authorization: Bearer sk-your-token" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kling-2.6",
    "prompt": "镜头缓缓推进,海浪拍打礁石",
    "resolution": "1080p",
    "image": "https://example.com/first-frame.jpg",
    "metadata": { "audio": "native" }
  }'

kling-3.0

Flagship quality: up to 4k, 3–15 s durations, multi-shot storyboarding, with original source audio.

ParameterValues
resolution720p / 1080p / 4k
duration3–15 s
audiooff / native / original
aspect_ratio16:9 / 9:16 / 1:1 / 4:3 / 3:4
FeaturesMulti-shot; element / voice references

Multi-shot example (customize scripting, see Submit Task · Multi-shot):

cURL
Python
Node.js
# Multi-shot storyboarding; Chinese prompts work best for the upstream model
curl -X POST https://api-model.shuntianchuang.cn/v1/videos \
  -H "Authorization: Bearer sk-your-token" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kling-3.0",
    "prompt": "一只猫的一天",
    "metadata": {
      "multi_shot": true,
      "shot_type": "customize",
      "multi_prompt": [
        { "index": 1, "prompt": "清晨,猫在窗台伸懒腰", "duration": 3 },
        { "index": 2, "prompt": "午后,猫在草地上追蝴蝶", "duration": 4 }
      ]
    }
  }'

kling-3.0-turbo

The fast tier of v3: same 3–15 s long durations, faster and cheaper. No audio track.

ParameterValues
resolution720p / 1080p
duration3–15 s
audioNot supported (non-off returns 400)
aspect_ratio16:9 / 9:16 / 1:1 / 4:3 / 3:4
FeaturesFast long-duration generation

Text-to-video example (defaults: 720p / 5 s / silent):

cURL
Python
Node.js
# Text-to-video with defaults (720p / 5 s / silent); Chinese prompt works best for the upstream model
curl -X POST https://api-model.shuntianchuang.cn/v1/videos \
  -H "Authorization: Bearer sk-your-token" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kling-3.0-turbo",
    "prompt": "城市夜景延时摄影,车流光轨",
    "duration": 5
  }'

kling-3.0-omni

The all-round model: multi-shot, reference-video input, 4k and original audio are all supported.

ParameterValues
resolution720p / 1080p / 4k
duration3–15 s
audiooff / native / original
aspect_ratio16:9 / 9:16 / 1:1 / 4:3 / 3:4
FeaturesMulti-shot; reference video (base_video etc.); element / voice

Reference-video example (base_video carries the source video):

cURL
Python
Node.js
# Reference video via base_video; Chinese prompt works best for the upstream model
curl -X POST https://api-model.shuntianchuang.cn/v1/videos \
  -H "Authorization: Bearer sk-your-token" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kling-3.0-omni",
    "prompt": "把视频画面转换成赛博朋克风格,保持人物动作不变",
    "metadata": {
      "contents": [
        { "type": "base_video", "url": "https://example.com/source.mp4" }
      ]
    }
  }'

kling-o1

Reference-video editing: upload a video and rewrite it per instructions. Without reference material only 5 / 10 s durations are available.

ParameterValues
resolution720p / 1080p
duration3–10 s (5 / 10 s without reference material)
audiooff / original
aspect_ratio16:9 / 9:16 / 1:1 / 4:3 / 3:4
FeaturesReference-video editing

Reference-video editing example:

cURL
Python
Node.js
# Reference-video editing; Chinese prompt works best for the upstream model
curl -X POST https://api-model.shuntianchuang.cn/v1/videos \
  -H "Authorization: Bearer sk-your-token" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kling-o1",
    "prompt": "去掉背景里的路人,整体调成暖色调",
    "metadata": {
      "contents": [
        { "type": "base_video", "url": "https://example.com/source.mp4" }
      ]
    }
  }'

kling-motion-3.0

Motion control: one character image plus one motion-reference video makes the character in the image follow the motions in the video. Material must be exactly one image + one video; the motion video must contain a clear human motion (a subject too small or missing an upper body is rejected and the task fails with the reason). The result duration follows the motion video — the requested duration is ignored. Accepts one element.

ParameterValues
resolution720p / 1080p
duration3–15 s (actual result follows the motion video)
audiooff / original (original keeps the motion-video audio)
aspect_ratio16:9 / 9:16 / 1:1 / 4:3 / 3:4
FeaturesMotion control; character_orientation required; element ≤ 1

Motion-control example:

cURL
Python
Node.js
# Motion control: exactly one character image + one motion video; Chinese prompt works best
curl -X POST https://api-model.shuntianchuang.cn/v1/videos \
  -H "Authorization: Bearer sk-your-token" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kling-motion-3.0",
    "metadata": {
      "character_orientation": "video",
      "audio": "original",
      "contents": [
        { "type": "image", "url": "https://example.com/character.webp" },
        { "type": "video", "url": "https://example.com/dance.mp4" },
        { "type": "prompt", "text": "跟随视频中的舞蹈动作" }
      ]
    }
  }'

kling-motion-2.6

The previous generation of motion control: same rules as kling-motion-3.0 (exactly one image + one video, result duration follows the motion video) but no element references.

ParameterValues
resolution720p / 1080p
duration3–15 s (actual result follows the motion video)
audiooff / original (original keeps the motion-video audio)
aspect_ratio16:9 / 9:16 / 1:1 / 4:3 / 3:4
FeaturesMotion control; character_orientation required; no element

Calling it is identical to kling-motion-3.0 — just switch model to kling-motion-2.6. See Submit Task · Motion Control.

Next Steps