🎉 Get Free $5 on Signup！
Models
Enterprise
Subscribe
Resource
Activity
Documentation
Console

/kling/kling-3.0-omni

K

Kling: Kling 3.0 Omni

Kling 3.0 Omni is Kuaishou's advanced multimodal video generation model designed for highly controllable cinematic creation. It supports text-to-video, image-to-video, video reference and editing, multi-shot storytelling, first-and-last-frame control, subject consistency, native audio-video generation, and native 4K output with flexible durations up to 15 seconds.

Modetext、image、video → video、audio
Input price$0.084 per M tokens
Output price—
Context length
Listed at2026-02-25T00:00:00Z

Kling

Latency—
Throughput—
Upload rate—
Context length—
Max output—
Input price$0.084per second
Output price—per second
Cache read—per second
Cache write—per second

Performance

Avg TPS—
Avg latency—
Avg success rate—
TPS—
TTFT—
Latency—
Success rate—

Success rate

Speed

Code Example

curl ${API_BASE_URL}/v1/videos/omni-video \
  -H "Authorization: Bearer <YOUR_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kling-3.0-omni",
    "messages": [
      {
        "role": "user",
        "content": "Hello"
      }
    ]
  }'

Replace <YOUR_API_KEY> with the API key generated on your token management page.

Authentication

All requests must include the Authorization: Bearer <TOKEN> header.

Endpoint Path

POST
kling-native

Supported Parameters

ParameterTypeDefaultDescription
stringstdControls video generation quality and resolution mode. Supported values include std, pro, and 4k.
integer5Controls the generated video duration. Kling 3.0 Omni supports flexible durations from 3 to 15 seconds. Video-reference workflows support up to 10 seconds.
string16:9Controls the output video aspect ratio.
stringoffControls native synchronized audio generation. Supported values: on and off.
booleanfalseEnables multi-shot video generation.
string-Controls storyboard generation mode. Intelligent storyboarding can automatically split a prompt into multiple shots.

Rate Limits

GroupRPMTPMRPD

RPM = requests per minute, TPM = tokens per minute, RPD = requests per day. Limits apply by token group.

Pricing

ProviderBilling typePrice summary
K
Kling
Per second
Input price$0.084per second
Completion price$—per second
Cache read price$—per second
Cache write price$—per second