Kling AI / Video

Kling O3
Capabilities & pricing

Kling O3 is designed for video scenes with expressive movement, characters and composition directed through a written brief.

Base rate
from 28 tokens per second
Category
Video
Access
MCP + website
Payment
Syntasy tokens
FROM IDEA TO RESULT

What can you do with Kling O3?

Put action at the center

Set the subject's behavior, pace and interaction with the setting. Explore shots where a gesture, walk, turn or product movement communicates the idea.

Camera and composition

Describe framing, angle and camera path. For an advertising shot, identify the main subject and details that should stay visible.

Sound as part of the scene

This model's catalog includes an audio-enabled mode. When selected, describe the intended sound as well as the visuals and review them together.

A scene from a written brief

Start without a prepared first frame. Describe the setting, action and camera movement, then choose generation settings.

Where it fits

Advertising, character scenes, product videos and directing concepts.

How to get a useful result

Separate character action from camera movement. Available audio and reference options depend on the selected mode.

TRANSPARENT PRICING

How much does it cost?

Current tariffs from the Syntasy catalog. Choose a mode and settings; check the final estimate before starting.

ModeSettingsSyntasy tokens
Text to video720p · 16:9 · 3–15 s · No audio · Text input28 tokens per second
Text to video720p · 16:9 · 3–15 s · With audio · Text input36 tokens per second
Text to video1080p · 16:9 · 3–15 s · No audio · Text input36 tokens per second
Text to video1080p · 16:9 · 3–15 s · With audio · Text input46 tokens per second
Text to video4k · 16:9 · 3–15 s · No audio · Text input134 tokens per second
Text to video4k · 16:9 · 3–15 s · With audio · Text input134 tokens per second
Image to video720p · 16:9 · 3–15 s · No audio · With image28 tokens per second
Image to video720p · auto · 3–15 s · No audio · With image28 tokens per second
Text to video720p · 9:16 · 3–15 s · No audio · Text input28 tokens per second
Image to video720p · 16:9 · 3–15 s · With audio · With image36 tokens per second
Image to video720p · auto · 3–15 s · With audio · With image36 tokens per second
Text to video720p · 9:16 · 3–15 s · With audio · Text input36 tokens per second
Image to video1080p · 16:9 · 3–15 s · No audio · With image36 tokens per second
Image to video1080p · auto · 3–15 s · No audio · With image36 tokens per second
Text to video1080p · 9:16 · 3–15 s · No audio · Text input36 tokens per second
Image to video1080p · 16:9 · 3–15 s · With audio · With image46 tokens per second
Image to video1080p · auto · 3–15 s · With audio · With image46 tokens per second
Text to video1080p · 9:16 · 3–15 s · With audio · Text input46 tokens per second
Image to video4k · 16:9 · 3–15 s · No audio · With image134 tokens per second
Image to video4k · auto · 3–15 s · No audio · With image134 tokens per second
Text to video4k · 9:16 · 3–15 s · No audio · Text input134 tokens per second
Image to video4k · 16:9 · 3–15 s · With audio · With image134 tokens per second
Image to video4k · auto · 3–15 s · With audio · With image134 tokens per second
Text to video4k · 9:16 · 3–15 s · With audio · Text input134 tokens per second
Reference to video720p · 16:9 · 3–15 s · No audio · With reference28 tokens per second
Image to video720p · 9:16 · 3–15 s · No audio · With image28 tokens per second
Text to video720p · 1:1 · 3–15 s · No audio · Text input28 tokens per second
Reference to video720p · 16:9 · 3–15 s · With audio · With reference36 tokens per second
Image to video720p · 9:16 · 3–15 s · With audio · With image36 tokens per second
Text to video720p · 1:1 · 3–15 s · With audio · Text input36 tokens per second
Reference to video1080p · 16:9 · 3–15 s · No audio · With reference36 tokens per second
Image to video1080p · 9:16 · 3–15 s · No audio · With image36 tokens per second
Text to video1080p · 1:1 · 3–15 s · No audio · Text input36 tokens per second
Reference to video1080p · 16:9 · 3–15 s · With audio · With reference46 tokens per second
Image to video1080p · 9:16 · 3–15 s · With audio · With image46 tokens per second
Text to video1080p · 1:1 · 3–15 s · With audio · Text input46 tokens per second
Reference to video4k · 16:9 · 3–15 s · No audio · With reference134 tokens per second
Image to video4k · 9:16 · 3–15 s · No audio · With image134 tokens per second
Text to video4k · 1:1 · 3–15 s · No audio · Text input134 tokens per second
Reference to video4k · 16:9 · 3–15 s · With audio · With reference134 tokens per second
Image to video4k · 9:16 · 3–15 s · With audio · With image134 tokens per second
Text to video4k · 1:1 · 3–15 s · With audio · Text input134 tokens per second
Reference to video720p · 9:16 · 3–15 s · No audio · With reference28 tokens per second
Image to video720p · 1:1 · 3–15 s · No audio · With image28 tokens per second
Reference to video720p · 9:16 · 3–15 s · With audio · With reference36 tokens per second
Image to video720p · 1:1 · 3–15 s · With audio · With image36 tokens per second
Reference to video720p · 16:9 · 3–15 s · With video40 tokens per second
Reference to video720p · auto · 3–15 s · With video40 tokens per second
Reference to video1080p · 9:16 · 3–15 s · No audio · With reference36 tokens per second
Image to video1080p · 1:1 · 3–15 s · No audio · With image36 tokens per second
Reference to video1080p · 16:9 · 3–15 s · With video54 tokens per second
Reference to video1080p · auto · 3–15 s · With video54 tokens per second
Reference to video1080p · 9:16 · 3–15 s · With audio · With reference46 tokens per second
Image to video1080p · 1:1 · 3–15 s · With audio · With image46 tokens per second
Reference to video4k · 16:9 · 3–15 s · With video134 tokens per second
Reference to video4k · auto · 3–15 s · With video134 tokens per second
Reference to video4k · 9:16 · 3–15 s · No audio · With reference134 tokens per second
Image to video4k · 1:1 · 3–15 s · No audio · With image134 tokens per second
Reference to video4k · 9:16 · 3–15 s · With audio · With reference134 tokens per second
Image to video4k · 1:1 · 3–15 s · With audio · With image134 tokens per second
Video to video720p · 16:9 · 3–15 s · With video40 tokens per second
Video to video720p · auto · 3–15 s · With video40 tokens per second
Video to video1080p · 16:9 · 3–15 s · With video54 tokens per second
Video to video1080p · auto · 3–15 s · With video54 tokens per second
Video to video4k · 16:9 · 3–15 s · With video134 tokens per second
Video to video4k · auto · 3–15 s · With video134 tokens per second
Reference to video720p · 1:1 · 3–15 s · No audio · With reference28 tokens per second
Reference to video720p · 1:1 · 3–15 s · With audio · With reference36 tokens per second
Reference to video720p · 9:16 · 3–15 s · With video40 tokens per second
Reference to video1080p · 1:1 · 3–15 s · No audio · With reference36 tokens per second
Reference to video1080p · 9:16 · 3–15 s · With video54 tokens per second
Reference to video1080p · 1:1 · 3–15 s · With audio · With reference46 tokens per second
Reference to video4k · 9:16 · 3–15 s · With video134 tokens per second
Reference to video4k · 1:1 · 3–15 s · No audio · With reference134 tokens per second
Reference to video4k · 1:1 · 3–15 s · With audio · With reference134 tokens per second
Video to video720p · 9:16 · 3–15 s · With video40 tokens per second
Video to video1080p · 9:16 · 3–15 s · With video54 tokens per second
Video to video4k · 9:16 · 3–15 s · With video134 tokens per second
Reference to video720p · 1:1 · 3–15 s · With video40 tokens per second
Reference to video1080p · 1:1 · 3–15 s · With video54 tokens per second
Reference to video4k · 1:1 · 3–15 s · With video134 tokens per second
Video to video720p · 1:1 · 3–15 s · With video40 tokens per second
Video to video1080p · 1:1 · 3–15 s · With video54 tokens per second
Video to video4k · 1:1 · 3–15 s · With video134 tokens per second

This is the rate for the specified billing unit. Duration, output count and input length may change the total.

Available modes

Text to video

Text input

16:9without_audio720pwith_audio1080p4K9:161:13456789101112131415

Image to video

With image

16:9autowithout_audio720pwith_audio1080p4K9:161:13456789101112131415

Reference to video

With reference

16:9without_audio720pwith_audio1080p4K9:161:13456789101112131415

Reference to video

With video

16:9autoany720p1080p4K9:161:13456789101112131415

Video to video

With video

16:9autoany720p1080p4K9:161:13456789101112131415

Resolutions: 720p, 1080p, 4K

Aspect ratios: 16:9, 9:16, 1:1, auto

MODEL CONTEXT PROTOCOL

Use Kling O3 via MCP

Connect Syntasy in your AI client and authorize access. Ask it to find this model, calculate the price and show the settings before generation.

  1. Open Access & tokens in the MCP section and create an MCP token.
  2. Add the server URL to your client: /api/mcp
  3. Ask: “Find Kling O3. Show its modes and estimate the cost before starting.”
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "syntasy_list_models",
    "arguments": {
      "kind": "video",
      "query": "Kling O3"
    }
  }
}

The example discovers models and does not start a paid generation. Replace YOUR_MCP_TOKEN with your own token.

Frequently asked questions

What are Syntasy tokens?

They are the shared balance used to pay for models in Syntasy. Token pack prices are available on the pricing page. View token packs

Why can the final cost differ from the base rate?

A per-second tariff is multiplied by duration, an image tariff by output count, and a character tariff by text length. Check the estimate on the website or use syntasy_estimate_generation via MCP for your chosen settings.

Kling O3 — capabilities & pricing | Syntasy