Kling V3 API

Create videos with Kling V3 using text, images. Available resolutions: 720p / 1080p. Try the current API settings, preview results and reuse your inputs.

Modalities

TextImageVideo

Published

Standard

$0/ request

Platform price · USD

Input

Generation mode720p · $0 / secondPrompt 204 / 100,000

resolutionaspect ratiogenerate audio

Duration3–15 seconds

Request preview

{
  "model": "kling-v3",
  "input": {
    "seconds": 5,
    "resolution": "720p",
    "aspect_ratio": "16:9",
    "generate_audio": true,
    "prompt": "One continuous cinematic tracking shot through a quiet coastal library at sunrise. Linen curtains move in a light breeze, reflected water ripples naturally, and the camera glides forward at walking speed."
  }
}

API keySign in to generate

API key for this model

Output

Example output

Open original ↗

Build with this model

The example follows your Playground parameters.

curl --request POST 'https://astralgames.ai/v1/tasks' \
  --header 'Content-Type: application/json' \
  --header "Authorization: Bearer $MODEL_API_KEY" \
  --data '{
  "model": "kling-v3",
  "input": {
    "seconds": 5,
    "resolution": "720p",
    "aspect_ratio": "16:9",
    "generate_audio": true,
    "prompt": "One continuous cinematic tracking shot through a quiet coastal library at sunrise. Linen curtains move in a light breeze, reflected water ripples naturally, and the camera glides forward at walking speed."
  }
}'

Set MODEL_API_KEY in your environment. Keep your secret key on the server. Full documentation ↗

Kling V3 pricing

Estimate one request, then choose a budget for your workflow.

Specification

Usage	Quantity	Rate	Cost
Standard	1 request	$0/ request	$0

Cost per request$0

Public USD estimate. Your account rate and final recorded usage determine the actual charge.

View all specifications and prices

Specification	Our price	Official reference
Standard	$0 / request	—

Related models

Video models ↗

Model	Price	Resolution	Input → output
KuaishouKling V3Current	$0 / request	720p / 1080p	TextImageVideo
KuaishouKling V3 OmniBoth declare text, image inputSame billing units	$0 / request	720p / 1080p	TextImageVideoVideo
GoogleGemini Omni FlashBoth declare text, image inputSame billing units	$0 / request	720p	TextImageVideoVideo
ByteDanceSeedance 2.0Both declare text, image input	$0.05 / second	480p / 720p / 1080p	TextImageVideoAudioVideo
ByteDanceSeedance 2.0 FastBoth declare text, image input	$0.03 / second	480p / 720p	TextImageVideoAudioVideo

See what it can create.

Capability-based prompts and platform-generated examples are labeled separately, with their sources.

Official capability source ↗ · 2026-10-14

Multi-shot storytelling

Shot 1: a wide street after rain. Shot 2: an original robot picks up a paper lantern. Shot 3: a close-up as it lights up. Preserve character, lighting and action continuity.

Describe narrative beats shot by shot; choose durations and shot options from the actual API.

Motion and physical detail

Track a white horse running through shallow water, capturing splashes and a coherent gait in morning backlight. Keep physical motion natural.

Direct continuous movement, physical detail and lighting together.

Platform-generated examples

Coastal architecture tracking shot

View prompt

One continuous cinematic tracking shot through a quiet coastal library at sunrise. Linen curtains move in a light breeze, reflected water ripples naturally, and the camera glides forward at walking speed.

Original media ↗Try this prompt ↗

Vertical fashion motion study

View prompt

Vertical editorial fashion motion study in a minimal cobalt studio. A model in an original sculptural ivory outfit turns once while fabric moves naturally and the camera performs a gentle handheld push.

Original media ↗Try this prompt ↗

Miniature workshop story

View prompt

A whimsical miniature workshop where tiny original robot craftspeople assemble a paper lantern. Warm practical lights flicker, small tools move with believable weight, and the camera slowly cranes down.

Original media ↗Try this prompt ↗

Kinetic paper sculpture

View prompt

A minimal kinetic sculpture made from folded ivory paper and thin cobalt rods rotates slowly in a quiet gallery. Soft daylight changes across the surfaces while the camera makes one smooth lateral move.

Original media ↗Try this prompt ↗

What is Kling V3?

Create videos with Kling V3 using text, images. Available resolutions: 720p / 1080p. Try the current API settings, preview results and reuse your inputs.

Kling VIDEO 3.0 emphasizes native audio, subject consistency and multi-shot narratives with storyboard and camera controls.

Official model information ↗ · 2026-10-14

Kling V3 specifications

Model ID	kling-v3
Provider	Kuaishou
API	/v1/tasks
Resolution	720p / 1080p
Aspect ratio	16:9 / 9:16 / 1:1
Duration	3–15 seconds
Frame images	Up to 2
Generated audio	Configurable; reference-video restrictions may apply

Before you generate

Use the current model ID and the API request shape shown on this page.
Generation is asynchronous. Keep the returned task ID to retrieve the result and billing status.
Frame and reference modes may be mutually exclusive. Check the combination constraints before submitting.
Only options supported by the current platform contract are exposed in Playground.

Compare Kling V3 with related models

Specification	Kling V3	Kling V3 Omni	Gemini Omni Flash
Provider	Kuaishou	Kuaishou	Google
Input → output	TextImageVideo	TextImageVideoVideo	TextImageVideoVideo
Start / end frames	Supported · 1 or 2 images	Supported · 1 or 2 images	—
Reference videos	—	1	1
Reference audio	—	—	—
Selection basis	Current model	Both declare text, image input · Same billing units	Both declare text, image input · Same billing units
Resolution	720p / 1080p	720p / 1080p	720p
Reference images	—	3	20
Starting price	$0 / request	$0 / request	$0 / request

Choose by the input types, output settings and billing unit your workflow needs. Try the same prompt across models to compare results for your own use case.

BUILD WITH ASTRAL NEXUS

Build with Kling V3 in your app

Submit parameters through the Media Tasks API, then retrieve the result with the task ID. Image and video models keep their own input requirements.

01
Get your API key
Sign in and prepare a key with access to this model.
02
Configure your request
Choose parameters in Playground and copy the API example.
03
Run and inspect the result
Review status, outputs and charges in History.

Read the model API guide ↗

API integration

POST /v1/tasks · Authorization: Bearer

cURL

curl 'https://astralgames.ai/v1/tasks' \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $MODEL_API_KEY" \
  --data '{
  "model": "kling-v3",
  "input": {
    "seconds": 5,
    "resolution": "720p",
    "aspect_ratio": "16:9",
    "generate_audio": true,
    "prompt": "A quiet mountain lake at sunrise, soft morning light."
  }
}'

JavaScript

const response = await fetch("https://astralgames.ai/v1/tasks", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Authorization": "Bearer $MODEL_API_KEY"
  },
  body: JSON.stringify({
    "model": "kling-v3",
    "input": {
      "seconds": 5,
      "resolution": "720p",
      "aspect_ratio": "16:9",
      "generate_audio": true,
      "prompt": "A quiet mountain lake at sunrise, soft morning light."
    }
  })
});
if (!response.ok) throw new Error(await response.text());
console.log(await response.text());

Python

import json
import requests

response = requests.post(
    "https://astralgames.ai/v1/tasks",
    headers=json.loads("{\"Content-Type\":\"application/json\",\"Authorization\":\"Bearer $MODEL_API_KEY\"}"),
    json=json.loads("{\"model\":\"kling-v3\",\"input\":{\"seconds\":5,\"resolution\":\"720p\",\"aspect_ratio\":\"16:9\",\"generate_audio\":true,\"prompt\":\"A quiet mountain lake at sunrise, soft morning light.\"}}"),
    timeout=300,
)
response.raise_for_status()
print(response.text)

Poll the returned task ID for processing status and output assets.

curl -H "Authorization: Bearer $MODEL_API_KEY" "https://astralgames.ai/v1/tasks/$TASK_ID"

Documentation: Authentication · Task status and results · Error handling

Full API parameters and combination constraints

Request parameters

Parameter	Type	Values & constraints
`prompt` *	string
`seconds`	integer	Default: 5
`resolution`	JSON	"720p" · "1080p"Default: "720p"
`aspect_ratio`	JSON	"16:9" · "9:16" · "1:1"Default: "16:9"
`frames_images`	array
`generate_audio`	boolean	Default: true

Full JSON Schema and combination constraints

{
  "type": "object",
  "required": [
    "prompt"
  ],
  "properties": {
    "prompt": {
      "type": "string",
      "maxLength": 100000,
      "minLength": 1
    },
    "seconds": {
      "type": "integer",
      "default": 5,
      "maximum": 15,
      "minimum": 3
    },
    "resolution": {
      "enum": [
        "720p",
        "1080p"
      ],
      "default": "720p"
    },
    "aspect_ratio": {
      "enum": [
        "16:9",
        "9:16",
        "1:1"
      ],
      "default": "16:9"
    },
    "frames_images": {
      "type": "array",
      "items": {
        "type": "string",
        "format": "uri",
        "pattern": "^https?://"
      },
      "maxItems": 2,
      "minItems": 1
    },
    "generate_audio": {
      "type": "boolean",
      "default": true
    }
  },
  "additionalProperties": false
}

Kling V3 API · Common questions

Answers about pricing, inputs, integration and results.

How much does Kling V3 cost?

The current public price starts at $0 / request. The pricing section lists each specification. Playground checks your account price before submitting; the completed request records the final charge.

How do I get a Astral Nexus API key?

Sign in and open Quick Start above the workspace. Select or create a key with access to this model, then copy the request example.

Which inputs and output settings are supported?

Supported input fields: prompt, seconds, resolution, aspect_ratio, frames_images, generate_audio. The parameter table includes allowed values and defaults.

Can I use reference images?

This model accepts frame images. Use start-frame mode for one image, or first-and-last-frame mode for two images. These define the video frames, unlike general reference images.

How do I retrieve results and past requests?

Save the returned task ID and query the task until it succeeds or fails. The History tab lets you reopen your tasks and reuse their parameters.

What happens if the model is closed?

The model keeps its page and identity, but new generation requests are blocked. Existing task records remain accessible. An upstream outage is reported separately from an administrator closing the model.

Read the API documentation ↗