Kling 3.0 Turbo

curl --request POST \
  --url https://{api_domain}/v3/kling/text-to-video/kling-3.0-turbo

const options = {method: 'POST'};

fetch('https://{api_domain}/v3/kling/text-to-video/kling-3.0-turbo', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://{api_domain}/v3/kling/text-to-video/kling-3.0-turbo",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"net/http"
	"io"
)

func main() {

	url := "https://{api_domain}/v3/kling/text-to-video/kling-3.0-turbo"

	req, _ := http.NewRequest("POST", url, nil)

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

require 'uri'
require 'net/http'

url = URI("https://{api_domain}/v3/kling/text-to-video/kling-3.0-turbo")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)

response = http.request(request)
puts response.read_body

POST

kling

text-to-video

kling-3.0-turbo

Kling 3.0 Turbo

curl --request POST \
  --url https://{api_domain}/v3/kling/text-to-video/kling-3.0-turbo

const options = {method: 'POST'};

fetch('https://{api_domain}/v3/kling/text-to-video/kling-3.0-turbo', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://{api_domain}/v3/kling/text-to-video/kling-3.0-turbo",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"net/http"
	"io"
)

func main() {

	url := "https://{api_domain}/v3/kling/text-to-video/kling-3.0-turbo"

	req, _ := http.NewRequest("POST", url, nil)

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

require 'uri'
require 'net/http'

url = URI("https://{api_domain}/v3/kling/text-to-video/kling-3.0-turbo")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)

response = http.request(request)
puts response.read_body

Parameters and usage are aligned with the official API. For detailed parameters, refer directly to the official documentation.

1. Overview

This document explains how to use text-to-video and image-to-video capabilities through the Kling 3.0 Turbo native protocol. Turbo uses the same native protocol as standard Kling 3.0, with identical request and response structures, differing only in capability scope, resolution tiers, and billing. Both capabilities use an asynchronous task model:

Call the corresponding creation API.
Save the data.id from the creation response.
Query the task status using the same API Key that was used to create the task.
After the task succeeds, retrieve and save the generated video from outputs.

1.1 API Endpoints

Capability	Create Task	Query Task
Text-to-Video	`POST /v3/kling/text-to-video/kling-3.0-turbo`	`GET /v3/kling/tasks`
Image-to-Video	`POST /v3/kling/image-to-video/kling-3.0-turbo`	`GET /v3/kling/tasks`

In the examples in this document, the full address is https://{api_domain} plus the API path in the table, where {api_domain} is the API domain you use. Turbo only provides text-to-video and image-to-video; it does not support Omni video or motion control.

1.2 Authentication

All requests require an API Key. POST requests must also specify the JSON content type:

Authorization: Bearer <YOUR_API_KEY>
Content-Type: application/json

1.3 Response Structure

The data in the creation response is an object. Common fields include id (the task ID generated by the Kling system, used for subsequent queries), external_id (the echo of options.external_task_id; may be omitted if not set), and status (the task status after creation, usually submitted). The data in the query response is an array. Each task contains id, external_id, status (submitted, processing, succeeded, or failed), message, create_time, update_time, and outputs. Common fields for video results in outputs are type, id, url, watermark_url, and duration, where url is the non-watermarked result URL, watermark_url is the watermarked result URL, and duration is the video duration in seconds.

2. Text-to-Video

2.1 Create Task

POST https://{api_domain}/v3/kling/text-to-video/kling-3.0-turbo

Request Fields:

Field	Type	Required	Default / Allowed Values	Description
`prompt`	string	Yes		Text prompt, can include positive and negative descriptions; up to 3072 characters, recommended no more than 2500 characters
`settings.resolution`	string	No	Default `720p`; `720p`, `1080p`	Resolution of the generated video
`settings.aspect_ratio`	string	No	Default `16:9`; `16:9`, `9:16`, `1:1`	Aspect ratio (width:height) of the generated video
`settings.duration`	int	No	Default 5; integer from 3 to 15	Duration of the generated video, in seconds
`options.callback_url`	string	No		URL to receive callback notifications when the task status changes
`options.external_task_id`	string	No		Custom task ID; does not override the system task ID, can be used for queries, must be unique per user
`options.watermark_info.enabled`	boolean	No	Default `false`	Whether to generate a watermarked result

Multi-shot video is implemented using a fixed format in prompt: “Shot n, m, words; Shot n, m, words;” (separated by half-width punctuation). Here, n is the shot index (1 to 6 shots), m is the shot duration (each not less than 1, and the sum of all shot durations equals the total video duration), and words is the shot prompt (up to 512 characters).

2.2 Create Example

curl -X POST 'https://{api_domain}/v3/kling/text-to-video/kling-3.0-turbo' \
  -H 'Authorization: Bearer <YOUR_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{
    "prompt": "A cinematic tracking shot of a red sports car driving along a coastal road at sunset",
    "settings": {
      "resolution": "1080p",
      "aspect_ratio": "16:9",
      "duration": 5
    },
    "options": {
      "external_task_id": "turbo-text-20260826-0001"
    }
  }'

After successful creation, the task ID is returned:

{
  "code": 0,
  "message": "success",
  "request_id": "provider-request-id",
  "data": {
    "id": "kling-turbo-text-task-id",
    "external_id": "turbo-text-20260826-0001",
    "status": "submitted",
    "create_time": 1781080778802,
    "update_time": 1781080794151
  }
}

Please save data.id. If options.external_task_id is not provided, data.external_id may not be returned.

2.3 Query Task

GET https://{api_domain}/v3/kling/tasks?task_ids={task_id}

Use the same API Key that was used to create the task. You can also use external_task_ids to query custom task IDs. For each request, exactly one of task_ids and external_task_ids must be provided. Both support 1–50 IDs separated by English commas. The data in the response is an array and preserves the order of the requested IDs.

2.4 Query Example

curl -X GET 'https://{api_domain}/v3/kling/tasks?task_ids=kling-turbo-text-task-id' \
  -H 'Authorization: Bearer <YOUR_API_KEY>'

When the task succeeds, the response is:

{
  "code": 0,
  "message": "success",
  "request_id": "provider-request-id",
  "data": [
    {
      "id": "kling-turbo-text-task-id",
      "status": "succeeded",
      "outputs": [
        {
          "type": "video",
          "url": "https://your-result-cdn.example.com/turbo-text.mp4",
          "duration": 5
        }
      ]
    }
  ]
}

status=processing means the task is still running; it is recommended to query every 10–30 seconds. status=failed means the task failed and you should stop polling. After the task succeeds, save the file corresponding to outputs[type=video].url promptly, as the download URL may be valid for only a limited time.

2.5 Billing

Task cost = per-second price for the corresponding resolution × settings.duration

The price tier is determined only by settings.resolution (720p or 1080p). If duration is not provided, the default of 5 seconds is billed. Charges are applied at task creation based on the requested duration; if task creation fails or final generation fails, the fee is automatically refunded. Refer to the pricing page of the service you are using for specific unit prices.

3. Image-to-Video

3.1 Create Task

POST https://{api_domain}/v3/kling/image-to-video/kling-3.0-turbo

Request Fields:

Field	Type	Required	Default / Allowed Values	Description
`contents`	array	Yes		Collection of reference materials, must contain at least one item
`contents[].type`	string	Yes	`prompt`, `first_frame`	Material type: prompt, first frame image
`contents[].text`	string	No		Text prompt when `type=prompt`, up to 2500 characters
`contents[].url`	string	No		First frame image when `type=first_frame`, supports URL or Base64
`settings.resolution`	string	No	Default `720p`; `720p`, `1080p`	Resolution of the generated video
`settings.duration`	int	No	Default 5; integer from 3 to 15	Duration of the generated video, in seconds
`options.external_task_id`	string	No		Custom task ID; does not override the system task ID, can be used for queries, must be unique per user
`options.watermark_info.enabled`	boolean	No	Default `false`	Whether to generate a watermarked result

Images support .jpg, .jpeg, and .png formats. Files must not exceed 50 MB, width and height must be at least 300 pixels, and the aspect ratio must be between 1:2.5 and 2.5:1. Image-to-video only supports a first frame image; “first frame + last frame” and “last frame only” are not supported yet. options.callback_url can also be provided, with the same usage as in text-to-video. Multi-shot video is also implemented using the fixed format in prompt.

3.2 Create Example

curl -X POST 'https://{api_domain}/v3/kling/image-to-video/kling-3.0-turbo' \
  -H 'Authorization: Bearer <YOUR_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{
    "contents": [
      {
        "type": "prompt",
        "text": "The subject turns toward the camera while the wind moves naturally through the scene"
      },
      {
        "type": "first_frame",
        "url": "https://your-cdn.example.com/first-frame.png"
      }
    ],
    "settings": {
      "resolution": "1080p",
      "duration": 5
    },
    "options": {
      "external_task_id": "turbo-image-20260826-0001"
    }
  }'

On successful creation, the response is:

{
  "code": 0,
  "message": "success",
  "request_id": "provider-request-id",
  "data": {
    "id": "kling-turbo-image-task-id",
    "external_id": "turbo-image-20260826-0001",
    "status": "submitted",
    "create_time": 1781080778802,
    "update_time": 1781080794151
  }
}

3.3 Query Task

Query the task using data.id from the creation response:

GET https://{api_domain}/v3/kling/tasks?task_ids={task_id}

When querying with task_ids, use the same API Key that was used to create the task. You can also query using external_task_ids for the options.external_task_id passed at creation time. The query parameter supports 1–50 IDs separated by English commas.

3.4 Query Example

curl -X GET 'https://{api_domain}/v3/kling/tasks?task_ids=kling-turbo-image-task-id' \
  -H 'Authorization: Bearer <YOUR_API_KEY>'

When the task succeeds, the video URL is located at outputs[type=video].url:

{
  "code": 0,
  "message": "success",
  "request_id": "provider-request-id",
  "data": [
    {
      "id": "kling-turbo-image-task-id",
      "status": "succeeded",
      "outputs": [
        {
          "type": "video",
          "url": "https://your-result-cdn.example.com/turbo-image.mp4",
          "duration": 5
        }
      ]
    }
  ]
}

When status=processing, it is recommended to continue querying every 10–30 seconds. When status=failed, stop polling and correct the input based on the error message.

3.5 Billing

Task cost = per-second price for the corresponding resolution × settings.duration

4. Common Errors and Notes

API errors use the following structure:

{
  "code": 1203,
  "message": "task not found (trace_id: platform-trace-id)",
  "request_id": "",
  "data": null
}

Common status codes: 400/1200 (invalid parameters or content type, correct based on message), 401/1000 (API Key missing or invalid), 403/1103 (no permission to perform the operation), 404/1203 (task does not exist or no permission to query), 429/1302 (requests too frequent, reduce frequency and use exponential backoff), 500/5000, 503/5001, 504/5002 (service exception or timeout, retry later; avoid uncontrolled repeated submissions). If message contains trace_id, provide it when contacting technical support. Additional notes:

The request body does not need model or model_name; the model version is already included in the URL.
Persist data.id after creating the task; do not treat request_id as the task ID.
The maximum request body size is 64 MB; for larger images, it is recommended to use a publicly accessible URL for Kling.
Input material URLs must be publicly accessible by Kling and cannot rely on intranet access, cookies, or temporary login sessions.
Use a polling interval of 10–30 seconds for the query API, and set an overall timeout and exponential backoff.
A POST timeout does not necessarily mean the task was not created; query first with external_task_id before deciding whether to retry.
After receiving a successful status, save the file corresponding to outputs[type=video].url immediately, as the result URL may expire.

5. Python Example

The following example uses the standard requests library to demonstrate text-to-video creation and polling. For image-to-video, simply replace the creation API endpoint and request body.

import os
import time

import requests


api_domain = os.environ["API_DOMAIN"]
api_key = os.environ["PLATFORM_API_KEY"]
headers = {
    "Authorization": f"Bearer {api_key}",
    "Content-Type": "application/json",
}

payload = {
    "prompt": "A calm cinematic landscape at sunrise",
    "settings": {
        "resolution": "1080p",
        "aspect_ratio": "16:9",
        "duration": 5,
    },
    "options": {
        "external_task_id": "turbo-python-20260826-0001",
    },
}

created = requests.post(
    f"https://{api_domain}/v3/kling/text-to-video/kling-3.0-turbo",
    headers=headers,
    json=payload,
    timeout=60,
)
created.raise_for_status()
task_id = created.json()["data"]["id"]

while True:
    response = requests.get(
        f"https://{api_domain}/v3/kling/tasks",
        headers={"Authorization": f"Bearer {api_key}"},
        params={"task_ids": task_id},
        timeout=30,
    )
    response.raise_for_status()
    task = response.json()["data"][0]
    if task["status"] == "succeeded":
        video = next(item for item in task["outputs"] if item["type"] == "video")
        print(video["url"])
        break
    if task["status"] == "failed":
        raise RuntimeError(task)
    time.sleep(20)

Last modified on October 15, 2026

API Basics

API Key Management

Large Language Models

Images

Video

Audio

Kling 3.0 Turbo

1. Overview

1.1 API Endpoints

1.2 Authentication

1.3 Response Structure

2. Text-to-Video

2.1 Create Task

2.2 Create Example

2.3 Query Task

2.4 Query Example

2.5 Billing

3. Image-to-Video

3.1 Create Task

3.2 Create Example

3.3 Query Task

3.4 Query Example

3.5 Billing

4. Common Errors and Notes

5. Python Example

​1. Overview

​1.1 API Endpoints

​1.2 Authentication

​1.3 Response Structure

​2. Text-to-Video

​2.1 Create Task

​2.2 Create Example

​2.3 Query Task

​2.4 Query Example

​2.5 Billing

​3. Image-to-Video

​3.1 Create Task

​3.2 Create Example

​3.3 Query Task

​3.4 Query Example

​3.5 Billing

​4. Common Errors and Notes

​5. Python Example

1. Overview

1.1 API Endpoints

1.2 Authentication

1.3 Response Structure

2. Text-to-Video

2.1 Create Task

2.2 Create Example

2.3 Query Task

2.4 Query Example

2.5 Billing

3. Image-to-Video

3.1 Create Task

3.2 Create Example

3.3 Query Task

3.4 Query Example

3.5 Billing

4. Common Errors and Notes

5. Python Example