Kling 4.0 API
Video up to 30s at 720p or 1080p, with start, middle and end keyframes.
Kling 4.0 API playground
Params
Billed at this model’s published rate.
Result
Your generations will appear here
Other models from Kling
Same vendor, same API call — the differences are below.
| Model | Use case | Price | Resolution | Duration | Added |
|---|---|---|---|---|---|
| Kling 4.0 Flash | Text → Video | from $0.294533 / sec | — | 3–20s | Nov 2026 |
| Kling 4.0 Flash Omni | Text → Video | from $0.03 / sec | — | 3–20s | Nov 2026 |
| Kling 4.0 Omni | Text → Video | from $0.084 / sec | 720p · 1080p | 3–30s | Oct 2026 |
| Kling V3 Turbo | Text → Video | from $0.112 / sec | 720p · 1080p | 3–15s | Jun 2026 |
| Kling Video Effects | Image → Video | from $0.21 / gen | — | — | May 2026 |
| Kling 3.0 Image | Text → Image | from $0.0308 / gen | 1k · 2k · 4k | — | Mar 2026 |
| Kling O1 Image | Text → Image | from $0.0308 / gen | 1k · 2k | — | Mar 2026 |
| Kling Motion Control V3 | Image → Video | from $0.126 / sec | — | — | Feb 2026 |
Kling 4.0 API questions
What can the Kling 4.0 API do?
It renders 3 to 30 second clips at 720p or 1080p in 16:9, 9:16, 1:1 or 21:9. You can set the opening still, up to 8 middle frames and the final shot, add reference images for subject or style, and turn on sound with voice samples. For example videos and prompts, see the Kling 4.0 model page.
What can I build with the Kling 4.0 API?
Teams build product ads that open with a photo and close on a packshot, plus 9:16 clips for Reels, Shorts and TikTok. Storyboard panels passed as middle frames move one shot through each planned beat, while single takes up to 30 seconds suit walkthroughs, explainers or music visuals.
Is the Kling 4.0 API free?
No. The Kling 4.0 price is set per second of output: $0.29344 for 720p and $0.65744 for 1080p, with no seats and no subscription minimum. A 10-second 720p clip comes to about $2.93, and the SDK quotes the cost of every call before you run it.
Do I need a Kling API key?
No. Your Picsart API key, sent as a bearer token, calls Kling 4.0 and every other model in the catalog, so there is no separate vendor account to set up. If you already have Kling request bodies, the Advanced tab accepts them with their original parameter names.
How long can a Kling 4.0 video be?
Any length from 3 to 30 seconds, set in steps of one with the duration parameter, and 5 by default. Pricing is per second, so longer clips cost more. Draft short clips while you tune the prompt, then raise the duration for the final render.
Which resolutions and aspect ratios does Kling 4.0 support?
Video comes out at 720p or 1080p, with 720p as the default. Aspect ratios are 16:9, 9:16, 1:1 and 21:9, so one model covers widescreen, vertical, square and ultrawide formats. Keep in mind that 1080p costs more per second than 720p.
Can Kling 4.0 generate sound?
Yes, through the Advanced tab. Its native parameters include sound, which creates audio along with the video, and voice_list, which takes up to 2 references while that setting is on. The unified parameters on the API tab cover the visual settings only.
How do I switch from Kling 4.0 to another video model?
Change the model id in generate(), for example from kling-v4 to kling-v4-omni. On the unified API the request and response shape stay the same for every model. Requests on the Advanced tab use the vendor’s own names, so they only work with Kling models.
Kling 4.0 API in TypeScript, Python and REST
Install the SDK
TypeScript targets Node 20+ and ships with types; Python needs 3.10+ and is async. Over REST there is nothing to install: call https://api.picsart.com from any HTTP client.
npm install @picsart/ai-sdkpip install picsart-ai-sdkAuthenticate
Send your Picsart API key as a bearer token. The SDK does it for you once the client is created.
import { createClient } from '@picsart/ai-sdk';
const ai = createClient({
apiKey: process.env.PICSART_API_KEY, // sent as: Authorization: Bearer <key>
apiUrl: 'https://api.picsart.com',
});import os
from picsart_ai_sdk import create_client
ai = create_client(
api_key=os.environ["PICSART_API_KEY"], # sent as: Authorization: Bearer <key>
api_url="https://api.picsart.com",
)Authorization: Bearer <PICSART_API_KEY>Make a request
Call the model by its id. Over REST, one endpoint serves every model: POST /workflows/v1/models/execute with the model id and its input in the body. The outer params is the envelope every workflow takes; the inner one is this model's input, with the same names generate() takes.
import { createClient } from '@picsart/ai-sdk';
const ai = createClient({
apiKey: process.env.PICSART_API_KEY,
apiUrl: 'https://api.picsart.com',
});
const result = await ai.generate('kling-v4', {
prompt: "A serene mountain lake at golden hour, ultra detailed",
aspectRatio: "16:9",
duration: 5,
resolution: "720p"
});
console.log(result.url); // video URLimport asyncio
import os
from picsart_ai_sdk import create_client
async def main() -> None:
async with create_client(
api_key=os.environ["PICSART_API_KEY"],
api_url="https://api.picsart.com",
) as ai:
result = await ai.generate("kling-v4", {
"prompt": "A serene mountain lake at golden hour, ultra detailed",
"aspectRatio": "16:9",
"duration": 5,
"resolution": "720p",
})
print(result.url) # video URL
asyncio.run(main())curl -X POST 'https://api.picsart.com/workflows/v1/models/execute' \
-H 'Authorization: Bearer $PICSART_API_KEY' \
-H 'Content-Type: application/json' \
-d '{
"params": {
"model": "kling-v4",
"params": {
"prompt": "A serene mountain lake at golden hour, ultra detailed",
"aspectRatio": "16:9",
"duration": 5,
"resolution": "720p"
}
}
}'Async (submit & poll)
This model can run longer than the sync limit (~20s). generate() waits for you; to hold on to the job instead, submit it and poll. Over REST, send it to /workflows/v1/models/submit and poll /workflows/v1/models/{taskId}/result until response.status is COMPLETED or FAILED.
import { createClient } from '@picsart/ai-sdk';
const ai = createClient({
apiKey: process.env.PICSART_API_KEY,
apiUrl: 'https://api.picsart.com',
});
// Returns the generation id at once — store it to pick the job up later.
const generationId = await ai.submit('kling-v4', {
prompt: "A serene mountain lake at golden hour, ultra detailed",
aspectRatio: "16:9",
duration: 5,
resolution: "720p"
});
// Polls until the job completes; throws if it fails or is cancelled.
const result = await ai.result('kling-v4', generationId);
console.log(result.url); // video URLimport asyncio
import os
from picsart_ai_sdk import create_client
async def main() -> None:
async with create_client(
api_key=os.environ["PICSART_API_KEY"],
api_url="https://api.picsart.com",
) as ai:
# Returns the generation id at once — store it to pick the job up later.
generation_id = await ai.submit("kling-v4", {
"prompt": "A serene mountain lake at golden hour, ultra detailed",
"aspectRatio": "16:9",
"duration": 5,
"resolution": "720p",
})
# Polls until the job completes; raises ApiError if it fails or is cancelled.
result = await ai.result("kling-v4", generation_id)
print(result.url) # video URL
asyncio.run(main())# 1. Submit the job
curl -X POST 'https://api.picsart.com/workflows/v1/models/submit' \
-H 'Authorization: Bearer $PICSART_API_KEY' \
-H 'Content-Type: application/json' \
-d '{
"params": {
"model": "kling-v4",
"params": {
"prompt": "A serene mountain lake at golden hour, ultra detailed",
"aspectRatio": "16:9",
"duration": 5,
"resolution": "720p"
}
}
}'
# → { "status": "success", "response": { "id": "task_abc123" } }
# 2. Poll until response.status is COMPLETED
curl 'https://api.picsart.com/workflows/v1/models/task_abc123/result' \
-H 'Authorization: Bearer $PICSART_API_KEY'Parameters
7 parameters, the same for the SDK and for the inner params over REST. Required ones must be supplied; the rest fall back to their defaults.
| Parameter | Type | Required | Default | Details |
|---|---|---|---|---|
promptWhat to make, in plain language: the subject, style, composition and motion. With an input image or video, what to change. | text | yes | — | max 26000 chars |
aspectRatioShape of the output as width:height. An auto or adaptive option follows the input image. | enum | no | 16:9 | 16:9, 9:16, 1:1, 21:9 |
durationLength of the output, in seconds. | range | no | 5 | 3–30 (step 1) |
resolutionOutput size. Higher costs more and takes longer. | enum | no | 720p | 720p, 1080p |
startFrameThe first frame, as an image URL. The video starts on this image. | file (image) | no | — | — |
imageUrlsInput images, as URLs: frames to animate, or references for subject, style or composition. | file (image[]) | no | — | — |
endFrameThe last frame, as an image URL. The video ends on this image. | file (image) | no | — | — |
Response
generate() resolves once the job completes. A video URL. Over REST the output is at response.result, inside the gateway's status envelope with the task id, its status and the amount charged.
{
"items": [
{
"url": "https://cdn.picsart.com/…/result"
}
],
"model": "kling-v4"
}{
"status": "success",
"response": {
"id": "task_abc123",
"status": "COMPLETED",
"result": {
"url": "https://cdn.picsart.com/…/result",
"items": [
{
"url": "https://cdn.picsart.com/…/result"
}
],
"model": "kling-v4"
}
}
}Kling 4.0 API advanced usage
Overview
Alongside the unified model APIs, we expose compatibility APIs that take each vendor's original parameters exactly as the vendor defines them — nothing renamed, nothing reshaped on the way through.
That makes them the shortest path onto Picsart if you already work with the vendor directly: the request bodies you've already written keep working as they are. You keep their parameter names and defaults, and you get the vendor's full parameter set rather than the subset that is shared across every model.
The cost is that a request is written for one vendor — switching models later means rewriting it, and results come back in the vendor's own shape. When you'd rather write once and change models freely, use the unified API.
Make a request
Call the workflow with ai.apis.run() in TypeScript or Python, or hit /workflows/{workflow}/execute directly — params is passed through untouched either way.
These endpoints are addressed by workflow name rather than model id: the one in this model's header, since one model runs as one workflow. Authentication is unchanged — your Picsart API key as a bearer token (see Authentication).
import { createClient, ApiRunMode } from '@picsart/ai-sdk';
const ai = createClient({
apiKey: process.env.PICSART_API_KEY,
apiUrl: 'https://api.picsart.com',
});
// Calls the 'kling-text-to-video' workflow directly — params are sent as-is.
const { result, usage } = await ai.apis.run('kling-text-to-video', {
prompt: "A serene mountain lake at golden hour, ultra detailed"
}, {
mode: ApiRunMode.SYNC,
});
console.log(result); // workflow-specific output
console.log(usage?.credits); // amount charged, in $import asyncio
import os
from picsart_ai_sdk import ApiRunMode, create_client
async def main() -> None:
async with create_client(
api_key=os.environ["PICSART_API_KEY"],
api_url="https://api.picsart.com",
) as ai:
# Calls the 'kling-text-to-video' workflow directly — params are sent as-is.
response = await ai.apis.run("kling-text-to-video", {
"prompt": "A serene mountain lake at golden hour, ultra detailed",
}, mode=ApiRunMode.SYNC)
print(response["result"]) # workflow-specific output
print((response.get("usage") or {}).get("credits")) # amount charged, in $
asyncio.run(main())curl -X POST 'https://api.picsart.com/workflows/kling-text-to-video/execute' \
-H 'Authorization: Bearer $PICSART_API_KEY' \
-H 'Content-Type: application/json' \
-d '{
"params": {
"prompt": "A serene mountain lake at golden hour, ultra detailed"
}
}'Async (submit & poll)
This model can run longer than the sync limit (~20s). In the SDK, ai.apis.run() with ApiRunMode.ASYNC polls for you; over HTTP, submit and poll yourself.
import { createClient, ApiRunMode } from '@picsart/ai-sdk';
const ai = createClient({
apiKey: process.env.PICSART_API_KEY,
apiUrl: 'https://api.picsart.com',
});
// mode: ASYNC submits the job and polls under the hood — you just await.
const { result } = await ai.apis.run('kling-text-to-video', {
prompt: "A serene mountain lake at golden hour, ultra detailed"
}, {
mode: ApiRunMode.ASYNC,
});
console.log(result);import asyncio
import os
from picsart_ai_sdk import ApiRunMode, create_client
async def main() -> None:
async with create_client(
api_key=os.environ["PICSART_API_KEY"],
api_url="https://api.picsart.com",
) as ai:
# mode=ASYNC submits the job and polls under the hood — you just await.
response = await ai.apis.run("kling-text-to-video", {
"prompt": "A serene mountain lake at golden hour, ultra detailed",
}, mode=ApiRunMode.ASYNC)
print(response["result"])
asyncio.run(main())# 1. Submit the job
curl -X POST 'https://api.picsart.com/workflows/kling-text-to-video/submit' \
-H 'Authorization: Bearer $PICSART_API_KEY' \
-H 'Content-Type: application/json' \
-d '{
"params": {
"prompt": "A serene mountain lake at golden hour, ultra detailed"
}
}'
# → { "status": "success", "response": { "id": "wf_abc123" } }
# 2. Poll until response.status is COMPLETED
curl 'https://api.picsart.com/workflows/kling-text-to-video/wf_abc123/result' \
-H 'Authorization: Bearer $PICSART_API_KEY'Parameters
14 parameters, sent inside params. These are the vendor's own names, so they line up one-for-one with the vendor's documentation. Required ones must be supplied; the rest fall back to their defaults.
| Parameter | Type | Required | Default | Details |
|---|---|---|---|---|
model_nameModel name for video generation | string | no | kling-v2-6 | kling-v2-5-turbokling-v2-6kling-v3kling-v3-turbokling-v4-flashkling-v4 |
promptPrompt text for video generation (max 2500 characters; `kling-v4-flash` / `kling-v4`: English-only up to 26000, non-English-only up to 11000). Optional when multi_shot is enabled. | string | no | — | — |
negative_promptNegative prompt text for video generation (max 2500 characters) | string | no | — | — |
cfg_scaleConfiguration scale factor (range 0-1) | number | no | 0.5 | — |
soundGenerated sound simultaneously when generating videos | string | no | off | onoff |
modeMode for video generation. kling-v2-5-turbo only supports PRO mode. mode=4k is only supported by kling-v3. Other models does not support this parameter. | string | no | — | stdpro4k |
aspect_ratioAspect ratio for the video. `21:9` is only supported by `kling-v4-flash` / `kling-v4`; `adaptive` is not supported here. | string | no | 16:9 | 16:99:161:121:9adaptive |
resolutionOutput resolution of the generated video. Only supported by `kling-v3-turbo` / `kling-v4` (720p or 1080p) and `kling-v4-flash` (720p only); defaults to 720p when omitted. | string | no | — | 720p1080p |
durationDuration of the video in seconds. v2 models: 5 or 10. v3 models: 3-15. kling-v4-flash: 3-20. kling-v4: 3-30. | string | no | 5 | 5103467891112131415161718192021222324252627282930 |
multi_shotEnable multi-shot video generation (v3 only) | boolean | no | — | — |
shot_typeShot segmentation type for multi-shot generation | string | no | — | customizeintelligence |
multi_promptList of prompts for each shot in multi-shot mode (max 6 items) | MultiPromptItem[] | no | — | — |
└ indexIndex of the shot (starting from 0) | number | yes | — | — |
└ promptPrompt text for this shot (max 512 characters) | string | yes | — | — |
└ durationDuration of this shot in seconds | string | yes | — | — |
voice_listVoice references for video generation (max 2 items, requires sound=on) | VoiceItem[] | no | — | — |
└ voice_idVoice ID reference | string | yes | — | — |
optionsOptions controlling safety checks and drive integration | object | no | — | — |
└ safety_checksSafety check settings | object | no | — | — |
└ enabledWhether to run content moderation. Defaults to true. | boolean | no | — | — |
└ driveSave result to Picsart Drive | object | no | — | — |
└ nameFile name in Picsart Drive | string | yes | — | — |
└ attributesCustom attributes to attach to the file | object | no | — | — |
└ folderTarget folder in Picsart Drive | object | no | — | — |
└ inputs_transformationInput transformation settings | object | no | — | — |
└ downscale_oversized_imagesWhether to downscale oversized input images. Defaults to false. | boolean | no | — | — |
Response
Over HTTP the output arrives inside a status envelope, at response.result. ai.apis.run() unwraps that envelope for you and resolves to { result, usage } instead. Either way the result itself is the vendor's own shape.
{
"result": {
"url": "https://cdn.picsart.com/…/result.mp4",
"duration": "…",
"mimeType": "video/mp4",
"driveFile": {
"id": "wf_abc123"
}
}
}{
"status": "success",
"response": {
"result": {
"url": "https://cdn.picsart.com/…/result.mp4",
"duration": "…",
"mimeType": "video/mp4",
"driveFile": {
"id": "wf_abc123"
}
}
}
}Kling 4.0 API pricing
Kling API pricing is per second of video: $0.29344 for 720p and $0.65744 for 1080p, with no subscription minimum. That puts the Kling API cost of a 5-second 1080p clip at about $3.29, and a 30-second 720p one near $8.80.
Rates
What this model costs, in USD. Every row is an exact rate — the columns are the settings that change it.
| Tier | Rate |
|---|---|
| 720p | $0.29344 / sec |
| 1080p | $0.65744 / sec |