Kling 2.6 API on APIMart uses model ID kling-v2-6 for text-to-video and image-to-video. Choose std (720p, silent) or pro (1080p), 5 or 10 seconds, and add native audio or a last frame in pro mode. It also supports camera control and dynamic masks.
Service Highlights
Video link valid for 72 hours
Transparent pricing with no hidden fees. Pay only for what you use.
| Variant | Tier | GoldCurrent price | Platinum | Diamond | Official | Your savings |
|---|---|---|---|---|---|---|
kling-v2-6 | 720P | 0.368Credits(~$0.0368)/sec | 0.3496Credits(~$0.035)/sec | 0.3312Credits(~$0.0331)/sec | 0.46Credits(~$0.046)/sec | 20% |
| 1080P | 0.625Credits(~$0.0625)/sec | 0.5938Credits(~$0.0594)/sec | 0.5625Credits(~$0.0563)/sec | 0.7813Credits(~$0.0781)/sec | 20% | |
| 1080P+Sound | 1.25Credits(~$0.125)/sec | 1.1875Credits(~$0.1188)/sec | 1.125Credits(~$0.1125)/sec | 1.5625Credits(~$0.1563)/sec | 20% | |
| 1080P+Sound+Voice | 1.5Credits(~$0.15)/sec | 1.425Credits(~$0.1425)/sec | 1.35Credits(~$0.135)/sec | 1.875Credits(~$0.1875)/sec | 20% |
* Actual costs are subject to final output.
Call Kling 2.6 with one APIMart API key. Generate 5- or 10-second clips from text or a first frame, add a last frame or native audio in pro mode, and pay per second of output. It also supports camera control and dynamic masks.
50K+
Active Users
99.9%
Uptime
2x
Faster
—
Cost Savings
Call kling-v2-6 with one POST request. Generation is asynchronous: submit a task, then poll the task endpoint for the video URL.
Save the key you created above in the APIMART_API_KEY environment variable and send it as Authorization: Bearer <key> on every Kling API request.
POST /v1/videos/generations with model kling-v2-6, your prompt, mode, duration and aspect_ratio. Add image_urls for image to video, or audio: true in pro mode. The example.com URLs are placeholders: replace them with your own publicly accessible files. The task ID is in data[0].task_id.
Poll GET /v1/tasks/{task_id} until status is completed, then read the video URL from data.result.videos[0].url[0] and the final charge from cost. APIMart keeps results for 72 hours, so download the videos you want to keep.
See the Kling 2.6 API reference for every parameter, scenario and response field.
curl -X POST https://api.apimart.ai/v1/videos/generations \
-H "Authorization: Bearer $APIMART_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "kling-v2-6",
"prompt": "A barista pours latte art in a sunlit café, close-up, steam rising, soft clinking cups and café ambience",
"mode": "pro",
"duration": 5,
"aspect_ratio": "16:9",
"audio": true
}'import os
import time
import requests
API_BASE = "https://api.apimart.ai"
headers = {"Authorization": f"Bearer {os.environ['APIMART_API_KEY']}"}
# 1. Submit the generation task
payload = {
"model": "kling-v2-6",
"prompt": "A barista pours latte art in a sunlit café, close-up, steam rising, soft clinking cups and café ambience",
"mode": "pro",
"duration": 5,
"aspect_ratio": "16:9",
"audio": True
}
resp = requests.post(f"{API_BASE}/v1/videos/generations", headers=headers, json=payload, timeout=60)
resp.raise_for_status()
task_id = resp.json()["data"][0]["task_id"]
# 2. Poll the task until it finishes
for _ in range(200):
task_resp = requests.get(f"{API_BASE}/v1/tasks/{task_id}", headers=headers, timeout=30)
task_resp.raise_for_status()
task = task_resp.json()["data"]
if task["status"] == "completed":
print(task["result"]["videos"][0]["url"][0])
break
if task["status"] == "failed":
raise RuntimeError(task.get("error", {}).get("message", "generation failed"))
time.sleep(10)
else:
raise TimeoutError(f"task {task_id} did not finish in time; continue GET polling with this task ID")curl -X POST https://api.apimart.ai/v1/videos/generations \
-H "Authorization: Bearer $APIMART_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "kling-v2-6",
"prompt": "The flower bud in the first frame slowly opens into the full bloom of the last frame, smooth time-lapse",
"mode": "pro",
"duration": 5,
"image_urls": [
"https://example.com/frame-start.jpg",
"https://example.com/frame-end.jpg"
]
}'TASK_ID="task_xxx" # replace with the task_id returned by the POST request
curl "https://api.apimart.ai/v1/tasks/$TASK_ID" \
-H "Authorization: Bearer $APIMART_API_KEY"| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
model | string | Required | Default: kling-v2-6 | Use kling-v2-6 for Kling 2.6. |
prompt | string | Required | Default: — | Scene, action and style, up to 2,500 characters. |
negative_prompt | string | Optional | Default: — | Content to exclude, for example "blurry, low quality, distorted". |
mode | string | Optional | Default: std | std (720p, silent only) or pro (1080p; required for audio and last frames). |
duration | integer | Optional | Default: 5 | 5 or 10 seconds. Send a number, not a quoted string. |
aspect_ratio | string | Optional | Default: 16:9 | 16:9, 9:16 or 1:1. For image to video, the input image may override it. |
image_urls | array | Optional | Default: — | 1 public image URL as the first frame, or 2 as first and last frames (pro only, not with audio). |
audio | boolean | Optional | Default: false | Generate native audio. Pro mode only; cannot be combined with a last frame. |
watermark | boolean | Optional | Default: — | Add a watermark to the output. |
nsfw_check | boolean | Optional | Default: false | Review the prompt and input images with omni-moderation-latest before submission. |
Compare Kling video models on APIMart. Check each model’s availability, capabilities and pricing on its own page.
| Model | Best for | Resolution | Duration |
|---|---|---|---|
| Kling 4.0 API | Text, frame and multimodal generation, video editing and extension, always with stereo audio | 720P / 1080P | 3–30 s |
| Kling 3.0 API | Cinematic text-to-video and image-to-video with first/last-frame control and multi-shot prompts | 720P / 1080P / 4K | 3–15 s |
| Kling 3.0 Omni API | All-in-one generation from text, images and video, with reference roles and video editing | 720P / 1080P / 4K | 3–15 s |
| Kling 3.0 Turbo API | Speed-optimized text-to-video and first-frame image-to-video | 720P / 1080P | 3–15 s |
| Kling Video O1 API | One model for text-to-video, image references, first/last frames and video editing | 720P / 1080P | 5 s / 10 s |
| Kling 2.6 APIThis page | Native audio (pro mode), dynamic masks and camera control | 720P / 1080P | 5 s / 10 s |
| Kling Motion Control 2.6 API | Transfer motion from a reference video onto the subject of your image | 720P / 1080P | Follows reference video |
| Kling 3.0 Motion Control API | Newer Kling 3.0 generation of reference-video motion transfer | 720P / 1080P | Follows reference video |
Guides, comparisons and pricing analysis from the APIMart blog.
Every feature below matches the kling-v2-6 parameters in the APIMart docs.
Creative video production across industries
Start generating videos in three steps
Register on APIMart and create your API key.
Experiment with audio, camera control, and dynamic masks in our Playground.
Follow our API documentation to integrate video generation into your products.
Real feedback from developers and creators
“The audio generation is a game-changer. We use it for all our social media video ads now — the synchronized sound effects really boost engagement.”
Sarah Johnson
Creative Director
“The camera control feature gives us precise cinematic movements. Combined with the great cost-performance ratio, it's our go-to for production work.”
James Liu
Senior Developer
Modes, audio, frames, pricing and API integration.
The Kling 2.6 API gives you Kuaishou's Kling 2.6 video model through APIMart with model ID kling-v2-6. It turns a text prompt or a first-frame image into a 5- or 10-second clip, with native audio and last-frame control available in pro mode.
std renders 720p, produces silent video only and accepts one first-frame image. pro renders 1080p and supports native audio and a last frame. Pro has a higher per-second rate; see the pricing table on this page.
Set audio to true together with mode pro. The model generates sound along with the video. Audio is not available in std mode and cannot be combined with a last frame in the same request.
duration is 5 or 10 seconds (default 5). aspect_ratio is 16:9, 9:16 or 1:1; for image-to-video the input image may override it.
Up to two. One image is used as the first frame. Two images become the first and last frame, which requires pro mode with audio turned off.
Dynamic masks let you define specific motion trajectories for objects in the scene, while camera control adjusts the virtual camera's movement (pan, tilt, zoom, etc.). You can combine both in a single request to achieve precise control over both subject motion and camera perspective simultaneously.
Kling 2.6 is billed per second of generated video. The rate depends on the mode and on whether audio is on; the pricing table on this page shows the live price per second for each option. Multiply it by 5 or 10 seconds to get the cost of one clip. You only pay for successful requests.
No. There is no free quota for the Kling 2.6 API (kling-v2-6) on APIMart. Billing is pay-as-you-go per second of generated video, and you only pay for successful requests. Gold member prices are 20% off, Platinum and Diamond members save up to 28%, and this page's live table always shows current pricing.
Sign up for APIMart, open the API Keys page in your dashboard and create a new key. The same key calls this Kuaishou model and every other model on the platform, with pay-as-you-go billing and no subscription.
Yes. Prices shown on this page are Gold member prices, already 20% off. Platinum and Diamond members save even more, up to 28%, and you only pay for successful requests.
Send POST /v1/videos/generations with model kling-v2-6, a prompt and optional mode, duration, aspect_ratio, image_urls and audio. The response returns a task ID; poll GET /v1/tasks/{task_id} until the status is completed, then download the video within 72 hours. The API example on this page has ready-to-run code.
Kling 2.6 is the lower-cost choice for 5- or 10-second clips at 720p or 1080p. Kling 3.0 adds 3–15 second durations, 4K output, multi-shot prompts and audio in every mode. Compare all Kling API models in the family table on this page.
Explore more models in the same category.

Seedance 1.5 Pro
Experience the power of Seedance 1.5 Pro video generation technology. Compared to previous Seedance versions, it offers smoother motion, higher image quality, and stronger instruction following capabilities.

Seedance 1.0 Pro Fast
Experience Seedance 1.0 Pro Fast video generation technology. Generate stunning videos with logical motion and high fidelity from text or images.

Wan 2.6
WAN 2.6 API on APIMart is the latest generation AI video model, offering superior visual quality, high motion coherence, and professional-grade performance.

MiniMax Hailuo 02
MiniMax Hailuo 02 on APIMart is the latest generation AI video model, offering superior visual quality, high motion coherence, and professional-grade performance.