Kling 3.0

kwaivgi/kling-v3.0/text-to-video

kwaivgi/kling-v3.0/text-to-video. Выбирайте API моделей для изображений, видео и замены лиц. Испытайте модель и подключите ее через единый REST API.

Похожие модели

Все параметры, схема вывода и актуальные цены

Маркетплейс API моделей ИИОдна платформа для всегоСамый популярныйУсловияВыбирайте API моделей для изображений, видео и замены лиц. Испытайте модель и подключите ее через единый REST API.
promptPrompttextarea—≤ 5000 chars
negative_promptNegative Prompttextarea—≤ 5000 chars
durationDurationselect53 | 4 | 5 | 6 | 7 | 8 | 9 | 10 | …
resolutionGeneration Modeselect720P720P | 1080P | 4K
aspect_ratioAspect Ratioselect16:916:9 | 9:16 | 1:1
cfg_scaleCfg Scaleslider0.50 ~ 1 · step 0.01
soundSoundbooleanfalse—
element_listElement Listarray<object>—0–3 items
↳element_idElement Idtext——
multi_shotMulti Shotboolean——
shot_typeShot Typeselect—customize | intelligence
multi_promptMulti Promptarray<object>——
↳durationDurationnumber5—
↳promptPrompttext——

Все параметры, схема вывода и актуальные цены

ПодробнееОдна платформа для всегоВыбирайте API моделей для изображений, видео и замены лиц. Испытайте модель и подключите ее через единый REST API.
videosarray<string>

API

Выбирайте API моделей для изображений, видео и замены лиц. Испытайте модель и подключите ее через единый REST API.

cURL
# 1) Submit — returns { "task_uuid": "..." }
curl -X POST "https://www.namifusion.com/api/v1/marketplace/run/kwaivgi/kling-v3.0/text-to-video" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "input": {
    "prompt": "A futuristic cityscape at sunset with flying cars and glowing skyscrapers.",
    "negative_prompt": "Crowded streets, dull colors, and broken buildings.",
    "duration": 10,
    "resolution": "720P",
    "aspect_ratio": "16:9",
    "cfg_scale": 0.7,
    "sound": true,
    "shot_type": "intelligence"
  }
}'

# 2) Poll until status is "completed", then read the output URLs
curl "https://www.namifusion.com/api/v1/marketplace/run/tasks/TASK_UUID" \
  -H "Authorization: Bearer YOUR_API_KEY"
Python
import time, requests

API_KEY = "YOUR_API_KEY"
HEADERS = {"Authorization": f"Bearer {API_KEY}"}

# 1) Submit
resp = requests.post(
    "https://www.namifusion.com/api/v1/marketplace/run/kwaivgi/kling-v3.0/text-to-video",
    headers=HEADERS,
    json={
        "input": {
            "prompt": "A futuristic cityscape at sunset with flying cars and glowing skyscrapers.",
            "negative_prompt": "Crowded streets, dull colors, and broken buildings.",
            "duration": 10,
            "resolution": "720P",
            "aspect_ratio": "16:9",
            "cfg_scale": 0.7,
            "sound": True,
            "shot_type": "intelligence"
        }
    },
)
resp.raise_for_status()  # 401/402/429/5xx stop here instead of polling a bad task
task = resp.json()

# 2) Poll until a terminal state (completed / failed / cancelled).
#    This model is allowed up to 300s server-side.
deadline = time.time() + 360
while task.get("status") not in ("completed", "failed", "cancelled"):
    if time.time() > deadline:
        raise TimeoutError(f"still {task.get('status')} — keep the task_uuid and poll later")
    time.sleep(3)
    poll = requests.get(f"https://www.namifusion.com/api/v1/marketplace/run/tasks/{task['task_uuid']}", headers=HEADERS)
    poll.raise_for_status()
    task = poll.json()

print(task["status"], task.get("output"))
JavaScript
const API_KEY = "YOUR_API_KEY";
const HEADERS = { Authorization: `Bearer ${API_KEY}` };

// 1) Submit
const resp = await fetch("https://www.namifusion.com/api/v1/marketplace/run/kwaivgi/kling-v3.0/text-to-video", {
  method: "POST",
  headers: { ...HEADERS, "Content-Type": "application/json" },
  body: JSON.stringify({
    "input": {
      "prompt": "A futuristic cityscape at sunset with flying cars and glowing skyscrapers.",
      "negative_prompt": "Crowded streets, dull colors, and broken buildings.",
      "duration": 10,
      "resolution": "720P",
      "aspect_ratio": "16:9",
      "cfg_scale": 0.7,
      "sound": true,
      "shot_type": "intelligence"
    }
  }),
});
if (!resp.ok) throw new Error(`submit failed: ${resp.status} ${await resp.text()}`);
let task = await resp.json();

// 2) Poll until a terminal state (completed / failed / cancelled).
//    This model is allowed up to 300s server-side.
const deadline = Date.now() + 360 * 1000;
while (!["completed", "failed", "cancelled"].includes(task.status)) {
  if (Date.now() > deadline) throw new Error(`still ${task.status} — keep the task_uuid and poll later`);
  await new Promise((r) => setTimeout(r, 3000));
  const poll = await fetch(`https://www.namifusion.com/api/v1/marketplace/run/tasks/${task.task_uuid}`, { headers: HEADERS });
  if (!poll.ok) throw new Error(`poll failed: ${poll.status}`);
  task = await poll.json();
}

console.log(task.status, task.output);

Документация API

Kling 3.0 Standard

High-quality text-to-video generation with cinematic visuals and synchronized audio

Kling 3.0 Standard is a cost-efficient text-to-video model designed for smooth motion, cinematic visuals, and accurate prompt adherence. With flexible duration options, multiple aspect ratios, and optional synchronized sound, it delivers ready-to-share clips at affordable pricing. The model ensures high performance with no cold starts and is accessible via a REST inference API.


🚀 Key Features

  • Cinematic Visuals: Generate videos with smooth motion and high-quality visuals directly from text prompts.
  • Flexible Duration: Create clips ranging from 3 to 15 seconds to suit various production needs.
  • Multiple Aspect Ratios: Supports 16:9 (landscape), 9:16 (portrait), and 1:1 (square) formats for diverse platforms.
  • Synchronized Audio: Optionally generate synchronized sound alongside the video for immersive experiences.
  • Precise Prompt Control: Utilize negative prompts and CFG scale for fine-tuned output.
  • Multi-Prompt Support: Chain multiple prompts for scene transitions and consistent storytelling.

🛠️ Technical Specifications

ParameterTypeDefault ValueRange/OptionsDescription
PromptString--Text description of the scene, motion, camera style, and atmosphere.
Negative PromptString--Elements to exclude from the video.
DurationInteger53–15 secondsLength of the generated video.
Aspect RatioString16:916:9, 9:16, 1:1Output format for the video.
CFG ScaleNumber0.50.0–1.0Prompt adherence strength; higher values increase relevance to the prompt.
SoundBooleanDisabledEnabled/DisabledGenerate synchronized sound alongside the video.
Shot TypeStringCustomizeCustomize, IntelligentEditing mode; customize for manual control, intelligent for auto-detection.
Multi-PromptArray--Additional prompt segments for scene transitions and progressions.
Element ListArray--Reference list of visual elements for consistency.

💰 Pricing

ResolutionAttributePrice per Second (USD)
720PMuted0.0840
720PWith Audio0.1260
1080PMuted0.1120
1080PWith Audio0.1680
4KMuted0.4200
4KWith Audio0.4200

💡 Best Use Cases

  • Social Media Content: Generate portrait or square clips for TikTok, Reels, and Shorts at scale.
  • Concept Visualization: Quickly bring creative ideas and moods to life from text descriptions.
  • Marketing & Advertising: Produce promotional video content without a film crew.
  • Prototyping: Test visual ideas and prompt variations at Standard pricing before committing to Pro.

🔗 Related Models

  • Kling V3.0 Pro Text-to-Video: Maximum quality with Pro-tier capabilities.
  • Kling V3.0 Std Image-to-Video: Animate still images at Standard pricing.
  • Kling Video O3 Std Text-to-Video: Next-generation O3 Standard text-to-video.

Pro Tips

  • The more specific your prompt, the better — include camera angle, lighting style, character behavior, and atmosphere.
  • Use negative prompts to avoid common artifacts like blurry faces or unwanted motion.
  • Match aspect ratio to your platform: 16:9 for YouTube, 9:16 for TikTok, 1:1 for Instagram.
  • Enable sound for scenes with ambient environments, crowds, or action for a more immersive result.
  • Use shorter durations (3–5s) for rapid iteration, longer (10–15s) for final output.

Notes

  • Only the prompt is a required field; all other parameters are optional.
  • Duration range: minimum 3 seconds, maximum 15 seconds.
  • Sound generation increases cost by 1.5×.
  • Use the Kling Elements tool to generate visual elements and reference their IDs in your prompts.

Похожие модели

xAI Grok Imagine Video v1.5 Text to Video
Текст в видеоX Ai

xAI Grok Imagine Video v1.5 Text to Video

x-ai/grok-imagine-video-v1.5/text-to-video. Выбирайте API моделей для изображений, видео и замены лиц. Испытайте модель и подключите ее через единый REST API.

от $0.840 / за запуск
MiniMax H3 Text to Video
Текст в видеоMinimax

MiniMax H3 Text to Video

minimax/h3/text-to-video. Выбирайте API моделей для изображений, видео и замены лиц. Испытайте модель и подключите ее через единый REST API.

от $0.650 / за запуск
ltx-2.5/text-to-video
Текст в видеоLtx 2.5

ltx-2.5/text-to-video

ltx-2.5/text-to-video. Выбирайте API моделей для изображений, видео и замены лиц. Испытайте модель и подключите ее через единый REST API.

от $0.500 / за запуск
Kling Omni Video O3 Standard Text-To-Video
Текст в видеоKling

Kling Omni Video O3 Standard Text-To-Video

kwaivgi/kling-video-o3/text-to-video. Выбирайте API моделей для изображений, видео и замены лиц. Испытайте модель и подключите ее через единый REST API.

от $0.420 / за запуск
Kling V2.6 Text to Video API
Текст в видеоKling

Kling V2.6 Text to Video API

kwaivgi/kling-v2.6/text-to-video. Выбирайте API моделей для изображений, видео и замены лиц. Испытайте модель и подключите ее через единый REST API.

от $0.210 / за запуск
Gemini Omni Flash Text to Video API
Текст в видеоGoogle

Gemini Omni Flash Text to Video API

google/gemini-omni-flash/text-to-video. Выбирайте API моделей для изображений, видео и замены лиц. Испытайте модель и подключите ее через единый REST API.

от $1.04 / за запуск
Seedance 2.0 Mini Text to Video
Текст в видеоDoubao

Seedance 2.0 Mini Text to Video

doubao/seedance-2.0-mini/text-to-video. Выбирайте API моделей для изображений, видео и замены лиц. Испытайте модель и подключите ее через единый REST API.

от $0.378 / за запуск
Seedance 2.5 Text-to-Video
Текст в видеоDoubao

Seedance 2.5 Text-to-Video

doubao/seedance-2-5/text-to-video. Выбирайте API моделей для изображений, видео и замены лиц. Испытайте модель и подключите ее через единый REST API.

от $1.155 / за запуск