Kling 3.0

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

Kling 3.0 delivers high-quality text-to-video generation with smooth motion, cinematic visuals, accurate prompt adherence, and native audio for ready-to-share clips. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

Examples

Parameters

NameTypeDefaultConstraintsDescription
promptPrompttextarea≤ 5000 charsThe positive prompt for the generation.
negative_promptNegative Prompttextarea≤ 5000 charsThe negative prompt for the generation.
durationDurationselect53 | 4 | 5 | 6 | 7 | 8 | 9 | 10 | …The duration of the generated media in seconds.
resolutionGeneration Modeselect720P720P | 1080P | 4K
aspect_ratioAspect Ratioselect16:916:9 | 9:16 | 1:1The aspect ratio of the generated video.
cfg_scaleCfg Scaleslider0.50 ~ 1 · step 0.01Flexibility in video generation; The higher the value, the lower the model's degree of flexibility, and the stronger the relevance to the user's prompt.
soundSoundbooleanfalseWhether sound is generated simultaneously when generating a video.
element_listElement Listarray<object>0–3 itemsElement reference list.
element_idElement IdtextThe prompt for this shot.
multi_shotMulti ShotbooleanWhether to generate multi-shot video When true: the prompt parameter is invalid. When false: the shot_type and multi_prompt parameters are invalid
shot_typeShot Typeselectcustomize | intelligenceShot type for the generation.
multi_promptMulti Promptarray<object>List of multi-prompt elements for the generation.
durationDurationnumber5The duration of this shot in seconds.
promptPrompttextThe prompt for this shot.

API

Call this model through one unified REST API. Get a key on the API Keys page.

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);

Documentation

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
4KMuted0.1680
4KWith Audio0.2800

💡 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.

Related models

xAI Grok Imagine Video v1.5 Text to Video
Text to VideoX Ai

xAI Grok Imagine Video v1.5 Text to Video

Generate 1-15 second videos from text prompts at 480p, 720p, or 1080p.

from $0.840 / per run
MiniMax H3 Text to Video
Text to VideoMinimax

MiniMax H3 Text to Video

MiniMax H3 Text to Video generates coherent 2K videos from text prompts, with flexible 4-15 second duration and six selectable aspect ratios for cinematic scenes, creative videos, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

from $0.650 / per run
Kling Omni Video O3 Standard Text-To-Video
Text to VideoKling

Kling Omni Video O3 Standard Text-To-Video

Kling Omni Video O3 is Kuaishou's advanced unified multi-modal video model with MVL (Multi-modal Visual Language) technology. Text-to-Video mode generates cinematic videos from text prompts with subject consistency, natural physics simulation, and precise semantic understanding. Supports audio generation. Ready-to-use REST API, best performance, no coldstarts, affordable pricing.

from $0.420 / per run
Kling Omni Video O1 Text-To-Video
Text to VideoKling

Kling Omni Video O1 Text-To-Video

Kling Omni Video O1 is Kuaishou's first unified multi-modal video model with MVL (Multi-modal Visual Language) technology. Text-to-Video mode generates cinematic videos from text prompts with subject consistency, natural physics simulation, and precise semantic understanding. Ready-to-use REST API, best performance, no coldstarts, affordable pricing.

from $0.420 / per run
Kling V2.6 Text to Video API
Text to VideoKling

Kling V2.6 Text to Video API

Kling 2.6 delivers top-tier text-to-video generation with smooth motion, cinematic visuals, strong prompt adherence, and native audio for ready-to-share clips. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

from $0.210 / per run
Gemini Omni Flash Text to Video API
Text to VideoGoogle

Gemini Omni Flash Text to Video API

Gemini Omni Flash Text to Video creates short AI videos with synchronized audio from text prompts, combining visual generation and audio output for fast multimodal video creation. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

from $1.04 / per run
Seedance 2.0 Mini Text to Video
Text to VideoDoubao

Seedance 2.0 Mini Text to Video

Seedance 2.0 Mini Text to Video is ByteDance's faster, lower-cost text-to-video model for cinematic multi-shot videos. It generates narrative sequences from text prompts with AI camera control, consistent characters across scenes, 480P / 720P / 1080P / 4K output, 4-15s duration, and flexible aspect ratios. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

from $0.380 / per run
Seedance 2.5 Text-to-Video
Text to VideoDoubao

Seedance 2.5 Text-to-Video

Seedance 2.5 delivers next-generation high-quality video generation with text-to-video, multiple aspect ratios, 480p/720p/1080p resolution options, and AI-synchronized audio generation. It features improved prompt following, camera control, and motion quality.

from $1.16 / per run
Kling 3.0 API — Pricing, Playground & Docs | NamiFusion