Seedance 2.0 API — 即将上线Get early access
EvoLink.AIEvoLink.AI

Kling 3.0 API

Kling 3.0 video model with text-to-video, image-to-video, and custom element creation. Supports 3-15 second videos with per-second billing.

Kling 3.0 Text to VideoKling 3.0 Image to Video

Upload first frame or end frame image to generate video

Estimated Cost (5s)
5.4 Credits
Sample Result

No sample available

0 (suggested: 2,000)

First frame image. At least one of first/end frame is required.

Click to upload or drag and drop

Supported formats: JPG, JPEG, PNG
Maximum file size: 10MB; Maximum files: 1

End-frame image (optional)

Click to upload or drag and drop

Supported formats: JPG, JPEG, PNG
Maximum file size: 10MB; Maximum files: 1

5s
3s15s

Click Generate to see preview

History

最多保留20条

0 运行中 · 0 已完成

您的生成历史将显示在这里

Billing Rules

  • •Price shown is per second
  • •Duration range: 3-15 seconds
  • •Total = price/second × duration

Pricing

Popular
Kling 3.0 Image to Video
Video Generation
Quality:720p
Sound:Off
Price:
$0.0750/ second
(5.4 Credits)
Kling 3.0 Image to Video
Video Generation
Quality:720p
Sound:On
Price:
$0.1125/ second
(8.1 Credits)
Kling 3.0 Image to Video
Video Generation
Quality:1080p
Sound:Off
Price:
$0.1000/ second
(7.1982 Credits)
Kling 3.0 Image to Video
Video Generation
Quality:1080p
Sound:On
Price:
$0.1500/ second
(10.8 Credits)

If it's down, we automatically use the next cheapest available—ensuring 99.9% uptime at the best possible price.

面向视频创作的 Kling 3.0 API

使用 Kling 3.0 模型进行构建。从文本或图像生成视频——通过一个统一的 API 完成，支持 3-15 秒输出。

Kling 3.0 视频功能展示

利用 Kling 3.0 API 可以构建什么？

文生视频创作

使用 Kling 3.0 直接从文本提示生成视频。用自然语言描述场景、动作和风格，让模型生成 3-15 秒的片段，适用于营销、社交媒体或创意项目。

开始创作
文生视频功能展示

图像驱动的视频生成

使用图像来引导视频生成。Kling 3.0 支持图生视频模式，让团队精确控制视觉风格、角色一致性和场景构图。

探索模式
图像驱动视频功能展示

多镜头和音效

创建复杂的多镜头视频，支持场景切换和 AI 生成的音效。Kling 3.0 支持自定义镜头序列和音频生成，为专业级视频输出提供支持。

立即体验
多镜头视频功能展示

为什么团队选择 Kling 3.0

Kling 3.0 在单一模型家族中提供文生视频和图生视频两种模式，价格有竞争力。

两种专业模式

文本和图像模式覆盖核心视频创作工作流。

3.0 架构

基于 Kling 3.0 基础架构，提供高质量视频生成。

灵活的 3-15 秒输出

生成 3 到 15 秒的视频，按秒计费。

如何集成 Kling 3.0 API

从输入到生产就绪视频的三个步骤。

1

选择模式

根据您的工作流需求，选择文生视频或图生视频模式。

2

提交生成任务

发送带有提示词或图像的请求。跟踪异步任务直到结果就绪。

3

评审与迭代

下载结果，比较变体，并复用相同的结构在不同营销活动中快速迭代。

查看 API 文档

Kling 3.0 API 核心能力

视频 AI，两种专业模式

文本

文生视频生成

纯粹从文本描述生成视频。Kling 3.0 解读自然语言提示，无需任何视觉输入即可生成动态视频内容。

图像

图生视频转换

将静态图像转换为动态视频。提供参考图像，让 Kling 3.0 以自然的运动和场景动态将其动画化。

多镜头

多镜头支持

创建复杂的多镜头视频，支持自定义场景切换、每镜头提示词和时长控制，满足专业视频制作需求。

音效

音效

为视频添加 AI 生成的音效。根据需要开启或关闭音效，音频生成定价透明。

计费

按秒计费

按秒计费，只为生成的内容付费。视频范围从 3 到 15 秒，让团队对每个项目都有精确的成本控制。

质量

720p 和 1080p 质量

在标准 720p 和高质量 1080p 输出分辨率之间选择，为特定用例平衡质量和成本。

常见问题

Everything you need to know about the product and billing.

Kling 3.0 API 通过 EvoLink 提供对 Kling 3.0 视频模型的访问。它支持两种模式：文生视频和图生视频。每种模式生成 3-15 秒的视频，按秒计费。请在 EvoLink 控制台查看当前定价和可用性。
Kling 3.0 提供两种模式：文生视频用于从提示词生成，图生视频用于将图像动画化。每种模式都针对不同的生产工作流进行了优化。
Kling 3.0 生成 3 到 15 秒的视频。在此范围内按秒计费。短于 3 秒的视频按 3 秒最低标准计费。此范围适用于社交媒体片段、广告和短视频内容。
Kling 3.0 使用按秒计费，基础价格为每秒 5.4 积分。价格因质量和音效而异：720p+关闭音效 = 1.0x，720p+开启音效 = 1.5x，1080p+关闭音效 = 1.333x，1080p+开启音效 = 2.0x。请在 EvoLink 控制台查看您所在用户组的具体定价。
Kling O3 (V3 Omni) 支持四种模式，包括参考视频生成和视频编辑，而 Kling 3.0 专注于文生视频和图生视频。3.0 与 O3 相比有略微不同的定价因子。
从清晰的主体开始，用简单的术语描述动作、氛围和设置。对于图生视频，提供高质量的参考图像。当您的提示词结构在不同运行中保持稳定时，一致性会提高。
限制、定价和可用模式由您的提供商和地区决定。请将 EvoLink 控制台和 API 响应作为事实来源。查看 API 文档以获取最新的约束条件和参数。
POST
/v1/videos/generations

Create Video

Kling 3.0 Image to Video (kling-v3-image-to-video) transforms static images into dynamic videos using the 3.0 model. Supports first frame, end frame, subject control, multi-shot, and sound effects.

Asynchronous processing mode, use the returned task ID to query status.

Generated video links are valid for 24 hours, please save them promptly.

Important Notes

  • At least one of image_start (first frame) or image_end (end frame) is required.
  • Image requirements: JPG/JPEG/PNG, ≤ 10MB, width/height ≥ 300px, aspect ratio 1:2.5 ~ 2.5:1.
  • Video duration: 3-15 seconds, billed per second.
  • Pricing varies by quality and sound: 720p+off = 1.0x, 720p+on = 1.5x, 1080p+off = 1.333x, 1080p+on = 2.0x.

Request Parameters

modelstringRequiredDefault: kling-v3-image-to-video

Video generation model name.

Examplekling-v3-image-to-video
promptstringOptional

Text prompt describing what kind of motion and video to generate.

Notes
  • Max 2500 characters
  • Optional for image-to-video
ExampleA gentle breeze moves through the scene, creating subtle motion and life.
image_startstringOptional

First-frame image URL. At least one of image_start or image_end must be provided.

Notes
  • JPG/JPEG/PNG format
  • Max size: 10MB
  • Width/height ≥ 300px, aspect ratio 1:2.5 ~ 2.5:1
Examplehttps://example.com/first-frame.jpg
image_endstringOptional

End-frame image URL. At least one of image_start or image_end must be provided.

Notes
  • Optional
  • Same format requirements as image_start
Examplehttps://example.com/end-frame.jpg
durationintegerOptionalDefault: 5

Specifies the generated video duration in seconds.

Notes
  • Range: 3-15 seconds (integer)
  • Base price: 5.4 credits per second
  • Minimum billing: 3 seconds
Example5
aspect_ratiostringOptional

Video aspect ratio. When a first-frame image is provided, this can be omitted (auto-adapts to image ratio).

ValueDescription
16:9Landscape video
9:16Portrait video
1:1Square video
Example16:9
qualitystringOptionalDefault: 720p

Video resolution quality. Affects billing multiplier.

ValueDescription
720pStandard 720P (1.0x base)
1080pHigh quality 1080P (1.333x base)
Example720p
soundstringOptionalDefault: off

Sound effect control. Affects billing multiplier.

ValueDescription
offNo sound effects (1.0x)
onGenerate sound effects (1.5x)
Notes
  • Combined multiplier: 720p+off=1.0x, 720p+on=1.5x, 1080p+off=1.333x, 1080p+on=2.0x
Exampleoff
callback_urlstringOptional

HTTPS callback address after task completion.

Notes
  • Triggered on completion, failure, or cancellation
  • HTTPS only, no internal IPs
  • Max length: 2048 chars
  • Timeout: 10s, Max 3 retries
Examplehttps://your-domain.com/webhooks/video-task-completed
model_params.multi_shotbooleanOptionalDefault: false

Enable multi-shot mode for generating videos with multiple camera angles or scenes.

Notes
  • When enabled, shot_type and multi_prompt become relevant
Exampletrue
model_params.shot_typestringOptional

Shot type for multi-shot mode. Required when multi_shot is true.

ValueDescription
customizeCustom per-shot prompts and durations
intelligenceAI auto-plans shots based on prompt
Notes
  • Only effective when multi_shot=true
Examplecustomize
model_params.multi_promptarrayOptional

Per-shot prompt array. Required when multi_shot=true and shot_type=customize. Each item defines a shot segment.

Notes
  • Format: [{index: number, prompt: string, duration: string}, ...]
  • Max 6 shots
  • Total duration of all shots should match the requested duration
  • When used, top-level prompt can be empty
Example[{"index": 1, "prompt": "Scene one", "duration": "5"}, {"index": 2, "prompt": "Scene two", "duration": "5"}]
model_params.element_listarrayOptional

Subject library list for referencing pre-trained subjects in the video.

Notes
  • Format: [{element_id: long}, ...]
  • Max 3 subjects
  • Reference subjects in prompt using <<<element_N>>> placeholder
Example[{"element_id": 123456}]
negative_promptstringOptional

Negative prompt describing what you don't want in the video.

Notes
  • Max 2500 characters
  • Optional
Exampleblurry, watermark, text, low quality
model_params.watermark_infoobjectOptional

Watermark configuration for the generated video.

Notes
  • Format: {enabled: boolean}
Example{"enabled": false}

Request Example (First Frame)

{
  "model": "kling-v3-image-to-video",
  "prompt": "A gentle breeze moves through the scene",
  "image_start": "https://example.com/portrait.jpg",
  "duration": 5,
  "quality": "720p"
}

Request Example (First + End Frame)

{
  "model": "kling-v3-image-to-video",
  "prompt": "Transition from day to night",
  "image_start": "https://example.com/day.jpg",
  "image_end": "https://example.com/night.jpg",
  "duration": 10,
  "quality": "1080p",
  "sound": "on"
}

Response Example

{
  "created": 1757169743,
  "id": "task-unified-1757169743-v3i2v",
  "model": "kling-v3-image-to-video",
  "object": "video.generation.task",
  "progress": 0,
  "status": "pending",
  "task_info": {
    "can_cancel": true,
    "estimated_time": 180,
    "video_duration": 5
  },
  "type": "video",
  "usage": {
    "billing_rule": "per_second",
    "credits_reserved": 27.0,
    "user_group": "default"
  }
}
Kling 3.0 API：视频生成 | EvoLink