Kling O3 API
Kling O3 (V3 Omni) next-generation video model with text-to-video, image-to-video, reference-to-video, video editing, and custom element creation. Supports 3-15 second videos with per-second billing.
No sample available
Click Generate to see preview
History
最多保留20条0 运行中 · 0 已完成
Billing Rules
- •Price shown is per second
- •Duration range: 3-15 seconds
- •Total = price/second × duration
Pricing
| Model | Mode | Quality | Sound | Price |
|---|---|---|---|---|
| Kling O3 Text to Video | Video Generation | 720p | Off | Popular $0.0750/ second(5.4 Credits) |
| Kling O3 Text to Video | Video Generation | 720p | On | $0.1001/ second(7.2036 Credits) |
| Kling O3 Text to Video | Video Generation | 1080p | Off | $0.1001/ second(7.2036 Credits) |
| Kling O3 Text to Video | Video Generation | 1080p | On | $0.1250/ second(9.0018 Credits) |
If it's down, we automatically use the next cheapest available—ensuring 99.9% uptime at the best possible price.
面向新一代视频创作的 Kling O3 API
使用最新的 Kling V3 Omni 模型进行构建。从文本、图像或参考视频生成视频,并编辑现有素材——全部通过一个统一的 API 完成,支持 3-15 秒输出。

利用 Kling O3 API 可以构建什么?
为什么团队选择 Kling O3
Kling O3 采用最新的 V3 Omni 架构,在单一模型家族中提供四种专业模式——文生视频、图生视频、参考视频生成和视频编辑。
四种专业模式
文本、图像、参考和编辑模式覆盖完整的视频创作工作流。
最新 V3 Omni 架构
基于 Kling 最新一代架构,提供更高的质量和一致性。
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 O3 API
从输入到生产就绪视频的三个步骤。
选择模式
根据您的工作流需求,选择文生视频、图生视频、参考视频生成或视频编辑模式。
提交生成任务
发送带有提示词、图像或参考的请求。跟踪异步任务直到结果就绪。
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。
Kling O3 API 核心能力
新一代视频 AI,四种专业模式
文生视频生成
纯粹从文本描述生成视频。Kling O3 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 O3 以自然的运动和场景动态将其动画化。
参考视频引导
使用现有视频作为参考来引导新的生成。此模式有助于在多个输出之间保持视觉一致性和风格。
AI 视频编辑
使用 AI 驱动的工具编辑和转换现有素材。应用风格变化、场景调整和创意转换,无需手动编辑。
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。
V3 Omni 架构
基于 Kling 最新的 V3 Omni 基础架构,提供更好的视觉质量、更好的运动连贯性和更准确的提示词遵循。
常见问题
Everything you need to know about the product and billing.
API Reference
Select endpoint
Authentication
All APIs require Bearer Token authentication.
Authorization:
Bearer YOUR_API_KEY/v1/videos/generationsCreate Video
Kling O3 Text to Video (kling-o3-text-to-video) generates videos from text prompts using the V3 Omni model. Supports single-shot and multi-shot modes with optional 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
- Text-to-video mode: no image input required.
- Video duration: 3-15 seconds, billed per second.
- Pricing varies by quality and sound: 720p+off = 1.0x, 720p+on = 1.334x, 1080p+off = 1.334x, 1080p+on = 1.667x.
Request Parameters
modelstringRequiredDefault: kling-o3-text-to-videoVideo generation model name.
kling-o3-text-to-videopromptstringRequiredText prompt describing what kind of video to generate. When multi_shot=true and shot_type=customize, this can be empty (use multi_prompt instead).
Notes
- Max 2500 characters
A golden retriever running through a sunlit meadow, cinematic slow motion.durationintegerOptionalDefault: 5Specifies the generated video duration in seconds.
Notes
- Range: 3-15 seconds (integer)
- Base price: 5.4 credits per second
- Minimum billing: 3 seconds
5aspect_ratiostringOptionalVideo aspect ratio.
| Value | Description |
|---|---|
| 16:9 | Landscape video |
| 9:16 | Portrait video |
| 1:1 | Square video |
16:9qualitystringOptionalDefault: 720pVideo resolution quality. Affects billing multiplier.
| Value | Description |
|---|---|
| 720p | Standard 720P (1.0x base) |
| 1080p | High quality 1080P (1.334x base) |
720psoundstringOptionalDefault: offSound effect control. Affects billing multiplier.
| Value | Description |
|---|---|
| off | No sound effects (1.0x) |
| on | Generate sound effects (1.334x) |
Notes
- Combined multiplier: 720p+off=1.0x, 720p+on=1.334x, 1080p+off=1.334x, 1080p+on=1.667x
offcallback_urlstringOptionalHTTPS 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
https://your-domain.com/webhooks/video-task-completedmodel_params.multi_shotbooleanOptionalDefault: falseEnable multi-shot mode for generating videos with multiple camera angles or scenes.
Notes
- When enabled, shot_type and multi_prompt become relevant
truemodel_params.shot_typestringOptionalShot type for multi-shot mode. Required when multi_shot is true.
| Value | Description |
|---|---|
| customize | Custom per-shot prompts and durations |
Notes
- Only effective when multi_shot=true
customizemodel_params.multi_promptarrayOptionalPer-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
[{"index": 1, "prompt": "A person on a hilltop", "duration": "5"}, {"index": 2, "prompt": "Camera pulls back", "duration": "5"}]model_params.element_listarrayOptionalSubject library list for referencing pre-trained subjects in the video.
Notes
- Format: [{element_id: long}, ...]
- Max 7 subjects
- Reference subjects in prompt using <<<element_N>>> placeholder
[{"element_id": 123456}]model_params.watermark_infoobjectOptionalWatermark configuration for the generated video.
Notes
- Format: {enabled: boolean}
{"enabled": false}

