参数
| 参数名 | 描述 | 类型 | 必填 | 枚举值 |
|---|---|---|---|---|
| prompt | Video generation prompt. | string | 是 | - |
| aspect_ratio | Video aspect ratio. | string | 否 | 16:9, 9:16, 1:1 |
| duration | Video duration in seconds. Public API accepts integer values. Valid values are 3-15 when videos is not supplied. |
integer | 否 | 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 |
| images | Optional reference image list. | string[] | 否 | - |
| mode | Generation mode. | string | 否 | std, pro |
| multi_shot | Enable intelligent multi-shot generation. | boolean | 否 | true, false |
| shot_type | Required when multi_shot is true. Only intelligence is supported in the public API. |
string | 否 | intelligence |
| sound | Audio generation switch. Must remain off whenever videos is provided. |
string | 否 | on, off |
| videos | Optional reference video list. When provided, sound must be off and duration must be omitted. |
string[] | 否 | - |
价格
单位: $/sec
| 维度 | 价格 |
|---|---|
| mode: std / sound: on | 0.1500 |
| mode: pro / sound: on | 0.1900 |
| mode: std / sound: off | 0.1700 |
| mode: pro / sound: off | 0.2300 |
相关模型
- kling/kling-v3-t2i: [Core Function] Kling V3 T2I is the flagship text-to-image generation model. [Strengths] It delivers state-of-the-art aesthetic quality, high-resolution outputs (up to 2K), and exceptional prompt adherence. [Best For] Highly recommended for: professional concept art, photorealistic portraits, and high-fidelity image generation. [Limitations] Do NOT use this model if you need to strictly reference or edit an existing image. [Routing] Use this as the default model for all text-to-image requests on the Kling platform.
- kling/kling-v3-t2v: [Core Function] Kling V3 T2V is the next-generation text-to-video base model. [Strengths] It natively supports generating ultra-long 15-second videos, 4K resolution, and synchronized native audio directly from text. [Best For] Highly recommended for: high-end cinematic creation, 4K video generation, and creating long-form scenes with integrated sound. [Limitations] Do NOT use this model if you need complex multi-shot narratives or deep physics reasoning; use V3 Omni or Video O1 respectively. [Routing] Use this model by default for high-quality text-to-video tasks that require up to 15 seconds, 4K resolution, or native audio without reference images.
- kling/kling-v3-i2i: [Core Function] Kling V3 I2I is the flagship image-to-image editing model. [Strengths] It provides high-quality style transfer and image modification up to 2K resolution based on a reference image. [Best For] Highly recommended for: high-res style transfer and general image editing. [Limitations] Do NOT use this model for complex multi-element fusion (use Omni Image instead). [Routing] Use this by default for standard image-to-image tasks.
- kling/kling-v3-omni-image: [Core Function] Kling V3 Omni Image is a unified multimodal image generation endpoint. [Strengths] It supports complex element extraction and character consistency, allowing you to generate series of images with consistent subjects/elements using
<image_N>syntax. [Best For] Highly recommended for: generating comic books, character design sheets, and maintaining strict visual consistency across multiple generations. [Limitations] Do NOT use this model for simple, single-shot text-to-image tasks. [Routing] Use this model when the user requests ‘consistent characters’ or needs to fuse multiple image elements into a new scene. - kling/kling-v3-i2v: [Core Function] Kling V3 I2V is the next-generation image-to-video model. [Strengths] It transforms static images into video with support for 4K resolution, 15-second durations, and native audio, providing superior motion and character expressiveness. [Best For] Highly recommended for: animating concept art, bringing portraits to life in 4K, and generating long 15s scenes from a single frame. [Limitations] Do NOT use this model if you need multimodal reference elements (like character consistency across shots) or multi-shot generation; use V3 Omni instead. [Routing] Use this model by default for high-quality single-image-to-video tasks.
