kling-v1-6
kling
Kling 1.6 supports text, first or last frame, and multi-reference-image video generation.
- 上下文
- 待核
- 输入 / 1M tokens
- -
- 输出 / 1M tokens
- -
- 缓存读 / 1M
- -
- 缓存写 / 1M
- -
apiex模型广场
选择模型后可复制配置给 AI，也可以快速测试当前连接延迟。
重置筛选
全部 10文本 0图像 0音频 0视频 10
kling-v2-master
kling
Flagship of the 2.0 line, tuned for instruction following and cinematic aesthetics, with stylized effect presets. Outputs 1080p only.
- 上下文
- 待核
- 输入 / 1M tokens
- -
- 输出 / 1M tokens
- -
- 缓存读 / 1M
- -
- 缓存写 / 1M
- -
kling-v2-1
kling
Kling 2.1 image-to-video generation supports first and last frame control.
- 上下文
- 待核
- 输入 / 1M tokens
- -
- 输出 / 1M tokens
- -
- 缓存读 / 1M
- -
- 缓存写 / 1M
- -
kling-v2-1-master
kling
Quality-oriented tier of the 2.1 line, tuned for motion performance and semantic responsiveness. Supports text-to-video and image-to-video, suited for single-shot clips.
- 上下文
- 待核
- 输入 / 1M tokens
- -
- 输出 / 1M tokens
- -
- 缓存读 / 1M
- -
- 缓存写 / 1M
- -
kling-v2-5-turbo
kling
Cost-efficient tier in the 2.5 generation, with improved prompt adherence and physics under large-amplitude motion. Outputs silent 5- or 10-second clips.
- 上下文
- 待核
- 输入 / 1M tokens
- -
- 输出 / 1M tokens
- -
- 缓存读 / 1M
- -
- 缓存写 / 1M
- -
kling-2.6
kling
First version to add native audio, producing visuals, voiceover, sound effects, and ambience in one pass. Suited for finished clips up to 10 seconds.
- 上下文
- 待核
- 输入 / 1M tokens
- -
- 输出 / 1M tokens
- -
- 缓存读 / 1M
- -
- 缓存写 / 1M
- -
kling-3.0
kling
Core model of the 3.0 line, with first- and last-frame control, multi-shot storytelling, and native audio produced in the same pass. Suited for finished short-form work.
- 上下文
- 待核
- 输入 / 1M tokens
- -
- 输出 / 1M tokens
- -
- 缓存读 / 1M
- -
- 缓存写 / 1M
- -
kling-v3-omni
kling
Fully multimodal variant of the 3.0 line, accepting text, image, and video references in a single generation, with voice-driven characters and native audio.
- 上下文
- 待核
- 输入 / 1M tokens
- -
- 输出 / 1M tokens
- -
- 缓存读 / 1M
- -
- 缓存写 / 1M
- -
kling-3.0-turbo
kling
Speed-and-cost tier of the 3.0 line, covering text-to-video and first-frame image-to-video with multi-shot output. Suited for high-volume production.
- 上下文
- 待核
- 输入 / 1M tokens
- -
- 输出 / 1M tokens
- -
- 缓存读 / 1M
- -
- 缓存写 / 1M
- -
kling-o1
kling
Cinematic-oriented model with first- and last-frame control and video reference input, including edits driven by an existing clip. Suited for narrative shot sequences.
- 上下文
- 待核
- 输入 / 1M tokens
- -
- 输出 / 1M tokens
- -
- 缓存读 / 1M
- -
- 缓存写 / 1M
- -
需要完整模型清单或企业接入方案？进入控制台