apiex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。
kling
The oldest generation still available, limited to image-to-video with first- and last-frame control and no multi-image reference. Suited for basic, cost-sensitive clip generation.
kling
Kling 1.6 supports text, first or last frame, and multi-reference-image video generation.
kling
Flagship of the 2.0 line, tuned for instruction following and cinematic aesthetics, with stylized effect presets. Outputs 1080p only.
kling
Kling 2.1 image-to-video generation supports first and last frame control.
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.
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.
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.
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.
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.
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.
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.