cloudflareWorkersAI/klingai/kling-v4
Kling 4.0 is Kling AI's video generation model for text-to-video and multi-keyframe image-to-video, producing up to 30 seconds of 720p or 1080p video from prompts of up to 26,000 characters and up to 10 keyframes.
- Input modalities
- text
- Output modalities
- video
- Capabilities
- videoOutput
cloudflareWorkersAI/klingai/kling-v4-flash
Kling 4.0 Flash is Kling AI's fast text-to-video model, producing 3 to 20 seconds of 720p video from prompts of up to 26,000 characters.
- Input modalities
- text
- Output modalities
- video
- Capabilities
- videoOutput
cloudflareWorkersAI/klingai/kling-v3-image
Kling V3 Image is Kling AI's text-to-image model for photorealistic image generation.
- Input modalities
- text, image
- Output modalities
- image
- Capabilities
- imageOutput, multimodal, visionInput
cheaperInference/kling-v2.5-turbo-i2v
- Output modalities
- video
- Capabilities
- videoOutput, visionInput
cheaperInference/kling-v2.5-turbo-t2v
- Output modalities
- video
- Capabilities
- videoOutput, visionInput
cheaperInference/kling-v2.6-i2v
- Output modalities
- video
- Capabilities
- videoOutput, visionInput
vercelAIGatewayCatalog/klingai/kling-v2.6-motion-control
Kling 2.6 introduces a groundbreaking "Native Audio" capability, enabling the generation of complete videos in a single go, including natural voice, action sound effects, and environmental ambient sounds, providing an immersive "what you see if what you hear" experience.
- Input modalities
- text
- Output modalities
- video
- Capabilities
- videoOutput
cheaperInference/kling-v2.6-t2v
- Output modalities
- video
- Capabilities
- videoOutput, visionInput
cheaperInference/kling-v3.0-i2v
- Output modalities
- video
- Capabilities
- videoOutput, visionInput
vercelAIGatewayCatalog/klingai/kling-v3.0-i2v
Build upon an All-in-One product framework, the Kling 3.0 model series supports full multimodal input and output spanning text, images, audio, and video, bringing the understanding, generation, and editing of video together in one streamlined AI workflow. The models integrate mul
- Input modalities
- text
- Output modalities
- video
Benchmarks
- Vercel AI Gateway: 7.891%
vercelAIGatewayCatalog/klingai/kling-v3.0-motion-control
Kling 3.0 delivers a major leap in character fidelity for motion-driven generation, with stable facial features across multi-angle and long-duration motion, accurate complex emotions from multi-image face references, identity preservation through partial occlusions (hats, hands,
- Input modalities
- text
- Output modalities
- video
- Capabilities
- videoOutput
cheaperInference/kling-v3.0-t2v
- Output modalities
- video
- Capabilities
- videoOutput, visionInput