Generate 3–15 second video from text or reference frames with the Kling models currently available through LinkModel.
Kling AI is Kuaishou's video-generation family. Kuaishou launched Kling 3.0 with text-to-video, image-to-video, reference-led generation, up to 15-second output, and multilingual native audio, and later announced native 4K for the broader 3.0 series. LinkModel only presents models and request options that appear in its live catalog; the current standard Kling V3 endpoint exposes up to 1080P.
The current Kling V3 endpoint supports text-to-video and first- or last-frame image-to-video workflows at 720P or 1080P, with 3–15 second duration, three aspect ratios, and optional audio. This catalog only shows Kling models currently available through LinkModel.
1 model listed
Compare live Kling models for prompt-led video, reference-frame animation, output duration, resolution, aspect ratio, audio, and model-specific controls.
Kling V3Kuaishou's unified multimodal video model with native 4K/60fps output, AI Director multi-shot storyboarding, multilingual native audio, and ultimate character consistency, unifying video understanding, generation, and editing in one workflow.
Use Kling V3 when you need configurable text-to-video or image-to-video with optional audio and precise duration, resolution, and frame controls. Recommendations only appear when the matching model is live in LinkModel's catalog.
The current Kling V3 endpoint supports prompt-led video plus optional first and last reference frames, audio, duration, resolution, and aspect-ratio controls.
720P or 1080P · 3–15 seconds · optional audio · first and last frames
Official source ↗Use live Kling models for campaign video, product motion, vertical social content, and reference-guided creative production from one account.
Generate short campaign scenes with explicit duration, landscape or vertical framing, optional audio, and a reviewable production cost.
Animate a product, character, or key visual from a first frame and optionally guide the ending composition with a last frame.
Create 9:16, 1:1, or 16:9 variations while persisting task IDs and measuring spend per accepted clip.
Access supported Kling video models alongside other providers while keeping credentials, asynchronous tasks, usage, and billing in one workflow.
Use one LinkModel API key for supported Kling models and versions as they appear in the live catalog.
Compare Kling with Seedance, Hailuo, Wan, Sora, and other live video families without maintaining another provider account and billing flow.
Track asynchronous task status and pay-as-you-go charges in one account while recording the settings used for each generated clip.
Use one LinkModel credential to select a live Kling model, submit an asynchronous video task, and monitor it from the same account.
Create a LinkModel API key and use it to authenticate requests for the Kling models enabled for your account.
Open the model page to confirm the current ID, price, resolution, duration, aspect ratio, audio option, and whether you are sending text or reference frames.
Send the generation request, persist the returned task ID, and poll the asynchronous task until the video succeeds or fails.
2026-06-26
2026-07-14
2026-07-03
2026-07-03
FAQ
Model capabilities and selection guidance are reviewed against the official Kling sources listed here.
Editorial content reviewed: September 1, 2026
Kling and its model names belong to their respective owners. LinkModel is an independent API aggregation platform and does not imply a formal relationship.