Task
Video generation models that output 4K resolution.
4K models cost more per clip than their 1080p counterparts, so a common workflow is to iterate on prompts with a cheaper tier and render the final version in 4K.
Every model below is available with the same API key. Open a model for its full parameter list and request examples.
| Model | Tasks | Billing | Price |
|---|---|---|---|
| Kling Video O3 4k Image to Video kwaivgi/kling-video/o3/4k/image-to-video | Provider cost | ≈ $2.10 per clip, reference price | |
| Kling Video O3 4k Reference to Video kwaivgi/kling-video/o3/4k/reference-to-video | Provider cost | ≈ $2.10 per clip, reference price | |
| Kling Video O3 4k Text to Video kwaivgi/kling-video/o3/4k/text-to-video | Provider cost | ≈ $2.10 per clip, reference price | |
| Kling Video V3 4k Image to Video kwaivgi/kling-video/v3/4k/image-to-video | Provider cost | ≈ $2.10 per clip, reference price | |
| Kling Video V3 4k Text to Video kwaivgi/kling-video/v3/4k/text-to-video | Provider cost | ≈ $2.10 per clip, reference price |
On ScalingTensor, the lowest-priced 4k video model is Kling Video O3 4k Image to Video, listed at about $2.10 per clip and billed at the provider's actual cost. Prices across the 5 models are listed in the table above.
ScalingTensor currently offers 5 4k video models: Kling Video O3 4k Image to Video, Kling Video O3 4k Reference to Video, Kling Video O3 4k Text to Video, Kling Video V3 4k Image to Video and Kling Video V3 4k Text to Video.
Send POST /api/media/generate with the model ID and its params, authenticated with your apiKey header. The response contains a jobId; poll GET /api/media/result?jobId=... until the status is completed, then download the output from the returned URL.
Sign in with Google, top up your wallet from $10 and create an API key. The same key works for every model in the catalog.