---
title: "Kuaishou AI models — API access via RunAPI"
url: "https://runapi.ai/providers/kuaishou.md"
canonical: "https://runapi.ai/providers/kuaishou.md"
locale: "en"
provider: "Kuaishou"
line_count: 1
variant_count: 5
---

# Kuaishou

Kling video generation at up to 4K 60fps with AI avatar creation and multimodal audio.

Kuaishou develops the Kling video generation model, supporting text-to-video and image-to-video at up to 4K 60fps with multimodal audio synthesis and AI avatar generation for talking-head content.

## Models

- [Kling](https://runapi.ai/models/kling.md) — Video, 5 variants · from $0.080

## Variants

| Model | Variant | Billing | Starting price | URL |
|---|---|---|---|---|
| Kling | `3.0` | second | $0.140 | https://runapi.ai/models/kling/3.0.md |
| Kling | `ai-avatar-pro` | second | $0.160 | https://runapi.ai/models/kling/ai-avatar-pro.md |
| Kling | `ai-avatar-standard` | second | $0.080 | https://runapi.ai/models/kling/ai-avatar-standard.md |
| Kling | `v2.5-turbo-image-to-video-pro` | second | $0.090 | https://runapi.ai/models/kling/v2.5-turbo-image-to-video-pro.md |
| Kling | `v2.5-turbo-text-to-video-pro` | second | $0.090 | https://runapi.ai/models/kling/v2.5-turbo-text-to-video-pro.md |

## Install

```sh
npm install @runapi.ai/<line>
```

## FAQ

### Is this an official %{provider} integration?

RunAPI exposes a managed API surface with transparent pricing, capability, and error behavior.

### Do I need a %{provider} account?

No — your RunAPI key is enough for managed access.

### What&#39;s the latency overhead from proxying?

Typically under 20 ms. RunAPI keeps the proxy layer close to model execution regions.

### Are images / videos cached?

Generated outputs are stored and retrievable by task ID. Inputs are not cached.

### Can I bring my own key?

Not currently — calls use RunAPI-managed access.