🎞️视频 API已上线

ltx-2 API

LTX-2 已通过 API in One 接入真实生产路由 /api/v1/videos/generations，后端节点为 node50。一个 API Key 即可调用并按成功请求计费。

获取 API Key 查看文档

真实能力

以下能力来自当前已接入的模型配置和后端路由，不展示未上线 API。

稳定生产路由

4 specialized modes in one model

统一接口

Lipsync from audio input

透明计费

Video control with pose/depth/canny

快速接入

Up to 1080p and 20 seconds

请求方式

浏览器端只调用同源 API，服务端 BFF 再转发到对应 Worker。

方法端点积分用途

POST/api/v1/videos/generations24 积分

LTX-2 19B — advanced AI video generation with text-to-video, image-to-video, lipsync, and control modes. Up to 1080p, 5–20 seconds.

参数

promptstring

Text description (required for text-to-video and image-to-video)

可选

typestring

Mode: "text-to-video", "image-to-video", "lipsync", or "control"

可选

imagestring

Image URL for image-to-video mode

可选

audiostring

Audio URL for lipsync mode

可选

audio_durationnumber

Audio duration in seconds for lipsync (5–20)

可选

videostring

Video URL for control mode

可选

video_durationnumber

Video duration for control mode (5–20)

可选

modestring

Control mode: "pose", "depth", or "canny"

可选

audio_modestring

Audio mode for control: "preserve", "generate", or "none"

可选

resolutionstring

Output resolution: "480p", "720p", or "1080p"

可选 · 默认 720p

aspect_ratiostring

Aspect ratio: "16:9" or "9:16" (text-to-video only)

可选 · 默认 16:9

durationnumber

Video duration in seconds (5–20)

可选 · 默认 5

seednumber

Random seed for reproducibility (-1 for random)

可选 · 默认 -1

示例请求

{
  "endpoint": "/api/v1/videos/generations",
  "headers": {
    "Authorization": "Bearer <API_KEY>",
    "Content-Type": "application/json"
  },
  "body": {
    "model": "ltx-2",
    "prompt": "A cat playing piano in a jazz bar, cinematic lighting",
    "resolution": "720p",
    "aspect_ratio": "16:9",
    "duration": 5
  }
}

任务状态查询

图像、视频、音频和工具任务创建后，使用真实任务端点查询结果。

GET/api/v1/tasks/{task_id}查询生成任务状态和结果。

价格

20–512 credits per video (~$0.20–$5.12)

基础价格$0.24

积分24

计费按成功请求

使用场景

这些场景可通过当前模型和对应后端节点实现。

Generate high-quality videos from text prompts

Animate images into video with image-to-video mode

Create lipsync videos by combining audio with AI video

Apply pose/depth/edge control to existing video

常见问题

How much does LTX-2 cost?

Credits depend on mode, resolution, and duration. Text/image-to-video: 20–76 credits. Lipsync: 32–256 credits. Control: 64–512 credits.

What modes does LTX-2 support?

Four modes: text-to-video, image-to-video, lipsync (audio+video), and control (pose/depth/canny). Specify with the "type" parameter.

What resolutions are supported?

480p, 720p, and 1080p. Higher resolutions cost more credits.