模型市场支持← 返回应用

MiniMax H3

MiniMax H3 模型通过一个统一的异步任务 API 调用。用 POST /api/generate 发起任务，再轮询 GET /api/generate/{taskId} 直到完成。本系列提供 3 个端点。

概览

每个端点共享相同的外层结构 —— 只有 model 和 input 字段不同。可在模型市场的 playground 中运行任意一个。

认证

在 /api-keys 创建 API 密钥，然后作为 Bearer token 发送。已登录时从浏览器发起的请求也可通过会话 cookie 生效。

Authorization: Bearer <YOUR_API_KEY>

创建任务

POST
POST https://api.lithovas.com/api/generate

请求体：{ "model": "<slug>", "input": { … } }

响应：{ "taskId": "<id>", "state": "waiting" }

查询结果

GET
GET https://api.lithovas.com/api/generate/<taskId>

响应：{ "taskId", "state": "waiting" | "success" | "fail", "resultUrls": [ … ], "creditsConsumed", "failMsg", "balance" }

异步
创建任务返回 200 只表示任务已被接受 —— 并非已完成。请轮询此端点，直到 state 变为 success 或 fail。失败任务不计费。

端点

模型任务model slug
MiniMax H3Text to Videominimax-h3/text-to-video
MiniMax H3Image to Videominimax-h3/image-to-video
MiniMax H3Video to Videominimax-h3/reference-to-video

MiniMax H3 · Text to Video

POSTText to Videominimax-h3/text-to-video
input 字段
promptstring必填

Text prompt describing the desired video.

durationinteger可选

Output video duration in seconds.

aspect_ratioenum<string>可选

Output video aspect ratio.

resolutionenum<string>可选

Output video resolution tier currently exposed on the relay.

seedinteger可选

Random seed for reproducible generation.

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "minimax-h3/text-to-video",
  "input": {
    "prompt": "A cinematic red panda surfing through neon rain at dusk.",
    "duration": 5,
    "aspect_ratio": "16:9",
    "resolution": "768p",
    "seed": 42
  }
}'

MiniMax H3 · Image to Video

POSTImage to Videominimax-h3/image-to-video
input 字段
promptstring必填

Text prompt describing the desired motion and style.

image_urlsarray<string>必填

One or more input image URLs used to drive the video.

durationinteger可选

Output video duration in seconds.

aspect_ratioenum<string>可选

Output video aspect ratio.

resolutionenum<string>可选

Output video resolution tier currently exposed on the relay.

seedinteger可选

Random seed for reproducible generation.

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "minimax-h3/image-to-video",
  "input": {
    "prompt": "Animate the image with natural motion, subtle camera movement, and cinematic lighting.",
    "image_urls": [
      "https://example.com/input.jpg"
    ],
    "duration": 5,
    "aspect_ratio": "16:9",
    "resolution": "768p",
    "seed": 42
  }
}'

MiniMax H3 · Video to Video

POSTVideo to Videominimax-h3/reference-to-video
input 字段
promptstring必填

Prompt describing the target video, style, motion, and atmosphere.

reference_imagearray<string>必填

Reference image URLs for subject and style consistency.

videos_listarray<string>可选

Optional reference video URLs for motion and camera guidance.

audios_listarray<string>可选

Optional reference audio URLs for voice, music, or ambience guidance.

durationinteger可选

Output video duration in seconds.

aspect_ratioenum<string>可选

Output video aspect ratio.

resolutionenum<string>可选

Output video resolution tier currently exposed on the relay.

seedinteger可选

Random seed for reproducible generation.

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "minimax-h3/reference-to-video",
  "input": {
    "prompt": "Restyle the source footage with richer lighting, cleaner motion, and a cinematic grade.",
    "reference_image": [
      "https://example.com/input.jpg"
    ],
    "videos_list": [
      "https://example.com/reference.mp4"
    ],
    "audios_list": [
      "https://example.com/reference.mp3"
    ],
    "duration": 5,
    "aspect_ratio": "16:9",
    "resolution": "768p",
    "seed": 42
  }
}'