/v1/videos/generations

根据文本提示生成视频，也可选择提供图像。这是异步操作，会返回用于轮询的 request_id。

请求体

响应体

request_idstring

（string，必填）— 用于轮询结果的唯一请求 ID。

代码示例

**响应示例：**

curl -s https://api.x.ai/v1/videos/generations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $XAI_API_KEY" \
  -d '{
    "model": "grok-imagine-video-1.5",
    "prompt": "A serene lake at sunrise with mist rolling over the water"
  }'

const response = await fetch("https://api.x.ai/v1/videos/generations", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.XAI_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "grok-imagine-video-1.5",
    prompt: "A serene lake at sunrise with mist rolling over the water",
  }),
});

console.log(JSON.stringify(await response.json(), null, 2));

import json
import os

import requests

response = requests.post(
    "https://api.x.ai/v1/videos/generations",
    headers={
        "Authorization": f"Bearer {os.environ['XAI_API_KEY']}",
        "Content-Type": "application/json",
    },
    json={
        "model": "grok-imagine-video-1.5",
        "prompt": "A serene lake at sunrise with mist rolling over the water",
    },
)

print(json.dumps(response.json(), indent=2))

{
  "prompt": "A cat playing with a ball",
  "model": "grok-imagine-video",
  "duration": 6
}

{
  "request_id": "41eb9a5f-cbd4-9f21-8d59-79005f1e61b7"
}

视频编辑

/v1/videos/edits

根据 prompt 编辑视频。这是一个异步操作，会返回可用于轮询的 request_id。

请求体

promptstring

（string，必填）— 视频编辑的 prompt。

videoobject

（object，必填）— 用于编辑和扩展请求的视频输入。接受公开 URL、base64 编码 data URL 或 xAI 文件 API 中的 file_id。

响应体

request_idstring

（string，必填）— 用于轮询结果的唯一请求 ID。

代码示例

**响应示例：**

curl -s https://api.x.ai/v1/videos/edits \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $XAI_API_KEY" \
  -d "{
    \"model\": \"grok-imagine-video\",
    \"prompt\": \"Give the woman a silver necklace\",
    \"video\": {
      \"url\": \"$VIDEO_URL\"
    }
  }"

const response = await fetch("https://api.x.ai/v1/videos/edits", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.XAI_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "grok-imagine-video",
    prompt: "Give the woman a silver necklace",
    video: {
      url: process.env.VIDEO_URL,
    },
  }),
});

console.log(JSON.stringify(await response.json(), null, 2));

import json
import os

import requests

response = requests.post(
    "https://api.x.ai/v1/videos/edits",
    headers={
        "Authorization": f"Bearer {os.environ['XAI_API_KEY']}",
        "Content-Type": "application/json",
    },
    json={
        "model": "grok-imagine-video",
        "prompt": "Give the woman a silver necklace",
        "video": {
            "url": os.environ["VIDEO_URL"],
        },
    },
)

print(json.dumps(response.json(), indent=2))

{
  "prompt": "Add snow to the scene",
  "video": {
    "url": "https://example.com/video.mp4"
  },
  "model": "grok-imagine-video"
}

{
  "request_id": "69ad8ab2-3459-9c92-a372-cb3dcc3533b2"
}

视频扩展

/v1/videos/extensions

通过生成延续内容来扩展视频。这是一个异步操作，会返回可用于轮询的 request_id。

请求体

promptstring

（string，必填）— 描述视频中接下来应发生什么的 prompt。

videoobject

（object，必填）— 用于编辑和扩展请求的视频输入。接受公开 URL、base64 编码 data URL 或 xAI 文件 API 中的 file_id。

响应体

request_idstring

（string，必填）— 用于轮询结果的唯一请求 ID。

{
  "prompt": "The camera slowly zooms out to reveal the city skyline",
  "video": {
    "url": "https://example.com/video.mp4"
  },
  "model": "grok-imagine-video",
  "duration": 6
}

{
  "request_id": "a3d1008e-4544-40d4-d075-11527e794e4a"
}

获取视频生成结果

/v1/videos/{request_id}

获取延迟视频生成请求的结果。

路径参数

request_idstring

（string，必填）— 先前视频生成请求返回的延迟请求 id。

响应体

statusstring

（string，必填）— 视频生成状态；视频就绪时为 "done"。

代码示例

**响应示例：**

curl -s "https://api.x.ai/v1/videos/$VIDEO_REQUEST_ID" \
  -H "Authorization: Bearer $XAI_API_KEY"

const response = await fetch(
  `https://api.x.ai/v1/videos/${process.env.VIDEO_REQUEST_ID}`,
  {
    headers: {
      Authorization: `Bearer ${process.env.XAI_API_KEY}`,
    },
  },
);

console.log(JSON.stringify(await response.json(), null, 2));

import json
import os

import requests

request_id = os.environ["VIDEO_REQUEST_ID"]

response = requests.get(
    f"https://api.x.ai/v1/videos/{request_id}",
    headers={
        "Authorization": f"Bearer {os.environ['XAI_API_KEY']}",
    },
)

print(json.dumps(response.json(), indent=2))

No parameters.

{
  "status": "done",
  "video": {
    "url": "https://vidgen.x.ai/xai-vidgen-bucket/xai-video-cb3a83ec-322f-4318-990d-166bab11d328.mp4",
    "duration": 1,
    "respect_moderation": true
  },
  "model": "grok-imagine-video",
  "usage": {
    "cost_in_usd_ticks": 500000000
  },
  "progress": 100
}

最后更新：2026 年 4 月 13 日