快速开始

通过三次 API 调用创建 Seedance 视频任务并获取生成结果。

Open AI Image API 是异步 JSON API，支持文生视频、图生视频和参考素材生成视频。所有请求都使用 https://openaiimage.com 作为基础 URL。

01POST
/v1/videos/generations
02读取
task_id
03GET
/v1/tasks/{task_id}
04完成
success + outputs

1. 创建 API 密钥

前往设置 → API 密钥创建密钥。完整密钥只显示一次，请立即复制并保存到服务端的密钥管理工具中。

2. 创建生成任务

cURL

curl -X POST "https://openaiimage.com/v1/videos/generations" \
  -H "Authorization: Bearer sk_sd_example" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "seedance_2_0_fast",
  "prompt": "A paper boat crossing a rain-soaked neon street, cinematic camera movement",
  "parameters": {
    "duration": 5,
    "resolution": "720p",
    "aspect_ratio": "16:9",
    "generate_audio": true
  },
  "request_id": "72c1ca71-5e68-4a76-9c3b-bbc036261e30",
  "max_credits": 65
}'

响应

{
  "task_id": "d3a7b249c28a1e05f9210d16af47c86809a58cad92a36fc91138da677be03245",
  "status": "processing",
  "credits_used": 5,
  "outputs": []
}

JavaScript

const response = await fetch('https://openaiimage.com/v1/videos/generations', {
  method: 'POST',
  headers: {
    Authorization: 'Bearer sk_sd_example',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    "model": "seedance_2_0_fast",
    "prompt": "A paper boat crossing a rain-soaked neon street, cinematic camera movement",
    "parameters": {
      "duration": 5,
      "resolution": "720p",
      "aspect_ratio": "16:9",
      "generate_audio": true
    },
    "request_id": "72c1ca71-5e68-4a76-9c3b-bbc036261e30",
    "max_credits": 65
  }),
});
if (!response.ok) throw new Error(await response.text());
const task = await response.json();
console.log(task.task_id);

Python

import requests

response = requests.post(
    "https://openaiimage.com/v1/videos/generations",
    headers={"Authorization": "Bearer sk_sd_example"},
    json={
      "model": "seedance_2_0_fast",
      "prompt": "A paper boat crossing a rain-soaked neon street, cinematic camera movement",
      "parameters": {
        "duration": 5,
        "resolution": "720p",
        "aspect_ratio": "16:9",
        "generate_audio": True
      },
      "request_id": "72c1ca71-5e68-4a76-9c3b-bbc036261e30",
      "max_credits": 65
    },
    timeout=30,
)
response.raise_for_status()
task_id = response.json()["task_id"]
print(task_id)

3. 轮询任务

任务状态为 pending 或 processing 时，每隔 5–10 秒查询一次，并使用指数退避。

curl "https://openaiimage.com/v1/tasks/d3a7b249c28a1e05f9210d16af47c86809a58cad92a36fc91138da677be03245" \
  -H "Authorization: Bearer sk_sd_example"

当 status 变为 success，从 outputs[0].url 读取可长期访问的视频地址。如果任务变为 failed，请停止轮询。

已完成的任务

{
  "task_id": "d3a7b249c28a1e05f9210d16af47c86809a58cad92a36fc91138da677be03245",
  "status": "success",
  "credits_used": 5,
  "outputs": [
    {
      "url": "https://media.example.com/video.mp4"
    }
  ]
}

4. 查看可用积分

curl "https://openaiimage.com/v1/credits" \
  -H "Authorization: Bearer sk_sd_example"

credits 是新任务当前可以使用的积分。任务创建时扣除所需积分，生成失败后自动退回。