88API88API
User GuideAPI ReferenceAI ApplicationsHelp & Support
Video

OpenAI Video Format (Sora Format)

Calling the OpenAI video generation interface to generate videos, supporting models like Sora, and also supporting the use of the OpenAI video format to call Kling, Jimeng, and Vidu.

Generate Video

API Endpoint

POST /v1/videos

Request Headers

ParameterTypeRequiredDescription
AuthorizationstringYesUser Authentication Token (Bearer: sk-xxxx)

Request Parameters (multipart/form-data)

ParameterTypeRequiredDescription
promptstringYesText prompt describing the video to be generated
modelstringNoVideo generation model, defaults to sora-2
secondsstringNoVideo duration (seconds), defaults to 4 seconds
sizestringNoOutput resolution, format is width x height, defaults to 720x1280
input_referencefileNoInput image file (used for Image-to-Video)
metadatastringNoExtended parameters (JSON string format)

metadata Parameter Description

The metadata parameter is used to pass parameters unique to non-Sora models, such as Alibaba Cloud Wanxiang's image URL, watermark, prompt intelligent rewriting, etc. The format of the metadata parameter is a JSON string, for example:

{
  "img_url": "https://example.com/image.jpg",
  "watermark": false,
  "prompt_extend": true
}

Request Examples

Text-to-Video (Text Prompt Only)

curl https://88api.ai/v1/videos \
  -H "Authorization: Bearer sk-xxxx" \
  -F "prompt=一个穿着宇航服的宇航员在月球上行走, 高品质, 电影级" \
  -F "model=sora-2" \
  -F "seconds=5" \
  -F "size=1920x1080"

Image-to-Video (Text Prompt + Image File)

curl https://88api.ai/v1/videos \
  -H "Authorization: Bearer sk-xxxx" \
  -F "prompt=猫咪慢慢睁开眼睛,伸懒腰" \
  -F "model=sora-2" \
  -F "seconds=3" \
  -F "size=1920x1080" \
  -F "input_reference=@/path/to/cat.jpg"

Alibaba Cloud Wanxiang Video Generation Examples

Text-to-Video (Wanxiang 2.5)
curl https://88api.ai/v1/videos \
  -H "Authorization: Bearer sk-xxxx" \
  -F "prompt=一只可爱的小猫在花园里玩耍,阳光明媚,色彩鲜艳" \
  -F "model=wan2.5-t2v-preview" \
  -F "seconds=5" \
  -F "size=1920*1080"
Image-to-Video (Wanxiang 2.5)
curl https://88api.ai/v1/videos \
  -H "Authorization: Bearer sk-xxxx" \
  -F "prompt=让这张图片动起来,添加自然的运动效果" \
  -F "model=wan2.5-i2v-preview" \
  -F "seconds=5" \
  -F "size=1280P" \
  -F 'metadata={"img_url":"https://example.com/image.jpg"}'

Response Format

201 - Successfully Created

{
  "id": "video_123",
  "object": "video",
  "model": "sora-2",
  "created_at": 1640995200,
  "status": "processing",
  "progress": 0
}

Response Field Description

FieldTypeDescription
idstringVideo Task ID
objectstringObject type, fixed as "video"
modelstringName of the model used
created_atintegerCreation timestamp
statusstringTask status (processing: processing)
progressintegerGeneration progress percentage

Retrieve Video

Query the status and result of the video generation task based on the Task ID.

API Endpoint

GET /v1/videos/{video_id}

Path Parameters

ParameterTypeRequiredDescription
video_idstringYesVideo Task ID

Request Example

curl 'https://88api.ai/v1/videos/video_123' \
  -H "Authorization: Bearer sk-xxxx"

Response Format

200 - Successful Response

{
  "id": "video_123",
  "object": "video",
  "model": "sora-2",
  "created_at": 1640995200,
  "status": "succeeded",
  "progress": 100,
  "expires_at": 1641081600,
  "size": "1920x1080",
  "seconds": "5",
  "quality": "standard"
}

Response Field Description

FieldTypeDescription
idstringVideo Task ID
objectstringObject type, fixed as "video"
modelstringName of the model used
created_atintegerCreation timestamp
statusstringTask status (processing: processing, succeeded: successful, failed: failed)
progressintegerGeneration progress percentage
expires_atintegerResource expiration timestamp
sizestringVideo resolution
secondsstringVideo duration (seconds)
qualitystringVideo quality
urlstringVideo download link (when complete)

Get Video Task Status

Retrieve detailed information about the video generation task based on the Task ID.

API Endpoint

GET /v1/videos/{video_id}

Path Parameters

ParameterTypeRequiredDescription
video_idstringYesIdentifier of the video task to retrieve

Request Example

curl 'https://88api.ai/v1/videos/video_123' \
  -H "Authorization: Bearer sk-xxxx"

Response Format

{
  "id": "video_123",
  "object": "video",
  "model": "sora-2",
  "created_at": 1640995200,
  "status": "succeeded",
  "progress": 100,
  "expires_at": 1641081600,
  "size": "1920x1080",
  "seconds": "5",
  "quality": "standard",
  "remixed_from_video_id": null,
  "error": null
}

Response Field Description

FieldTypeDescription
idstringUnique identifier for the video task
objectstringObject type, fixed as "video"
modelstringName of the model that generated the video
statusstringCurrent lifecycle status of the video task
progressintegerApproximate completion percentage of the generation task
created_atintegerUnix timestamp (seconds) when the task was created
expires_atintegerUnix timestamp (seconds) when the downloadable resource expires, if set
sizestringGenerated video resolution
secondsstringDuration of the generated video clip (seconds)
qualitystringVideo quality
remixed_from_video_idstringIdentifier of the source video if this video is a remix
errorobjectObject containing error information if generation failed

Get Video Content

Download the completed video content.

API Endpoint

GET /v1/videos/{video_id}/content

Path Parameters

ParameterTypeRequiredDescription
video_idstringYesIdentifier of the video to download

Query Parameters

ParameterTypeRequiredDescription
variantstringNoType of downloadable resource to return, defaults to MP4 video

Request Example

curl 'https://88api.ai/v1/videos/video_123/content' \
  -H "Authorization: Bearer sk-xxxx" \
  -o "video.mp4"

Response Description

Directly returns the video file stream, Content-Type is video/mp4.

Response Headers

FieldDescription
Content-TypeVideo file type, usually video/mp4
Content-LengthVideo file size (bytes)
Content-DispositionFile download information

Error Responses

400 - Request Parameter Error

{
  "error": {
    "message": "string",
    "type": "invalid_request_error"
  }
}

401 - Unauthorized

{
  "error": {
    "message": "string",
    "type": "invalid_request_error"
  }
}

403 - Forbidden

{
  "error": {
    "message": "string",
    "type": "invalid_request_error"
  }
}

404 - Task Not Found

{
  "error": {
    "message": "string",
    "type": "invalid_request_error"
  }
}

500 - Internal Server Error

{
  "error": {
    "message": "string",
    "type": "server_error"
  }
}

Supported Models

OpenAI Compatible

  • sora-2: Sora video generation model

Other Services Called via OpenAI Format

  • Alibaba Cloud Wanxiang (Ali Wan): Use wan2.5-t2v-preview (Text-to-Video), wan2.5-i2v-preview (Image-to-Video), wan2.2-i2v-flash, wan2.2-i2v-plus, wanx2.1-i2v-plus, wanx2.1-i2v-turbo
  • Kling AI: Use kling-v1, kling-v2-master
  • Jimeng: Use jimeng_vgfm_t2v_l20, jimeng_vgfm_i2v_l20
  • Vidu: Use viduq1

Alibaba Cloud Wanxiang Special Instructions

Supported Features

  • Text-to-Video (t2v): Generates video using only a text prompt
  • Image-to-Video (i2v): Generates video using a text prompt + image
  • Keyframe-to-Video (kf2v): Generates video by specifying the start and end frame images
  • Audio Generation (s2v): Supports combining audio with video

Resolution Support

  • 480P: 832×480, 480×832, 624×624
  • 720P: 1280×720, 720×1280, 960×960, 1088×832, 832×1088
  • 1080P: 1920×1080, 1080×1920, 1440×1440, 1632×1248, 1248×1632

Special Parameters

  • watermark: Whether to add a watermark (default false)
  • prompt_extend: Whether to enable prompt intelligent rewriting (default true)
  • audio: Whether to add audio (only supported by wan2.5)
  • seed: Random seed

Model Characteristics

  • wan2.5-i2v-preview: Wanxiang 2.5 preview version, supports video with sound, recommended
  • wan2.2-i2v-flash: Wanxiang 2.2 Express version, fast generation speed, silent video
  • wan2.2-i2v-plus: Wanxiang 2.2 Professional version, higher image quality, silent video
  • wanx2.1-i2v-plus: Wanxiang 2.1 Professional version, stable version
  • wanx2.1-i2v-turbo: Wanxiang 2.1 Express version

Best Practices

  1. Request Format: Use multipart/form-data format, which is the official OpenAI recommended method
  2. input_reference Parameter: Used for the Image-to-Video function, use the @filename syntax when uploading image files
  3. Prompt Optimization: Use detailed and specific descriptive words, including style and quality requirements
  4. Parameter Settings: Reasonably set duration and resolution according to requirements
  5. Alibaba Cloud Wanxiang Special Instructions:
    • Direct file upload is not supported; all resources are passed via URL
    • Use the metadata parameter to pass all extended parameters (JSON string format)
    • Image-to-Video uses metadata.img_url to pass the image URL
    • Keyframe-to-Video uses metadata.first_frame_url and metadata.last_frame_url
  6. Error Handling: Implement appropriate retry mechanisms and error handling
  7. Asynchronous Processing: Video generation is an asynchronous task and requires polling for status checks
  8. Resource Management: Download and clean up unnecessary video files promptly

JavaScript Examples

async function generateVideoWithFormData() {
  const formData = new FormData();
  formData.append(
    'prompt',
    '一个穿着宇航服的宇航员在月球上行走, 高品质, 电影级'
  );
  formData.append('model', 'sora-2');
  formData.append('seconds', '5');
  formData.append('size', '1920x1080');

  const response = await fetch('https://88api.ai/v1/videos', {
    method: 'POST',
    headers: {
      Authorization: 'Bearer sk-xxxx',
    },
    body: formData,
  });

  const result = await response.json();
  return result.id;
}

// Image-to-Video Example
async function generateVideoWithImage() {
  const formData = new FormData();
  formData.append('prompt', '猫咪慢慢睁开眼睛,伸懒腰');
  formData.append('model', 'sora-2');
  formData.append('seconds', '3');
  formData.append('size', '1920x1080');

  // 添加图片文件
  const imageFile = document.getElementById('imageInput').files[0];
  formData.append('input_reference', imageFile);

  const response = await fetch('https://88api.ai/v1/videos', {
    method: 'POST',
    headers: {
      Authorization: 'Bearer sk-xxxx',
    },
    body: formData,
  });

  const result = await response.json();
  return result.id;
}

Alibaba Cloud Wanxiang Calling Example

// 阿里云万相文生视频
async function generateAliVideo() {
  const formData = new FormData();
  formData.append('prompt', '一只可爱的小猫在花园里玩耍,阳光明媚,色彩鲜艳');
  formData.append('model', 'wan2.5-t2v-preview');
  formData.append('seconds', '5');
  formData.append('size', '1920*1080');
  formData.append(
    'metadata',
    JSON.stringify({
      watermark: false,
      prompt_extend: true,
    })
  );

  const response = await fetch('https://88api.ai/v1/videos', {
    method: 'POST',
    headers: {
      Authorization: 'Bearer sk-xxxx',
    },
    body: formData,
  });

  const result = await response.json();
  return result.id;
}

// 阿里云万相图生视频
async function generateAliImageToVideo() {
  const formData = new FormData();
  formData.append('prompt', '让这张图片动起来,添加自然的运动效果');
  formData.append('model', 'wan2.5-i2v-preview');
  formData.append('seconds', '3');
  formData.append('resolution', '720P');
  formData.append('input_reference', imageFile);
  formData.append(
    'metadata',
    JSON.stringify({
      watermark: false,
      prompt_extend: true,
    })
  );

  const response = await fetch('https://88api.ai/v1/videos', {
    method: 'POST',
    headers: {
      Authorization: 'Bearer sk-xxxx',
    },
    body: formData,
  });

  const result = await response.json();
  return result.id;
}

// 阿里云万相首尾帧生视频
async function generateAliKeyframeVideo() {
  const formData = new FormData();
  formData.append('prompt', '从开始到结束的平滑过渡动画');
  formData.append('model', 'wan2.2-kf2v-flash');
  formData.append('seconds', '4');
  formData.append(
    'metadata',
    JSON.stringify({
      first_frame_url: 'https://example.com/start.jpg',
      last_frame_url: 'https://example.com/end.jpg',
      resolution: '720P',
      watermark: false,
    })
  );

  const response = await fetch('https://88api.ai/v1/videos', {
    method: 'POST',
    headers: {
      Authorization: 'Bearer sk-xxxx',
    },
    body: formData,
  });

  const result = await response.json();
  return result.id;
}