Create Video

Create a video generation task using the OpenAI/Sora-compatible request format. This endpoint is for models configured as video-generation channels, such as sora-2 and bytedance-seedance-1.5; actual availability depends on the model list and account channel configuration.

For the Alibaba Cloud Model Studio / DashScope native input / parameters format, see Aliyun Video Generation.

Try It

POST/v1/videoshttps://api-platform.ope.ai

Endpoints

Endpoint	Auth	Purpose
POST /v1/videos	Authorization: Bearer <api-key>	Create a video task with an API key
POST /api/videos	token: <jwt>	Frontend-token proxy endpoint; request body is the same

Use the token header for a normal frontend JWT. Admin JWTs may use Authorization: Bearer <jwt>.

Authentication

Use Bearer token authentication.

• Header: Authorization: Bearer <api-key>
• Example: Authorization: Bearer sk-xxxxxx

Request Body（application/json）

Field	Type	Required	Description
model	string	Yes	Video model ID, for example sora-2 or bytedance-seedance-1.5
prompt	string	Yes	Text prompt
size	string	Yes	Output size, preferably widthxheight, for example 720x1280
seconds	string	Yes	Video duration as a string, for example "4"; valid values depend on the model
generate_audio	boolean	No	Whether to generate audio, for models that support it
enhance_prompt	boolean	No	Whether to enhance the prompt, for models that support it
negative_prompt	string	No	Negative prompt
person_generation	string	No	Person-generation policy; supported values depend on the model
seed	integer	No	Random seed
remix_video_id	string	No	Existing video task ID for video remix/edit flows
input_reference.content	array	No	Multimodal reference content; each item supports only image_url, video_url, or audio_url

input_reference.content[] shape:

Field	Type	Required	Description
type	string	Yes	image_url, video_url, or audio_url
role	string	No	Reference role, for example reference_image
image_url.url	string	Conditional	Required when type=image_url; image URL or Data URL
video_url.url	string	Conditional	Required when type=video_url; video URL
audio_url.url	string	Conditional	Required when type=audio_url; audio URL

Field Restrictions

The platform rejects these incompatible fields: aspect_ratio, resolution, duration_seconds, top-level content, img_url in JSON requests, and legacy input_reference.file_id / input_reference.image_url. Put text in prompt; do not send input_reference.content[].text.

multipart/form-data is only for uploading a reference image file through the input_reference field. The file must be at most 10 MB and use image/jpeg, image/png, or image/webp. Do not send an input_reference file and remix_video_id in the same request.

Request Examples

cURL

curl -X POST "https://api-platform.ope.ai/v1/videos" \
  -H "Authorization: Bearer $OPEAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "sora-2",
    "prompt": "Create a short high-definition tech-style video showing AI video generation capabilities.",
    "size": "720x1280",
    "seconds": "4"
  }'

JavaScript

const res = await fetch("https://api-platform.ope.ai/v1/videos", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.OPEAI_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "sora-2",
    prompt: "Create a short high-definition tech-style video showing AI video generation capabilities.",
    size: "720x1280",
    seconds: "4",
  }),
});

console.log(await res.json());

Python

import os
import requests

resp = requests.post(
    "https://api-platform.ope.ai/v1/videos",
    headers={"Authorization": f"Bearer {os.environ['OPEAI_API_KEY']}"},
    json={
        "model": "sora-2",
        "prompt": "Create a short high-definition tech-style video showing AI video generation capabilities.",
        "size": "720x1280",
        "seconds": "4",
    },
    timeout=120,
)

print(resp.json())

Reference Content Example

{
  "model": "bytedance-seedance-1.5",
  "prompt": "Make the subject in the reference image turn naturally toward the camera with cinematic lighting.",
  "size": "1280x720",
  "seconds": "5",
  "input_reference": {
    "content": [
      {
        "type": "image_url",
        "role": "reference_image",
        "image_url": {
          "url": "https://example.com/reference.png"
        }
      }
    ]
  }
}

Response Example

The create endpoint returns a task ID. Poll Get Video Task Status, then download the result with Get Video Content after the task succeeds.

{
  "id": "video_690d9b52e2b081908a05ded32cbfc629",
  "object": "video",
  "status": "queued",
  "created_at": 1762499410,
  "model": "sora-2",
  "prompt": "Create a short high-definition tech-style video showing AI video generation capabilities.",
  "size": "720x1280",
  "seconds": "4"
}