Create Video（Official Format）

POST

/openai/v1/videos

Sora is OpenAI's latest video generation model, capable of generating detailed and dynamic videos based on text or images.
The model is based on multimodal diffusion research and possesses a deep understanding of 3D space, motion, and scene continuity.

Usage Process

Create video
Use the Create video endpoint, set the prompt, model, duration, resolution, and reference image. After submission, a task ID will be returned.

Check progress
Use the Retrieve video endpoint with the task ID to check the status.

Get video
When "status": "completed", use the Retrieve video content endpoint to obtain the video link.

Remix Feature

sora2 supports Remix video, allowing secondary creation based on an existing video's ID and a new prompt, enabling "existing video + new intent" regeneration.

Pricing

Model	Resolution	Price (PTC/sec)
sora-2	720×1280 / 1280×720	0.1
sora-2-pro	720×1280 / 1280×720	0.3
sora-2-pro	1024×1792 / 1792×1024	0.5

Request

Header Params

Body Params multipart/form-data

Request Code Samples

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location --request POST 'https://api.302.ai/openai/v1/videos' \
--header 'Authorization: Bearer sk-jls4AaVBGoe1GwZD64qZA1qyKTN1MPHa4NmvH1cT68z7K1Zz' \
--form 'prompt=""' \
--form 'model=""' \
--form 'seconds=""' \
--form 'size=""' \
--form 'input_reference=@""' \
--form 'callback=""'

Responses

🟢200成功

application/json

Body

Example

{
  "id": "video_68e8ad9626208190bd45207f436c170d01245ed4889680f2",
  "object": "video",
  "created_at": 1760079254,
  "status": "queued",
  "completed_at": null,
  "error": null,
  "expires_at": null,
  "model": "sora-2-pro",
  "progress": 0,
  "remixed_from_video_id": "video_68e8a9287af081908c7df81a1ca543480df74d068eccf1e9",
  "seconds": "4",
  "size": "1024x1792"
}

Modified at 2025-10-11 10:13:28

Sora2（Get task result）

Retrieve Video（Official Format）