sora-2

Name: sora-2
Brand: OpenAI

Video

It can generate detailed, dynamic 720p videos from text or reference images with synchronized audio tracks. It has excellent understanding of three-dimensional space, motion and lens continuity, and is suitable for the creation of 16-20 second cinematic short films.

Resolution

720p

Without video input

10% off

$0.36/ M

With video input

10% off

$0.36/ M

Input

Text

Output

Video

Input

Video script *

Duration (seconds)ResolutionExact sizeAspect ratio

Generate audio

SeedUse -1 for random; identical seeds are not guaranteed to match

Reference materials

Optional. Used for image-to-video, first/last frame driving, video style transfer, or audio-driven generation. Click or drag to upload a local file.

Last frame requires a first frame URL

First frame image

Click to upload

Last frame image

Click to upload

Reference video

Click to upload

Reference audio

Click to upload

Output

API

Quick Start

Drop-in code to call this model with EasyAPI's OpenAI-compatible API.

Get your API key

Create an API key from your dashboard and set it as an environment variable:

Replace sk-xxxxxxxx with your API token from the console (Bearer token).

Create API token

shell

export EASYAPI_API_KEY=sk-xxxxxxxx

Make your first request

Use openai/sora-2 with the EasyAPI API:

cURL

curl https://token.easyapi.com/v1/videos \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $EASYAPI_API_KEY" \
  -d '{"model":"openai/sora-2","prompt":"A golden retriever running on a sunny beach, cinematic camera movement","duration":5,"resolution":"720p","aspect_ratio":"adaptive","generate_audio":false,"seed":-1,"size":"1280x720","input_references":[{"type":"image","url":"https://cdn.example.com/portrait.jpg","role":"first_frame"}]}'

Endpoint

Submits a video generation task from a text prompt.

POSThttps://token.easyapi.com/v1/videos

Authorization: Bearer $EASYAPI_API_KEY
Content-Type: application/json
Model: openai/sora-2

根据 prompt 提交视频生成任务，响应含任务 ID 或结果 URL。 Docs

Parameters

Name	Type	Required	Description
`model`	string	Yes	模型 ID，如 bytedance/seedance-2.0；当前使用 openai/sora-2
`prompt`	string	Yes	视频描述，建议包含主体、动作、场景、镜头和风格。不同模型上限不同：Sora 500 字，Hailuo 2000 字，Wan T2V 1500 字、I2V 800 字。Gate.AI 本身不设硬性上限，超出后由上游拒绝并透传 502 / 503。
`duration`	integer	No	视频时长（秒），支持 4–15
`resolution`	string	No	输出分辨率：480p、720p 或 1080p
`aspect_ratio`	string	No	宽高比：16:9、4:3、1:1、3:4、9:16、21:9 或 adaptive
`generate_audio`	boolean	No	是否生成音频
`seed`	integer	No	随机种子，-1 到 4294967295；相同 seed 不保证完全一致
`size`	string	No	精确输出尺寸，如 1280x720
`input_references`	array	No	可选参考素材数组，用于图生视频、首尾帧驱动、视频风格迁移或音频驱动生成
`input_references[].type`	string	Yes	参考素材类型：image、video 或 audio，必须与 role 匹配
`input_references[].url`	string	Yes	参考素材的 HTTPS 地址
`input_references[].role`	string	Yes	参考素材用途：first_frame（首帧图）、last_frame（尾帧图）、reference（外观参考图）、reference_video（参考视频）、reference_audio（参考音频）
`metadata`	object	No	业务透传字段，用于审计或来源标记
`webhook_url`	string	No	任务完成或失败后的回调地址

Using third-party SDKs

Official OpenAI and other SDKs work by swapping the base URL. See integration guide

Related models

chatgpt-image-latest

OpenAI

Offering state-of-the-art visual quality, precise instruction following, and support for large-scale batch processing.

Image

15% off

Input price

$4.25/ M

Output price

$27.2/ M

Cache read

$1.0625/ M

Cache write

—

gpt-4.1

OpenAI

Stable code generation with predictable output.

TextMultimodal

15% off

Input price

$1.7/ M

Output price

$6.8/ M

Cache read

$0.425/ M

Cache write

$0/ M

gpt-4.1-mini

OpenAI

Near GPT-4o performance at lower latency and cost, suited for high-frequency interactions, coding, and vision tasks.

TextMultimodal

15% off

Input price

$0.34/ M

Output price

$1.36/ M

Cache read

$0.085/ M

Cache write

$0/ M

gpt-4.1-nano

OpenAI

Fastest GPT. Sub-second responses.

TextMultimodal

15% off

Input price

$0.085/ M

Output price

$0.34/ M

Cache read

$0.0213/ M

Cache write

$0/ M