Sora 2 系列 - QWave API

POST

tasks

Sora 2 系列

curl --request POST \
  --url https://www.qingbo.dev/v1/tasks \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "prompt": "<string>",
  "duration": 123,
  "resolution": "<string>",
  "aspect_ratio": "<string>",
  "seed": 123,
  "image_urls": [
    "<string>"
  ],
  "callback_url": "<string>",
  "callback_events": [
    "<string>"
  ]
}
'

import requests

url = "https://www.qingbo.dev/v1/tasks"

payload = {
    "model": "<string>",
    "prompt": "<string>",
    "duration": 123,
    "resolution": "<string>",
    "aspect_ratio": "<string>",
    "seed": 123,
    "image_urls": ["<string>"],
    "callback_url": "<string>",
    "callback_events": ["<string>"]
}
headers = {"Content-Type": "application/json"}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: '<string>',
    prompt: '<string>',
    duration: 123,
    resolution: '<string>',
    aspect_ratio: '<string>',
    seed: 123,
    image_urls: ['<string>'],
    callback_url: '<string>',
    callback_events: ['<string>']
  })
};

fetch('https://www.qingbo.dev/v1/tasks', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://www.qingbo.dev/v1/tasks"

	payload := strings.NewReader("{\n  \"model\": \"<string>\",\n  \"prompt\": \"<string>\",\n  \"duration\": 123,\n  \"resolution\": \"<string>\",\n  \"aspect_ratio\": \"<string>\",\n  \"seed\": 123,\n  \"image_urls\": [\n    \"<string>\"\n  ],\n  \"callback_url\": \"<string>\",\n  \"callback_events\": [\n    \"<string>\"\n  ]\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://www.qingbo.dev/v1/tasks")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"<string>\",\n  \"prompt\": \"<string>\",\n  \"duration\": 123,\n  \"resolution\": \"<string>\",\n  \"aspect_ratio\": \"<string>\",\n  \"seed\": 123,\n  \"image_urls\": [\n    \"<string>\"\n  ],\n  \"callback_url\": \"<string>\",\n  \"callback_events\": [\n    \"<string>\"\n  ]\n}")
  .asString();

{
  "task_id": "task-wave1775285160b950328499",
  "model": "sora-2",
  "action": "generate",
  "status": "queued",
  "created_at": 1775285160040,
  "progress": 0
}

OpenAI Sora 2 系列视频生成模型,以 物理一致性 / 原生音画同步 / 镜头语言 见长,适合 电影感短片 / 创意广告 / 概念演示 三类场景。支持文生视频与图生视频(单图作起始画面),异步出图。三档定位:

sora-2 — 标准档,日常默认首选,仅 720p,文生 / 图生通吃,性价比最高
sora-2-pro — 旗舰档,支持 720p / 1024p / 1080p 三档分辨率,画质最强,单价最高
sora-2-preview — 预览档,能力与价格同标准档 sora-2 对齐,用于尝鲜 / 灰度

按 分辨率 × 时长 计费,每秒单价,时长仅支持 4 / 8 / 12 / 16 / 20 秒固定档位。

定价

模型	720p	1024p	1080p
`sora-2`	`$0.09` / 秒	—	—
`sora-2-preview`	`$0.09` / 秒	—	—
`sora-2-pro`	`$0.27` / 秒	`$0.45` / 秒	`$0.63` / 秒

价为售价(USD)。按秒计费 = 单价/秒 × duration。例:sora-2-pro 1080p 8 秒 = $0.63 × 8 = $5.04。

调用示例

curl -X POST https://www.qingbo.dev/v1/tasks \
  -H "Authorization: Bearer $WAVE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "sora-2",
    "prompt": "瀑布飞泻而下,水雾中升起一道彩虹,电影感光影",
    "duration": 8,
    "resolution": "720p",
    "aspect_ratio": "16:9"
  }'

curl -X POST https://www.qingbo.dev/v1/tasks \
  -H "Authorization: Bearer $WAVE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "sora-2",
    "prompt": "镜头缓缓推近,人物迎风转身",
    "image_urls": ["https://cdn.example.com/portrait.jpg"],
    "duration": 8,
    "resolution": "720p"
  }'

curl -X POST https://www.qingbo.dev/v1/tasks \
  -H "Authorization: Bearer $WAVE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "sora-2-pro",
    "prompt": "黄昏的海滩,女孩迎着夕阳奔跑,长发飞扬,海浪声与脚步声同步",
    "duration": 12,
    "resolution": "1080p",
    "aspect_ratio": "16:9"
  }'

{
  "task_id": "task-wave1775285160b950328499",
  "model": "sora-2",
  "action": "generate",
  "status": "queued",
  "created_at": 1775285160040,
  "progress": 0
}

提交后用 GET /v1/tasks/{task_id} 轮询状态,详见任务系统。

可用模型

模型 ID	分辨率	时长	支持 action	备注
`sora-2`	720p	4 / 8 / 12 / 16 / 20 秒	generate	标准档,日常首选
`sora-2-pro`	720p / 1024p / 1080p	4 / 8 / 12 / 16 / 20 秒	generate	旗舰档,画质最强
`sora-2-preview`	720p	4 / 8 / 12 / 16 / 20 秒	generate	预览档,价格同标准档

通用参数

model

string

必填

模型 ID,见可用模型表

prompt

string

必填

视频描述文本,建议描述 场景 / 主体 / 动作 / 镜头 / 氛围

duration

integer

默认值:"4"

视频时长(秒),仅支持固定档位:4 / 8 / 12 / 16 / 20

resolution

string

默认值:"720p"

输出分辨率。sora-2 / sora-2-preview 仅支持 720p;sora-2-pro 支持 720p / 1024p / 1080p

aspect_ratio

string

默认值:"16:9"

画面宽高比,可选值:

16:9 — 横版宽屏
9:16 — 竖版长屏
1:1 — 正方形

传 image_urls(图生视频)时,aspect_ratio 被忽略,方向由参考图自动决定。

seed

integer

随机种子,相同 prompt + seed 可复现相似结果

image_urls

string[]

参考图片 URL 数组,用于图生视频。最多 1 张,不传则为文生视频。需公网可下载链接

callback_url

string

Webhook 回调地址,任务终态时调用。详见回调机制

callback_events

string[]

订阅的回调事件,默认订阅终态(succeeded / failed / cancelled)

模型特定参数

Sora 2 系列无模型特定参数,所有可选项均在通用参数中。

资源限制

项目	限制
参考图片	最多 1 张,单张 ≤ 10MB,JPG / PNG / WEBP
Prompt 长度	建议 ≤ 2000 字符
视频时长	4 / 8 / 12 / 16 / 20 秒固定档位
分辨率	`sora-2` / `preview` 仅 720p;`pro` 支持 720p / 1024p / 1080p
输出	MP4,链接 24 小时有效

相关文档

任务系统详解 — 任务状态机 / 轮询节奏 / 异步推送
请求响应格式 — 通用错误码 / Headers / 限流
认证 — API Key 申请与使用

PixVerse V6PixVerse V6 — 文生 / 图生统一模型,1-15 秒任意时长,可选音频直出,360p-1080p 四档

Sora 2 系列

curl --request POST \
  --url https://www.qingbo.dev/v1/tasks \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "prompt": "<string>",
  "duration": 123,
  "resolution": "<string>",
  "aspect_ratio": "<string>",
  "seed": 123,
  "image_urls": [
    "<string>"
  ],
  "callback_url": "<string>",
  "callback_events": [
    "<string>"
  ]
}
'

import requests

url = "https://www.qingbo.dev/v1/tasks"

payload = {
    "model": "<string>",
    "prompt": "<string>",
    "duration": 123,
    "resolution": "<string>",
    "aspect_ratio": "<string>",
    "seed": 123,
    "image_urls": ["<string>"],
    "callback_url": "<string>",
    "callback_events": ["<string>"]
}
headers = {"Content-Type": "application/json"}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: '<string>',
    prompt: '<string>',
    duration: 123,
    resolution: '<string>',
    aspect_ratio: '<string>',
    seed: 123,
    image_urls: ['<string>'],
    callback_url: '<string>',
    callback_events: ['<string>']
  })
};

fetch('https://www.qingbo.dev/v1/tasks', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://www.qingbo.dev/v1/tasks"

	payload := strings.NewReader("{\n  \"model\": \"<string>\",\n  \"prompt\": \"<string>\",\n  \"duration\": 123,\n  \"resolution\": \"<string>\",\n  \"aspect_ratio\": \"<string>\",\n  \"seed\": 123,\n  \"image_urls\": [\n    \"<string>\"\n  ],\n  \"callback_url\": \"<string>\",\n  \"callback_events\": [\n    \"<string>\"\n  ]\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://www.qingbo.dev/v1/tasks")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"<string>\",\n  \"prompt\": \"<string>\",\n  \"duration\": 123,\n  \"resolution\": \"<string>\",\n  \"aspect_ratio\": \"<string>\",\n  \"seed\": 123,\n  \"image_urls\": [\n    \"<string>\"\n  ],\n  \"callback_url\": \"<string>\",\n  \"callback_events\": [\n    \"<string>\"\n  ]\n}")
  .asString();

{
  "task_id": "task-wave1775285160b950328499",
  "model": "sora-2",
  "action": "generate",
  "status": "queued",
  "created_at": 1775285160040,
  "progress": 0
}

​定价

​调用示例

​可用模型

​通用参数

​模型特定参数

​资源限制

​相关文档

定价

调用示例

可用模型

通用参数

模型特定参数

资源限制

相关文档