Appearance
🎬 视频模型 Google Veo
- 2025.08.06 本站已经支持
google
视频模型 - 支持的模型有:
veo2
veo2-fast
veo2-fast-components
veo2-fast-frames
veo2-pro
veo3
veo3-fast
veo3-fast-frames
veo3-frames
veo3-pro-frames
veo3-pro
- 支持
文生视频
图生视频
关键帧生视频
- 计费是按次数,一次一个视频
价格及计费
- 1 元=10000 积分
模型 | 价格(积分) |
---|---|
veo2 | 10000 |
veo2-fast | 10000 |
veo2-fast-components | 10000 |
veo2-fast-frames | 10000 |
veo3 | 20000 |
veo3-fast | 20000 |
veo3-fast-frames | 20000 |
veo3-frames | 20000 |
veo2-pro | 100000 |
veo3-pro-frames | 100000 |
veo3-pro | 100000 |
Google Veo API
- 约定头文件 都得带
Authorization
Content-Type
shell
'Authorization: Bearer hk-your-key'
'Content-Type: application/json'
'Authorization: Bearer hk-your-key'
'Content-Type: application/json'
1.生成任务
shell
curl --request POST \
--url https://api.openai-hk.com/veo/v1/video/create \
--header 'Authorization: Bearer hk-your-hk-key' \
--header 'Content-Type: application/json' \
--data '{
"prompt": "A casual street interview on a busy New York City sidewalk in the afternoon. The interviewer holds a plain, unbranded microphone and asks: Have you seen Google's new Veo3 model It is a super good model. Person replies: Yeah I saw it, it's already available on openai-hk, It's so crazy.",
"model": "veo3",
"enhance_prompt": true
}'
curl --request POST \
--url https://api.openai-hk.com/veo/v1/video/create \
--header 'Authorization: Bearer hk-your-hk-key' \
--header 'Content-Type: application/json' \
--data '{
"prompt": "A casual street interview on a busy New York City sidewalk in the afternoon. The interviewer holds a plain, unbranded microphone and asks: Have you seen Google's new Veo3 model It is a super good model. Person replies: Yeah I saw it, it's already available on openai-hk, It's so crazy.",
"model": "veo3",
"enhance_prompt": true
}'
- 请求体
json
{
"prompt": "A casual street interview on a busy New York City sidewalk in the afternoon. The interviewer holds a plain, unbranded microphone and asks: Have you seen Google's new Veo3 model It is a super good model. Person replies: Yeah I saw it, it's already available on openai-hk, It's so crazy.",
"model": "veo3-fast",
"enhance_prompt": true,
"images": ["https://a.com/1.jpg", "https://a.com/2.jpg"]
}
{
"prompt": "A casual street interview on a busy New York City sidewalk in the afternoon. The interviewer holds a plain, unbranded microphone and asks: Have you seen Google's new Veo3 model It is a super good model. Person replies: Yeah I saw it, it's already available on openai-hk, It's so crazy.",
"model": "veo3-fast",
"enhance_prompt": true,
"images": ["https://a.com/1.jpg", "https://a.com/2.jpg"]
}
请求体关键字说明
字段 类型 说明 prompt string 生成视频的提示词 model string 生成视频的模型名称 enhance_prompt boolean 是否增强提示词 images string[] 生成视频的图片列表 images
当模型是带 veo2-fast-frames 最多支持两个,分别是首尾帧,当模型是 veo3-pro-frames 最多支持一个首帧,当模型是 veo2-fast-components 最多支持 3 个,此时图片为视频中的元素返回体
json
{
"id": "veo3-fast:1754487582-iib208CF9a",
"status": "pending"
}
{
"id": "veo3-fast:1754487582-iib208CF9a",
"status": "pending"
}
2.查询任务状态
shell
curl --request GET \
--url https://api.openai-hk.com/veo/v1/video/feed/veo3-fast:1754487582-iib208CF9a \
--header 'Authorization: Bearer hk-your-hk-key' \
--header 'Content-Type: application/json'
curl --request GET \
--url https://api.openai-hk.com/veo/v1/video/feed/veo3-fast:1754487582-iib208CF9a \
--header 'Authorization: Bearer hk-your-hk-key' \
--header 'Content-Type: application/json'
- 返回体
json
{
"id": "veo3-fast:1754487582-iib208CF9a",
"status": "completed",
"video_url": "https://filesystem.site/cdn/20250806/5VpavR5qkSpnsbFbTbTpC6aVPQMrgi.mp4"
}
{
"id": "veo3-fast:1754487582-iib208CF9a",
"status": "completed",
"video_url": "https://filesystem.site/cdn/20250806/5VpavR5qkSpnsbFbTbTpC6aVPQMrgi.mp4"
}
- 关键字说明
字段 | 类型 | 说明 |
---|---|---|
id | string | 任务 id |
status | string | 任务状态 completed failed pending video_generating |
video_url | string | 视频地址 |