Skip to content
Google · Released 2025-09-01

Veo 3

TextImage

Veo 3 is Google’s powerful video generation model that creates realistic videos from text and image prompts with built-in synchronized audio. It delivers cinematic visuals, natural motion, and strong scene understanding, enabling high-quality video creation for creative workflows, storytelling, advertising, and professional content production.

google/veo3

Official example

Input
Prompt

一名超高速超级英雄,酷似闪电侠,深夜在茂密幽暗的森林中疾驰。他移动时,树木模糊成绿黑交织的残影。每跨出一步,身后都迸发着火光轨迹,将部分低矮灌木丛点燃,燃起闪烁的余烬。 他在树木间灵活穿梭时,身后留下的炽热轨迹,在森林地面上逐渐以灼热的熔岩火勾勒出“VEO 3 FAST”的字样。镜头拉远,完整呈现这段文字。

Output

Parameters

Derived from the model input schema
ParameterTypeDefaultDescription
promptRequiredstring提示词
negative_promptstring反向提示词
aspect_ratiostring16:9视频宽高比16:9 · 9:16
duration_secondsinteger8视频时长(秒)8
resolutionstring720p分辨率720p · 1080p
generate_audioboolean是否生成音频
enhance_promptbooleantrue是否使用Gemini优化提示词
person_generationstringallow_adult人物生成控制allow_adult · dont_allow
sample_countinteger1采样数量1 · 2 · 3 · 4
seedinteger-1随机种子-1 – 4294967295
imagestring输入图片Google Cloud Storage URI
storage_uristringGoogle Cloud Storage 存储 URI

API example

Submit a generation task, then poll for the result — one API key for every model.

Get API Key Get API Key
# Submit task
curl https://router-integration.test.cogfoundry.ai/api/v1/tasks/generations \
  -H "Authorization: Bearer $MODEL_CENTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "google/veo3",
  "aspect_ratio": "16:9",
  "duration_seconds": 8,
  "enhance_prompt": true,
  "generate_audio": true,
  "person_generation": "allow_adult",
  "prompt": "一名超高速超级英雄,酷似闪电侠,深夜在茂密幽暗的森林中疾驰。他移动时,树木模糊成绿黑交织的残影。每跨出一步,身后都迸发着火光轨迹,将部分低矮灌木丛点燃,燃起闪烁的余烬。\n\n他在树木间灵活穿梭时,身后留下的炽热轨迹,在森林地面上逐渐以灼热的熔岩火勾勒出“VEO 3 FAST”的字样。镜头拉远,完整呈现这段文字。",
  "resolution": "1080p",
  "sample_count": 1
}'

# Poll result(REQUEST_ID 来自上一步返回的 data.request_id)
curl https://router-integration.test.cogfoundry.ai/api/v1/tasks/generations/REQUEST_ID \
  -H "Authorization: Bearer $MODEL_CENTER_API_KEY"

Pricing

USD · live rate
PricingUSD
不带音频$0.20
带音频$0.40

Providers

Channels serving this model
Provider From
VertexTask $0.20

More from Google