Google · Released 2025-10-16

Veo 3.1 Fast

Name: Veo 3.1 Fast
Brand: Google
Price: 0.08 USD
Availability: InStock

TextImage

Veo 3.1 Fast is Google’s fast and cost-efficient video generation model, delivering high-quality video with synchronized audio from text or image prompts. It provides faster generation than Veo 3.1 while maintaining strong visual quality, with support for frame conditioning, multiple resolutions, flexible aspect ratios, and SynthID watermarking for production-ready creative workflows.

google/veo3.1-fast-preview

Official example

Input

Prompt

特写：两个人盯着墙上的神秘图画，手电筒的光芒闪烁不定。女人看着他，兴奋地低声说：“你发现了什么？”，男人低声说：“一定是这个。这就是密码。”

Output

Parameters

Derived from the model input schema

Parameter	Type	Default	Description
`prompt`Required	string	—	提示词
`negative_prompt`	string	—	反向提示词
`aspect_ratio`	string	16:9	视频宽高比16:9 · 9:16
`duration_seconds`	integer	8	视频时长（秒）4 · 6 · 8
`resolution`	string	720p	分辨率720p · 1080p
`generate_audio`	boolean	—	是否生成音频
`enhance_prompt`	boolean	true	是否使用Gemini优化提示词
`person_generation`	string	allow_adult	人物生成控制allow_adult · dont_allow
`sample_count`	integer	1	采样数量1 · 2 · 3 · 4
`seed`	integer	-1	随机种子-1 – 4294967295
`image`	string	—	输入图片Google Cloud Storage URI
`reference_images`	array	—	最多3张素材图片或1张风格图片≤ 3
`storage_uri`	string	—	Google Cloud Storage 存储 URI
`last_frame`Required	string	—	结束帧图片URL或GCS 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/veo3.1-fast-preview",
  "aspect_ratio": "16:9",
  "duration_seconds": 8,
  "enhance_prompt": true,
  "generate_audio": true,
  "person_generation": "allow_adult",
  "prompt": "特写：两个人盯着墙上的神秘图画，手电筒的光芒闪烁不定。女人看着他，兴奋地低声说：“你发现了什么？”，男人低声说：“一定是这个。这就是密码。” ",
  "resolution": "720p",
  "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"

import requests

BASE = "https://router-integration.test.cogfoundry.ai/api/v1"
KEY = "$MODEL_CENTER_API_KEY"
headers = {"Authorization": f"Bearer {KEY}", "Content-Type": "application/json"}

# Submit task
resp = requests.post(f"{BASE}/tasks/generations", headers=headers, data='''{
  "model": "google/veo3.1-fast-preview",
  "aspect_ratio": "16:9",
  "duration_seconds": 8,
  "enhance_prompt": true,
  "generate_audio": true,
  "person_generation": "allow_adult",
  "prompt": "特写：两个人盯着墙上的神秘图画，手电筒的光芒闪烁不定。女人看着他，兴奋地低声说：“你发现了什么？”，男人低声说：“一定是这个。这就是密码。” ",
  "resolution": "720p",
  "sample_count": 1
}''')
request_id = resp.json()["data"]["request_id"]

# Poll result
result = requests.get(f"{BASE}/tasks/generations/{request_id}", headers=headers)
print(result.json())

const BASE = "https://router-integration.test.cogfoundry.ai/api/v1";
const KEY = "$MODEL_CENTER_API_KEY";
const headers = { Authorization: "Bearer " + KEY, "Content-Type": "application/json" };

// Submit task
const payload = {
  "model": "google/veo3.1-fast-preview",
  "aspect_ratio": "16:9",
  "duration_seconds": 8,
  "enhance_prompt": true,
  "generate_audio": true,
  "person_generation": "allow_adult",
  "prompt": "特写：两个人盯着墙上的神秘图画，手电筒的光芒闪烁不定。女人看着他，兴奋地低声说：“你发现了什么？”，男人低声说：“一定是这个。这就是密码。” ",
  "resolution": "720p",
  "sample_count": 1
};
const resp = await fetch(BASE + "/tasks/generations", {
  method: "POST",
  headers,
  body: JSON.stringify(payload),
});
const { data } = await resp.json();

// Poll result
const result = await fetch(BASE + "/tasks/generations/" + data.request_id, { headers });
console.log(await result.json());