Veo 3.1 Fast vs Veo 3.1
何时使用哪一个 — 经过整理的结论,而非基准测试表格
同一代、同一张规格表——720p/1080p、4/6/8 秒、24 fps、最多两张引导图、原生音频——所以差别纯粹是费率:fast 变体带音频每输出秒 $0.15、静音 $0.1,对比 $0.4 和 $0.2,大约便宜 2.7 倍和 2 倍。两者都提供静音费率,当你打算自己配乐时那是更省的路径。在规格如此一致的情况下,fast 变体就是默认选择。
定价
| Veo 3.1 Fast | Veo 3.1 | Δ | |
|---|---|---|---|
| 每秒输出(带音频) | $0.15 | $0.4 | 0.37× |
| 每秒输出(静音) | $0.1 | $0.2 | 0.5× |
费率取自构建时的实时目录;每个模型页面均附有当前的费率卡。
它们的位置 — 以该计费单位计费的所有 7 个 视频生成 模型的 每输出秒的价格(对数刻度)
能力
| Veo 3.1 Fast | Veo 3.1 | |
|---|---|---|
| 原生音频 | 是 | 是 |
规格
| Veo 3.1 Fast | Veo 3.1 | |
|---|---|---|
| 输入模态 | 文本 图像 | 文本 图像 |
| 输出模态 | 视频 | 视频 |
| 发布日期 | 2025-10 | 2025-10 |
| 分辨率 | 720p / 1080p (固定选项) | 720p / 1080p (固定选项) |
| 片段长度 | 4 / 6 / 8 s (固定选项) | 4 / 6 / 8 s (固定选项) |
| 帧率 | 24 fps | 24 fps |
| 宽高比 |
|
|
| 输入模式 |
|
|
| 格式 | .mp4 | .mp4 |
规格转录自各供应商的文档;若供应商未发布某项数据,则直接省略该行,而非进行推断。 完整来源: Veo 3.1 Fast · Veo 3.1
单个 Prompt,两个模型 —— 通过网关实测
模型返回 1280×720 时长 8s 延迟 63 s
模型返回 1280×720 时长 8s 延迟 63 s
统一提示词,每个模型单次请求,无重试且无择优挑选 —— 均为各模型返回的首个结果。尺寸与时长均未固定:各模型使用自身的默认值,因为试图适配所有模型的请求参数无法展现任何模型的优势。此处文件已为 Web 重新编码,因此请评判构图与提示词遵循度,而非压缩质量。
只需一行代码即可在它们之间切换
两个 ID 都包含在下方的每个选项卡中 — 高亮显示的两行是唯一的修改。相同的端点,相同的密钥,相同的请求结构。
import time
import requests
BASE = "https://synthorai.io/v1"
HEADERS = {"Authorization": "Bearer sk-syn-..."}
# 1) create the video generation job (POST /v1/videos)
task = requests.post(
f"{BASE}/videos",
headers=HEADERS,
json={
"model": "veo-3.1-fast-generate-001",
# "model": "veo-3.1-generate-001", # 取消注释此行,注释上一行
"prompt": "a watercolor lighthouse at dawn, waves rolling in, camera pulling back",
"resolution": "720p",
"duration": 5,
},
).json()
# 2) poll the job until it reaches a terminal state
while task["status"] in ("queued", "in_progress"):
time.sleep(5)
task = requests.get(f"{BASE}/videos/{task['id']}", headers=HEADERS).json()
# 3) completed → signed video URL (valid ~24h — download and store it promptly)
if task["status"] == "completed":
print(task["data"][0]["url"])
else:
print(task["error"])const HEADERS = {
Authorization: "Bearer sk-syn-...",
"Content-Type": "application/json",
};
interface VideoTask {
id: string;
status: "queued" | "in_progress" | "completed" | "failed" | "cancelled";
data?: Array<{ url: string }>;
error?: { code: string; message: string };
}
// 1) create the video generation job (POST /v1/videos)
const created = await fetch("https://synthorai.io/v1/videos", {
method: "POST",
headers: HEADERS,
body: JSON.stringify({
model: "veo-3.1-fast-generate-001",
// model: "veo-3.1-generate-001", // 取消注释此行,注释上一行
prompt: "a watercolor lighthouse at dawn, waves rolling in, camera pulling back",
resolution: "720p",
duration: 5,
}),
});
let task = (await created.json()) as VideoTask;
// 2) poll the job until it reaches a terminal state
while (task.status === "queued" || task.status === "in_progress") {
await new Promise((r) => setTimeout(r, 5000));
const res = await fetch(`https://synthorai.io/v1/videos/${task.id}`, { headers: HEADERS });
task = (await res.json()) as VideoTask;
}
// 3) completed → signed video URL (valid ~24h — download and store it promptly)
if (task.status === "completed") console.log(task.data?.[0]?.url);
else console.error(task.error);# Create the job; "Prefer: wait" holds the request up to 60s and returns the
# completed task when generation finishes in time (else the queued task).
curl https://synthorai.io/v1/videos \
-H "Authorization: Bearer sk-syn-..." \
-H "Content-Type: application/json" \
-H "Prefer: wait=60" \
-d '{
"model": "veo-3.1-fast-generate-001",
# "model": "veo-3.1-generate-001", # 取消注释此行,注释上一行
"prompt": "a watercolor lighthouse at dawn, waves rolling in, camera pulling back",
"resolution": "720p",
"duration": 5
}'
# Still queued / in_progress? Poll until completed → data[0].url (valid ~24h).
curl https://synthorai.io/v1/videos/vid_9f2e8c1a4b7d \
-H "Authorization: Bearer sk-syn-..."package main
import (
"bytes"
"encoding/json"
"fmt"
"net/http"
"time"
)
const base = "https://synthorai.io/v1"
type videoTask struct {
ID string `json:"id"`
Status string `json:"status"`
Data []struct {
URL string `json:"url"`
} `json:"data"`
}
func call(method, url string, body []byte) (t videoTask) {
req, _ := http.NewRequest(method, url, bytes.NewReader(body))
req.Header.Set("Authorization", "Bearer sk-syn-...")
req.Header.Set("Content-Type", "application/json")
resp, _ := http.DefaultClient.Do(req)
defer resp.Body.Close()
json.NewDecoder(resp.Body).Decode(&t)
return t
}
func main() {
// 1) create the video generation job (POST /v1/videos)
payload, _ := json.Marshal(map[string]any{
"model": "veo-3.1-fast-generate-001",
// "model": "veo-3.1-generate-001", // 取消注释此行,注释上一行
"prompt": "a watercolor lighthouse at dawn, waves rolling in, camera pulling back",
"resolution": "720p",
"duration": 5,
})
task := call("POST", base+"/videos", payload)
// 2) poll the job until it reaches a terminal state
for task.Status == "queued" || task.Status == "in_progress" {
time.Sleep(5 * time.Second)
task = call("GET", base+"/videos/"+task.ID, nil)
}
// 3) completed → signed video URL (valid ~24h — download and store promptly)
if task.Status == "completed" {
fmt.Println(task.Data[0].URL)
}
}import java.net.URI;
import java.net.http.HttpClient;
import java.net.http.HttpRequest;
import java.net.http.HttpResponse;
// JDK built-in HttpClient — no extra dependency needed.
HttpClient http = HttpClient.newHttpClient();
// 1) create the job; "Prefer: wait=60" holds the request up to 60s and
// returns the completed task when generation finishes in time
HttpRequest create = HttpRequest.newBuilder(URI.create("https://synthorai.io/v1/videos"))
.header("Authorization", "Bearer sk-syn-...")
.header("Content-Type", "application/json")
.header("Prefer", "wait=60")
.POST(HttpRequest.BodyPublishers.ofString("""
{"model": "veo-3.1-fast-generate-001",
// {"model": "veo-3.1-generate-001", // 取消注释此行,注释上一行
"prompt": "a watercolor lighthouse at dawn, waves rolling in, camera pulling back",
"resolution": "720p", "duration": 5}"""))
.build();
String task = http.send(create, HttpResponse.BodyHandlers.ofString()).body();
System.out.println(task); // {"id":"vid_…","status":…} — completed → data[0].url
// 2) still queued / in_progress? Poll GET https://synthorai.io/v1/videos/{id} until the
// status turns completed, then download data[0].url (valid ~24h).常见问题
Veo 3.1 Fast 和 Veo 3.1 哪个更便宜?
在 每秒输出(带音频) 方面,Veo 3.1 Fast 更便宜($0.15 对比 $0.4,相差 2.7×)。其他行可能得出相反的结论——上方表格提供了完整信息,实际成本取决于你的组合使用情况。
我可以在不进行两次集成的情况下,对 Veo 3.1 Fast 和 Veo 3.1 进行 A/B 测试吗?
可以。两者均通过同一个兼容 OpenAI 的端点提供服务,并使用同一把 API 密钥——切换只需更改一行模型字符串,因此你可以将一部分流量路由到各个模型并直接比较账单。
它们支持哪些片段长度和分辨率?
上方的规格表格列出了各个模型公布的分辨率和片段长度,并标注了该值是固定选项还是连续范围——两者看起来相似,但定价方式不同,因为按秒计费会乘以长度。