NOW LIVESeedance 2.5 is now live on I2V.aiTry it now
i2v.ai
  • Studio
  • Models
  • Seedance 2.5
  • Pricing
模型 / 视频

Google

Google Veo 3.1

google-veo3.1

8-second text-to-video generation with audio

Text to video720p / 1080p / 4kAudio output
通过 API 调用
在线体验价格API模型介绍常见问题

Detailed descriptions of scenes, actions, and styles will result in better generation quality

Veo 3 models have a fixed duration of 8 seconds

Loading...

Join Discord community
Content policy notice
Each provider applies its own content policy. Some models may reject unsafe requests or certain real-person reference inputs. If a task is rejected, review the model guidance and try permitted source material.

按模式与输出规格计价

Studio 与 API 共用同一积分余额。以下美元估算基于 $9.90 Mini Pack;购买更大积分包或使用优惠后,实际单次成本可能更低。

模式配置积分预估美元价格
Text input720p · 8s30$0.38
Text input1080p · 8s33$0.42
Text input4k · 8s90$1.14
Modes
Text to video
Duration
8 seconds
Resolution
720p, 1080p, 4k
Aspect ratios
16:9, 9:16
Audio
Supported

通过 Google Veo 3.1 构建产品

创建任务后保留返回的 task ID,并通过 recordInfo 轮询结果。页面会展示准确模型价格,方便你在运行前估算产品成本。

获取 API 密钥
POST /api/v1/jobs/createTask
{
  "model": "google-veo3.1",
  "inputs": {
    "prompt": "A cinematic tracking shot through a futuristic city at sunset",
    "duration": "8s",
    "aspectRatio": "16:9",
    "resolution": "720p"
  }
}

什么是 Google Veo 3.1?

Google Veo 3.1 is a video model from Google. In practical terms, the Veo family produces short AI video sequences with model-specific support for text, image input, resolution, and generated audio. 8-second text-to-video generation with audio.

On I2V, Google Veo 3.1 supports Text to video. Available output options include 720p, 1080p, 4k, with aspect-ratio behavior shown as 16:9, 9:16. The same public model ID and credit balance work in Studio and through the task API.

Google Veo 3.1 能做什么

Input workflows

Google Veo 3.1 exposes Text to video. The model-locked Studio form only shows controls that apply to this model.

Output control

Configured output resolution: 720p, 1080p, 4k. Supported aspect-ratio behavior: 16:9, 9:16.

Reference-led creation

Use source images, frames, or reference media when the selected mode accepts visual input.

Google Veo 3.1 的适用场景

Short-form storytelling

Create self-contained shots for social posts, trailers, mood films, and narrative prototypes.

Product and campaign motion

Explore product reveals, camera movement, environments, and campaign concepts before a full production shoot.

Storyboard previsualization

Turn prompts or approved frames into moving references that help teams evaluate pacing and shot direction.

何时选择 Google Veo 3.1

Choose a Veo variant when its fixed duration, input mode, resolution, and audio support fit the shot; compare Lite, Standard, and Pro before committing credits. I2V shows the exact valid configurations before you run the task, so model selection can be based on both capability and cost.

Google Veo 3.1 常见问题

What is Google Veo 3.1?+

Google Veo 3.1 is a Google video model available in I2V Studio and through the I2V task API. It supports Text to video.

What inputs and outputs does Google Veo 3.1 support?+

Google Veo 3.1 supports Text to video. Output resolution is 720p, 1080p, 4k, with aspect-ratio behavior listed as 16:9, 9:16. The live form is restricted to valid options for this model.

How much does Google Veo 3.1 cost on I2V?+

Google Veo 3.1 starts at 30 credits ($0.38 using the current Mini Pack reference) for Text input, 720p · 8s. The pricing table lists other valid configurations.

Can I use Google Veo 3.1 through an API?+

Yes. Use the public model ID google-veo3.1 with POST /api/v1/jobs/createTask, then poll GET /api/v1/jobs/recordInfo until the task succeeds or fails. Studio and API share one credit balance.

继续探索

相关模型

查看全部模型

Google Veo 3.1 Lite

发布日期: March 2026

8-second text or image-to-video generation with audio

标准 · 720p · 8s

$0.19

标准 · 1080p · 8s

$0.23

标准 · 4k · 8s

$0.95

打开模型

Google Veo 3.1 Pro

发布日期: October 2025

8-second text-to-video generation with audio

标准 · 720p · 8s

$1.59

标准 · 1080p · 8s

$1.62

标准 · 4k · 8s

$2.35

打开模型

Seedance 2.5

发布日期: July 2026

Text, image, keyframe, and multimodal reference video generation

含音频 · 480p · 5s

$0.69

视频输入 · 480p · 5s

$0.42

含音频 · 720p · 5s

$1.47

视频输入 · 720p · 5s

$0.89

打开模型
Resources
  • Blog
  • Studio
  • Scenes
  • Works
  • Prompts
  • Image to Prompt
  • Batch Image to Prompt
Company & Legal
  • About
  • Contact
  • Privacy Policy
  • Terms of Service
  • Refund Policy
Image Models
  • Qwen Image 2
  • Seedream 4.5
  • Seedream 5.0
  • Nano Banana Pro
  • Nano Banana Flash
  • Nano Banana 2
Video Models
  • Google Veo 3.1
  • Google Veo 3.1 Lite
  • Google Veo 3.1 Pro
  • Seedance 1.5 Pro
  • Seedance Fast
  • Seedance Quality
  • Seedance 2.0
  • Kling v3.0
  • Kling v3.0 Pro
i2v.ai

I2V AI — image and video creation, with API access

DiscordEmail

This website is an independent third-party platform. We are not affiliated with, endorsed by, or officially representing any AI model providers referenced on this site. All trademarks and brand names belong to their respective owners.

© 2026 I2V AI All Rights Reserved.

Privacy Policyprivacy@i2v.aisupport@i2v.ai