Gemini

Veo 3.1

GooglePer Request
Alias:veo_3_1
Create API Key

Compare veo_3_1 API pricing, supported endpoints, capabilities and access options on Modelsell.

文生视频图生视频声画同步首尾帧
Starting price
Per Request
Context
—
Maximum input window
Modalities
→

Pricing by Supplier

Google AI Studio
-50%
谷歌官方接口
Price$0.2$0.1/ request
Google Vertex
-30%
谷歌官方接口
Price$0.2$0.14/ request
标准按次
图片音频视频等多模态按次计费
Price$0.2/ request

Capabilities / Supported modalities

Function callingToolsJSON modeStructured outputVision
Input
Output

Provider & data privacy

Provider
GoogleDocs
Tokenizer
SentencePiece (Gemini)
License
Proprietary (commercial)Proprietary
Data retention60 daysNot used for upstream training by default

Performance

Benchmarks

Scores on standardized evaluations. Higher percentages are better — and rank percentile shows

Metrics sourced fromArtificial Analysis 2026-09-30·Veo 3.1

This model is not included in the current benchmark snapshot.

Missing models or measurements are not zero scores.

Benchmark charts preserve the source model selection and reasoning settings. Missing models or measurements are not zero scores, and benchmark cost or speed is not this site’s service commitment.

About Veo 3.1

Veo 3.1 的创作重点是让画面与声音一起讲故事。你可以描述一个场景中的人物、动作和相机运动,同时安排环境声、动作声或对白,生成带原生声音的短片。它适合需要认真设计氛围的广告镜头、人物片段与故事分镜,也能从图片提供的视觉起点继续生成。

用镜头建立情绪

同样是一个人走进房间,远景可以交代空间,近景可以强调表情,缓慢推近则能让观众靠近一个细节。提示词里把机位、动作节奏和光线说清楚,能让短片围绕一个明确意图展开。要有对白时,写出具体句子、说话者和语气,再说明是否需要字幕,避免台词与画面要求互相冲突。

让声音有明确的来源

脚步、雨滴、杯子轻放和远处车声,可以帮助建立空间,也可以成为动作的重点。声音要求与具体画面对应,通常比泛泛要求“配一段电影音效”更有效。人物口型、语言发音和动作接触仍需要检查,尤其是对白较长或多人同时说话的场面。

图片引导适合延续商品、人物和场景的视觉起点。想保持外观时,使用清晰主体图,明确服装、结构和重要细节,再安排克制的动作。首帧、尾帧和参考图分别承担不同控制任务,创作时应先确定自己要约束的是开场、收尾还是主体。先完成一个简洁的镜头,再扩展成更长故事,更容易获得可用素材。

Use cases and prompting

咖啡店迎客镜头

雨后街角的小咖啡店,镜头从窗边缓慢推进到桌上的热咖啡。店员将杯子轻放到桌面,微笑说:“欢迎,先喝杯热的。”室内暖光,窗外有细雨声,杯子落下时有轻微瓷器声。一段连续镜头,不出现字幕,不加入背景音乐。

先检查对白、杯子动作与声音,再调整镜头推进速度。

声音需要另外写吗? 需要把关键声音、说话者和台词说明白,声音应服务于场景。

多人对白适合一次完成吗? 先用单人短句验证效果,再逐步增加互动,比较容易检查口型与说话关系。

已有产品图怎样使用? 用它确定开场外观,再描述动作与运镜,避免提示词改变原有产品结构。

API access

API documentation

veo_3_1

Use the linked documentation for model-specific request parameters and examples.

Authentication

All requests must include Authorization: Bearer <TOKEN> header. Anthropic-formatted endpoints accept the x-api-key header instead.

Generate tokens from the Tokens page; you can scope them to specific models, groups, IPs, and rate-limits.

Rate limits

SupplierRPMTPMRPD
Google AI StudioUnlimitedUnlimitedUnlimited
Google VertexUnlimitedUnlimitedUnlimited
标准按次UnlimitedUnlimitedUnlimited

No restriction

Frequently asked questions about veo_3_1

What is veo_3_1?

Compare veo_3_1 API pricing, supported endpoints, capabilities and access options on Modelsell.

How do I call veo_3_1?

Create an API key with access to veo_3_1, then use the exact model ID and a supported endpoint from the API access section. Request fields depend on the selected endpoint.

How is veo_3_1 priced?

Pricing depends on the selected provider group and the model billing unit. The current input, output, request, or media prices are shown on this page before sign-up.

How should I evaluate veo_3_1 for my project?

Start with the use cases and prompting guidance on this page, then evaluate the model with representative inputs from your project.