Gemini

Veo 3.1 Generate Preview

GooglePer Request
Alias:veo-3.1-generate-preview
Create API Key

Compare veo-3.1-generate-preview 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$0.4$0.2/ request
Google Vertex
-30%
谷歌官方接口
Price$0.4$0.28/ request

Capabilities / Supported modalities

Function callingToolsJSON modeStructured outputVision
Input
Output

Provider & data privacy

Provider
GoogleDocs
Tokenizer
SentencePiece (Gemini)
License
Proprietary (commercial)Proprietary
Data retention9 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 Generate Preview

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 Generate Preview

Veo 3.1 Preview 适合把一个场面从纸面分镜推进成有画面、有声音的片段。它能理解文字描述,也能以图片作为视觉引导,生成带原生声音的短视频。人物怎么走、相机如何跟随、空间里听到什么,可以围绕同一个叙事目标一起安排。

故事片段可以从情绪明确的小场面开始:旅行者走进清晨车站,孩子在门口等待家人,或者店主整理刚开门的店铺。提示词里交代角色、动作、光线与机位,再用环境声音补足空间。对白最好简短、说话者明确;长台词和多人交谈会增加口型、发音与动作检查的难度。

已有分镜图或人物图时,可以用它确定主体与开场气氛,再让文字描述后续变化。首帧、尾帧和主体参考承担不同任务:一个约束开始,一个引导结束,一个帮助延续形象。想控制结尾时,应先选择符合这种创作方式的输入,让画面起点和终点能够自然衔接。

生成后需要检查人物外观、手部、道具接触、对白与环境声,多个片段还应统一色调和声音。与其一次写完复杂剧情,不如先验证一个关键场面,再逐步扩展成完整故事。

Use cases and prompting

清晨车站的告别场面

清晨的安静车站,一位年轻旅行者背着帆布包,站在站台边,回头向画外的人微笑说:“到了给你打电话。”镜头从半身缓慢靠近,柔和晨光,远处有列车低鸣和轻微风声。没有字幕,没有背景音乐,只有一个人说话。

先检查表情、台词与镜头节奏,再考虑补充列车进站的另一个片段。

对白怎样写更容易理解? 给出说话者、原句、语气和是否需要字幕,避免多个人同时说话。

图片参考能解决人物一致性吗? 有帮助,但每个片段仍应比较面部、服装和配件。

怎样做成更长的故事? 分段生成关键场面,检查衔接,再在剪辑中统一节奏与声音。

API access

API documentation

veo-3.1-generate-preview

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

No restriction

Frequently asked questions about veo-3.1-generate-preview

What is veo-3.1-generate-preview?

Compare veo-3.1-generate-preview API pricing, supported endpoints, capabilities and access options on Modelsell.

How do I call veo-3.1-generate-preview?

Create an API key with access to veo-3.1-generate-preview, 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-generate-preview 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-generate-preview for my project?

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