Google's state-of-the-art video generation model, built for maximum visual fidelity in final production cuts. Veo 3.1 generates high-quality 1080p video from text or image prompts with native synchronized audio — including dialogue, ambient effects, and background sound. Supports scene extension (up to 20 chained clips for 140+ second narratives), frames-to-video transitions between two images, vertical video for Shorts, and 4K upscaling.
Google: Veo 3.1 的示例输出摘要
试验场
基准测试
标准化评测得分,以及此模型针对共用基准测试提示词的实际输出。百分比越高越好,每项排名显示此模型在该来源所评测的模型中的位置。
| 来源 | 基准测试 | 得分 |
|---|---|---|
| Artificial Analysis | Veo 3.1 Elo | 959 |
| Artificial Analysis | Veo 3.1 Preview Elo | 1,220 |
Google: Veo 3.1 的基准测试输出摘要
- Traffic light: A fixed camera on a single traffic light against a plain grey sky. The light starts red, changes to green, and then changes to amber, in that exact order, each colour holding for a clearly visible moment. No other objects, no camera movement, no cuts. (在此提示词中并列第 第 1 名,共 28 名)
- Five candles: A fixed straight-on shot of five lit candles in a row on a dark table. The candles go out one at a time from left to right until all five are out. No hand or person visible, no camera movement, no cuts. (在此提示词中并列第 第 17 名,共 28 名)
- Wrong-way escalator: A fixed shot of an empty upward-moving escalator. A single red rubber ball bounces down the escalator steps from top to bottom, against the direction of the escalator's movement, and exits the frame at the bottom. No people, no cuts. (在此提示词中并列第 第 17 名,共 28 名)
- Frozen crowd: A busy pedestrian plaza in daylight where every single person stands perfectly still like a statue for the entire clip. Only the flags on the buildings move in the wind. No person moves at all, not even slightly. Fixed camera, no cuts. (在此提示词中并列第 第 4 名,共 28 名)
- Sign stays readable: A slow steady dolly toward a shop window sign reading exactly "OPEN 7 DAYS - COFFEE & BAGELS - EST. 2003". The text stays sharp, correctly spelled and unchanged for the whole clip as the camera approaches. No other text in the frame. (在此提示词中并列第 第 4 名,共 28 名)
- Glass of water: A fixed close shot of a full glass of water on a wooden table. A rolling orange bumps into the glass. The glass tips over away from the camera, water spills across the table and spreads outward, and the empty glass rolls slightly and comes to rest. No hands, no cuts. (在此提示词中排名第 第 27 名,共 28 名)
- Domino run: A fixed side-on shot of exactly eight upright black dominoes in a straight evenly spaced row on a white surface. The leftmost domino tips right and the whole row falls in a single left-to-right chain until all eight are flat. No hands after the start, no cuts. (在此提示词中并列第 第 7 名,共 28 名)
- Mirror walk: A fixed shot of a large wall mirror in a bright dance studio. A man in a green t-shirt walks from left to right in front of the mirror. His reflection matches his movement exactly, mirrored, for the entire clip. No cuts. (在此提示词中并列第 第 18 名,共 28 名)
- Behind the pillar: A fixed camera on a wide walkway with a single thick concrete pillar in the middle. A woman in a yellow raincoat walks at a steady pace from the left edge to the right edge, passing behind the pillar. She is briefly hidden, then reappears on the other side wearing exactly the same clothes, and exits frame right. No cuts. (在此提示词中并列第 第 24 名,共 28 名)
- Steaming mug: Thin steam rises from the coffee and drifts slowly to the right. Everything else holds still: the mug and its painted design, the table, the background, the lighting and the framing stay exactly as in the reference. Static camera. No cuts. (在此提示词中并列第 第 1 名,共 27 名)
- Walk out: The person from the reference turns and walks out of the frame to the right. Their face, hair and clothing stay exactly as in the reference until they exit. The background does not change. No cuts. (在此提示词中并列第 第 15 名,共 26 名)
- Continuous shot: A single continuous shot, no cuts, orbiting exactly once, slowly, around a stone statue of a horse in an empty courtyard. The statue stays centred the whole time and the camera ends where it started. Nothing else enters the frame. (在此提示词中并列第 第 2 名,共 28 名)
提供商
此模型由一家提供商托管。OpenRouter 直接转发每个请求,不进行路由。
| US$0.40 | US$0.20 | 86.23s | 3.5 s/min |
- 视频 + 音频 US$0.40 / 仅视频 US$0.2086.23 秒延迟100.00% 正常运行时间
性能
生成时间是指视频从提交到完成所需的时间(越低越好)。速度是指每分钟生成时间内生成的视频秒数(越高越好)。
P50,最佳提供商
P50,所有提供商中的最佳值
正常运行时间
正常运行时间是指过去 3 天中至少有一家提供商响应请求的时间百分比。可用性是指成功提供推理服务的时间百分比。OpenRouter 会持续监控,并在某家提供商返回错误时使用次优提供商。
过去 3 天的可用性
最近 72 小时过去 24 小时的可用性
当上游提供商发生错误时,如果您的请求筛选条件允许,我们可以通过路由到另一家健康的提供商来恢复服务。您可以通过以下接口以编程方式访问各提供商的正常运行时间数据: 端点 API。了解更多有关我们的 负载均衡和提供商路由选项。
应用
向此模型发送最多流量的公开应用。这能很好地反映实际生产工作负载的情况,也能提示此模型最适合哪些用例。
暂无图表数据
活动
此模型的 token 用量和请求流量随时间的变化。
API
可直接用于调用此模型的代码。OpenRouter 的 API 与 OpenAI 兼容——大多数 SDK 只需替换基础 URL 即可使用。切换模型时,唯一需要更改的是下方的模型标识符。
目前无法通过 EU 区域内路由使用。 区域内路由文档
文档
在 OpenRouter 上使用 Google: Veo 3.1 构建应用的指南、实用教程、博客文章和工具。
常见问题
Google's state-of-the-art video generation model, built for maximum visual fidelity in final production cuts. Veo 3.1 generates high-quality 1080p video from text or image prompts with native synchronized audio — including dialogue, ambient effects, and background sound.
OpenRouter 上的 Veo 3.1 文档包括 Best Image-to-Video AI Models in 2026: Cost, Resolution, and Control 博客文章。快速入门介绍了 API 密钥和您的首次请求,API 参考列出了所有参数。
Veo 3.1 的费用为 Video (with audio) 的价格为 从 US$0.40/second(1080p)到 US$0.60/second(4K)和Video (no audio) 的价格为 从 US$0.20/second(1080p)到 US$0.40/second(4K)。
Veo 3.1 支持 4、6和8 秒 的片段、可通过 first frame和last frame 图像进行引导和生成匹配的音轨.
Veo 3.1 接受 文本和图像 作为输入,并返回 视频。
在 OpenRouter 上,Veo 3.1 由 1 家提供商提供服务:Google Vertex。
Veo 3.1 Fast和Veo 3.1 Lite 是 Google 的其他 视频 模型。
Veo 3.1 于 2026年3月23日 发布。