Vidu

Viduq3 Turbo

ViduToken-basedSpecial billing expression
Alias:viduq3-turbo
Create API Key

Compare viduq3-turbo API pricing, supported endpoints, capabilities and access options on Modelsell.

视频生成Q3文生视频图生视频首尾帧视频540p720p1080p
Starting price
View full pricing
Context
—
Maximum input window
Modalities
→

Pricing by Supplier

Special billing expression
Prices are calculated using the billing rules below.

Capabilities / Supported modalities

Vision
Input
Output

Provider & data privacy

Provider
Unknown
Tokenizer
BPE (vendor-specific)
License
Provider-specificUnknown
Data retention43 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·Viduq3 Turbo

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 Viduq3 Turbo

模型能力

Vidu Q3 Turbo 视频生成模型,支持音画同步和智能切镜,面向高效率的视频创作;当前渠道提供文生、图生与首尾帧生成。 当前渠道支持文生视频、图生视频、首尾帧视频。视频时长为 1–16 秒,默认 5 秒;默认 720p,可选 540p、720p、1080p。具体媒体格式与参数由上游校验。

Q3 默认启用音画同步;需要静音视频时显式传入 audio: false。

官方标准价

以下为 2026-10-30 核对的 Vidu 中国站 API 标准价。1 积分 = ¥0.03125,系统按本次配置的 ¥6.8/美元折算,用户分组倍率另行应用。ePhone 供货折扣不替代此基准价。

  • 文生/图生/首尾帧 540p:7 积分/秒(¥0.21875/秒)
  • 文生/图生/首尾帧 720p:12 积分/秒(¥0.375/秒)
  • 文生/图生/首尾帧 1080p:13 积分/秒(¥0.40625/秒)

创建时按请求参数预扣,成功后优先按上游返回的有效 credits 结算,积分缺失或异常时按冻结参数公式计算,失败任务按网关流程退款;查询不重复收费。本渠道当前提供即时生成,暂不接受 off_peak: true。视频延长和智能多帧不在本次接口范围内。

资料:Vidu 模型地图、官方定价、ePhone AI。

Vidu 官方另有参考生视频能力;当前 ePhone 目录未列出该组合,本渠道文档先仅列出已确认的三种操作。

当前渠道暂不提供 is_rec: true 自动推荐提示词,请直接提供 prompt。

Use cases and prompting

原生调用

使用自己的网关 API key 发送 POST /ent/v2/text2video:

{
  "model": "viduq3-turbo",
  "prompt": "镜头固定,蓝色小球缓慢向右滚动。",
  "duration": 5,
  "resolution": "720p",
  "audio": false,
  "off_peak": false,
  "watermark": false
}

创建响应的 task_id 为网关公开任务 ID。使用同一网关令牌调用 GET /ent/v2/tasks/{task_id}/creations,建议每 10–15 秒查询一次;state: success 时读取 creations[0].url。结果地址有有效期,请及时保存。

统一视频接口

也可调用 POST /v1/videos 或 POST /v1/video/generations,使用同一模型名、prompt、seconds 和 size。图片放入 images,Vidu 专有参数放入 metadata。需要指定操作时设置 metadata.vidu_operation 为 text2video、img2video、start-end2video 或 reference2video,并选择该模型支持的操作。Q2 参考生建议使用原生接口或显式指定 reference2video。

API access

API documentation

Code samples

Create taskPOST/v1/video/generations
Example request
Parameters
ParameterTypeDefault / rangeDescription
promptrequired
string—Text description of the desired video
size
enum
=720p
Output video resolution
seconds
integer
=4>= 1
Video length in seconds
images
array—Reference images for image-to-video generation
metadata
object—Provider-specific video generation options
Query taskGET/v1/video/generations/{task_id}
Example request
Parameters
ParameterTypeDefault / rangeDescription
task_idrequired
string—Task identifier returned by the generation request

Replace <YOUR_API_KEY> with the API key from your token settings.

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
ViduUnlimitedUnlimitedUnlimited

No restriction

Frequently asked questions about viduq3-turbo

What is viduq3-turbo?

Compare viduq3-turbo API pricing, supported endpoints, capabilities and access options on Modelsell.

How do I call viduq3-turbo?

Create an API key with access to viduq3-turbo, then use the exact model ID and a supported endpoint from the API access section. Request fields depend on the selected endpoint.

How is viduq3-turbo 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 viduq3-turbo for my project?

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