模型解析页

Veo 3.1

Veo 3.1 is provided by ToAPIs with General capabilities. Current pricing reference: Pay-as-you-go pricing. This page helps you understand positioning, parameters, and production-ready use cases before integration.

厂商

ToAPIs

能力

General

价格

Pay-as-you-go pricing

更新

在 Playground 中打开文档

模型概览

快速结论

Veo 3.1 supports Text-to-Video, Image-to-Video, R2V, and Video Edit in one workflow.
Use this model guide page to validate parameters with minimal request/response examples.
Stabilize prompts here first, then move to production API integration.

Veo 3.1模型特点

核心能力

能力一览与工程实践价值

Unified multi-mode testing

Switch across Text-to-Video, Image-to-Video, R2V, and Video Edit in one place.

Parameter-first validation

Iterate quickly on prompts, durations, and references before production rollout.

Production-ready handoff

Minimal request/response structure helps you move stable configs into API workflows.

如何使用 Veo 3.1 API

Fill prompt and key parameters.
Run, inspect output structure, then iterate.
Move stable settings into production API.

关键参数

参数	类型	必填	默认值	取值范围	说明
model	string	是	gemini_omni	-	Model identifier. Use the fixed value `gemini_omni`.
prompt	string	是	-	-	Main instruction describing the subject, action, scene, and style.
aspect_ratio	string	否	16:9	16:9 \| 9:16	Video aspect ratio. Defaults to `16:9`, corresponding to landscape or portrait output.
duration	integer	否	6	6 \| 10	Output duration in seconds. Defaults to `6` and currently supports only `6` and `10`.
resolution	string	否	720P	720P	Output resolution. Currently only `720P` is supported; if omitted, the default value is used.

常见错误

400 invalid_request_error

触发条件: Request payload misses required fields or has invalid field types.

修复建议: Validate model, mode, and input schema before request.

重试策略: Retry only after fixing payload; avoid blind retries.

401 authentication_error

触发条件: Missing Authorization header or invalid API key.

修复建议: Verify Bearer token format and API key scope.

重试策略: Retry after auth fix; rotate key if repeated failures continue.

429 rate_limit_exceeded

触发条件: Request rate, concurrency, or current quota hits upstream rate limiting.

修复建议: Apply exponential backoff first, then review request rate, concurrency, and quota usage.

重试策略: Use exponential backoff (e.g., 1s/2s/4s) with jitter; if it persists, reduce submission pressure.

500 internal_error

触发条件: Transient upstream error or internal processing failure.

修复建议: Capture request id and trigger retry workflow.

重试策略: Retry 2-3 times with short delays; escalate if persistent.

FAQ

When should I use Veo 3.1?

Use it to validate video concepts quickly, compare mode behavior, and converge prompts before API rollout.

How do I choose Text-to-Video vs Image-to-Video?

Use Text-to-Video when you only have instructions; use Image-to-Video when you already have key frames or composition.

What is the difference between R2V and Video Edit?

R2V focuses on reference-guided generation, while Video Edit focuses on modifying existing video assets.

图像视频模型报错：invalid apitype: -1

这类错误通常说明接口走错了。图像和视频模型一般不走 chat 接口，而是按对应文档发起 HTTP 任务请求，并通过任务状态接口轮询结果。排查时建议先看用户的实际请求代码、请求地址和请求体。

用户进行生成图片/视频的任务时出现任务失败，但是扣款

先让用户提供任务日志或截图，重点看是否出现了输入或输出 token 统计。如果有这类 token 记录，大概率是用户把图片/视频模型走成了 chat 接口；这不是正确用法。图片和视频模型通常是异步任务接口，需要通过 HTTP 请求先提交任务，再拿到任务 ID 轮询状态，详细以对应文档为准。

模式说明

Text to Video 模式（Veo 3.1）

Generate videos directly from prompts.

模式参数

modelpromptaspect_ratiodurationresolution

最佳应用场景

Ad storyboard preview
Shot draft generation
Social content prototyping