GoogleVideo model检查中
Veo 3.1 API
google-veo3-1-lite-text-to-video-stableGoogle's Veo 3.1 video model in Pro, Fast and Lite variants, for text to video, image to video and start and end frame transitions in 16:9 or 9:16.
- 图生视频
- 文生视频
- Up to 3 input images
- Up to 8 seconds
- 720p, 1080p or 4K output
- Start and end frames
在 Playground 中运行 Veo 3.1
The form is the request body: every field shows its key. Sign in to run it; a run is billed like an API task.
参数
modelVeo 3.1Lite text to videogoogle-veo3-1-lite-text-to-video-stable
高级参数 (2)
input.negativePromptElements to exclude from the generated video. 0–20000 chars
input.seedRandom seed for reproducible results. -1–2147483647
任务接收时预留额度,仅成功后扣费。失败任务释放预留额度;结果未确认时会保留额度,直到核实。
请求预览
{"model": "google-veo3-1-lite-text-to-video-stable","input": {"aspectRatio": "16:9","resolution": "1080p","duration": "6"}}网页 Playground 使用你的登录会话发送此请求体。在代码中请使用 API Key 发送相同内容。
结果
运行请求后,结果会显示在这里,并附上状态和费用。
Veo 3.1 价格
各可用版本和规格的价格以美元显示,计费单位随费率注明;只有找到可匹配的官方标价时才显示参考价格。
- Charged only on success仅对成功任务扣费。失败任务释放预留额度;结果尚未确认的任务会保留额度,直到结果核实。
- Safe retries使用相同幂等密钥重试不会重复扣费。
- Price changes发送 expectedPriceMicros:若展示后价格发生变化,任务会以 PRICE_CHANGED 被拒绝。
对比 Veo 3.1 各版本
每个变体都有独立的模型 ID 和输入参数。请先选择任务和版本;变体存在差异时会显示额外字段。
google-veo3-1-pro-start-end-to-video-channel-low-price图生视频; 文本, 图像; 8 s; 720p, 1080p, 4K; 16:9, 9:16
firstFrameUrllastFrameUrldurationgoogle-veo3-1-pro-image-to-video-channel-low-price图生视频; 文本, 图像; 8 s; 720p, 1080p, 4K; 16:9, 9:16
imageUrldurationgoogle-veo3-1-fast-start-end-to-video-channel-low-price图生视频; 文本, 图像; 8 s; 720p, 1080p, 4K; 16:9, 9:16
firstFrameUrllastFrameUrldurationgoogle-veo3-1-fast-image-to-video-channel-low-price图生视频; 文本, 图像; 8 s; 720p, 1080p, 4K; 16:9, 9:16
imageUrlsdurationgoogle-veo3-1-pro-text-to-video-channel-low-price文生视频; 文本; 8 s; 720p, 1080p, 4K; 16:9, 9:16
google-veo3-1-fast-text-to-video-channel-low-price文生视频; 文本; 8 s; 720p, 1080p, 4K; 16:9, 9:16
google-veo3-1-lite-start-end-to-video-stable图生视频; 文本, 图像; 720p, 1080p; 16:9, 9:16
firstImageUrllastImageUrlnegativePromptseedgoogle-veo3-1-lite-image-to-video-stable图生视频; 文本, 图像; 4–8 s; 720p, 1080p; 16:9, 9:16
negativePromptimageUrldurationseedgoogle-veo3-1-lite-text-to-video-stable文生视频; 文本; 4–8 s; 720p, 1080p; 16:9, 9:16
negativePromptseed
| 版本 | 任务类型 | 输入 | 时长 | 分辨率 | Aspect ratios | Extra fields |
|---|---|---|---|---|---|---|
Pro start end to videogoogle-veo3-1-pro-start-end-to-video-channel-low-price | 图生视频 | 文本, 图像 | 8 s | 720p, 1080p, 4K | 16:9, 9:16 | firstFrameUrllastFrameUrlduration |
Pro image to videogoogle-veo3-1-pro-image-to-video-channel-low-price | 图生视频 | 文本, 图像 | 8 s | 720p, 1080p, 4K | 16:9, 9:16 | imageUrlduration |
Fast start end to videogoogle-veo3-1-fast-start-end-to-video-channel-low-price | 图生视频 | 文本, 图像 | 8 s | 720p, 1080p, 4K | 16:9, 9:16 | firstFrameUrllastFrameUrlduration |
Fast image to videogoogle-veo3-1-fast-image-to-video-channel-low-price | 图生视频 | 文本, 图像 | 8 s | 720p, 1080p, 4K | 16:9, 9:16 | imageUrlsduration |
Pro text to video默认值google-veo3-1-pro-text-to-video-channel-low-price | 文生视频 | 文本 | 8 s | 720p, 1080p, 4K | 16:9, 9:16 | — |
Fast text to videogoogle-veo3-1-fast-text-to-video-channel-low-price | 文生视频 | 文本 | 8 s | 720p, 1080p, 4K | 16:9, 9:16 | — |
Lite start end to videogoogle-veo3-1-lite-start-end-to-video-stable | 图生视频 | 文本, 图像 | — | 720p, 1080p | 16:9, 9:16 | firstImageUrllastImageUrlnegativePromptseed |
Lite image to videogoogle-veo3-1-lite-image-to-video-stable | 图生视频 | 文本, 图像 | 4–8 s | 720p, 1080p | 16:9, 9:16 | negativePromptimageUrldurationseed |
Lite text to videogoogle-veo3-1-lite-text-to-video-stable | 文生视频 | 文本 | 4–8 s | 720p, 1080p | 16:9, 9:16 | negativePromptseed |
Veo 3.1 能做什么
Google describes Veo 3.1 as a video model with native audio and creative controls such as reference images and first and last frames. These are manufacturer-level capabilities; the controls available through Hermes depend on the individual variant and request fields shown below. Google also publishes a separate Veo 3.1 Lite model card describing its text- and image-conditioned video with audio.
Veo 3.1 on Hermes AI API comes in three tiers, each with its own model IDs. Pro and Fast cover text to video, image to video and start and end frames, at 720p, 1080p or 4K and a fixed 8 second duration. Lite covers the same three tasks at 720p or 1080p; its text and image to video variants take a duration of 4, 6 or 8 seconds, and it adds negativePrompt and seed.
The listed variants offer 16:9 or 9:16 through aspectRatio. The image inputs differ by variant: one imageUrl, up to three imageUrls on Fast image to video, or a first and last frame for transitions.
Check the current status and price of the exact variant before sending a task. Manufacturer features such as scene extension should not be assumed to be available unless the selected Hermes schema lists the corresponding input.
能力
Up to 8 seconds
Clips are 8 seconds long.
durationEvery variant except Lite start end to video
Start and end frames
Set the first frame and, optionally, the last frame the clip moves to.
firstFrameUrllastFrameUrlfirstImageUrllastImageUrl版本: Pro start end to video, Fast start end to video, Lite start end to video
720p, 1080p or 4K output
Pick the output resolution: 720p, 1080p or 4K.
resolutionEvery variant
2 aspect ratios
16:9 or 9:16.
aspectRatioEvery variant
Up to 3 input images
Send up to 3 images in one request as HTTPS URLs or uploaded media references.
imageUrls版本: Fast image to video
反向提示词
Describe what to keep out of the result.
negativePrompt版本: Lite start end to video, Lite image to video, Lite text to video
随机种子
Accepts a seed value.
seed版本: Lite start end to video, Lite image to video, Lite text to video
使用场景
Vertical and horizontal video
Choose 9:16 for vertical placements or 16:9 for players and presentations.
Transitions between two frames
The start and end frame variants take a first frame and a last frame and generate the motion between them.
Animate a still image
Image to video turns a product shot or an illustration into a clip.
用代码调用 Veo 3.1
Every image, video and music model uses the same asynchronous job API: submit a task, then poll for the result.
- 1
创建 API Key
In the dashboard, with the jobs:create and jobs:read scopes. API 密钥 - 2
提交任务
POST /api/v1/jobswith the model ID and an input object. The response is 202 with a task ID. - 3
Poll for the result
GET /api/v1/jobs/{id}until the status is succeeded, then download the output URLs.
最小请求
Required fields only, generated from the schema of Lite text to video. Set HERMES_API_KEY in your environment.
- 模型 ID
google-veo3-1-lite-text-to-video-stable- 端点
https://api.hermes-ai.net/api/v1/jobs
# 1. Submit the task (asynchronous; returns 202 with a task id)
curl -X POST https://api.hermes-ai.net/api/v1/jobs \
-H "Authorization: Bearer $HERMES_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $(uuidgen)" \
-d '{
"model": "google-veo3-1-lite-text-to-video-stable",
"input": {
"prompt": "A lighthouse on a rocky coast at sunrise, soft light",
"resolution": "1080p",
"duration": "6"
}
}'
# 2. Poll until status is succeeded, failed or reconciliation_required
curl https://api.hermes-ai.net/api/v1/jobs/TASK_ID \
-H "Authorization: Bearer $HERMES_API_KEY"输入参数
Fields of Lite text to video (google-veo3-1-lite-text-to-video-stable). 未知字段会被拒绝并返回 INVALID_MODEL_INPUT。
| 字段 | 类型 | 必填 | 默认值 | 可选值与约束 |
|---|---|---|---|---|
prompt | string | 必填 | — | Text description of the scene, motion, camera style, and atmosphere. 1–20000 chars |
negativePrompt | string | 可选 | — | Elements to exclude from the generated video. 0–20000 chars |
aspectRatio | string | 可选 | "16:9" | Output aspect ratio. 可选值: |
resolution | string | 必填 | "1080p" | Output resolution. 可选值: |
duration | string | 必填 | "6" | 可选值: |
seed | integer | 可选 | — | Random seed for reproducible results. -1–2147483647 |
Headers, response, task statuses and errors
| 请求头 | 值 | 说明 |
|---|---|---|
Authorization | Bearer <API key> | 也可以通过 x-api-key 发送密钥。 |
Content-Type | application/json | |
Idempotency-Key | <unique string ≤128> | 必填。仅在重试完全相同的请求时复用。 |
| 字段 | 类型 | 说明 |
|---|---|---|
id | string | Hermes AI 任务 ID,用于轮询。 |
model | string | 模型 slug。 |
status | string | 参见任务状态。 |
errorCode | string | null | 任务失败或需要核对时设置。 |
priceMicros | integer | 接收时锁定的报价,美元微单位。 |
currency | "USD" | |
createdAt / updatedAt | string | ISO 8601 时间戳。 |
assets[] | array | { id, type, url?, text? }。url 为同源 /api/v1/results/<uuid> 链接。 |
replayed | boolean | 仅提交时返回。幂等重试命中时为 true。 |
| 状态 | 终态 | 含义 |
|---|---|---|
queued | 否 | 已接收,等待执行。 |
submitting | 否 | 正在提交给模型提供方。 |
running | 否 | 模型生成中。 |
succeeded | 是 | 已完成,结果位于 assets。 |
failed | 是 | 未产生结果,预留额度已释放。 |
reconciliation_required | 是 | 结果正在核实。请保留任务 ID,不要自动重新提交。 |
| HTTP | 代码 | 含义与处理方式 |
|---|---|---|
401 | AUTH_REQUIRED | 缺少或无效的 API Key 或会话。 |
403 | INSUFFICIENT_SCOPE | API Key 缺少此端点所需的权限。 |
403 | PERMISSION_DENIED | 此凭据无权执行该操作。 |
429 | API_KEY_RATE_LIMITED | 已达到 API Key 的频率限制,请遵循 Retry-After。 |
429 | API_KEY_USAGE_EXCEEDED | API Key 已达到使用上限,请创建新密钥。 |
400 | INVALID_REQUEST | 请求体不是 JSON 对象,或缺少必需值。 |
400 | INVALID_IDEMPOTENCY_KEY | Idempotency-Key 必须是 1–128 个可打印 ASCII 字符。 |
400 | INVALID_MODEL_INPUT | input 与模型 schema 不匹配(未知字段、缺少必填字段或值无效)。 |
400 / 413 | INPUT_TOO_LARGE | 请求体超过 256 KB。请先上传媒体并发送媒体引用。 |
404 | REQUEST_NOT_FOUND | No chat request with this ID belongs to your account. |
404 | MODEL_NOT_FOUND | 没有此 slug 对应的模型。 |
404 | JOB_NOT_FOUND | 你的账户中没有此 ID 的任务。 |
409 | IDEMPOTENCY_CONFLICT | 此 Idempotency-Key 已用于不同的输入。新请求请使用新密钥。 |
409 | PRICE_CHANGED | 价格与 expectedPriceMicros 不一致。请重新获取价格并确认。 |
409 | MODEL_PRICE_UNAVAILABLE | 此模型尚未配置价格,暂不可运行。 |
409 | PAYMENT_REVIEW_REQUIRED | 退款后余额不足。请联系支持或补足余额后再提交任务。 |
409 | INSUFFICIENT_CREDITS | 可用额度不足以支付此任务。 |
429 | RATE_LIMITED | 每分钟提交次数过多,请稍后重试。 |
429 | EXPORT_RATE_LIMITED | 本分钟内导出 CSV 次数过多,请按 Retry-After 等待后重试。 |
429 | CONCURRENCY_LIMITED | 未完成任务过多,请等待任务完成。 |
503 | EXECUTION_UNAVAILABLE | 此模型当前未配置执行能力。 |
429 | UPSTREAM_RATE_LIMITED | The model provider is rate limiting chat requests. Retry with backoff; nothing was charged. |
502 | UPSTREAM_ERROR | The model provider failed the chat request. Nothing was charged; retry later. |
503 | PLATFORM_BUDGET_EXCEEDED | 此模型暂时不可用,请稍后重试。 |
503 | EXECUTION_TEMPORARILY_UNAVAILABLE | 执行暂时不可用,请使用相同的 Idempotency-Key 重试。 |
503 | AUTH_UNAVAILABLE | 身份验证暂时不可用,请稍后重试。 |
503 | API_UNAVAILABLE | API 暂时不可用,请稍后重试。 |
Veo 3.1 API 常见问题
Answers built from the model's schema and the Hermes AI API contract.
Which Veo 3.1 variants output 4K?
The Pro and Fast variants list 4k in resolution, next to 720p and 1080p. The Lite variants list 720p and 1080p only.
How long are Veo 3.1 clips?
Pro and Fast take a duration of 8 seconds. Lite text to video and image to video take 4, 6 or 8 seconds.
What can the Veo 3.1 API do?
Google 的 Veo 3.1 支持图生视频 和 文生视频。目录列有9 variants, each,每个变体都有自己的模型 ID 和输入参数。提交请求前请先确认当前可用状态。
Which durations, resolutions and aspect ratios does Veo 3.1 support?
Across its variants, Veo 3.1 supports durations from 4 to 8 seconds, 720p, 1080p 和 4K resolution 和 aspect ratios 16:9 和 9:16. Each variant accepts its own subset; the variants table on this page lists them.
What input does Veo 3.1 accept?
A text prompt of up to 20,000 characters, plus 图像 input (up to 3 images per request). Media fields take a public HTTPS URL or a media:<uuid> reference returned by POST /api/v1/media, so local files can be uploaded first. 未知字段会被拒绝并返回 INVALID_MODEL_INPUT。
How is Veo 3.1 priced and billed?
You pay per successful task from prepaid credits, with no subscription. The price depends on the variant and the specification you choose, such as resolution or duration; see the pricing table on this page or the pricing page. Credits are reserved when a task is accepted and charged only when it succeeds; a failed task returns the reservation to your balance.
Which Veo 3.1 variant should I choose?
For 图生视频, Pro start end to video, Pro image to video, Fast start end to video, Fast image to video, Lite start end to video 和 Lite image to video differ in fields: Pro start end to video adds firstFrameUrl, lastFrameUrl, duration; Pro image to video adds imageUrl, duration; Fast start end to video adds firstFrameUrl, lastFrameUrl, duration; Fast image to video adds imageUrls, duration; Lite start end to video adds firstImageUrl, lastImageUrl, negativePrompt, seed; Lite image to video adds negativePrompt, imageUrl, duration, seed; for 文生视频, Pro text to video, Fast text to video 和 Lite text to video differ in fields: Lite text to video adds negativePrompt, seed. Pick the task first, then compare the tiers in the variants table.
How do I call the Veo 3.1 API from code?
Send POST https://api.hermes-ai.net/api/v1/jobs with the variant's model ID and an input object, then poll GET /api/v1/jobs/{id} until the status is succeeded or failed. The API section has cURL, JavaScript and Python examples generated from the schema.
Can I try Veo 3.1 without writing code?
Yes. Sign in and use the playground on this page: it sends the same request as the API with your session and charges the same price. Code needs an API key from the dashboard.
What happens when a task fails or I hit a rate limit?
A failed task is not charged and its reserved credits are returned. Too many submissions per minute return 429 RATE_LIMITED, and too many unfinished tasks return 429 CONCURRENCY_LIMITED; retry later or wait for a task to finish.