Veo 3.1 Fast

NEW

Model ID

Put this value in the request body's `model` field — not the display name above.

Video generationClosed source

by Google · Google Veo video generation (asynchronous task).

Try it now

Quick start

EndpointPOST /v1/videos/generations
AuthenticationAuthorization: Bearer sk-gpushare-…Get API key
Call styleAsynchronous: submit for an ID, then poll until it settles
Base URLhttps://qd.zsopc.com/v1
① Submit the task · cURL
curl https://qd.zsopc.com/v1/videos/generations \
  -H "Authorization: Bearer sk-gpushare-xxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "tvod-veo-3.1-fast",
    "content": [
      {"type": "text", "text": "海边日落,无人机航拍视角 --ratio 16:9"}
    ],
    "duration": 5
  }'
# 返回 {"id": "...", "status": "queued"}
# 图生视频:content 里追加 {"type":"image_url","image_url":{"url":"https://..."}}
# ⚠️ duration 缺省按 12 秒预扣,结算按实际时长 —— 建议显式传
② Poll for the result · cURL
curl https://qd.zsopc.com/v1/videos/generations/$TASK_ID \
  -H "Authorization: Bearer sk-gpushare-xxxxxxxx"

# status: queued -> running -> succeeded / failed / expired / cancelled
# 建议 5-10 秒轮询一次。轮询免费。

This is an async task: submit for a task ID, then poll until it settles. Polling itself is free.

Pricing

Billed per second of delivered video; tiered SKUs use the rate for the resolution actually delivered.

Rates
per second720p40.44Credits1080p48.528Credits
Settlement
Pre-authorize on submit (by requested length) → settle on actual length → refund the difference
  • Unit price × your requested `duration` is pre-authorized on submit, settled against the actual delivered length with the difference refunded; failed or expired tasks are refunded in full.
  • With no `duration`, 12 seconds is pre-authorized — pass it explicitly so less of your balance is held.
  • Failed or expired tasks are refunded in full.
  • Polling task status is free and does not count toward usage.
  • All your API keys share one balance; when it runs out the API returns HTTP 402 `quota_exceeded`.

Sign in and any personal discount on your account will show up here. Sign in

Capabilities & specs

Category
Video generation
Endpoint family
Video generation (Videos)
Released
2026-06-26
License
Closed source

Try it

Models like this bill for real per image / per second / per call and are mostly async tasks, so there is no one-click test here. Use the sample code above, or generate in the matching workbench (which has a parameter panel and a cost estimate).

Open the workbench

Common errors

404 model_not_found

You passed the display name instead of the model ID.✗ Veo 3.1 Fast→✓ tvod-veo-3.1-fast

→ Copy the Model ID at the top of this page

402 quota_exceeded

Insufficient account balance. All your API keys share one balance.

→ Add funds in your account

401 / 403

The API key is invalid, or it has a model allowlist that doesn't include this ID.

→ Check the key's status and allowed models

400 invalid_request

`resolution` is required on Lite (`-lite`) SKUs and only accepts 720p / 1080p; anything else also returns 400.

→ Check your request body against the sample code above

Try it

Veo 3.1 Fast FAQ

How do I call Veo 3.1 Fast?
Set the model field of the request body to tvod-veo-3.1-fast, send it to https://qd.zsopc.com/v1/videos/generations, and put your key (it starts with sk-gpushare-) in the Authorization: Bearer header. This is not a chat SKU; submit tasks to the dedicated endpoint above.
How much does the Veo 3.1 Fast API cost?
  • 720p, per second of output: 40.44 credits (≈ ¥0.674 / ≈ $0.1)
  • 1080p, per second of output: 48.53 credits (≈ ¥0.809 / ≈ $0.12)
  • Prices are in credits: 60 credits = ¥1. Each call first holds the most it could cost, then settles on actual usage and refunds the difference.

Prices and details updated 2026-11-17. Markdown version of this page: /en/models/tvod-veo-3.1-fast.md

Related