POST
/
api
/
v1
/
veo
/
generate
Generate Veo3 Video
curl --request POST \
  --url https://api.veo3api.ai/api/v1/veo/generate \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "prompt": "A dog playing in a park",
  "imageUrls": [
    "http://example.com/image1.jpg"
  ],
  "model": "veo3",
  "watermark": "MyBrand",
  "callBackUrl": "http://your-callback-url.com/complete",
  "aspectRatio": "9:16",
  "seeds": 123456,
  "enableFallback": false
}'
{
  "code": 200,
  "msg": "success",
  "data": {
    "taskId": "veo_task_abcdef123456"
  }
}
This document serves as the API documentation for Google Veo 3, which primarily includes two models: Veo 3 Quality API and Veo 3 Fast API. The primary difference between these models lies in their parameters, with ‘veo3’ corresponding to Veo 3 Quality and ‘veo3_fast’ representing the Fast model. Before diving into the specifics, here are some general details you should be aware of:
  1. Both Veo 3 Quality and Veo 3 Fast support text-to-video and image-to-video generation. The pricing for these APIs is significantly lower, being up to 70% more affordable than mainstream alternatives. For more details, please visit Billing Information.
  2. Currently, the concurrency is set to allow up to 20 new generation requests within a 10-second window. This quota is more than sufficient for most use cases.
  3. Veo 3 follows a strict censoring policy, which may result in some false positives where compliant content could be rejected. We’re awaiting an official fix from the team.
  4. You can obtain the results through two methods: via callback or by using the “get info” interface.
  5. We retain generated files for 14 days. After this period, files will be deleted, so it’s important to store them securely.
  6. If you encounter issues during development, it’s highly recommended to copy the relevant documentation and ask the AI for assistance. In most cases, this will help you resolve the issue faster. Should you need to contact us, feel free to reach out via Discord or Telegram, but remember to include the task ID to help us identify the issue.
  7. We also provide an n8n workflow for those who are less familiar with coding, making it easier to get started.

​
Intelligent Fallback (enableFallback)

We’ve added a fallback mechanismto the Veo 3 API. If Google’s strict content filters wrongly flag a normal prompt or image—triggering errors like**“public error minor upload,” “content policy violations,”or“public error prominent people upload”—you can now reroute the request through an alternative, more lenient Veo 3 channel.The fallback usesthe same Veo 3 model, with audio and the same quality;**only the path changes, greatly reducing false positives and boosting success rates.
PropertyTypeDefault
enableFallbackbooleanfalse
SettingenableFallback: trueinstructs the platform to reroute eligible failures to the secondary Veo 3 backend, raising completion rates for edge cases.

​
Limitations

  • 16 : 9 only – non‑conforming inputs are auto‑cropped before retry.
  • Billing – a successful fallback consumes a separate (higher‑priced) credit tier. See veo3api.ai/billing for the exact table.
Behaviour when disabledWithenableFallbackleft atfalse(default), the errors above surface as HTTP422responses and no additional credits are consumed.

​
Fallback Functionality

By setting the enableFallback parameter, you can enable intelligent fallback functionality. When the primary model encounters specific errors, the system will automatically switch to a backup model to continue generation, improving task success rates. Fallback Features:
  • Enabling Conditions: Set enableFallback: true, aspect ratio 16:9, and encounter specific errors
  • Applicable Errors: public error minor upload, content policy violations, public error prominent people upload
  • Image Requirements: Must be 16:9 ratio, otherwise automatic cropping will occur
  • Credit Calculation: Successful fallback has different credit consumption, please see https://veo3api.ai/billing for billing details.
  • Resolution: Fallback videos now default to 1080p resolution, but the Get 1080P Video endpoint may not work for fallback videos
Important Notes
  • Fallback functionality only takes effect in specific error scenarios
  • When fallback is not enabled, encountering fallback-eligible errors will return a 422 status code
  • While fallback videos now generate at 1080p resolution, the dedicated 1080p upgrade endpoint may not be compatible with fallback-generated videos

Authorizations

​
Authorization
string
header
required

All APIs require authentication via Bearer Token.

Get API Key:

  1. Visit API Key Management Page to get your API Key

Usage: Add to request header: Authorization: Bearer YOUR_API_KEY

Body

application/json

Response

200
application/json

Request successful

The response is of type object.