Veo3.1 Video Generation¶

Google DeepMind’s upgraded AI video model for realistic motion generation, extended clip duration, multi-image reference control, and synchronized audio output in native 1080p. Pricing: min 90 credits per video

Authentication¶

All API requests require a Bearer Token in the request header:

x-api-key: YOUR_API_KEY

Get API Key:

Visit API Key to get your API Key
Add to request header: x-api-key: Your_API_Key

1. Create Generation Task¶

API Information¶

URL: POST https://api.revidapi.com/paid/veo/create
Header: x-api-key: Your_API_Key

Capability	Details
Models	• Veo 3.1 Quality — flagship model, highest fidelity • Veo 3.1 Fast — cost‑efficient variant that still delivers strong visual results
Tasks	• Text → Video • Image → Video (single reference frame or first and last frames) •Material → Video (based on material images)
Generation Modes	• TEXT_2_VIDEO — Text-to-video: using text prompts only •FIRST_AND_LAST_FRAMES_2_VIDEO — First and last frames to video: generate transition videos using two images • REFERENCE_2_VIDEO — Material-to-video: based on material images (only supports Fast model and 16:9 aspect ratio)
Aspect Ratios	We now support both native 16:9 and 9:16 outputs, allowing you to generate horizontal or vertical videos without any extra processing. In addition, the Auto mode automatically matches the aspect ratio based on the uploaded image.
Languages	Google’s native support is English‑only; our multilingual prompt pre‑processing extends reliable generation to most major languages.
Audio Track	All videos ship with background audio by default. In < 5 % of cases Google suppresses audio when the scene is deemed sensitive (e.g. minors)
---
### Model Parameter

The model parameter specifies which AI model to use for content generation.

Model	Price	Description
`veo3`	`90 credit`	The exact model identifier for this API
`veo3_fast`	`300 credit`	The exact model identifier for this API

Type string Must be passed as a string value Required yes This parameter is mandatory for all requests

Note: The model parameter must match exactly as shown above. Different models have different capabilities and parameter requirements.

Why our Veo 3.1 API is different¶

True vertical video – Native Veo 3.1 now fully supports 9:16 output, delivering authentic vertical videos without the need for re-framing or manual editing.
Global language reach – Prompt sanitisation, token‑weight rebalancing lift non‑English success rates far above stock Veo 3.1 behaviour.
Significant cost savings – Our rates are 25 % of Google’s direct API pricing.

Request Example¶

curl --request POST \
  --url https://api.revidapi.com/paid/veo/create \
  --header 'x-api-key: Your-API-Key' \
  --Body '
{
  "prompt": "A dog playing in a park",
  "imageUrls": [
    "http://example.com/image1.jpg",
    "http://example.com/image2.jpg"
  ],
  "model": "veo3_fast",
  "watermark": "MyBrand",
  "callBackUrl": "http://your-callback-url.com/complete",
  "aspectRatio": "16:9",
  "seeds": 12345,
  "enableFallback": false,
  "enableTranslation": true,
  "generationType": "REFERENCE_2_VIDEO"
}
'

Response Example¶

{
  "code": 200,
  "msg": "success",
  "data": {
    "taskId": "veo_task_abcdef123456"
  }
}

Body¶

prompt string required

Text prompt describing the desired video content. Required for all generation modes.

Should be detailed and specific in describing video content
Can include actions, scenes, style and other information
For image-to-video, describe how you want the image to come alive

Example:

`"A dog playing in a park"`¶

imageUrls string[]

Image URL list (used in image-to-video mode). Supports 1 or 2 images:

1 image: The generated video will unfold around this image, with the image content presented dynamically
2 images: The first image serves as the video's first frame, and the second image serves as the video's last frame, with the video transitioning between them
Must be valid image URLs
Images must be accessible to the API server.

model enum<string> default:veo3_fast

Select the model type to use.

veo3: Veo 3.1 Quality, supports both text-to-video and image-to-video generation. Pricing :300 credit
veo3_fast: Veo3.1 Fast generation model, supports both text-to-video and image-to-video generation. Pricing: 90 credit

Available options: veo3 , veo3_fast veo3: 300 credit per video veo3_fast: 90 credit per video

Example: "veo3_fast"

generationType enum<string>

Video generation mode (optional). Specifies different video generation approaches:

TEXT_2_VIDEO: Text-to-video - Generate videos using only text prompts
FIRST_AND_LAST_FRAMES_2_VIDEO: First and last frames to video - Flexible image-to-video generation mode
- 1 image: Generate video based on the provided image
- 2 images: First image as first frame, second image as last frame, generating transition video
REFERENCE_2_VIDEO: Reference-to-video - Generate videos based on reference images, requires 1-3 images in imageUrls (minimum 1, maximum 3)

Important Notes:

REFERENCE_2_VIDEO mode currently only supports veo3_fast model and 16:9 aspect ratio
If not specified, the system will automatically determine the generation mode based on whether imageUrls are provided

Available options:TEXT_2_VIDEO, FIRST_AND_LAST_FRAMES_2_VIDEO, REFERENCE_2_VIDEO Example: "TEXT_2_VIDEO"

aspectRatio enum<string> default:16:9

Video aspect ratio. Specifies the dimension ratio of the generated video. Available options:

16:9: Landscape video format, supports 1080P HD video generation (Only 16:9 aspect ratio supports 1080P)
9:16: Portrait video format, suitable for mobile short videos
Auto: In auto mode, the video will be automatically center-cropped based on whether your uploaded image is closer to 16:9 or 9:16.

Default value is 16:9.

Available options:16:9,9:16,Auto

Example:"16:9"

seeds integer

(Optional) Random seed parameter to control the randomness of the generated content. Value range: 10000-99999. The same seed will generate similar video content, different seeds will generate different content. If not provided, the system will assign one automatically.

Required range: 10000 <= x <= 99999

Example: 12345

callBackUrl

string

Completion callback URL for receiving video generation status updates.

Optional but recommended for production use
System will POST task completion status to this URL when the video generation is completed
Callback will include task results, video URLs, and status information
Your callback endpoint should accept POST requests with JSON payload
For detailed callback format and implementation guide,
Alternatively, use the Get Video Details endpoint to poll task status

Example:

"http://your-callback-url.com/complete"

enableFallback boolean default:false deprecated

Deprecated Enable fallback functionality. When set to true, if the official Veo3.1 video generation service is unavailable or encounters exceptions, the system will automatically switch to a backup model for video generation to ensure task continuity and reliability. Default value is false.

When fallback is enabled, backup model will be used for the following errors:
- public error minor upload
- Your prompt was flagged by Website as violating content policies
- public error prominent people upload
Fallback mode requires 16:9 aspect ratio and uses 1080p resolution by default
Note: Videos generated through fallback mode cannot be accessed via the Get 1080P Video endpoint
Credit Consumption: Successful fallback has different credit consumption, please see https://revidapi.com/ for billing details

Note: This parameter is deprecated. Please remove this parameter from your requests. The system has automatically optimized the content review mechanism without requiring manual fallback configuration.

Example: false

enableTranslation boolean default:true

Enable prompt translation to English. When set to true, the system will automatically translate prompts to English before video generation for better generation results. Default value is true.

true: Enable translation, prompts will be automatically translated to English
false: Disable translation, use original prompts directly for generation

Example:true

watermark string Watermark text.

Optional parameter
If provided, a watermark will be added to the generated video

Example: "MyBrand"

2. # Get Veo3.1 Video Details¶

Query the execution status and results of Veo3.1 video generation tasks.

API Information¶

URL: POST https://api.revidapi.com/paid/get/veo/info
Parameter: taskId (passed via URL parameter)

Request Example¶

curl --request POST \
  --url https://api.revidapi.com/paid/get/veo/info \
  --header 'x-api-key: Your-API-Key'

Response Example¶

{
  "code": 200,
  "msg": "success",
  "data": {
    "taskId": "veo_task_abcdef123456",
    "paramJson": "{\"prompt\":\"A futuristic city with flying cars at sunset.\",\"waterMark\":\"RevidAPI\"}",
    "completeTime": "2025-06-06 10:30:00",
    "response": {
      "taskId": "veo_task_abcdef123456",
      "resultUrls": [
        "http://example.com/video1.mp4"
      ],
      "originUrls": [
        "http://example.com/original_video1.mp4"
      ],
      "resolution": "1080p"
    },
    "successFlag": 1,
    "errorCode": null,
    "errorMessage": "",
    "createTime": "2025-06-06 10:25:00",
    "fallbackFlag": false
  }
}

Response Parameters¶

Status Descriptions¶

0: Generating - Task is currently being processed
1: Success - Task completed successfully
2: Failed - Task generation failed
3: Generation Failed - Task created successfully but generation failed

Important Notes¶

Query task status in real-time using taskId
Recommend periodic polling until task completion
Response includes fallbackFlag field indicating whether fallback model was used

Response Field Description¶

fallbackFlag boolean

Whether generated using fallback model. true means backup model was used, false means primary model was used

Fallback Status Identification¶

The fallbackFlag field can identify whether the task used a fallback model:

true: Generated using fallback model, video resolution is 720p
false: Generated using primary model, may support 1080P (16:9 aspect ratio)

3. # Get 1080P Video¶

Get the high-definition 1080P version of a Veo3.1 video generation task.

Note: Videos generated through fallback mode cannot be accessed via this endpoint, as they are already generated in 1080p resolution by default.

API Information¶

URL: POST https://api.revidapi.com/paid/veo/get-1080p-video
Parameter: taskId (passed via URL parameter)

Request Example¶

POST https://api.revidapi.com/paid/veo/get-1080p-video?taskId=281e5b0*********************f39b9

Response Example¶

{
  "code": 200,
  "msg": "success",
  "data": {
    "resultUrl": "https://tempfile.aiquickdraw.com/p/42f4f8facbb040c0ade87c27cb2d5e58_1749711595.mp4"
  }
}

Usage Instructions¶

Only videos with 16:9 aspect ratio support 1080P HD video generation.
1080P generation requires extra processing time (about 2 minutes under normal conditions). Please wait before calling this endpoint.
If the 1080P video is not ready yet, the endpoint may return an error. In this case, simply wait a little longer and retry until the result is available.

Response¶

Response status code

200: Success - Request has been processed successfully
400: Your prompt was flagged by Website as violating content policies. Only English prompts are supported at this time. Failed to fetch the image. Kindly verify any access limits set by you or your service provider. public error unsafe image upload.
401: Unauthorized - Authentication credentials are missing or invalid
404: Not Found - The requested resource or endpoint does not exist
422: Validation Error - The request parameters failed validation checks. record is null. Temporarily supports records within 14 days. record result data is blank. record status is not success. record result data not exist. record result data is empty.
451: Failed to fetch the image. Kindly verify any access limits set by you or your service provider.
455: Service Unavailable - System is currently undergoing maintenance
500: Server Error - An unexpected error occurred while processing the request. Timeout Internal Error, Please try again later.

Veo3.1 Video Generation¶

Authentication¶

1. Create Generation Task¶

API Information¶

Why our Veo 3.1 API is different¶

Request Example¶

Response Example¶

Body¶

"A dog playing in a park"¶

2. # Get Veo3.1 Video Details¶

API Information¶

Request Example¶

Response Example¶

Response Parameters¶

Status Descriptions¶

Important Notes¶

Response Field Description¶

Fallback Status Identification¶

3. # Get 1080P Video¶

API Information¶

Request Example¶

Response Example¶

Usage Instructions¶

Response¶

`"A dog playing in a park"`¶