Veo 3.1 API Reference

Overview

Property	Value
Model ID	`veo-3-1`
Type	Text-to-Video, Image-to-Video
Pricing	Fast: $0.2/video · Quality: $1.5/video
Average Time	120 seconds

Authentication

All API requests require authentication using a Bearer token in the Authorization header:

Authorization: Bearer YOUR_API_KEY

Endpoints

1. Submit Generation Task

POST https://api.apixo.ai/api/v1/generateTask/veo-3-1

2. Query Task Status

GET https://api.apixo.ai/api/v1/statusTask/veo-3-1?taskId={taskId}

Request Parameters

Request Body Structure

{
  "request_type": "async",
  "callback_url": "https://your-server.com/callback",
  "input": {
    "mode": "quality",
    "prompt": "Your video description",
    "generationType": "TEXT_2_VIDEO",
    ...
  }
}

Top-Level Parameters

Parameter	Type	Required	Description
`request_type`	string	Yes	Request mode: `async` (poll results) or `callback` (webhook notification)
`callback_url`	string	No	Webhook URL for callback mode. Must be publicly accessible
`input`	object	Yes	Generation parameters (see below)

Input Parameters

Parameter	Type	Required	Default	Description
`mode`	string	Yes	`quality`	Quality mode: `quality` ($1.5, high quality) or `fast` ($0.2, cost-effective)
`prompt`	string	Yes	-	Video description (max 10,000 characters)
`generationType`	string	Yes	-	Generation type: `TEXT_2_VIDEO`, `FIRST_AND_LAST_FRAMES_2_VIDEO`, or `REFERENCE_2_VIDEO`
`image_urls`	string[]	No	-	1-3 images for image-to-video (max 10MB, JPG/PNG). Count depends on generationType
`aspect_ratio`	string	No	`16:9`	Aspect ratio: `16:9`, `9:16`, or `auto`
`enableTranslation`	boolean	No	`true`	Auto-translate non-English prompts
`watermark`	string	No	-	Custom watermark text
`seed`	integer	No	-	Random seed for reproducibility

Generation Types:

TEXT_2_VIDEO: Text-only, no images
FIRST_AND_LAST_FRAMES_2_VIDEO: 1 image (base frame) or 2 images (first & last frame transition)
REFERENCE_2_VIDEO: Up to 3 reference images (fast mode & 16:9 only)

Response Format

Task Submission Response

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678"
  }
}

Status Query Response

Processing:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678",
    "state": "processing",
    "createTime": 1698765400000
  }
}

Success:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678",
    "state": "success",
    "resultJson": "{\"resultUrls\":[\"https://example.com/video.mp4\"]}",
    "costTime": 125000,
    "createTime": 1698765400000,
    "completeTime": 1698765525000
  }
}

Failed:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678",
    "state": "failed",
    "failCode": "CONTENT_VIOLATION",
    "failMsg": "Content does not meet safety guidelines",
    "createTime": 1698765400000,
    "completeTime": 1698765525000
  }
}

Response Fields:

Field	Type	Description
`code`	integer	HTTP status code (200 = success)
`data.taskId`	string	Unique task identifier
`data.state`	string	Task state: `pending`, `processing`, `success`, `failed`
`data.resultJson`	string	JSON string with `resultUrls` array (on success)
`data.costTime`	integer	Generation time in milliseconds
`data.failCode`	string	Error code (on failure)
`data.failMsg`	string	Error message (on failure)

Callback Response

When the task is completed, the system will send a POST request to your callBackUrl in the following format:

Success Callback

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678",
    "state": "success",
    "resultJson": "{\"resultUrls\":[\"https://example.com/result.mp4\"]}",
    "completeTime": 1698765525000,
    "createTime": 1698765400000,
    "costTime": 125000
  }
}

Failure Callback

{
  "code": 400,
  "message": "failed",
  "data": {
    "taskId": "task_12345678",
    "state": "failed",
    "failCode": "CONTENT_VIOLATION",
    "failMsg": "Content does not meet safety guidelines",
    "completeTime": 1698765525000,
    "createTime": 1698765400000,
    "costTime": 125000
  }
}

Quick Start

1. Text-to-Video Generation

curl -X POST https://api.apixo.ai/api/v1/generateTask/veo-3-1 \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "request_type": "async",
    "input": {
      "mode": "fast",
      "prompt": "A dog playing in a park",
      "generationType": "TEXT_2_VIDEO",
      "aspect_ratio": "16:9"
    }
  }'

Response:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678"
  }
}

2. Check Task Status

curl -X GET "https://api.apixo.ai/api/v1/statusTask/veo-3-1?taskId=task_12345678" \
  -H "Authorization: Bearer YOUR_API_KEY"

Response (Success):

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678",
    "state": "success",
    "resultJson": "{\"resultUrls\":[\"https://example.com/video.mp4\"]}"
  }
}

3. Image-to-Video with Frame Transition

curl -X POST https://api.apixo.ai/api/v1/generateTask/veo-3-1 \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "request_type": "async",
    "input": {
      "mode": "quality",
      "prompt": "Smooth transition between the two landscapes",
      "generationType": "FIRST_AND_LAST_FRAMES_2_VIDEO",
      "image_urls": [
        "https://example.com/first-frame.jpg",
        "https://example.com/last-frame.jpg"
      ],
      "aspect_ratio": "16:9"
    }
  }'

Best Practices

Request Mode Selection

Mode	Use When
Callback	Production environments with public server endpoints
Async	Client-side apps or when webhook setup is not feasible

Performance Tips

Async Mode: Wait 120 seconds before first poll, then poll every 10 seconds
Timeout: Set maximum wait time to 10 minutes
Rate Limiting: Avoid excessive concurrent requests
Error Handling: Always check state field and handle failures gracefully

Resource Management

Video URLs may be temporary - download and store important results
Clean up failed tasks appropriately
Log taskId for debugging and support
REFERENCE_2_VIDEO mode only supports fast mode and 16:9 aspect ratio