Veo3.1-Lite Video Generation

curl --request POST \
  --url https://api.evolink.ai/v1/videos/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "veo-3.1-lite-generate-preview",
  "prompt": "A golden retriever puppy running through a sunlit meadow, slow motion, cinematic lighting"
}
'

{
  "created": 1757169743,
  "id": "task-unified-1757169743-7cvnl5zw",
  "model": "veo-3.1-lite-generate-preview",
  "object": "video.generation.task",
  "progress": 0,
  "status": "processing",
  "task_info": {
    "can_cancel": false,
    "estimated_time": 600,
    "video_duration": 4
  },
  "type": "video",
  "usage": {
    "billing_rule": "per_call",
    "credits_reserved": 12.24,
    "user_group": "default"
  }
}

{
  "error": {
    "code": "invalid_parameter",
    "message": "Invalid request parameters",
    "type": "invalid_request_error"
  }
}

{
  "error": {
    "code": "unauthorized",
    "message": "Invalid or expired token",
    "type": "authentication_error"
  }
}

{
  "error": {
    "code": "insufficient_quota",
    "message": "Insufficient quota. Please top up your account.",
    "type": "insufficient_quota"
  }
}

{
  "error": {
    "code": "model_access_denied",
    "message": "Token does not have access to model: veo-3.1-lite-generate-preview",
    "type": "invalid_request_error"
  }
}

{
  "error": {
    "code": "rate_limit_exceeded",
    "message": "Too many requests, please try again later",
    "type": "rate_limit_error"
  }
}

{
  "error": {
    "code": "internal_error",
    "message": "Internal server error",
    "type": "api_error"
  }
}

POST

videos

generations

curl --request POST \
  --url https://api.evolink.ai/v1/videos/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "veo-3.1-lite-generate-preview",
  "prompt": "A golden retriever puppy running through a sunlit meadow, slow motion, cinematic lighting"
}
'

{
  "created": 1757169743,
  "id": "task-unified-1757169743-7cvnl5zw",
  "model": "veo-3.1-lite-generate-preview",
  "object": "video.generation.task",
  "progress": 0,
  "status": "processing",
  "task_info": {
    "can_cancel": false,
    "estimated_time": 600,
    "video_duration": 4
  },
  "type": "video",
  "usage": {
    "billing_rule": "per_call",
    "credits_reserved": 12.24,
    "user_group": "default"
  }
}

{
  "error": {
    "code": "invalid_parameter",
    "message": "Invalid request parameters",
    "type": "invalid_request_error"
  }
}

{
  "error": {
    "code": "unauthorized",
    "message": "Invalid or expired token",
    "type": "authentication_error"
  }
}

{
  "error": {
    "code": "insufficient_quota",
    "message": "Insufficient quota. Please top up your account.",
    "type": "insufficient_quota"
  }
}

{
  "error": {
    "code": "model_access_denied",
    "message": "Token does not have access to model: veo-3.1-lite-generate-preview",
    "type": "invalid_request_error"
  }
}

{
  "error": {
    "code": "rate_limit_exceeded",
    "message": "Too many requests, please try again later",
    "type": "rate_limit_error"
  }
}

{
  "error": {
    "code": "internal_error",
    "message": "Internal server error",
    "type": "api_error"
  }
}

Authorizations

Authorization

string

header

required

All APIs require Bearer Token authentication

Get API Key:

Visit API Key Management Page to get your API Key

Add to request header:

Authorization: Bearer YOUR_API_KEY

Body

application/json

model

enum<string>

default:veo-3.1-lite-generate-preview

required

Video generation model name. image_start, image_end and model_params are not accepted on this model (returns 400)

Available options:

veo-3.1-lite-generate-preview

Example:

"veo-3.1-lite-generate-preview"

prompt

string

required

Prompt describing the video, up to 2000 tokens. Counted with cl100k; tokens are not characters. Google lists English as the supported prompt language. EvoLink does not reject requests based on prompt language; results in other languages are not guaranteed.

Example:

"A golden retriever puppy running through a sunlit meadow, slow motion, cinematic lighting"

image_urls

string<uri>[]

Input image URLs for image-to-video

Notes:

Up to 2 images per request: 1 image is used as the first frame, 2 images are used as the first and last frames
Image size: no larger than 10 MB
Supported file formats: .jpg, .jpeg, .png

Maximum array length: 2

Example:

["https://example.com/first-frame.jpg"]

generation_type

enum<string>

Generation mode. When omitted it is inferred from the number of images:

TEXT: Text-to-video (input images, if any, are not used)
FIRST&LAST: First-last frame, 1-2 images

REFERENCE (reference images) is not supported by this model and returns 400

Available options:

TEXT,

FIRST&LAST

aspect_ratio

enum<string>

Video aspect ratio. auto is the same as omitting aspect_ratio: no ratio is specified and the model decides

Available options:

auto,

16:9,

9:16

generate_audio

boolean

default:true

Whether to generate audio, default true. Generating audio increases the per-second rate

duration

enum<integer>

default:4

Video duration in seconds, default 4. Longer videos cost more

Available options:

4,

6,

8

integer

default:1

Number of videos to generate, default 1. Each video is billed separately

Required range: 1 <= x <= 4

quality

enum<string>

default:720p

Output resolution, default 720p. 1080p has a higher per-second rate; 4k is not supported by this model

Available options:

720p,

1080p

seed

integer

Random seed used to reproduce generation results

Required range: 1 <= x <= 4294967295

negative_prompt

string

Negative prompt describing content to exclude from the video

person_generation

enum<string>

Person generation control. When omitted, the upstream default is allow_adult. allow_adult: allow adults only; dont_allow: do not generate videos containing people or faces

Available options:

allow_adult,

dont_allow

resize_mode

enum<string>

Image resize mode for image-to-video. When omitted, the upstream default is pad. pad: add padding to fit the output aspect ratio; crop: center-crop to fit the output aspect ratio. Requires an input image; providing this parameter without an image returns 400

Available options:

pad,

crop

callback_url

string<uri>

HTTPS callback URL for task completion

Callback Timing:

Triggered when the task is completed or failed
Sent after billing confirmation

Security Restrictions:

HTTPS protocol only
Internal IP addresses are prohibited (127.0.0.1, 10.x.x.x, 172.16-31.x.x, 192.168.x.x, etc.)
URL length must not exceed 2048 UTF-8 bytes

Callback Mechanism:

Timeout: 10 seconds
Maximum 3 retries after failure (at 1/2/4 seconds after failure)
Callback response format is consistent with task query API
2xx status code is considered successful, other codes trigger retry

Example:

"https://your-domain.com/webhooks/video-task-completed"

Response

Video generation task created successfully

created

integer

Task creation timestamp

Example:

1757169743

string

Task ID

Example:

"task-unified-1757169743-7cvnl5zw"

model

string

Actual model name used

Example:

"veo-3.1-lite-generate-preview"

object

enum<string>

Specific type of the task

Available options:

video.generation.task

progress

integer

Task progress percentage (0-100)

Required range: 0 <= x <= 100

Example:

0

status

enum<string>

Task status

Available options:

pending,

processing,

completed,

failed

Example:

"processing"

task_info

object

Video task details

Show child attributes

type

enum<string>

Output type of the task

Available options:

text,

image,

audio,

video

Example:

"video"

usage

object

Usage and billing information

Show child attributes

Image Series

Video Series

Audio Series

Text Series

Account Management

Task Management

File Management

Veo3.1-Lite Video Generation

Authorizations

All APIs require Bearer Token authentication

Body

Response