Skip to main content
POST
/
v1
/
videos
/
generations
curl --request POST \
  --url https://api.foxapi.cc/v1/videos/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "veo-3.1-reference-to-video",
  "prompt": "A woman walking through a garden",
  "reference_image_urls": [
    "https://example.com/ref1.jpg"
  ],
  "duration": 8,
  "resolution": "1080p",
  "reference_type": "STYLE"
}
'
{
  "created": 1757165031,
  "id": "task-unified-1757165031-uyujaw3d",
  "model": "<string>",
  "object": "video.generation.task",
  "progress": 0,
  "status": "pending",
  "task_info": {
    "can_cancel": true,
    "estimated_time": 45
  },
  "type": "video"
}

Authorizations

​
Authorization
string
header
required

All APIs require Bearer Token authentication

Add to request header:

Authorization: Bearer YOUR_API_KEY

Body

application/json
​
model
string
default:veo-3.1-reference-to-video
required

veo-3.1-reference-to-video: Standard reference-to-video veo-3.1-fast-reference-to-video: Fast version

Examples:

"veo-3.1-reference-to-video"

"veo-3.1-fast-reference-to-video"

​
prompt
string
required

Text prompt describing the desired video content

Notes:

  • Supports both Chinese and English
Example:

"A woman walking through a garden"

​
reference_image_urls
string[]
required

List of reference image URLs

Notes:

  • Quantity: 1 - 3 images
  • Multiple reference images are used for character / style consistency
Required array length: 1 - 3 elements
Example:
["https://example.com/ref1.jpg"]
​
aspect_ratio
string
default:16:9

Output video aspect ratio

Options:

  • 16:9 — Landscape (default)
  • 9:16 — Portrait
Example:

"16:9"

​
duration
integer
default:8

Output video duration (seconds)

Notes:

  • Reference-to-video is fixed at 8 seconds
Example:

8

​
resolution
string
default:1080p

Output video resolution

Options:

  • 720p — Standard definition
  • 1080p — High definition (default)
  • 4k — 4K Ultra HD
Example:

"720p"

​
generate_audio
boolean
default:false

Whether to generate accompanying audio

Notes:

  • Disabled by default
Example:

true

​
auto_fix
boolean | null

Auto-fix prompt; both model variants support this field.

Do not pass this parameter unless necessary.

Example:

true

​
safety_tolerance
integer | null

Content safety level, 1 is the strictest, 6 is the most permissive.

Do not pass this parameter unless necessary.

Required range: 1 <= x <= 6
Example:

3

​
enhance_prompt
boolean | null

Automatically enhance the prompt

Model differences:

  • Only available for veo-3.1-reference-to-video
  • Not applicable for veo-3.1-fast-reference-to-video

Do not pass this parameter unless necessary.

Example:

true

​
person_generation
string | null

Person generation control

Options: dont_allow / allow_adult

Model differences:

  • Only available for veo-3.1-reference-to-video
  • Not applicable for veo-3.1-fast-reference-to-video

Do not pass this parameter unless necessary.

Example:

"allow_adult"

​
reference_type
string | null

Reference image type

Options: ASSET / STYLE

Model differences:

  • Only available for veo-3.1-reference-to-video
  • Not applicable for veo-3.1-fast-reference-to-video

Do not pass this parameter unless necessary.

Example:

"STYLE"

Response

Task created successfully

​
created
integer

Task creation timestamp

Example:

1757165031

​
id
string

Task ID

Example:

"task-unified-1757165031-uyujaw3d"

​
model
string

Actual model name used

​
object
enum<string>

Specific task type

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:

"pending"

​
task_info
object

Asynchronous task info

​
type
enum<string>

Task output type

Available options:
video
Example:

"video"