Skip to main content
POST
/
v1
/
images
/
generations
curl --request POST \
  --url https://api.foxapi.cc/v1/images/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "gemini-3.1-flash-image-preview",
  "prompt": "A futuristic city skyline at dusk, cyberpunk style",
  "aspect_ratio": "16:9",
  "resolution": "1K"
}
'
{
  "created": 1757165031,
  "id": "task-unified-1757165031-uyujaw3d",
  "model": "<string>",
  "progress": 0,
  "status": "pending",
  "task_info": {
    "can_cancel": true,
    "estimated_time": 45
  },
  "type": "image"
}

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:gemini-3.1-flash-image-preview
required

gemini-3.1-flash-image-preview: Supports text-to-image, image-to-image, and image editing

Example:

"gemini-3.1-flash-image-preview"

​
prompt
string
required

Image generation prompt

Notes:

  • Text-to-image mode: describe the image content you want to generate
  • Image editing mode: describe the editing instructions for the reference image
Example:

"A futuristic city skyline at dusk, cyberpunk style"

​
aspect_ratio
string
default:1:1

Output image aspect ratio

Model differences:

  • gemini-3.1-flash-image-preview: available values include 1:1, 1:4, 1:8, 2:3, 3:2, 3:4, 4:1, 4:3, 4:5, 5:4, 8:1, 9:16, 16:9, 21:9, match_input_image
  • gemini-3-pro-image-preview: available values include 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9, match_input_image

Notes:

  • match_input_image means the output will try to match the input image's aspect ratio
Example:

"1:1"

​
resolution
string
default:1K

Output image resolution

Model differences:

  • gemini-3.1-flash-image-preview: supports 512, 0.5K, 1K, 2K, 4K
  • gemini-3-pro-image-preview: supports 1K, 2K, 4K

Notes:

  • 512 and 0.5K both represent half-size output
  • 1K: approximately 1MP
  • 2K: approximately 4MP
  • 4K: approximately 16MP
Example:

"512"

​
image_urls
string[] | null

Reference/editing image list

Model differences:

  • gemini-3.1-flash-image-preview: supports image-to-image and image editing
  • gemini-3-pro-image-preview: supports image editing

Notes:

  • When provided, the mode automatically switches to image editing
  • It is recommended to use publicly accessible image URLs
Example:
["https://example.com/photo.jpg"]
​
output_format
string | null

Output format

Notes:

  • Both models support this field
  • Common values: jpg, png, webp

Do not pass this parameter unless necessary.

Example:

"png"

​
google_search
boolean | null

Enable search for real-time information

Notes:

  • Both gemini-3.1-flash-image-preview and gemini-3-pro-image-preview support this field

Do not pass this parameter unless necessary.

Example:

true

​
image_search
boolean | null

Enable image search to assist generation

Model differences:

  • gemini-3.1-flash-image-preview: supported
  • gemini-3-pro-image-preview: not supported

Do not pass this parameter unless necessary.

Example:

true

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:
image.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

Async task information

​
type
enum<string>

Task output type

Available options:
image
Example:

"image"