Skip to main content
POST
/
v1
/
images
/
generations
# model can be "gemini-2.5-flash-image-preview", or the compatible alias "nano-banana-ext"
curl --request POST \
  --url https://api.apimart.ai/v1/images/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "gemini-2.5-flash-image-preview",
    "prompt": "A bamboo forest path under moonlight",
    "size": "1:1",
    "n": 1,
    "image_urls": [
      "https://openai-documentation.vercel.app/images/cat_and_otter.png"
    ]
  }'

{
  "code": 200,
  "data": [
    {
      "status": "submitted",
      "task_id": "task_01K8SGYNNNVBQTXNR4MM964S7K"
    }
  ]
}
Model name compatibility note: This endpoint also accepts the alias nano-banana-ext, which is equivalent to gemini-2.5-flash-image-preview. The two are interchangeable and produce identical results.
# model can be "gemini-2.5-flash-image-preview", or the compatible alias "nano-banana-ext"
curl --request POST \
  --url https://api.apimart.ai/v1/images/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "gemini-2.5-flash-image-preview",
    "prompt": "A bamboo forest path under moonlight",
    "size": "1:1",
    "n": 1,
    "image_urls": [
      "https://openai-documentation.vercel.app/images/cat_and_otter.png"
    ]
  }'

{
  "code": 200,
  "data": [
    {
      "status": "submitted",
      "task_id": "task_01K8SGYNNNVBQTXNR4MM964S7K"
    }
  ]
}

​
Authorizations

​
Authorization
string
required
All API endpoints require Bearer Token authenticationGet your API Key:Visit the API Key Management Page to get your API KeyAdd it to the request header:
Authorization: Bearer YOUR_API_KEY

​
Body

​
model
string
default:"gemini-2.5-flash-image-preview"
required
Image generation model nameSupported models:
  • gemini-2.5-flash-image-preview - Standard version (compatible alias nano-banana-ext)
  • gemini-2.5-flash-image-preview-official - Official version (compatible alias nano-banana)
Example: "gemini-2.5-flash-image-preview" or "gemini-2.5-flash-image-preview-official"
For backward compatibility, the aliases nano-banana-ext (for gemini-2.5-flash-image-preview) and nano-banana (for gemini-2.5-flash-image-preview-official) remain usable.
​
prompt
string
required
Text description for image generationMaximum 1000 characters
​
size
string
Image generation sizeSupported formats:
  • Ratio: auto, 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9
For text-to-image, when size is auto, the default is 1:1 or 16:9; for image-to-image, the aspect ratio follows the upstream response. We recommend specifying an aspect ratio.
​
resolution
string
default:"1K"
Output image resolutionSupported values:
  • 1K - 1K resolution (default)
​
n
integer
Number of images to generateRange: 1Default: 1⚠️ Note: Must enter a plain number (e.g., 1), do not use quotes or it will cause an error
​
official_fallback
boolean
default:"false"
Whether to use the official channel fallback
  • false: Do not use (default)
  • true: Use official channel
When using the official channel (gemini-2.5-flash-image-preview-official), this parameter cannot be used.
​
image_urls
array
List of reference image URLs for image-to-image or image editing💡 Quick Fill (Try it area):
  1. Click ”+ Add an item” to add an image URL
  2. Enter the complete image URL address or base64 data
Limit: Maximum 14 images

​
Response

​
code
integer
Response status code
​
data
array
Response data array