メインコンテンツへスキップ
POST
/
v1
/
images
/
generations
curl --request POST \
  --url https://toapis.com/v1/images/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "gemini-3-pro-image-preview",
    "prompt": "Futuristic city skyline with neon lights",
    "size": "16:9",
    "n": 1,
    "metadata": {
      "resolution": "1K",
      "orientation": "landscape"
    }
  }'

{
  "id": "task_img_abc123def456",
  "object": "generation.task",
  "model": "gemini-3-pro-image-preview",
  "status": "queued",
  "progress": 0,
  "created_at": 1703884800,
  "metadata": {}
}
  • Google Gemini 3 Pro powerful image generation model (Nano banana2)
  • Use model parameter to select gemini-3-pro-image-preview model
  • Supports text-to-image generation
  • Async task management, query results by task ID
Important Change: For better performance and cost control, we no longer support passing base64 image data directly in image_urls. Please use the Upload 画像API first to upload images and get URLs, then call this endpoint.

​
Authorizations

​
Authorization
string
必須
All endpoints require Bearer Token authenticationGet your API Key from the API Key Management PageAdd to request header:
Authorization: Bearer YOUR_API_KEY

​
Body

​
model
string
デフォルト:"gemini-3-pro-image-preview"
必須
Image generation model nameモデル alias: nano-banana-proExample: "gemini-3-pro-image-preview"
​
prompt
string
必須
Text description for image generationThe upstream model input limit is 65,536 tokens. ToAPIs does not add a 1000-character cap.
​
size
string
Image generation aspect ratioSupported formats:
  • Ratios: 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9
​
n
integer
デフォルト:1
Number of images to generateFixed at 1⚠️ Note: Must be a pure number (e.g. 1), do not add quotes, otherwise it will error
​
metadata
object
Metadata parameters for passing additional configuration options
​
image_urls
object[]
List of reference image URLs for image-to-image or image editingLimit: Maximum 14 images

​
レスポンス

​
id
string
Unique task identifier for status queries
​
object
string
Object type, always generation.task
​
model
string
モデル name used
​
status
string
Task status
  • queued - Queued for processing
  • in_progress - Processing
  • completed - Successfully completed
  • failed - Failed
​
progress
integer
Task progress percentage (0-100)
​
created_at
integer
Task creation timestamp (Unix timestamp)
​
metadata
object
Task metadata
curl --request POST \
  --url https://toapis.com/v1/images/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "gemini-3-pro-image-preview",
    "prompt": "Futuristic city skyline with neon lights",
    "size": "16:9",
    "n": 1,
    "metadata": {
      "resolution": "1K",
      "orientation": "landscape"
    }
  }'

{
  "id": "task_img_abc123def456",
  "object": "generation.task",
  "model": "gemini-3-pro-image-preview",
  "status": "queued",
  "progress": 0,
  "created_at": 1703884800,
  "metadata": {}
}