Gemini-3.1-Flash Image Generation

Generate images using Google Gemini 3.1 Flash model with extreme aspect ratios and Google Search enhancement

POST /v1/images/generations

cURL

curl --request POST \
  --url https://toapis.com/v1/images/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "gemini-3.1-flash-image-preview",
    "prompt": "A cyberpunk city at night with flickering neon lights",
    "size": "16:9",
    "n": 1,
    "metadata": {
      "resolution": "2K"
    }
  }'

200

{
  "id": "task_img_abc123def456",
  "object": "generation.task",
  "model": "gemini-3.1-flash-image-preview",
  "status": "queued",
  "progress": 0,
  "created_at": 1703884800,
  "metadata": {}
}

• Google Gemini 3.1 Flash image generation model (Nano banana2)
• Use model parameter to select gemini-3.1-flash-image-preview model
• Supports text-to-image and image-to-image, up to 4K resolution output
• Up to 14 reference images to maintain style/character consistency
• Supports extreme aspect ratios (1:4, 4:1, 1:8, 8:1)
• Integrated Google Search enhancement for more accurate real-world images
• 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 Image API first to upload images and get URLs, then call this endpoint.

Authorizations

Authorization · string · required

All endpoints require Bearer Token authentication

Get your API Key from the API Key Management Page

Add to request header:

Authorization: Bearer YOUR_API_KEY

Body

model · string · default: "gemini-3.1-flash-image-preview" · required

Image generation model name

Example: "gemini-3.1-flash-image-preview"

prompt · string · required

Text description for image generation

size · string

Image aspect ratio

Supported ratios:

Value	Use Case
1:1	Square, avatar, social media
3:2 / 2:3	Standard photo
4:3 / 3:4	Traditional display ratio
16:9 / 9:16	Widescreen / vertical video cover
5:4 / 4:5	Instagram images
21:9	Ultra-wide banner
1:4 / 4:1	Long poster / banner
1:8 / 8:1	Extreme long image / ad banner

n · integer · default: 1

Number of images to generate

⚠️ Note: Must be a pure number (e.g. 1), do not add quotes, otherwise it will error

image_urls · object[]

List of reference image URLs for image-to-image or image editing

Show Detailed field description

url · string · required

Image URL address

⚠️ URL format only (base64 no longer supported)

• Publicly accessible image URL (http:// or https://)
• Example: https://example.com/image.jpg
• You can use the Upload Image API to upload local images and get URLs

Limitations:

• Single image must not exceed 10MB
• Supported formats: .jpeg, .jpg, .png, .webp

Limit: Maximum 14 images (recommended: up to 10 object references + 4 character references)

metadata · object

Metadata parameters for passing additional configuration options

Show Supported metadata fields

resolution · string · default: "1K"

Output image resolution

Supported values:

• 0.5K - ~512px, low-resolution preview
• 1K - ~1024px, standard resolution (default)
• 2K - ~2048px, high resolution
• 4K - ~4096px, ultra-high resolution

Note: Pricing varies by resolution; 4K costs more than 1K

google_search · boolean · default: "false"

Enable Google text search enhancement

• true: The model will first search the web for text information to assist in image generation, suitable for scenarios requiring real-world accuracy
• false: Disabled (default)

google_image_search · boolean · default: "false"

Enable Google image search enhancement

• true: In addition to text search, also searches for reference images to assist generation, suitable for scenarios requiring visual references
• false: Disabled (default)

Note: Must be used together with google_search: true

Response

id · string

Unique task identifier for status queries

object · string

Object type, always generation.task

model · string

Model 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

curl --request POST \
  --url https://toapis.com/v1/images/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "gemini-3.1-flash-image-preview",
    "prompt": "A cyberpunk city at night with flickering neon lights",
    "size": "16:9",
    "n": 1,
    "metadata": {
      "resolution": "2K"
    }
  }'

200

{
  "id": "task_img_abc123def456",
  "object": "generation.task",
  "model": "gemini-3.1-flash-image-preview",
  "status": "queued",
  "progress": 0,
  "created_at": 1703884800,
  "metadata": {}
}