Skip to main content
POST
/
v3
/
gemini-3.1-flash-image-text-to-image
Nano Banana 2 (text to image)
curl --request POST \
  --url https://api.myrouter.ai/v3/gemini-3.1-flash-image-text-to-image \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: <content-type>' \
  --data '
{
  "size": "<string>",
  "google": {
    "web_search": true,
    "image_search": true
  },
  "prompt": "<string>",
  "aspect_ratio": "<string>",
  "output_format": "<string>"
}
'
{
  "image_urls": [
    {}
  ],
  "grounding_metadata": {}
}

Documentation Index

Fetch the complete documentation index at: https://docs.myrouter.ai/llms.txt

Use this file to discover all available pages before exploring further.

Generate images from text prompts using the Gemini 3.1 Flash Image Preview model. Supports configurable image size, aspect ratio, and thinking depth for higher quality generation results.

​
Request Headers

​
Content-Type
string
required
Enum: application/json
​
Authorization
string
required
Bearer authentication format: Bearer {{API Key}}.

​
Request Body

​
size
string
default:"1K"
Output image pixel dimensions (width*height). 0.5K (512px) is only available for Gemini 3.1 Flash.Possible values: 0.5K, 1K, 2K, 4K
​
google
object
Google search options
​
prompt
string
required
Text prompt describing the image to generate
​
aspect_ratio
string
default:"1:1"
Aspect ratio of the generated image.Possible values: 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
​
output_format
string
default:"image/png"
MIME type of the output image. Supports PNG and JPEG formats.Possible values: image/png, image/jpeg

​
Response

​
image_urls
array
required
List of generated image URLs
​
grounding_metadata
object
Model grounding metadata. Returned when Google server-side tools (e.g., search) are invoked. Note: tool invocation depends on Google. Enabling the parameter makes the tool available but does not guarantee 100% tool invocation.