Skip to main content
POST
/
v1
/
images
/
generate
curl --request POST \
  --url https://openapi.imini.ai/imini/router/v1/images/generate \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "google/nano-banana-2",
  "prompt": "A cute shiba inu in a spacesuit standing on the moon, 3D cartoon style",
  "aspect_ratio": "1:1",
  "resolution": "512"
}
'
{
  "task_id": "task_2041350318103396352",
  "model": "google/nano-banana",
  "created_at": "2026-04-07T03:00:17.062Z",
  "request_id": "285f20ce-8158-401b-945c-7bc6a7ef6ead"
}

Authorizations

​
Authorization
string
header
required

Pass Authorization: Bearer <YOUR_API_KEY> in the request header. Go to the API Keys management page to create and manage API Keys.

Body

application/json
​
model
string
required

Fixed value google/nano-banana-2.

​
prompt
string
required

The prompt. Up to 6000 characters. Supports English and Chinese; detail-rich descriptions yield better results.

Example:

"A cute shiba inu in a spacesuit standing on the moon, 3D cartoon style"

​
images
object[]

Reference image list. Omitting or passing an empty array means text-to-image mode; passing images switches to image-to-image / style reference mode. Up to 14 images.

Maximum array length: 14
​
aspect_ratio
enum<string>
default:1:1

Output aspect ratio. Supports 14 values: 1:1 2:3 3:2 3:4 4:3 4:5 5:4 9:16 16:9 21:9 1:4 1:8 4:1 8:1

When reference images are provided and this parameter is omitted, the model automatically infers the aspect ratio from the reference images and uses it as the output ratio.

Available options:
1:1,
2:3,
3:2,
3:4,
4:3,
4:5,
5:4,
9:16,
16:9,
21:9,
1:4,
1:8,
4:1,
8:1
​
resolution
enum<string>
default:1K

Output quality tier: 512 / 1K / 2K / 4K.

512 is an exclusive low-resolution tier for this model family, ideal for quick previews or prototype validation — the lowest cost and fastest option.

Available options:
512,
1K,
2K,
4K

Response

Submitted successfully

​
task_id
string

Unique task ID, used for subsequent polling

Example:

"task_2041350318103396352"

​
model
string

The model ID used for this task

Example:

"google/nano-banana"

​
created_at
string

Task creation time

Example:

"2026-04-07T03:00:17.062Z"

​
request_id
string

Unique request ID

Example:

"285f20ce-8158-401b-945c-7bc6a7ef6ead"