Skip to main content
POST
/
vendors
/
google
/
v1
/
nano-banana-pro
/
generation
Text to Image Generation
curl --request POST \
  --url https://api.mulerun.com/vendors/google/v1/nano-banana-pro/generation \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "prompt": "A beautiful sunset over the mountains",
  "aspect_ratio": "5:4",
  "resolution": "2K"
}
'
{
  "task_info": {
    "id": "123e4567-e89b-12d3-a456-426614174000",
    "status": "pending",
    "created_at": "2025-09-21T00:00:00.000Z",
    "updated_at": "2025-09-21T00:00:00.000Z"
  }
}
Beta
This model is currently in public testing. Not everyone has access, and API requests may also be unstable.

​
Overview

Generate ultra-sharp, cinematic frames from short text prompts using Google’s Gemini Nano Banana Pro model. Compared with the base Nano Banana release, the Pro tier unlocks:
  • Wider aspect ratios (from square up to 21:9 panoramic)
  • Higher fidelity presets (resolution up to 4K)
  • Better prompt adherence thanks to an upgraded vision-language alignment stack

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json

Text to image generation request body

​
prompt
string
required

Text prompt for image generation

​
aspect_ratio
enum<string>
default:1:1

Aspect ratio of the generated image

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

Output resolution preset (longest side in pixels)

Available options:
1K,
2K

Response

202 - application/json

Task created successfully

​
task_info
object