Skip to main content
POST
/
api
/
v1
/
llm
/
images
/
generations
Python (SDK)
from mka1 import SDK


with SDK(
    bearer_auth="<YOUR_BEARER_TOKEN_HERE>",
) as sdk:

    res = sdk.llm.images.create(prompt="A serene mountain landscape at sunset with a lake reflection", model="meetkai:z-image-turbo", n=1, quality="hd", response_format="url", size="1024x1024", style="vivid")

    # Handle response
    print(res)
{
  "created": 1704067200,
  "data": [
    {
      "url": "https://example.com/generated-image.png",
      "revised_prompt": "A serene mountain landscape at sunset with a calm lake reflection, digital art style"
    }
  ]
}

Authorizations

​
Authorization
string
header
required

Gateway auth: send Authorization: Bearer <mka1-api-key>. For multi-user server-side integrations, you can also send X-On-Behalf-Of: <external-user-id>.

Body

application/json

Request parameters for generating images. Creates one or more images from a text prompt.

​
prompt
string
required

A text description of the desired image(s). The maximum length is 1000 characters.

Required string length: 1 - 1000
​
model
string
default:meetkai:z-image-turbo

The model to use for image generation. Defaults to 'meetkai:z-image-turbo'.

​
n
integer
default:1

The number of images to generate. Must be between 1 and 10. Defaults to 1.

Required range: 1 <= x <= 10
​
quality
enum<string>
default:standard

The quality of the image that will be generated. 'hd' creates images with finer details and greater consistency. Defaults to 'standard'.

Available options:
standard,
hd
​
response_format
enum<string>
default:url

The format in which the generated images are returned. 'url' returns a URL to the image, 'b64_json' returns the image as a base64-encoded JSON string. Defaults to 'url'.

Available options:
url,
b64_json
​
size
enum<string>
default:1024x1024

The size of the generated images. Must be one of 256x256, 512x512, 1024x1024, 1792x1024, or 1024x1792. Defaults to 1024x1024.

Available options:
256x256,
512x512,
1024x1024,
1792x1024,
1024x1792
​
style
enum<string>
default:vivid

The style of the generated images. 'vivid' causes the model to lean towards generating hyper-real and dramatic images. 'natural' causes the model to produce more natural, less hyper-real looking images. Defaults to 'vivid'.

Available options:
vivid,
natural
​
user
string

A unique identifier representing your end-user, which can help monitor and detect abuse.

Response

200 - application/json

OK

Response from the image generation endpoint containing the generated images and metadata.

​
created
number
required

The Unix timestamp (in seconds) of when the image generation was completed.

​
data
object[]
required

A list of image objects containing the generated image data.