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="auto", 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"
    }
  ]
}

Documentation Index

Fetch the complete documentation index at: https://docs.mka1.com/llms.txt

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

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>.

Headers

​
X-On-Behalf-Of
string

Optional external end-user identifier forwarded by the API gateway.

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:auto

The model to use for image generation. Defaults to 'auto'.

​
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:auto

The quality tier of the generated image. Higher tiers may incur higher latency or cost. 'auto' lets the gateway pick a sensible value per model. 'standard' and 'hd' are accepted as legacy aliases.

Available options:
low,
medium,
high,
auto,
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 image. 'auto' defers to the model's default.

Available options:
256x256,
512x512,
1024x1024,
1024x1536,
1536x1024,
1792x1024,
1024x1792,
auto
​
style
enum<string>
default:vivid

The style of the generated image. 'vivid' leans toward hyper-real and dramatic. 'natural' produces more naturalistic results. Conditionally supported.

Available options:
vivid,
natural
​
output_format
enum<string>

Output file format. Conditionally supported.

Available options:
png,
webp,
jpeg
​
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.