Skip to main content
GET
/
api
/
v1
/
llm
/
usage
/
classify
Python (SDK)
from mka1 import SDK


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

    res = sdk.llm.usage.classify(start_time=1704067200, end_time=1704153600, bucket_width="1d", limit=30, page="cursor_abc123", user_ids=[
        "user_123",
        "user_456",
    ], group_by=[
        "model",
    ], models=[
        "meetkai:functionary-urdu-mini-pak",
    ])

    # Handle response
    print(res)
{
  "object": "page",
  "data": [
    {
      "object": "bucket",
      "start_time": 1704067200,
      "end_time": 1704153600,
      "results": [
        {
          "object": "organization.usage.classify.result",
          "input_tokens": 700,
          "output_tokens": 140,
          "num_classifications": 20,
          "user_id": "user_123",
          "api_key_id": "key_abc123",
          "model": "meetkai:functionary-urdu-mini-pak"
        }
      ]
    }
  ],
  "has_more": false,
  "next_page": null
}

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.

Query Parameters

​
start_time
integer
required

Start time (Unix seconds), inclusive

Required range: -9007199254740991 <= x <= 9007199254740991
Example:

1704067200

​
end_time
integer

End time (Unix seconds), exclusive

Required range: -9007199254740991 <= x <= 9007199254740991
Example:

1704153600

​
bucket_width
enum<string>
default:1d

Width of each time bucket (1m, 1h, 1d)

Available options:
1m,
1h,
1d
Example:

"1d"

​
limit
integer

Number of buckets to return

Required range: 1 <= x <= 1440
Example:

30

​
page
string

Pagination cursor

Example:

"cursor_abc123"

​
user_ids
string[]

Filter by external Subs (externalUserIds)

Example:
["user_123", "user_456"]
​
group_by
enum<string>[]

Group by specified fields

Available options:
user_id,
api_key_id,
model
​
models
string[]

Filter by model names

Response

200 - application/json

OK

​
object
any
required
​
data
object[]
required
​
has_more
boolean
required

Whether there are more pages

​
next_page
string | null
required

Cursor for next page, null if no more pages