cannot suceed in getting custom model with "category" param

[raul-nugis]

There is no code sample on category model virtually nowhere (but quite a bunch of resources go into training category models)

Based on this github's example, code:

import os, requests, uuid, json
# If you encounter any issues with the base_url or path, make sure
# that you are using the latest endpoint: https://docs.microsoft.com/azure/cognitive-services/translator/reference/v3-0-translate
path = '/translate?api-version=3.0'
params = '&to=et&allowFallback=false&category=fb67ae7d-c962-47dc-ae06-21b6086316c2-INTERNT'
constructed_url = endpoint + path + params

headers = {
    'Ocp-Apim-Subscription-Key': key,
    'Ocp-Apim-Subscription-Region': region,
    'Content-type': 'application/json',
    'X-ClientTraceId': str(uuid.uuid4())
}

# You can pass more than one object in body.
body = [{
    'text' : 'Hello World!'
}]
request = requests.post(constructed_url, headers=headers, json=body)
response = request.json()

print(json.dumps(response, sort_keys=True, indent=4, ensure_ascii=False, separators=(',', ': ')))

Error:

{
    "error": {
        "code": 400079,
        "message": "The custom system requested for translation between from and to language does not exist."
    }
}

This model is dictionary, but full models give same error

If I replace params with

params = '&to=et&category=fb67ae7d-c962-47dc-ae06-21b6086316c2-INTERNT'

Then it responds (though custom model is required, not the fallback)

Please help figure out what is missing