curl --request POST \
  --url https://api.pramaan.dev/v1/capabilities/gpu.endpoint.update \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --header 'Idempotency-Key: <idempotency-key>' \
  --data '
{
  "endpointId": "inference",
  "changes": {
    "workersMax": 2
  }
}
'

const options = {
  method: 'POST',
  headers: {
    'Idempotency-Key': '<idempotency-key>',
    Authorization: 'Bearer <token>',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({endpointId: 'inference', changes: {workersMax: 2}})
};

fetch('https://api.pramaan.dev/v1/capabilities/gpu.endpoint.update', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

import requests

url = "https://api.pramaan.dev/v1/capabilities/gpu.endpoint.update"

payload = {
    "endpointId": "inference",
    "changes": { "workersMax": 2 }
}
headers = {
    "Idempotency-Key": "<idempotency-key>",
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

{
  "endpointId": "<unknown>",
  "type": "queue",
  "workersMin": 4503599627370495,
  "workersMax": 4503599627370495,
  "timeoutSeconds": 1,
  "scaling": {
    "type": "queue-delay",
    "seconds": 1800.25
  },
  "idleSeconds": 1800,
  "gpuCount": 4,
  "createdAt": "2023-11-07T05:31:56Z"
}

{
  "error": {
    "code": "addendum_required",
    "message": "<string>",
    "next": "<string>",
    "request_id": "<string>",
    "retryable": true,
    "effect": "none",
    "slot": "<string>",
    "required_micro": 123,
    "reason": "balance",
    "plan": "<string>",
    "needs": [
      {
        "kind": "approval",
        "detail": "<string>",
        "step": "<string>"
      }
    ]
  }
}