Sending Requests to OpenAI-Compatible API using curl

This guide explains how to send requests to Kakoti’s OpenAI-Compatible server using the curl command.

🔧 Prerequisites

1. Having an API Key (Access Token) that you’ve received from the Kakoti panel.
2. Having curl installed on your system (usually pre-installed on Linux and Mac).
3. Basic familiarity with sending HTTP requests.

🧭 Base URL

Use the following address to send requests:

Base URL

https://llm-api.kakoti.com/v1

🧰 Sending Requests

Send the API key in the Authorization header:

Authorization Header

Authorization: Bearer YOUR_API_KEY

📝 Example Request

cURL Example

curl -X POST https://llm-api.kakoti.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "gpt-4o-mini", "messages": [{"role": "user", "content": "Hello"}]}'

🔌 Using Postman or Insomnia

If you use Postman or Insomnia to send HTTP requests, you can import the request using the curl command given above.

🧾 Explanation of Different Parts of the Command

📤 Server Response

On success, the response is usually in the following format:

{
  "id": "chatcmpl-12345",
  "object": "chat.completion",
  "created": 1731000000,
  "model": "gpt-4o-mini",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you?"
      },
      "finish_reason": "stop"
    }
  ]
}