import requests
import json  # for getting a structured output with indentation
response = requests.post(
    "https://api.ai-kar.com/v1/chat/completions",
    headers={
        # Insert your AI-KAR API Key instead of <YOUR_AI-KARAPI_KEY>:
        "Authorization": "Bearer <YOUR_AI-KARAPI_KEY>",
        "Content-Type": "application/json"
    },
    json={
        "model": "nvidia/nemotron-nano-12b-v2-vl",
        "messages": [
            {
                "role": "user",
                "content": "Hello"  # insert your prompt here, instead of Hello
            }
        ]
    }
)
data = response.json()
print(json.dumps(data, indent=2, ensure_ascii=False))

{
  "id": "gen-1762343744-rdCcOL8byCQwRBZ8QCkv",
  "provider": "DeepInfra",
  "model": "nvidia/nemotron-nano-12b-v2-vl",
  "object": "chat.completion",
  "created": 1762343744,
  "choices": [
    {
      "logprobs": null,
      "finish_reason": "stop",
      "native_finish_reason": "stop",
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "\n\nHello! How can I assist you today?\n",
        "refusal": null,
        "reasoning": "Okay, the user said \"Hello\". Let me start by greeting them back in a friendly and welcoming way. I should keep it simple and approachable, maybe something like \"Hello! How can I assist you today?\" That should work. I want to make sure they feel comfortable and open to asking for help. Let me check if there's anything else I need to add. No, keeping it straightforward is best here. Ready to respond.\n",
        "reasoning_details": [
          {
            "type": "reasoning.text",
            "text": "Okay, the user said \"Hello\". Let me start by greeting them back in a friendly and welcoming way. I should keep it simple and approachable, maybe something like \"Hello! How can I assist you today?\" That should work. I want to make sure they feel comfortable and open to asking for help. Let me check if there's anything else I need to add. No, keeping it straightforward is best here. Ready to respond.\n",
            "format": "unknown",
            "index": 0
          }
        ]
      }
    }
  ],
  "usage": {
    "prompt_tokens": 14,
    "completion_tokens": 102,
    "total_tokens": 116,
    "prompt_tokens_details": null
  }
}