API request - Crazyrouter API Document

You can paste the command below into your terminal to run your first API request. Make sure to replace YOUR_API_KEY with your secret API key.

cURL (Linux/macOS)

cURL (Windows CMD)

curl https://crazyrouter.com/v1/chat/completions -H "Content-Type: application/json" -H "Authorization: Bearer YOUR_API_KEY" -d "{\"model\": \"gpt-5.2\", \"messages\": [{\"role\": \"user\", \"content\": \"Say this is a test!\"}], \"temperature\": 0.7}"

Python

Node.js

This request queries the gpt-5.2 model to complete text starting with the prompt "Say this is a test". You should receive a response similar to the following:

{
   "id": "foaicmpl-f835557f-2759-4090-8d17-66b48ddea702",
   "object": "chat.completion",
   "created": 1768904876,
   "model": "gpt-5.2",
   "choices": [
      {
         "index": 0,
         "message": {
            "role": "assistant",
            "content": "This is a test!"
         },
         "finish_reason": "stop"
      }
   ],
   "usage": {
      "prompt_tokens": 2104,
      "completion_tokens": 9,
      "total_tokens": 2113,
      "prompt_tokens_details": {
         "cached_tokens": 1920
      }
   }
}

Now you have generated your first chat completion. We can see that finish_reason is stop, which means the API returned the complete completion generated by the model. In the request above, we only generated one message, but you can set the n parameter to generate multiple message choices. In this example, gpt-5.2 is more suited for traditional text completion tasks. This model is also optimized for chat applications.