Making requests

You can paste the command below into your terminal to run your first API request. Make sure to replace $OPENAI_API_KEY with your secret API key. If you are using a legacy user key and you have multiple projects, you will also need to specify the Project Id. For improved security, we recommend transitioning to project based keys instead.

curl https://api.openai.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -d '{
     "model": "gpt-4o-mini",
     "messages": [{"role": "user", "content": "Say this is a test!"}],
     "temperature": 0.7
   }'

This request queries the gpt-4o-mini model (which under the hood points to a gpt-4o-mini model variant) to complete the text starting with a prompt of "Say this is a test". You should get a response back that resembles the following:

{
    "id": "chatcmpl-abc123",
    "object": "chat.completion",
    "created": 1677858242,
    "model": "gpt-4o-mini",
    "usage": {
        "prompt_tokens": 13,
        "completion_tokens": 7,
        "total_tokens": 20,
        "completion_tokens_details": {
            "reasoning_tokens": 0,
            "accepted_prediction_tokens": 0,
            "rejected_prediction_tokens": 0
        }
    },
    "choices": [
        {
            "message": {
                "role": "assistant",
                "content": "\n\nThis is a test!"
            },
            "logprobs": null,
            "finish_reason": "stop",
            "index": 0
        }
    ]
}

Now that you've generated your first chat completion, let's break down the response object. We can see the finish_reason is stop which means the API returned the full chat completion generated by the model without running into any limits. In the choices list, we only generated a single message but you can set the n parameter to generate multiple messages choices.