How To Find GPTs Gizmo Name?

The LLM API | Basic Completions From PiAPI enables users to automate interactions with various public ChatGPT's GPTs via the standard OpenAI Completions API. Note that only public GPTs are supported by this endpoint, and file upload/download functionality or third-party authorization is not available.

Pricing

The GPTS Gizmo API follows a token-based pricing model with minimal charges. For detailed pricing information, please refer to LLM API | Basic Completions.

How to Retrieve the Gizmo Model Name

To obtain the Gizmo model name, visit the official ChatGPT website, browse through the available GPTs, and initiate a conversation with the GPT of your choice. The model name will appear in the webpage URL, for example: https://chatgpt.com/g/g-gFt1ghYJl-logo-creator. The model name to use would be gpt-4-gizmo-g-gFt1ghYJl.

Request Example (cURL)

curl --location --request POST 'https://api.piapi.ai/v1/chat/completions' --header 'Content-Type: application/json' --header 'Authorization: Bearer YOUR_API_KEY' --data-raw '{
    "model": "gpt-4-gizmo-g-pmuQfob8d",
    "messages": [
        {
            "role": "user",
            "content": "red hair girl"
        }
    ]
}'

Response Example

{
    "choices": [
        {
            "finish_reason": "stop",
            "index": 0,
            "message": {
                "content": "{
  "size": "1024x1024",
  "prompt": "A girl with long, flowing red hair. Her vibrant red locks cascade down her back, with a few strands gently blowing in the wind. The background is simple, focusing on her radiant hair, and her expression is serene, highlighted by soft natural lighting.",
  "image": "https://files.oaiusercontent.com/file-12345-4753-8ba0-8c24a9439564.webp"
} Here is the image of a girl with long, flowing red hair. Let me know if you'd like to adjust any details!",
                "role": "assistant"
            }
        }
    ],
    "created": 1726205460,
    "id": "chatcmpl-1726205460587259321",
    "model": "gpt-4-gizmo-g-pmuQfob8d",
    "object": "chat.completion",
    "usage": {
        "completion_tokens": 277,
        "prompt_tokens": 8,
        "total_tokens": 285
    }
}