REQUEST RESPONSE RETRY START LLM END
POST /v1/chat/completions
{ "model": "gpt-4", "messages": [ {"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "Hello!"} ], "temperature": 0.7, "max_tokens": 100 } HTTP 200 OK { "id": "chatcmpl-123", "choices": [{ "message": { "role": "assistant", "content": "Hi there! How can I help you today?" } }] }