Update main.py

main.py

@@ -519,7 +519,9 @@ async def chat_completions(request: ChatRequest, req: Request, api_key: str = De
                         yield f"data: {json.dumps(response_chunk)}\n\n"
                     
                     # After all chunks are sent, send the final message with finish_reason
-                    prompt_tokens = sum(len(msg['content'].split()) for msg in request.messages)
+                    # *** Key Correction Starts Here ***
+                    prompt_tokens = sum(len(msg.content.split()) for msg in request.messages)
+                    # *** Key Correction Ends Here ***
                     completion_tokens = len(assistant_content.split())
                     total_tokens = prompt_tokens + completion_tokens
                     estimated_cost = calculate_estimated_cost(prompt_tokens, completion_tokens)