diff --git a/engine_llm.py b/engine_llm.py
index b8b7eaf..4a8804b 100644
--- a/engine_llm.py
+++ b/engine_llm.py
@@ -16,6 +16,7 @@ import argparse
 import multiprocessing
 import os
 import re
+import json
 import requests
 from collections import deque
 
@@ -102,7 +103,13 @@ def run_llm_processor(in_queue, out_queue, args):
             headers={"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"},
             timeout=getattr(args, "post_correct_llm_timeout", 8.0),
         )
-        response.raise_for_status()
+        if response.status_code >= 400:
+            try:
+                payload = response.json()
+                detail = json.dumps(payload, ensure_ascii=True)
+            except Exception:
+                detail = response.text.strip()
+            raise RuntimeError(f"OpenAI API error {response.status_code}: {detail}")
         return response.json()["choices"][0]["message"]["content"].strip()
 
     def call_ollama(prompt, temperature):