diff --git a/backend/pipeline/llm_client.py b/backend/pipeline/llm_client.py
index 3ecf1df..f7d23f0 100644
--- a/backend/pipeline/llm_client.py
+++ b/backend/pipeline/llm_client.py
@@ -140,6 +140,13 @@ class LLMClient:
                 **kwargs,
             )
             raw = response.choices[0].message.content or ""
+            usage = getattr(response, "usage", None)
+            if usage:
+                logger.info(
+                    "LLM response: prompt_tokens=%s, completion_tokens=%s, total=%s, content_len=%d, finish=%s",
+                    usage.prompt_tokens, usage.completion_tokens, usage.total_tokens,
+                    len(raw), response.choices[0].finish_reason,
+                )
             if modality == "thinking":
                 raw = strip_think_tags(raw)
             return raw
@@ -161,6 +168,13 @@ class LLMClient:
                 **kwargs,
             )
             raw = response.choices[0].message.content or ""
+            usage = getattr(response, "usage", None)
+            if usage:
+                logger.info(
+                    "LLM response (fallback): prompt_tokens=%s, completion_tokens=%s, total=%s, content_len=%d, finish=%s",
+                    usage.prompt_tokens, usage.completion_tokens, usage.total_tokens,
+                    len(raw), response.choices[0].finish_reason,
+                )
             if modality == "thinking":
                 raw = strip_think_tags(raw)
             return raw