diff --git a/mineru/cli/fast_api.py b/mineru/cli/fast_api.py
index eeaaee8..3a822b8 100644
--- a/mineru/cli/fast_api.py
+++ b/mineru/cli/fast_api.py
@@ -413,7 +413,13 @@ def _estimate_tokens(text: str) -> int:
     return max(1, int(ascii_chars / 4) + int(non_ascii_chars * 1.5))
 
 
-def _get_mindmap_context_budget(prompt: str, reserve_output_tokens: int = 4096) -> tuple[int, int]:
+def _get_mindmap_max_output_tokens() -> int:
+    return int(os.getenv("MINDMAP_LLM_MAX_OUTPUT_TOKENS", "4096"))
+
+
+def _get_mindmap_context_budget(prompt: str, reserve_output_tokens: Optional[int] = None) -> tuple[int, int]:
+    if reserve_output_tokens is None:
+        reserve_output_tokens = _get_mindmap_max_output_tokens()
     max_context_tokens = int(os.getenv("MINDMAP_LLM_MAX_CONTEXT_TOKENS", "32768"))
     prompt_tokens = _estimate_tokens(prompt)
     safety_tokens = int(os.getenv("MINDMAP_LLM_SAFETY_TOKENS", "1024"))
@@ -503,6 +509,7 @@ def _call_mindmap_llm(markdown: str, mode: str = "smart", custom_prompt: Optiona
     model = os.getenv("MINDMAP_LLM_MODEL", "gemma-4-26B")
     api_key = os.getenv("MINDMAP_LLM_API_KEY", "")
     timeout = int(os.getenv("MINDMAP_LLM_TIMEOUT", "180"))
+    max_output_tokens = _get_mindmap_max_output_tokens()
 
     if not base_url:
         raise RuntimeError("未配置智能整理模型服务，请设置 MINDMAP_LLM_BASE_URL")
@@ -515,8 +522,8 @@ def _call_mindmap_llm(markdown: str, mode: str = "smart", custom_prompt: Optiona
 {compact_markdown}
 """
     logger.info(
-        "Mindmap LLM request start task_id={} role={} model={} base_url={} mode={} input_chars={} input_tokens_est={} prompt_chars={}",
-        task_id or "-", request_role, model, base_url, mode, len(compact_markdown), _estimate_tokens(compact_markdown), len(prompt_template)
+        "Mindmap LLM request start task_id={} role={} model={} base_url={} mode={} input_chars={} input_tokens_est={} prompt_chars={} max_tokens={}",
+        task_id or "-", request_role, model, base_url, mode, len(compact_markdown), _estimate_tokens(compact_markdown), len(prompt_template), max_output_tokens
     )
 
     payload = {
@@ -526,6 +533,7 @@ def _call_mindmap_llm(markdown: str, mode: str = "smart", custom_prompt: Optiona
             {"role": "user", "content": prompt},
         ],
         "temperature": float(os.getenv("MINDMAP_LLM_TEMPERATURE", "0.2")),
+        "max_tokens": max_output_tokens,
     }
     data = json.dumps(payload, ensure_ascii=False).encode("utf-8")
     headers = {"Content-Type": "application/json"}