diff --git a/docs/usage/environment_variables.md b/docs/usage/environment_variables.md
index 9353947298..043ae0b378 100644
--- a/docs/usage/environment_variables.md
+++ b/docs/usage/environment_variables.md
@@ -227,5 +227,8 @@ environment_variables: dict[str, Callable[[], Any]] = {
 
     # XPU MoE FFN quant type map
     "FD_XPU_MOE_FFN_QUANT_TYPE_MAP": lambda: os.getenv("FD_XPU_MOE_FFN_QUANT_TYPE_MAP", ""),
+
+    # Worker process health check timeout when waiting for responses in seconds (default: 30)
+    "FD_WORKER_ALIVE_TIMEOUT": lambda: int(os.getenv("FD_WORKER_ALIVE_TIMEOUT", "30")),
 }
 ```
diff --git a/docs/zh/usage/environment_variables.md b/docs/zh/usage/environment_variables.md
index d7455471c1..82b3004092 100644
--- a/docs/zh/usage/environment_variables.md
+++ b/docs/zh/usage/environment_variables.md
@@ -227,5 +227,8 @@ environment_variables: dict[str, Callable[[], Any]] = {
 
     # XPU MoE FFN 量化类型映射
     "FD_XPU_MOE_FFN_QUANT_TYPE_MAP": lambda: os.getenv("FD_XPU_MOE_FFN_QUANT_TYPE_MAP", ""),
+
+    # Worker 进程响应等待时的健康检查超时时间（秒），默认 30 秒
+    "FD_WORKER_ALIVE_TIMEOUT": lambda: int(os.getenv("FD_WORKER_ALIVE_TIMEOUT", "30")),
 }
 ```
diff --git a/fastdeploy/entrypoints/openai/serving_chat.py b/fastdeploy/entrypoints/openai/serving_chat.py
index 580b11199a..fa3a0f74d5 100644
--- a/fastdeploy/entrypoints/openai/serving_chat.py
+++ b/fastdeploy/entrypoints/openai/serving_chat.py
@@ -24,6 +24,7 @@ from typing import List, Optional
 
 import numpy as np
 
+import fastdeploy.envs as envs
 import fastdeploy.metrics.trace as tracing
 from fastdeploy.entrypoints.openai.protocol import (
     ChatCompletionRequest,
@@ -266,7 +267,7 @@ class OpenAIServingChat:
                 except asyncio.TimeoutError:
                     current_waiting_time += 10
                     if current_waiting_time == 300:
-                        status, msg = self.engine_client.check_health()
+                        status, msg = self.engine_client.check_health(time_interval_threashold=envs.FD_WORKER_ALIVE_TIMEOUT)
                         if not status:
                             if choices:
                                 chunk.choices = choices
@@ -576,7 +577,7 @@ class OpenAIServingChat:
                 except asyncio.TimeoutError:
                     current_waiting_time += 10
                     if current_waiting_time == 300:
-                        status, msg = self.engine_client.check_health()
+                        status, msg = self.engine_client.check_health(time_interval_threashold=envs.FD_WORKER_ALIVE_TIMEOUT)
                         if not status:
                             raise ValueError(f"Engine is not healthy: {msg}")
                         else:
diff --git a/fastdeploy/entrypoints/openai/serving_completion.py b/fastdeploy/entrypoints/openai/serving_completion.py
index fd86fe273c..a810ee6d4e 100644
--- a/fastdeploy/entrypoints/openai/serving_completion.py
+++ b/fastdeploy/entrypoints/openai/serving_completion.py
@@ -25,6 +25,7 @@ from typing import List, Optional
 
 import numpy as np
 
+import fastdeploy.envs as envs
 import fastdeploy.metrics.trace as tracing
 from fastdeploy.engine.request import RequestOutput
 from fastdeploy.entrypoints.openai.protocol import (
@@ -284,7 +285,7 @@ class OpenAIServingCompletion:
                 except asyncio.TimeoutError:
                     current_waiting_time += 10
                     if current_waiting_time == 300:
-                        status, msg = self.engine_client.check_health()
+                        status, msg = self.engine_client.check_health(time_interval_threashold=envs.FD_WORKER_ALIVE_TIMEOUT)
                         if not status:
                             raise ValueError(f"Engine is not healthy: {msg}")
                         else:
@@ -454,7 +455,7 @@ class OpenAIServingCompletion:
                 except asyncio.TimeoutError:
                     current_waiting_time += 10
                     if current_waiting_time == 300:
-                        status, msg = self.engine_client.check_health()
+                        status, msg = self.engine_client.check_health(time_interval_threashold=envs.FD_WORKER_ALIVE_TIMEOUT)
                         if not status:
                             raise ValueError(f"Engine is not healthy: {msg}")
                         else:
diff --git a/fastdeploy/envs.py b/fastdeploy/envs.py
index 15a64cda77..67ff60c5f5 100644
--- a/fastdeploy/envs.py
+++ b/fastdeploy/envs.py
@@ -159,6 +159,8 @@ environment_variables: dict[str, Callable[[], Any]] = {
     "FD_OTLP_EXPORTER_MAX_EXPORT_BATCH_SIZE": lambda: int(os.getenv("FD_OTLP_EXPORTER_MAX_EXPORT_BATCH_SIZE", "64")),
     "FD_TOKEN_PROCESSOR_HEALTH_TIMEOUT": lambda: int(os.getenv("FD_TOKEN_PROCESSOR_HEALTH_TIMEOUT", "120")),
     "FD_XPU_MOE_FFN_QUANT_TYPE_MAP": lambda: os.getenv("FD_XPU_MOE_FFN_QUANT_TYPE_MAP", ""),
+    # Timeout for worker process health check in seconds
+    "FD_WORKER_ALIVE_TIMEOUT": lambda: int(os.getenv("FD_WORKER_ALIVE_TIMEOUT", "30")),
 }