diff --git a/backend/open_webui/env.py b/backend/open_webui/env.py
index cd0136a5c8..a4117c33ce 100644
--- a/backend/open_webui/env.py
+++ b/backend/open_webui/env.py
@@ -403,6 +403,16 @@ ENABLE_WEBSOCKET_SUPPORT = (
     os.environ.get("ENABLE_WEBSOCKET_SUPPORT", "True").lower() == "true"
 )
 
+MODEL_LIST_CACHE_TTL = os.environ.get("MODEL_LIST_CACHE_TTL", "1")
+if MODEL_LIST_CACHE_TTL == "":
+    MODEL_LIST_CACHE_TTL = None
+else:
+    try:
+        MODEL_LIST_CACHE_TTL = int(MODEL_LIST_CACHE_TTL)
+    except Exception:
+        MODEL_LIST_CACHE_TTL = 1
+
+
 WEBSOCKET_MANAGER = os.environ.get("WEBSOCKET_MANAGER", "")
 
 WEBSOCKET_REDIS_URL = os.environ.get("WEBSOCKET_REDIS_URL", REDIS_URL)
diff --git a/backend/open_webui/routers/ollama.py b/backend/open_webui/routers/ollama.py
index 9c1e1fdb00..44ba3d5774 100644
--- a/backend/open_webui/routers/ollama.py
+++ b/backend/open_webui/routers/ollama.py
@@ -59,6 +59,7 @@ from open_webui.config import (
 from open_webui.env import (
     ENV,
     SRC_LOG_LEVELS,
+    MODEL_LIST_CACHE_TTL,
     AIOHTTP_CLIENT_SESSION_SSL,
     AIOHTTP_CLIENT_TIMEOUT,
     AIOHTTP_CLIENT_TIMEOUT_MODEL_LIST,
@@ -330,7 +331,7 @@ def merge_ollama_models_lists(model_lists):
     return list(merged_models.values())
 
 
-@cached(ttl=1)
+@cached(ttl=MODEL_LIST_CACHE_TTL)
 async def get_all_models(request: Request, user: UserModel = None):
     log.info("get_all_models()")
     if request.app.state.config.ENABLE_OLLAMA_API:
diff --git a/backend/open_webui/routers/openai.py b/backend/open_webui/routers/openai.py
index ab35a673fc..1f72f9fc57 100644
--- a/backend/open_webui/routers/openai.py
+++ b/backend/open_webui/routers/openai.py
@@ -21,6 +21,7 @@ from open_webui.config import (
     CACHE_DIR,
 )
 from open_webui.env import (
+    MODEL_LIST_CACHE_TTL,
     AIOHTTP_CLIENT_SESSION_SSL,
     AIOHTTP_CLIENT_TIMEOUT,
     AIOHTTP_CLIENT_TIMEOUT_MODEL_LIST,
@@ -386,7 +387,7 @@ async def get_filtered_models(models, user):
     return filtered_models
 
 
-@cached(ttl=1)
+@cached(ttl=MODEL_LIST_CACHE_TTL)
 async def get_all_models(request: Request, user: UserModel) -> dict[str, list]:
     log.info("get_all_models()")