diff --git a/.env.template b/.env.template
index 376233b1f..61853b983 100644
--- a/.env.template
+++ b/.env.template
@@ -21,7 +21,10 @@ LLM_PROVIDER="openai"
 LLM_ENDPOINT=""
 LLM_API_VERSION=""
 LLM_MAX_TOKENS="16384"
-LLM_INSTRUCTOR_MODE="json_schema_mode" # this mode is used for gpt-5 models
+# Instructor's modes determine how structured data is requested from and extracted from LLM responses
+# You can change this type (i.e. mode) via this env variable
+# Each LLM has its own default value, e.g. gpt-5 models have "json_schema_mode"
+LLM_INSTRUCTOR_MODE=""
 
 EMBEDDING_PROVIDER="openai"
 EMBEDDING_MODEL="openai/text-embedding-3-large"
diff --git a/cognee/infrastructure/llm/config.py b/cognee/infrastructure/llm/config.py
index c87054ff6..2e300dc0c 100644
--- a/cognee/infrastructure/llm/config.py
+++ b/cognee/infrastructure/llm/config.py
@@ -38,7 +38,7 @@ class LLMConfig(BaseSettings):
     """
 
     structured_output_framework: str = "instructor"
-    llm_instructor_mode: Optional[str] = None
+    llm_instructor_mode: str = ""
     llm_provider: str = "openai"
     llm_model: str = "openai/gpt-5-mini"
     llm_endpoint: str = ""
@@ -182,7 +182,7 @@ class LLMConfig(BaseSettings):
               instance.
         """
         return {
-            "llm_instructor_mode": self.llm_instructor_mode,
+            "llm_instructor_mode": self.llm_instructor_mode.lower(),
             "provider": self.llm_provider,
             "model": self.llm_model,
             "endpoint": self.llm_endpoint,
diff --git a/cognee/infrastructure/llm/structured_output_framework/litellm_instructor/llm/get_llm_client.py b/cognee/infrastructure/llm/structured_output_framework/litellm_instructor/llm/get_llm_client.py
index 537eda1b2..6ab3b91ad 100644
--- a/cognee/infrastructure/llm/structured_output_framework/litellm_instructor/llm/get_llm_client.py
+++ b/cognee/infrastructure/llm/structured_output_framework/litellm_instructor/llm/get_llm_client.py
@@ -81,7 +81,7 @@ def get_llm_client(raise_api_key_error: bool = True):
             model=llm_config.llm_model,
             transcription_model=llm_config.transcription_model,
             max_completion_tokens=max_completion_tokens,
-            instructor_mode=llm_config.llm_instructor_mode,
+            instructor_mode=llm_config.llm_instructor_mode.lower(),
             streaming=llm_config.llm_streaming,
             fallback_api_key=llm_config.fallback_api_key,
             fallback_endpoint=llm_config.fallback_endpoint,
@@ -102,7 +102,7 @@ def get_llm_client(raise_api_key_error: bool = True):
             llm_config.llm_model,
             "Ollama",
             max_completion_tokens=max_completion_tokens,
-            instructor_mode=llm_config.llm_instructor_mode,
+            instructor_mode=llm_config.llm_instructor_mode.lower(),
         )
 
     elif provider == LLMProvider.ANTHROPIC:
@@ -113,7 +113,7 @@ def get_llm_client(raise_api_key_error: bool = True):
         return AnthropicAdapter(
             max_completion_tokens=max_completion_tokens,
             model=llm_config.llm_model,
-            instructor_mode=llm_config.llm_instructor_mode,
+            instructor_mode=llm_config.llm_instructor_mode.lower(),
         )
 
     elif provider == LLMProvider.CUSTOM:
@@ -130,7 +130,7 @@ def get_llm_client(raise_api_key_error: bool = True):
             llm_config.llm_model,
             "Custom",
             max_completion_tokens=max_completion_tokens,
-            instructor_mode=llm_config.llm_instructor_mode,
+            instructor_mode=llm_config.llm_instructor_mode.lower(),
             fallback_api_key=llm_config.fallback_api_key,
             fallback_endpoint=llm_config.fallback_endpoint,
             fallback_model=llm_config.fallback_model,
@@ -150,7 +150,7 @@ def get_llm_client(raise_api_key_error: bool = True):
             max_completion_tokens=max_completion_tokens,
             endpoint=llm_config.llm_endpoint,
             api_version=llm_config.llm_api_version,
-            instructor_mode=llm_config.llm_instructor_mode,
+            instructor_mode=llm_config.llm_instructor_mode.lower(),
         )
 
     elif provider == LLMProvider.MISTRAL:
@@ -166,7 +166,7 @@ def get_llm_client(raise_api_key_error: bool = True):
             model=llm_config.llm_model,
             max_completion_tokens=max_completion_tokens,
             endpoint=llm_config.llm_endpoint,
-            instructor_mode=llm_config.llm_instructor_mode,
+            instructor_mode=llm_config.llm_instructor_mode.lower(),
         )
 
     elif provider == LLMProvider.MISTRAL: