diff --git a/cookbook/ai_coding_tool_guides/claude_code_quickstart/guide.md b/cookbook/ai_coding_tool_guides/claude_code_quickstart/guide.md
index b2d81be25bb..3a9e58b8565 100644
--- a/cookbook/ai_coding_tool_guides/claude_code_quickstart/guide.md
+++ b/cookbook/ai_coding_tool_guides/claude_code_quickstart/guide.md
@@ -47,7 +47,7 @@ Set your environment variables:
 
 ```bash
 export ANTHROPIC_API_KEY="your-anthropic-api-key"
-export LITELLM_MASTER_KEY="sk-1234567890"  # Generate a secure key
+export LITELLM_MASTER_KEY="sk-<paste-a-long-random-key>"  # Generate a secure key
 ```
 
 ## Step 2: Start Proxy
diff --git a/cookbook/nova_sonic_realtime.py b/cookbook/nova_sonic_realtime.py
index ab510556254..b9cf588d7f1 100644
--- a/cookbook/nova_sonic_realtime.py
+++ b/cookbook/nova_sonic_realtime.py
@@ -33,7 +33,7 @@ CHUNK_SIZE = 1024
 
 # LiteLLM proxy configuration
 LITELLM_PROXY_URL = "ws://localhost:4000/v1/realtime?model=bedrock-sonic"
-LITELLM_API_KEY = "sk-12345"  # Your LiteLLM API key
+LITELLM_API_KEY = "sk-<your-litellm-api-key>"  # Your LiteLLM API key
 
 
 class RealtimeClient:
diff --git a/litellm/proxy/auth/user_api_key_auth.py b/litellm/proxy/auth/user_api_key_auth.py
index 57a6abda8c0..4362ef3a87b 100644
--- a/litellm/proxy/auth/user_api_key_auth.py
+++ b/litellm/proxy/auth/user_api_key_auth.py
@@ -386,7 +386,7 @@ def _get_bearer_token_or_received_api_key(api_key: str) -> str:
         api_key = api_key.replace("bearer ", "")
     elif api_key.startswith("AWS4-HMAC-SHA256"):
         # Handle AWS Signature V4 format from LangChain
-        # Format: AWS4-HMAC-SHA256 Credential=Bearer sk-12345/date/region/service/aws4_request, SignedHeaders=..., Signature=...
+        # Format: AWS4-HMAC-SHA256 Credential=Bearer sk-<your-litellm-api-key>/date/region/service/aws4_request, SignedHeaders=..., Signature=...
         # Extract the Bearer token from the Credential field
         match = re.search(r"Credential=Bearer\s+([^/\s,]+)", api_key)
         if match:
@@ -482,7 +482,7 @@ def _get_bearer_token(
         api_key = api_key.replace("bearer ", "")
     elif api_key.startswith("AWS4-HMAC-SHA256"):
         # Handle AWS Signature V4 format from LangChain
-        # Format: AWS4-HMAC-SHA256 Credential=Bearer sk-12345/date/region/service/aws4_request, SignedHeaders=..., Signature=...
+        # Format: AWS4-HMAC-SHA256 Credential=Bearer sk-<your-litellm-api-key>/date/region/service/aws4_request, SignedHeaders=..., Signature=...
         # Extract the Bearer token from the Credential field
         match = re.search(r"Credential=Bearer\s+([^/\s,]+)", api_key)
         if match:
diff --git a/litellm/proxy/hooks/model_max_budget_limiter.py b/litellm/proxy/hooks/model_max_budget_limiter.py
index efaaab277a9..c9e61d5686b 100644
--- a/litellm/proxy/hooks/model_max_budget_limiter.py
+++ b/litellm/proxy/hooks/model_max_budget_limiter.py
@@ -262,7 +262,7 @@ class _PROXY_VirtualKeyModelMaxBudgetLimiter(RouterBudgetLimiting):
     """
     Handles budgets for model + virtual key
 
-    Example: key=sk-1234567890, model=gpt-4o, max_budget=100, time_period=1d
+    Example: key=sk-<virtual-key>, model=gpt-4o, max_budget=100, time_period=1d
     """
 
     def __init__(self, dual_cache: DualCache):
@@ -431,7 +431,7 @@ class _PROXY_VirtualKeyModelMaxBudgetLimiter(RouterBudgetLimiting):
         """
         Track spend for virtual key + model in DualCache
 
-        Example: key=sk-1234567890, model=gpt-4o, max_budget=100, time_period=1d
+        Example: key=sk-<virtual-key>, model=gpt-4o, max_budget=100, time_period=1d
         """
         verbose_proxy_logger.debug("in RouterBudgetLimiting.async_log_success_event")
         standard_logging_payload: Final[StandardLoggingPayload | None] = kwargs.get("standard_logging_object", None)