fix count_tokens_with_anthropic_api

litellm/proxy/utils.py

@@ -131,7 +131,6 @@ else:
 
 unified_guardrail = UnifiedLLMGuardrails()
 
-_anthropic_async_clients = {}
 
 def print_verbose(print_statement):
     """
@@ -961,8 +960,8 @@ class ProxyLogging:
         Returns:
             Updated data dictionary if guardrail passes, None if guardrail should be skipped
         """
-        from litellm.types.guardrails import GuardrailEventHooks
         from litellm.integrations.prometheus import PrometheusLogger
+        from litellm.types.guardrails import GuardrailEventHooks
 
         # Determine the event type based on call type
         event_type = GuardrailEventHooks.pre_call
@@ -4292,74 +4291,6 @@ def construct_database_url_from_env_vars() -> Optional[str]:
     return None
 
 
-async def count_tokens_with_anthropic_api(
-    model_to_use: str,
-    messages: Optional[List[Dict[str, Any]]],
-    deployment: Optional[Dict[str, Any]] = None,
-) -> Optional[Dict[str, Any]]:
-    """
-    Helper function to count tokens using Anthropic API directly.
-
-    Args:
-        model_to_use: The model name to use for token counting
-        messages: The messages to count tokens for
-        deployment: Optional deployment configuration containing API key
-
-    Returns:
-        Optional dict with token count and tokenizer info, or None if failed
-    """
-    if not messages:
-        return None
-
-    try:
-        import os
-
-        import anthropic
-
-        # Get Anthropic API key from deployment config
-        anthropic_api_key = None
-        if deployment is not None:
-            anthropic_api_key = deployment.get("litellm_params", {}).get("api_key")
-
-        # Fallback to environment variable
-        if not anthropic_api_key:
-            anthropic_api_key = os.getenv("ANTHROPIC_API_KEY")
-
-        if anthropic_api_key and messages:
-            # Call Anthropic API directly for more accurate token counting
-            
-            # Use cached client if available to avoid socket exhaustion
-            if anthropic_api_key not in _anthropic_async_clients:
-                _anthropic_async_clients[anthropic_api_key] = anthropic.AsyncAnthropic(api_key=anthropic_api_key)
-            
-            client = _anthropic_async_clients[anthropic_api_key]
-
-            # Call with explicit parameters to satisfy type checking
-            # Type ignore for now since messages come from generic dict input
-            response = await client.beta.messages.count_tokens(
-                model=model_to_use,
-                messages=messages,  # type: ignore
-                betas=["token-counting-2024-11-01"],
-            )
-            total_tokens = response.input_tokens
-            tokenizer_used = "anthropic_api"
-
-            return {
-                "total_tokens": total_tokens,
-                "tokenizer_used": tokenizer_used,
-            }
-
-    except ImportError:
-        verbose_proxy_logger.warning(
-            "Anthropic library not available, falling back to LiteLLM tokenizer"
-        )
-    except Exception as e:
-        verbose_proxy_logger.warning(
-            f"Error calling Anthropic API: {e}, falling back to LiteLLM tokenizer"
-        )
-    return None
-
-
 async def get_available_models_for_user(
     user_api_key_dict: "UserAPIKeyAuth",
     llm_router: Optional["Router"],