fix(langfuse.py): log litellm response cost as part of langfuse metadata

litellm/__init__.py

@@ -215,7 +215,6 @@ add_function_to_prompt: bool = (
 )
 client_session: Optional[httpx.Client] = None
 aclient_session: Optional[httpx.AsyncClient] = None
-module_level_aclient = AsyncHTTPHandler()
 model_fallbacks: Optional[List] = None  # Deprecated for 'litellm.fallbacks'
 model_cost_map_url: str = (
     "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json"
@@ -232,6 +231,7 @@ max_user_budget: Optional[float] = None
 max_end_user_budget: Optional[float] = None
 #### RELIABILITY ####
 request_timeout: float = 6000
+module_level_aclient = AsyncHTTPHandler(timeout=request_timeout)
 num_retries: Optional[int] = None  # per model endpoint
 default_fallbacks: Optional[List] = None
 fallbacks: Optional[List] = None

litellm/integrations/langfuse.py

@@ -396,6 +396,8 @@ class LangFuseLogger:
             cost = kwargs.get("response_cost", None)
             print_verbose(f"trace: {cost}")
 
+            clean_metadata["litellm_response_cost"] = cost
+
             if (
                 litellm._langfuse_default_tags is not None
                 and isinstance(litellm._langfuse_default_tags, list)

litellm/proxy/_super_secret_config.yaml

@@ -29,6 +29,12 @@ model_list:
 - model_name: tts
   litellm_params:
     model: openai/tts-1
+- model_name: gpt-4-turbo-preview
+  litellm_params:
+    api_base: https://openai-france-1234.openai.azure.com
+    api_key: os.environ/AZURE_FRANCE_API_KEY
+    model: azure/gpt-turbo
+
 router_settings:
   enable_pre_call_checks: true