fix(bedrock_httpx.py): fix async client check

litellm/llms/bedrock_httpx.py

@@ -1731,7 +1731,7 @@ class BedrockConverseLLM(BaseLLM):
         headers={},
         client: Optional[AsyncHTTPHandler] = None,
     ) -> Union[ModelResponse, CustomStreamWrapper]:
-        if client is None:
+        if client is None or not isinstance(client, AsyncHTTPHandler):
             _params = {}
             if timeout is not None:
                 if isinstance(timeout, float) or isinstance(timeout, int):

litellm/model_prices_and_context_window_backup.json

@@ -760,6 +760,36 @@
         "litellm_provider": "azure_ai",
         "mode": "chat"
     },
+    "azure_ai/Meta-Llama-31-8B-Instruct": {
+        "max_tokens": 128000,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 128000,
+        "input_cost_per_token": 0.0000003,
+        "output_cost_per_token": 0.00000061,
+        "litellm_provider": "azure_ai",
+        "mode": "chat",
+        "source":"https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-8b-instruct-offer?tab=PlansAndPrice"
+    },
+    "azure_ai/Meta-Llama-31-70B-Instruct": {
+        "max_tokens": 128000,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 128000,
+        "input_cost_per_token": 0.00000268,
+        "output_cost_per_token": 0.00000354,
+        "litellm_provider": "azure_ai",
+        "mode": "chat",
+        "source":"https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-70b-instruct-offer?tab=PlansAndPrice"
+    },
+    "azure_ai/Meta-Llama-31-405B-Instruct": {
+        "max_tokens": 128000,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 128000,
+        "input_cost_per_token": 0.00000533,
+        "output_cost_per_token": 0.000016,
+        "litellm_provider": "azure_ai",
+        "mode": "chat",
+        "source":"https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-405b-instruct-offer?tab=PlansAndPrice"
+    },
     "babbage-002": {
         "max_tokens": 16384,
         "max_input_tokens": 16384,

litellm/proxy/_new_secret_config.yaml

@@ -1,9 +1,8 @@
 model_list:
-  - model_name: anthropic-claude
+  - model_name: "*"             # all requests where model not in your config go to this deployment
     litellm_params:
-      model: claude-3-haiku-20240307
+      model: "openai/*"           # passes our validation check that a real provider is given
+      api_key: "" 
 
-litellm_settings:
-  callbacks: ["logfire"]
-  redact_user_api_key_info: true
-  return_response_headers: true
+general_settings:
+  completion_model: "gpt-3.5-turbo"