diff --git a/litellm/main.py b/litellm/main.py
index e01603b7e7..d7e01c107f 100644
--- a/litellm/main.py
+++ b/litellm/main.py
@@ -735,6 +735,7 @@ def completion(
     ]
     litellm_params = [
         "metadata",
+        "tags",
         "acompletion",
         "atext_completion",
         "text_completion",
@@ -3150,6 +3151,7 @@ def embedding(
         "allowed_model_region",
         "model_config",
         "cooldown_time",
+        "tags",
     ]
     default_params = openai_params + litellm_params
     non_default_params = {
@@ -4379,6 +4381,8 @@ def transcription(
     proxy_server_request = kwargs.get("proxy_server_request", None)
     model_info = kwargs.get("model_info", None)
     metadata = kwargs.get("metadata", {})
+    tags = kwargs.pop("tags", [])
+
     drop_params = kwargs.get("drop_params", None)
     client: Optional[
         Union[
@@ -4551,6 +4555,7 @@ def speech(
 ) -> HttpxBinaryResponseContent:
 
     model, custom_llm_provider, dynamic_api_key, api_base = get_llm_provider(model=model, custom_llm_provider=custom_llm_provider, api_base=api_base)  # type: ignore
+    tags = kwargs.pop("tags", [])
 
     optional_params = {}
     if response_format is not None:
diff --git a/litellm/proxy/proxy_config.yaml b/litellm/proxy/proxy_config.yaml
index 7e78cf3177..81ed12c07e 100644
--- a/litellm/proxy/proxy_config.yaml
+++ b/litellm/proxy/proxy_config.yaml
@@ -4,14 +4,12 @@ model_list:
       model: openai/fake
       api_key: fake-key
       api_base: https://exampleopenaiendpoint-production.up.railway.app/
-    model_info:
-      tier: free # 👈 Key Change - set `tier`
+      tags: ["free"]
   - model_name: gpt-4
     litellm_params:
       model: openai/gpt-4o
       api_key: os.environ/OPENAI_API_KEY
-    model_info:
-      tier: paid # 👈 Key Change - set `tier`
+      tags: ["paid"]
 
 general_settings: 
   master_key: sk-1234