test fixes, fk azure

Author: ishaan-jaff

proxy_server_config.yaml

@@ -7,10 +7,8 @@ model_list:
       id: "1"
   - model_name: gpt-3.5-turbo-end-user-test
     litellm_params:
-      model: azure/gpt-4.1-mini
-      api_base: os.environ/AZURE_API_BASE
-      api_version: "2023-05-15"
-      api_key: os.environ/AZURE_API_KEY # The `os.environ/` prefix tells litellm to read this from the env. See https://docs.litellm.ai/docs/simple_proxy#load-api-keys-from-vault
+      model: openai/gpt-4.1-mini
+      api_key: os.environ/OPENAI_API_KEY # The `os.environ/` prefix tells litellm to read this from the env. See https://docs.litellm.ai/docs/simple_proxy#load-api-keys-from-vault
   - model_name: gpt-3.5-turbo
     litellm_params:
       model: openai/gpt-4.1-mini
@@ -24,10 +22,8 @@ model_list:
       stream_timeout: 60
   - model_name: gpt-4
     litellm_params:
-      model: azure/gpt-4.1-mini
-      api_base: os.environ/AZURE_API_BASE
-      api_version: "2023-05-15"
-      api_key: os.environ/AZURE_API_KEY # The `os.environ/` prefix tells litellm to read this from the env. See https://docs.litellm.ai/docs/simple_proxy#load-api-keys-from-vault
+      model: openai/gpt-4.1-mini
+      api_key: os.environ/OPENAI_API_KEY # The `os.environ/` prefix tells litellm to read this from the env. See https://docs.litellm.ai/docs/simple_proxy#load-api-keys-from-vault
       rpm: 480
       timeout: 300
       stream_timeout: 60
@@ -37,10 +33,8 @@ model_list:
       input_cost_per_second: 0.000420  
   - model_name: text-embedding-ada-002
     litellm_params: 
-      model: azure/text-embedding-ada-002
-      api_key: os.environ/AZURE_API_KEY
-      api_base: os.environ/AZURE_API_BASE
-      api_version: "2023-05-15"
+      model: openai/text-embedding-ada-002
+      api_key: os.environ/OPENAI_API_KEY
     model_info:
       mode: embedding
       base_model: text-embedding-ada-002