diff --git a/litellm/proxy/proxy_cli.py b/litellm/proxy/proxy_cli.py
index 373577580..663befe04 100644
--- a/litellm/proxy/proxy_cli.py
+++ b/litellm/proxy/proxy_cli.py
@@ -74,15 +74,16 @@ def open_config():
 @click.option('--config', is_flag=True, help='Create and open .env file from .env.template')
 @click.option('--test', flag_value=True, help='proxy chat completions url to make a test request to')
 @click.option('--local', is_flag=True, default=False, help='for local debugging')
-def run_server(host, port, api_base, model, deploy, debug, temperature, max_tokens, drop_params, add_function_to_prompt, max_budget, telemetry, config, test, local):
+@click.option('--cost', is_flag=True, default=False, help='for viewing cost logs')
+def run_server(host, port, api_base, model, deploy, debug, temperature, max_tokens, drop_params, add_function_to_prompt, max_budget, telemetry, config, test, local, cost):
     if config:
         open_config()
     
     if local:
-        from proxy_server import app, initialize, deploy_proxy
+        from proxy_server import app, initialize, deploy_proxy, print_cost_logs
         debug = True
     else:
-        from .proxy_server import app, initialize, deploy_proxy
+        from .proxy_server import app, initialize, deploy_proxy, print_cost_logs
 
     if deploy == True:
         print(f"\033[32mLiteLLM: Deploying your proxy to api.litellm.ai\033[0m\n")
@@ -95,6 +96,9 @@ def run_server(host, port, api_base, model, deploy, debug, temperature, max_toke
         return
     if model and "ollama" in model: 
         run_ollama_serve()
+    if cost == True:
+        print_cost_logs()
+        return
     if test != False:
         click.echo('LiteLLM: Making a test ChatCompletions request to your proxy')
         import openai
diff --git a/litellm/proxy/proxy_server.py b/litellm/proxy/proxy_server.py
index 28bd22223..d4ad0834d 100644
--- a/litellm/proxy/proxy_server.py
+++ b/litellm/proxy/proxy_server.py
@@ -215,16 +215,18 @@ async def track_cost(response):
             format='%(asctime)s - %(message)s',
             datefmt='%Y-%m-%d %H:%M:%S'
         )
-        import datetime
-
         response_cost = litellm.completion_cost(completion_response=response)
-
-        logging.info(f"Model {response.model} Cost: {response_cost:.8f}")
-
+        logging.info(f"Model {response.model} Cost: ${response_cost:.8f}")
     except:
         pass
 
-
+def print_cost_logs():
+    with open('cost.log', 'r') as f:
+        # print this in green
+        print("\033[1;32m")
+        print(f.read())
+        print("\033[0m")
+    return
 
 @router.get("/ollama_logs")
 async def retrieve_server_log(request: Request):