diff --git a/Dockerfile b/Dockerfile
index 31c2a0892f7..a6127dd4e5d 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -73,4 +73,4 @@ EXPOSE 4000/tcp
 ENTRYPOINT ["litellm"]
 
 # Append "--detailed_debug" to the end of CMD to view detailed debug logs 
-CMD ["--port", "4000", "--config", "stable_config.yaml"]
+CMD ["--port", "4000"]
diff --git a/stable_config.yaml b/stable_config.yaml
deleted file mode 100644
index 325e8a0e5a7..00000000000
--- a/stable_config.yaml
+++ /dev/null
@@ -1,24 +0,0 @@
-general_settings:
-  store_model_in_db: true
-  database_connection_pool_limit: 20
-
-model_list:
-  - model_name: fake-openai-endpoint
-    litellm_params:
-      model: openai/my-fake-model
-      api_key: my-fake-key
-      api_base: https://exampleopenaiendpoint-production.up.railway.app/
-router_settings:
-  routing_strategy: "latency-based-routing"
-  routing_strategy_args: {"ttl": 100} # Average the last 10 calls to compute avg latency per model
-  allowed_fails: 1
-  num_retries: 3
-  retry_after: 5 # seconds to wait before retrying a failed request
-  cooldown_time: 30 # seconds to cooldown a deployment after failure
-  enable_pre_call_checks: true
-litellm_settings:
-  return_response_headers: true
-  callbacks: ["prometheus"]
-  cache: true
-  cache_params:
-    type: "redis"