diff --git a/deploy/charts/litellm/README.md b/deploy/charts/litellm/README.md
index 817781ed04..e005280b8b 100644
--- a/deploy/charts/litellm/README.md
+++ b/deploy/charts/litellm/README.md
@@ -2,7 +2,7 @@
 
 ## Prerequisites
 
-- Kubernetes 1.23+
+- Kubernetes 1.21+
 - Helm 3.8.0+
 
 If `db.deployStandalone` is used:
@@ -33,6 +33,7 @@ If `db.useStackgresOperator` is used (not yet implemented):
 | `proxy_config.*`                                           | See [values.yaml](./values.yaml) for default settings.  See [example_config_yaml](../../../litellm/proxy/example_config_yaml/) for configuration examples.                            | N/A  |
 
 #### Example `environmentSecrets` Secret 
+
 ```
 apiVersion: v1
 kind: Secret
diff --git a/deploy/charts/litellm/values.yaml b/deploy/charts/litellm/values.yaml
index cc53fc59c9..891c44f2a9 100644
--- a/deploy/charts/litellm/values.yaml
+++ b/deploy/charts/litellm/values.yaml
@@ -6,7 +6,6 @@ replicaCount: 1
 
 image:
   # Use "ghcr.io/berriai/litellm-database" for optimized image with database
-  # Alternatively, use "ghcr.io/berriai/litellm" for the default image
   repository: ghcr.io/berriai/litellm-database
   pullPolicy: IfNotPresent
   # Overrides the image tag whose default is the chart appVersion.
@@ -85,10 +84,13 @@ proxy_config:
       litellm_params:
         model: gpt-3.5-turbo
         api_key: eXaMpLeOnLy
+    - model_name: fake-openai-endpoint
+      litellm_params:
+        model: openai/fake
+        api_key: fake-key
+        api_base: https://exampleopenaiendpoint-production.up.railway.app/
   general_settings:
     master_key: os.environ/PROXY_MASTER_KEY
-#  litellm_settings:
-#    cache: true
 
 resources: {}
   # We usually recommend not to specify default resources and to leave this as a conscious
diff --git a/docs/my-website/docs/proxy/deploy.md b/docs/my-website/docs/proxy/deploy.md
index 175806d274..5a5b5d99fb 100644
--- a/docs/my-website/docs/proxy/deploy.md
+++ b/docs/my-website/docs/proxy/deploy.md
@@ -150,17 +150,20 @@ To avoid issues with predictability, difficulties in rollback, and inconsistent
 
 
 ## Deploy with Database
+### Docker, Kubernetes, Helm Chart
+
+
+<Tabs>
+
+<TabItem value="docker-deploy" label="Dockerfile">
 
 We maintain a [seperate Dockerfile](https://github.com/BerriAI/litellm/pkgs/container/litellm-database) for reducing build time when running LiteLLM proxy with a connected Postgres Database 
 
-<Tabs>
-<TabItem value="docker-deploy" label="Dockerfile">
-
-```
+```shell
 docker pull docker pull ghcr.io/berriai/litellm-database:main-latest
 ```
 
-```
+```shell
 docker run --name litellm-proxy \
 -e DATABASE_URL=postgresql://<user>:<password>@<host>:<port>/<dbname> \
 -p 4000:4000 \
@@ -233,6 +236,8 @@ Your OpenAI proxy server is now running on `http://0.0.0.0:4000`.
 </TabItem>
 <TabItem value="helm-deploy" label="Helm">
 
+Use this to deploy litellm using a helm chart. Link to [the LiteLLM Helm Chart](https://github.com/BerriAI/litellm/tree/main/deploy/charts/litellm)
+
 #### Step 1. Clone the repository
 
 ```bash
@@ -241,9 +246,11 @@ git clone https://github.com/BerriAI/litellm.git
 
 #### Step 2. Deploy with Helm
 
+Run the following command in the root of your `litellm` repo. This will set the litellm proxy master key as `sk-1234`
+
 ```bash
 helm install \
-  --set masterkey=SuPeRsEcReT \
+  --set masterkey=sk-1234 \
   mydeploy \
   deploy/charts/litellm
 ```