diff --git a/docker-compose.override.yml.example b/docker-compose.override.yml.example
index c34502344..3fa254ff7 100644
--- a/docker-compose.override.yml.example
+++ b/docker-compose.override.yml.example
@@ -122,6 +122,7 @@ version: '3.4'
 #      - ./litellm/litellm-config.yaml:/app/config.yaml
 #    command: [ "--config", "/app/config.yaml", "--port", "8000", "--num_workers", "8" ]
 #    environment:
+#      OPENAI_API_KEY: none ## needs to be set if ollama's openai api compatibility is used
 #      REDIS_HOST: redis
 #      REDIS_PORT: 6379
 #      REDIS_PASSWORD: RedisChangeMe
diff --git a/docs/install/configuration/litellm.md b/docs/install/configuration/litellm.md
index 04fba6c5e..d0f4ca427 100644
--- a/docs/install/configuration/litellm.md
+++ b/docs/install/configuration/litellm.md
@@ -48,13 +48,13 @@ model_list:
       rpm: 1440
   - model_name: mixtral
     litellm_params:
-      model: ollama/mixtral:8x7b-instruct-v0.1-q5_K_M
-      api_base: http://ollama:11434
+      model: openai/mixtral:8x7b-instruct-v0.1-q5_K_M      # use openai/* for ollama's openai api compatibility
+      api_base: http://ollama:11434/v1
       stream: True
   - model_name: mistral
     litellm_params:
-      model: ollama/mistral
-      api_base: http://ollama:11434
+      model: openai/mistral                                # use openai/* for ollama's openai api compatibility
+      api_base: http://ollama:11434/v1
       stream: True
 litellm_settings:
   success_callback: ["langfuse"]
@@ -95,4 +95,4 @@ Key components and features include:
 - **Deployment and Performance**: Information on deploying LiteLLM Proxy and its performance metrics.
 - **Proxy CLI Arguments**: A wide range of command-line arguments for customization.
 
-Overall, LiteLLM Server offers a comprehensive suite of tools for managing, deploying, and interacting with a variety of LLMs, making it a versatile choice for large-scale AI applications.
\ No newline at end of file
+Overall, LiteLLM Server offers a comprehensive suite of tools for managing, deploying, and interacting with a variety of LLMs, making it a versatile choice for large-scale AI applications.