From 5845b5c6576aa7292bb1fa95d16f834b9e7a576a Mon Sep 17 00:00:00 2001
From: Ishaan Jaff <ishaanjaffer0324@gmail.com>
Date: Fri, 18 Apr 2025 19:05:31 -0700
Subject: [PATCH] docs openai codex with litellm

---
 .../my-website/docs/tutorials/openai_codex.md | 107 +++++++++++++++---
 1 file changed, 89 insertions(+), 18 deletions(-)

diff --git a/docs/my-website/docs/tutorials/openai_codex.md b/docs/my-website/docs/tutorials/openai_codex.md
index a4fa5ecd60..08881d79ae 100644
--- a/docs/my-website/docs/tutorials/openai_codex.md
+++ b/docs/my-website/docs/tutorials/openai_codex.md
@@ -1,39 +1,70 @@
 import Image from '@theme/IdealImage';
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';
 
 # Using LiteLLM with OpenAI Codex
 
-This tutorial walks you through setting up and using [OpenAI Codex](https://github.com/openai/codex) with LiteLLM Proxy. LiteLLM enables you to use various LLM models (including Gemini) through the Codex interface.
+This guide walks you through connecting OpenAI Codex to LiteLLM. Using LiteLLM with Codex allows teams to:
+- Access 100+ LLMs through the Codex interface
+- Use powerful models like Gemini through a familiar interface
+- Track spend and usage with LiteLLM's built-in analytics
+- Control model access with virtual keys
 
 <Image img={require('../../img/litellm_codex.gif')} />
 
-## Prerequisites
+## Quickstart
 
-- LiteLLM Proxy running (see [Docker Quick Start Guide](../proxy/docker_quick_start.md) for setup details)
-- Node.js and npm installed
+Make sure to set up LiteLLM with the [LiteLLM Getting Started Guide](../proxy/docker_quick_start.md).
 
-## Step 1: Install OpenAI Codex
+## 1. Install OpenAI Codex
 
 Install the OpenAI Codex CLI tool globally using npm:
 
+<Tabs>
+<TabItem value="npm" label="npm">
+
 ```bash
 npm i -g @openai/codex
 ```
 
-## Step 2: Configure Codex to use LiteLLM Proxy
-
-Set the required environment variables to point Codex to your LiteLLM Proxy:
+</TabItem>
+<TabItem value="yarn" label="yarn">
 
 ```bash
-# Point to your LiteLLM Proxy server
-export OPENAI_BASE_URL=http://0.0.0.0:4000 
-
-# Use your LiteLLM API key
-export OPENAI_API_KEY="sk-1234"
+yarn global add @openai/codex
 ```
 
-## Step 3: LiteLLM Configuration
+</TabItem>
+</Tabs>
 
-Ensure your LiteLLM Proxy is properly configured to route to your desired models. Here's the example configuration:
+## 2. Start LiteLLM Proxy
+
+<Tabs>
+<TabItem value="docker" label="Docker">
+
+```bash
+docker run \
+    -v $(pwd)/litellm_config.yaml:/app/config.yaml \
+    -p 4000:4000 \
+    ghcr.io/berriai/litellm:main-latest \
+    --config /app/config.yaml
+```
+
+</TabItem>
+<TabItem value="pip" label="LiteLLM CLI">
+
+```bash
+litellm --config /path/to/config.yaml
+```
+
+</TabItem>
+</Tabs>
+
+LiteLLM should now be running on [http://localhost:4000](http://localhost:4000)
+
+## 3. Configure LiteLLM for Model Routing
+
+Ensure your LiteLLM Proxy is properly configured to route to your desired models. Create a `litellm_config.yaml` file with the following content:
 
 ```yaml
 model_list:
@@ -52,7 +83,19 @@ litellm_settings:
 
 This configuration enables routing to OpenAI, Anthropic, and Gemini models.
 
-## Step 4: Run Codex with Gemini
+## 4. Configure Codex to Use LiteLLM Proxy
+
+Set the required environment variables to point Codex to your LiteLLM Proxy:
+
+```bash
+# Point to your LiteLLM Proxy server
+export OPENAI_BASE_URL=http://0.0.0.0:4000 
+
+# Use your LiteLLM API key (if you've set up authentication)
+export OPENAI_API_KEY="sk-1234"
+```
+
+## 5. Run Codex with Gemini
 
 With everything configured, you can now run Codex with Gemini:
 
@@ -60,14 +103,42 @@ With everything configured, you can now run Codex with Gemini:
 codex --model gemini/gemini-2.0-flash --full-auto
 ```
 
+<Image img={require('../../img/litellm_codex.gif')} />
+
 The `--full-auto` flag allows Codex to automatically generate code without additional prompting.
 
+## 6. Advanced Options
+
+### Using Different Models
+
+You can use any model configured in your LiteLLM proxy:
+
+```bash
+# Use Claude models
+codex --model anthropic/claude-3-opus-20240229
+
+# Use OpenAI models
+codex --model openai/gpt-4o
+```
+
+### Enabling Debugging
+
+For troubleshooting, enable verbose output:
+
+```bash
+export DEBUG=1
+codex --model gemini/gemini-2.0-flash --full-auto
+```
+
 ## Troubleshooting
 
 - If you encounter connection issues, ensure your LiteLLM Proxy is running and accessible at the specified URL
-- Verify your LiteLLM API key is valid
+- Verify your LiteLLM API key is valid if you're using authentication
 - Check that your model routing configuration is correct
+- For model-specific errors, ensure the model is properly configured in your LiteLLM setup
 
 ## Additional Resources
 
-For more details on starting and configuring LiteLLM, refer to the [Docker Quick Start Guide](../proxy/docker_quick_start.md).
+- [LiteLLM Docker Quick Start Guide](../proxy/docker_quick_start.md)
+- [OpenAI Codex GitHub Repository](https://github.com/openai/codex)
+- [LiteLLM Virtual Keys and Authentication](../proxy/virtual_keys.md)