OpenAI Codex

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

Quickstart

info

Requires LiteLLM v1.66.3.dev5 and higher

Make sure to set up LiteLLM with the LiteLLM Quickstart.

1. Install OpenAI Codex

Install the OpenAI Codex CLI tool globally using npm:

curl
npm
yarn

curl -fsSL https://chatgpt.com/codex/install.sh | sh

npm i -g @openai/codex

yarn global add @openai/codex

2. Start LiteLLM Proxy

Docker
LiteLLM CLI

docker run \
    -v $(pwd)/litellm_config.yaml:/app/config.yaml \
    -p 4000:4000 \
    docker.litellm.ai/berriai/litellm:latest \
    --config /app/config.yaml

litellm --config /path/to/config.yaml

LiteLLM should now be running on 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:

model_list:
  - model_name: o3-mini
    litellm_params:
      model: openai/o3-mini
      api_key: os.environ/OPENAI_API_KEY
  - model_name: claude-3-7-sonnet-latest
    litellm_params:
      model: anthropic/claude-3-7-sonnet-latest
      api_key: os.environ/ANTHROPIC_API_KEY
  - model_name: gemini-2.0-flash
    litellm_params:
      model: gemini/gemini-2.0-flash
      api_key: os.environ/GEMINI_API_KEY
  - model_name: gpt-5.6-luna
    litellm_params:
      model: openai/gpt-5.6-luna
      api_key: os.environ/OPENAI_API_KEY
  - model_name: gpt-5.6-sol
    litellm_params:
      model: openai/gpt-5.6-sol
      api_key: os.environ/OPENAI_API_KEY
  - model_name: gpt-5.6-terra
    litellm_params:
      model: openai/gpt-5.6-terra
      api_key: os.environ/OPENAI_API_KEY

litellm_settings:
  drop_params: true

This configuration enables routing to specific OpenAI, Anthropic, and Gemini models with explicit names.

4. Configure Codex to Use LiteLLM Proxy

Set the required environment variables to point Codex to your LiteLLM Proxy:

# Use your LiteLLM API key (if you've set up authentication)
export LITELLM_API_KEY="sk-1234"

You can also configure Codex directly via ~/.codex/config.toml:

model = "gpt-5.6-terra"
model_provider = "litellm"
model_reasoning_effort = "medium"
approvals_reviewer = "user"

[model_providers.litellm]
name = "litellm"
base_url = "http://localhost:4000/v1"
env_key = "LITELLM_API_KEY"
wire_api = "responses"
stream_idle_timeout_ms = 7200000
stream_max_retries = 5
request_max_retries = 4

[projects."/path/to/your/project"]
trust_level = "trusted"

[tui.model_availability_nux]
"gpt-5.6-terra" = 1

5. Run Codex

With everything configured, you can now run Codex:

codex

6. Advanced Options

Using Different Models

You can use any model configured in your LiteLLM proxy:

# Use Claude models
codex --model claude-3-7-sonnet-latest

# Use Google AI Studio Gemini models
codex --model gemini/gemini-2.0-flash

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 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

Quickstart​

1. Install OpenAI Codex​

2. Start LiteLLM Proxy​

3. Configure LiteLLM for Model Routing​

4. Configure Codex to Use LiteLLM Proxy​

5. Run Codex​

6. Advanced Options​

Using Different Models​

Troubleshooting​

Additional Resources​