Codex

Arbytra connects to Codex through two environment variables, routing your completions through Arbytra instead of OpenAI.

Prerequisites

Codex CLI installed
An Arbytra API key

Install Codex

Run the official install script:

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

Or install via npm:

npm install -g @openai/codex

Or via Homebrew (macOS):

brew install --cask codex

Open a new terminal after installing, then confirm Codex is available:

codex --help

The install script writes PATH to ~/.bashrc, which non-interactive shells don’t source. In CI, GitHub Actions, or agent-driven sessions, add this before invoking codex:

export PATH="$HOME/.codex/bin:$PATH"

Set your API key

Add these two lines to your shell profile (~/.zshrc on macOS, ~/.bashrc on Linux):

export OPENAI_API_KEY="ak_live_..."    # your Arbytra API key
export OPENAI_BASE_URL="https://api.arbytra.com/v1"

The variable names are OPENAI_* because Codex reads OpenAI-standard environment variables. Your Arbytra API key goes in OPENAI_API_KEY. Your key starts with ak_live_ (production) or ak_test_ (testing). The base URL must include /v1. Codex appends /responses directly. If you’ve logged in to Codex with a ChatGPT account, these environment variables override the ChatGPT login. Codex routes completions through OPENAI_BASE_URL instead of chatgpt.com. Reload your shell after saving:

source ~/.zshrc   # or: source ~/.bashrc

Or open a new terminal.

Use Arbytra alongside a ChatGPT Pro subscription

To keep your default codex connected to ChatGPT, create a wrapper command instead of modifying your shell profile.Add your Arbytra API key to your shell profile (~/.zshrc or ~/.bashrc):

export ARBYTRA_API_KEY="ak_live_..."

Create the wrapper script:

mkdir -p ~/.local/bin
cat > ~/.local/bin/codex-arbytra << 'EOF'
#!/usr/bin/env bash
export OPENAI_API_KEY="${ARBYTRA_API_KEY}"
export OPENAI_BASE_URL="https://api.arbytra.com/v1"
exec codex "$@"
EOF
chmod +x ~/.local/bin/codex-arbytra

Add ~/.local/bin to your PATH if it isn’t already:

export PATH="$HOME/.local/bin:$PATH"

Reload your shell, then verify:

codex-arbytra exec -m gpt-5.4-mini "Say exactly: setup-ok"

Use codex-arbytra for Arbytra sessions and codex for your ChatGPT subscription.

Verify

Run a test completion:

codex exec -m gpt-5.4-mini "Say exactly: setup-ok"

Codex prints sandbox setup output on first run. The model response follows. Expect two cosmetic warnings:

Model metadata for '...' not found: metadata isn’t available for models served through custom base URLs.
missing field 'models': the response uses the standard data field instead of a models field.

Use different models

Pass any model ID with the -m flag:

codex -m gpt-5.5 "Summarize this repo"
codex -m gpt-5.4 "Review my code"

To switch models mid-session, type /model <id>.

Codex uses the Response API with hosted tools, which only GPT models support. Non-GPT models (Claude, DeepSeek, Gemini) return a hosted_tool_not_supported error.

These are the models available through Arbytra that work with Codex:

Model	Author	Context
`gpt-5.5`	OpenAI	1M
`gpt-5.4`	OpenAI	1M
`gpt-5.4-mini`	OpenAI	400K
`gpt-5.4-nano`	OpenAI	400K
`gpt-5-codex`	OpenAI	400K
`o4-mini`	OpenAI	200K
`o3`	OpenAI	200K
`gpt-4o`	OpenAI	128K

gpt-5.4-nano works for basic tasks but doesn’t support all Codex tools (e.g., tool_search). Complex multi-tool sessions may require a larger model. To list all Arbytra models (only GPT models with Response API support work with Codex):

curl -s -H "Authorization: Bearer $OPENAI_API_KEY" \
  https://api.arbytra.com/v1/models | jq '.data[].id'

Control routing

Configure routing in the Arbytra dashboard. See routing options for details.

Uninstall

Remove OPENAI_API_KEY and OPENAI_BASE_URL from your shell profile (~/.zshrc or ~/.bashrc). If you created a codex-arbytra wrapper, delete ~/.local/bin/codex-arbytra.

Troubleshoot

Symptom	Cause	Fix
Completions go to ChatGPT, not Arbytra	`OPENAI_API_KEY` not set; ChatGPT auth takes over	Export `OPENAI_API_KEY` with your Arbytra key
`hosted_tool_not_supported`	Non-GPT model used	Use a GPT model (see model table above)
404 on requests	`OPENAI_BASE_URL` missing `/v1`	Use exactly `https://api.arbytra.com/v1`
”Model metadata not found” warning	Built-in metadata not available for custom-provider models	Cosmetic. No action needed
”missing field `models`” warning	Arbytra’s model list format differs slightly from OpenAI’s	Cosmetic. No action needed
401 or “API key is invalid”	Wrong key value or expired key	Run `echo $OPENAI_API_KEY` to check. Verify at `curl -H "Authorization: Bearer $OPENAI_API_KEY" https://api.arbytra.com/v1/me`
`codex: command not found`	Install script PATH not loaded	Run `export PATH="$HOME/.codex/bin:$PATH"` or open a new terminal

Get Started

Guides

Response API

Frameworks

Integrations

Specifications

Platform

Changelog

Prerequisites

Install Codex

Set your API key

Verify

Use different models

Control routing

Uninstall

Troubleshoot

​Prerequisites

​Install Codex

​Set your API key

​Verify

​Use different models

​Control routing

​Uninstall

​Troubleshoot

Prerequisites

Install Codex

Set your API key

Verify

Use different models

Control routing

Uninstall

Troubleshoot