Prerequisites
- Codex CLI installed
- An Auriko API key
Install Codex
Run the official install script:~/.bashrc, which non-interactive shells don’t source. In CI, GitHub Actions, or agent-driven sessions, add this before invoking codex:
Set your API key
Add these two lines to your shell profile (~/.zshrc on macOS, ~/.bashrc on Linux):
OPENAI_* because Codex reads OpenAI-standard environment variables. Your Auriko 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:
Use Auriko alongside a ChatGPT Pro subscription
Use Auriko alongside a ChatGPT Pro subscription
To keep your default Create the wrapper script:Add Reload your shell, then verify:Use
codex connected to ChatGPT, create a wrapper command instead of modifying your shell profile.Add your Auriko API key to your shell profile (~/.zshrc or ~/.bashrc):~/.local/bin to your PATH if it isn’t already:codex-auriko for Auriko sessions and codex for your ChatGPT subscription.Verify
Run a test completion:Model metadata for '...' not found: metadata isn’t available for models served through custom base URLs.missing field 'models': the response uses the standarddatafield instead of amodelsfield.
Use different models
Pass any model ID with the-m flag:
/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.| 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 Auriko models (only GPT models with Response API support work with Codex):
Control routing
Configure routing in the Auriko dashboard. See routing options for details.Uninstall
RemoveOPENAI_API_KEY and OPENAI_BASE_URL from your shell profile (~/.zshrc or ~/.bashrc). If you created a codex-auriko wrapper, delete ~/.local/bin/codex-auriko.
Troubleshoot
| Symptom | Cause | Fix |
|---|---|---|
| Completions go to ChatGPT, not Auriko | OPENAI_API_KEY not set; ChatGPT auth takes over | Export OPENAI_API_KEY with your Auriko 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.auriko.ai/v1 |
| ”Model metadata not found” warning | Built-in metadata not available for custom-provider models | Cosmetic. No action needed |
”missing field models” warning | Auriko’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 $OPENAI_API_KEY" https://api.auriko.ai/v1/me |
codex: command not found | Install script PATH not loaded | Run export PATH="$HOME/.codex/bin:$PATH" or open a new terminal |