Codex CLI

Set up Codex CLI on this machine to use RouterPlex, an OpenAI- and Anthropic-compatible AI gateway. Keep working until a real request from Codex CLI succeeds through RouterPlex.
 
My RouterPlex API key: YOUR_ROUTERPLEX_API_KEY
 
Key handling:
- If the key line above is a placeholder rather than a real key (real keys start with sk-), use my ROUTERPLEX_API_KEY environment variable. If that is empty too, ask me for the key once, then continue.
- Store the key only in user-level config or my user environment. Never put it in a project file, never commit it, and do not repeat the full key in your replies.
 
Full guide: https://docs.routerplex.com/codex-cli
 
Step 1. Prove the key and the RouterPlex gateway work before changing anything else. Run:
   curl -sS https://api.routerplex.com/v1/chat/completions -H "Authorization: Bearer YOUR_ROUTERPLEX_API_KEY" -H "Content-Type: application/json" -d '{"model":"claude-sonnet-4-6","max_tokens":32,"messages":[{"role":"user","content":"Reply with exactly: RouterPlex connected."}]}'
   On Windows PowerShell, use curl.exe with the body in a file, or Invoke-RestMethod.
   - A reply containing "RouterPlex connected.": go on.
   - 401: the key is wrong or revoked. Stop and ask me for a correct key.
   - 402: my balance or trial credit is used up. 403: this key reached its own spending limit. Stop and tell me; retrying cannot fix these.
   - Network, DNS, TLS, or proxy errors: find and fix the cause (proxy variables, VPN, firewall, system clock, outdated CA certificates), then run it again.
 
Step 2. Configure Codex CLI:
   - Run codex --version. If Codex is missing, install it with the official installer (curl -fsSL https://chatgpt.com/codex/install.sh | sh).
   - Merge this into my user-level ~/.codex/config.toml (Windows: %USERPROFILE%\.codex\config.toml; use $CODEX_HOME/config.toml if CODEX_HOME is set). Keep my other settings, put model and model_provider above any [table] header, and update an existing [model_providers.routerplex] block instead of adding a second one:
 
model_provider = "routerplex"
model = "gpt-5.6-terra"
model_reasoning_effort = "low"
 
[model_providers.routerplex]
name = "RouterPlex"
base_url = "https://api.routerplex.com/v1"
wire_api = "responses"
env_key = "ROUTERPLEX_API_KEY"
 
   - wire_api = "responses" is required. env_key makes Codex read the key from ROUTERPLEX_API_KEY.
   - Make ROUTERPLEX_API_KEY permanent for my user so new terminals get it:
     - macOS/Linux: add export ROUTERPLEX_API_KEY='<key>' to the startup file of the shell I use (check $SHELL: zsh uses ~/.zshrc; bash uses ~/.bashrc, plus ~/.bash_profile or ~/.profile if they do not source ~/.bashrc). Update an existing line instead of adding a second one.
     - Windows: run [Environment]::SetEnvironmentVariable('ROUTERPLEX_API_KEY', '<key>', 'User'). Only terminals and apps started after this see it.
     - WSL, SSH, or a dev container: set it inside that environment, where the tool actually runs.
 
Step 3. Test Codex CLI itself from a new terminal or a restarted app, so you test the saved setup rather than the shell you changed:
   From an empty temporary folder: codex exec --skip-git-repo-check --model 'gpt-5.6-terra' 'Reply with exactly: RouterPlex connected. Do not read files or run tools.'
   Expected reply: "RouterPlex connected."
 
Step 4. If step 1 works but step 3 fails, the problem is Codex CLI's configuration or environment, not RouterPlex. Check these, fix what is wrong, and repeat step 3:
   - The key or base URL is set in one place but not where Codex CLI starts: zsh vs bash startup files, login vs non-login shells, a desktop launcher, a background service, Windows vs WSL, or a remote SSH or container environment.
   - Another setting wins: OPENAI_API_KEY, OPENAI_BASE_URL, OPENAI_API_BASE, ANTHROPIC_API_KEY, ANTHROPIC_BASE_URL, or a project-level config that overrides the user-level one.
   - Codex CLI is outdated, or still needs a full restart to read the new settings.
   - If an environment variable cannot be made to reach Codex CLI reliably and Codex CLI accepts a key in its user-level config, put the key there instead.
 
Keep repeating steps 3 and 4 until the test reply comes back. Stop early only for a 401, 402, or 403, or for a step only I can do, such as a click in a settings window or a login. Then tell me exactly what to do, wait for me, and continue testing afterwards.
 
When it works, tell me which files you changed, where the key is stored, and the final test output.

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

powershell -ExecutionPolicy ByPass -c "irm https://chatgpt.com/codex/install.ps1 | iex"

model_provider = "routerplex"
model = "gpt-5.6-terra"
model_reasoning_effort = "low"
 
[model_providers.routerplex]
name = "RouterPlex"
base_url = "https://api.routerplex.com/v1"
wire_api = "responses"
env_key = "ROUTERPLEX_API_KEY"

export ROUTERPLEX_API_KEY='YOUR_ROUTERPLEX_API_KEY'
codex exec --skip-git-repo-check --model 'gpt-5.6-terra' 'Reply with exactly: RouterPlex connected. Do not read files or run tools.'

$env:ROUTERPLEX_API_KEY = 'YOUR_ROUTERPLEX_API_KEY'
codex exec --skip-git-repo-check --model 'gpt-5.6-terra' 'Reply with exactly: RouterPlex connected. Do not read files or run tools.'

model = "claude-sonnet-4-6"