# Codex (/en/docs/cookbook/coding-agents/codex)







Connect Praxis to Codex and drive OpenAI's terminal coding agent with your own key—editing code, running commands, answering questions. The key lives in an environment variable, never in the config file.

Every step lists its **expected result**: follow along yourself, or hand this page to an AI assistant that can operate your computer and let it do the install, setup, and verification for you.

## What you'll accomplish [#what-youll-accomplish]

* Call Praxis models with the `codex` command in your terminal
* Done when: `codex exec "…"` returns a model reply
* Time needed: **3–5 minutes** (excluding the Node.js install)
* Protocol: OpenAI Responses (Codex's native protocol)

## Prerequisites [#prerequisites]

Confirm each item before you start:

* **A Praxis API key** (starting with `sk-praxis-`). If you don't have one, create it at [Console → API Keys](https://console.deepraxis.ai/keys): click "Create Key"—the name is required, the validity defaults to 90 days (or pick permanent)—the dialog then shows the full key once—copy it right away. You can also re-copy the full key any time from the copy icon that appears when hovering its row in the key list. If the dialog sticks on "Creating…", refresh the list—the key exists and row copy still retrieves it in full. New accounts ship with **$1 of free credit**. See [Quickstart](/en/docs/developers/model/quickstart) for the full flow.
* **Node.js 18 or newer.** Check with `node --version`; install the LTS from [nodejs.org](https://nodejs.org) if needed.
* **Install the Codex CLI**:

  ```bash
  npm install -g @openai/codex
  ```

  Expected: `codex --version` prints `codex-cli <version>` (this page follows 0.162.1).

## Configure [#configure]

**Step 1: write the config file**

Create `~/.codex/config.toml` (on Windows, `%USERPROFILE%\.codex\config.toml`):

```toml
model = "deepseek-flash"
model_provider = "praxis"

[model_providers.praxis]
name = "Praxis"
base_url = "https://api.deepraxis.com/openai/v1"
env_key = "PRAXIS_API_KEY"
wire_api = "responses"
```

Three notes:

* The key does **not** go into this file—`env_key` declares that Codex reads it from the `PRAXIS_API_KEY` environment variable, set in the next step.
* `wire_api` must be `responses`: Codex speaks the OpenAI Responses protocol, not classic chat completions.
* `model` takes a catalog model ID; `deepseek-flash` is the platform's sample model—cheap, fast, good at both Chinese and English.

Expected: the next `codex` launch picks up the new config (restart any session already running).

<img alt="The actual ~/.codex/config.toml shown in a terminal" src="__img0" />

**Step 2: set the key environment variable**

macOS / Linux (WSL included):

```bash
export PRAXIS_API_KEY=sk-praxis-your-key
```

Add the line to `~/.bashrc` or `~/.zshrc` to persist it. Windows PowerShell: `$env:PRAXIS_API_KEY="your-key"` (or set a system environment variable and reopen the terminal).

Expected: `echo $PRAXIS_API_KEY` prints your key (`echo $env:PRAXIS_API_KEY` on PowerShell).

## Verify [#verify]

From a code project directory (a git repository), run:

```bash
codex exec "Reply with exactly: connected"
```

Expected: the reply contains `connected`, ending with a tokens-used line—**a reply means you're connected**. The first run may print "Model metadata for … not found … Defaulting to fallback metadata"; that's the normal fallback notice for custom models and doesn't affect usage.

<img alt="A real codex exec run in a terminal" src="__img1" />

Drop `exec` and run `codex` for the full interactive workspace (the version banner and input box mark entry; not verified on this page).

You can also verify from the command line. Set the variable first (copying the curl verbatim without it yields a 401):

```bash
export PRAXIS_API_KEY=sk-praxis-your-key
```

```bash
curl https://api.deepraxis.com/openai/v1/responses \
  -H "Authorization: Bearer $PRAXIS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "deepseek-flash", "input": "Hello", "max_output_tokens": 256}'
```

Expected: HTTP 200 means you're connected. The block in `output` with `type` `text` is the reply—`deepseek-flash` is a reasoning model, so a `reasoning` block may come first; that's normal.

> The commands above are written for macOS / Linux / WSL (bash). On Windows PowerShell: a successful `codex exec` above already means you're connected—feel free to skip; for the CLI route, run `$env:PRAXIS_API_KEY="your-key"` first, use `curl.exe` (PowerShell's `curl` is an alias with different syntax), and join the command into a single line (dropping the trailing `\`).

Finally, check [Console → Usage & Billing](https://console.deepraxis.ai/usage): the call you just made is already on the books—every call is billed and traceable.

## FAQ [#faq]

| Symptom                            | Cause                                                                                                     | Fix                                                                            |
| ---------------------------------- | --------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------ |
| `Model metadata … not found`       | Custom models aren't in Codex's built-in metadata table                                                   | Normal fallback notice—just use it; chats and tool calls are unaffected        |
| Invalid token / 401                | `PRAXIS_API_KEY` not exported, copied incompletely, or the terminal wasn't reopened after editing shellrc | Check with `echo $PRAXIS_API_KEY`; copy it again in full; reopen the terminal  |
| `Not inside a trusted directory …` | Run outside a git repository                                                                              | Run from a project directory, or pass `--skip-git-repo-check`                  |
| `unknown configuration field`      | An older Codex build doesn't recognize newer config keys                                                  | Upgrade with `npm install -g @openai/codex` and retry                          |
| "Model not found"                  | Model ID doesn't match the catalog                                                                        | Copy the exact ID from [Console → Models](https://console.deepraxis.ai/models) |

## Advanced [#advanced]

* **How much did that session cost?** [Console → Usage & Billing](https://console.deepraxis.ai/usage)—pay per call, no idle fees
* **Switch models**: set `model` in `config.toml` or run `codex -m <model-id>`. Use `deepseek-flash` or `deepseek-v4-flash`. Codex requires a model that declares Responses support; open the model details in the [model catalog](https://console.deepraxis.ai/models) and confirm Responses is listed before selecting it.
* **Use it in a project**: interactive `codex` reads files, edits code, and runs commands, asking for your confirmation before sensitive actions

## Related recipes [#related-recipes]

* [Claude Code](/en/docs/cookbook/coding-agents/claude-code) (the Anthropic-protocol sibling) · [Cline](/en/docs/cookbook/coding-agents/cline) · [OpenCode](/en/docs/cookbook/coding-agents/opencode)
* Prefer a GUI? See [Cherry Studio](/en/docs/cookbook/chat-clients/cherry-studio) · [Chatbox](/en/docs/cookbook/chat-clients/chatbox)