> ## Documentation Index
> Fetch the complete documentation index at: https://docs.toolken.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Codex

> Route OpenAI Codex CLI traffic through Toolken by defining a custom provider in config.toml. Every request is attributed and visible in the dashboard.

**Codex CLI supports custom model providers in `~/.codex/config.toml` -- define a Toolken provider, select it, and every Codex request flows through the gateway with full cost tracking.**

<Steps>
  <Step title="Get your two keys">
    You need two keys:

    | Key          | Where to get it           | Looks like    |
    | ------------ | ------------------------- | ------------- |
    | Toolken key  | Dashboard, under API Keys | `tk_live_...` |
    | Provider key | Your OpenAI account       | `sk-...`      |

    Toolken forwards your provider key verbatim and never stores it.
  </Step>

  <Step title="Add the Toolken provider to config.toml">
    Open (or create) `~/.codex/config.toml` and add the following:

    ```toml theme={null}
    model = "gpt-4o"
    model_provider = "toolken"

    [model_providers.toolken]
    name = "toolken"
    base_url = "https://gateway.toolken.ai/v1"
    env_key = "OPENAI_API_KEY"

    [model_providers.toolken.http_headers]
    X-Toolken-Key = "tk_live_..."
    X-Toolken-Metadata-Agent = "codex"
    ```

    `env_key` tells Codex which environment variable holds your provider key. That key is sent as `Authorization: Bearer` and forwarded to the provider untouched.

    <Tip>Keep `tk_live_...` in an environment variable too. You can reference it with `${TOOLKEN_KEY}` if your shell pre-processes the file, or store it directly in `config.toml` and keep the file out of version control.</Tip>
  </Step>

  <Step title="Set your provider key and run Codex">
    Export your OpenAI key, then run Codex as normal:

    ```bash theme={null}
    export OPENAI_API_KEY="sk-..."
    codex
    ```

    Codex selects the `toolken` provider from `config.toml`, attaches `X-Toolken-Key` and `X-Toolken-Metadata-Agent`, and routes the request through the gateway.
  </Step>

  <Step title="Confirm in your dashboard">
    Within seconds your request appears in the Toolken dashboard, grouped under the `codex` agent. Cost, token usage, and latency are all captured automatically.
  </Step>
</Steps>

<Note>Codex uses the OpenAI Responses API (`/v1/responses`). The Toolken gateway supports the Responses API natively, so the integration works without any server-side shim or protocol translation.</Note>

## Next

<CardGroup cols={2}>
  <Card title="Claude Code" icon="terminal" href="/integrations/claude-code">Route Claude Code traffic through Toolken with three environment variables.</Card>
  <Card title="Continue" icon="puzzle-piece" href="/integrations/continue">Add Toolken as a model provider in Continue's config.yaml.</Card>
</CardGroup>