> ## Documentation Index
> Fetch the complete documentation index at: https://docs.a2agent.me/llms.txt
> Use this file to discover all available pages before exploring further.

# Use OpenAI Codex CLI with A2Agent for Cheaper Models

> Redirect OpenAI's Codex CLI to A2Agent by setting two environment variables. Get DeepSeek, Kimi, GLM, and more at a fraction of official pricing.

OpenAI's Codex CLI respects the standard `OPENAI_BASE_URL` environment variable, which means you can redirect every request it makes to A2Agent's OpenAI-compatible endpoint. The result is full Codex CLI functionality backed by models like DeepSeek, Kimi, GLM, and MiniMax — at significantly lower cost.

## Prerequisites

* Codex CLI installed — follow the [official installation guide](https://github.com/openai/codex) if needed
* An A2Agent API key — [sign up at a2agent.me/register](https://a2agent.me/register) to get one

## Setup

<Steps>
  <Step title="Set the required environment variables">
    Before running Codex, export your A2Agent key and base URL in your current shell session:

    ```bash theme={null}
    export OPENAI_API_KEY="YOUR_A2AGENT_KEY"
    export OPENAI_BASE_URL="https://api.a2agent.me/v1"
    ```

    <Note>
      `OPENAI_API_KEY` here is your **A2Agent** API key, not an OpenAI key. A2Agent accepts requests in the OpenAI API format and routes them to the model you select.
    </Note>
  </Step>

  <Step title="Run Codex and verify the connection">
    With those variables set, run Codex as you normally would — it will automatically route all requests through A2Agent:

    ```bash theme={null}
    codex "add error handling to this function"
    ```

    If Codex returns a response, your setup is working correctly.
  </Step>

  <Step title="(Optional) Specify a model">
    Pass the `--model` flag to select a particular A2Agent model for the task at hand:

    ```bash theme={null}
    codex --model deepseek-v4-pro "refactor this function to be more readable"
    ```

    **Recommended models for coding tasks:**

    | Model             | Best for                             |
    | ----------------- | ------------------------------------ |
    | `deepseek-v4-pro` | Complex refactoring and architecture |
    | `glm-5.1`         | General-purpose coding assistance    |
    | `kimi-k2.7-code`  | Code generation and debugging        |
    | `minimax-m2.5`    | Long-context code analysis           |
  </Step>
</Steps>

## Persist the configuration

To avoid re-exporting the variables every session, add them to your shell profile:

```bash ~/.bashrc or ~/.zshrc theme={null}
export OPENAI_API_KEY="YOUR_A2AGENT_KEY"
export OPENAI_BASE_URL="https://api.a2agent.me/v1"
```

After saving, reload your profile:

```bash theme={null}
source ~/.bashrc   # or source ~/.zshrc
```

From that point on, every new terminal session will automatically use A2Agent when you run Codex.

## Troubleshooting

<AccordionGroup>
  <Accordion title="401 Unauthorized">
    Codex is reaching A2Agent but your credentials are being rejected. Double-check that `OPENAI_API_KEY` is set to your full A2Agent key with no extra spaces, quotes, or newline characters.
  </Accordion>

  <Accordion title="Connection refused or could not resolve host">
    Confirm that `OPENAI_BASE_URL` is set to exactly `https://api.a2agent.me/v1` — including the `/v1` path and no trailing slash. Run `echo $OPENAI_BASE_URL` to verify the value in your current shell.
  </Accordion>

  <Accordion title="Model not found">
    The model name you passed with `--model` must match an A2Agent model ID exactly — for example, `deepseek-v4-pro`, `kimi-k2.7-code`, `glm-5.1`, or `minimax-m2.5`. Check the [A2Agent model list](https://a2agent.me) for all available IDs.
  </Accordion>

  <Accordion title="Environment variables not recognised after editing shell profile">
    Run `source ~/.bashrc` (or `source ~/.zshrc`) in your current terminal after editing the profile, or open a new terminal session for the changes to take effect.
  </Accordion>
</AccordionGroup>