> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/Soju06/codex-lb/llms.txt
> Use this file to discover all available pages before exploring further.

# Client Integration Overview

> Connect any OpenAI-compatible client to Codex-LB

Codex-LB provides OpenAI-compatible endpoints that work with any client that supports the OpenAI API. This includes popular CLI tools, IDEs, SDKs, and custom applications.

## Supported Endpoints

Codex-LB exposes two main endpoint types:

<CardGroup cols={2}>
  <Card title="OpenAI v1" icon="code" href="/api/chat-completions">
    Standard OpenAI-compatible `/v1` endpoints

    `http://127.0.0.1:2455/v1`
  </Card>

  <Card title="Codex Backend API" icon="terminal" href="/api/codex-responses">
    Codex-specific `/backend-api/codex` endpoints

    `http://127.0.0.1:2455/backend-api/codex`
  </Card>
</CardGroup>

## Supported Clients

Codex-LB works seamlessly with these popular clients:

| Client                           | Endpoint                                  | Documentation                      |
| -------------------------------- | ----------------------------------------- | ---------------------------------- |
| **Codex CLI**                    | `http://127.0.0.1:2455/backend-api/codex` | [Setup Guide](/clients/codex-cli)  |
| **OpenCode**                     | `http://127.0.0.1:2455/v1`                | [Setup Guide](/clients/opencode)   |
| **OpenClaw**                     | `http://127.0.0.1:2455/v1`                | [Setup Guide](/clients/openclaw)   |
| **OpenAI Python SDK**            | `http://127.0.0.1:2455/v1`                | [Setup Guide](/clients/openai-sdk) |
| **Any OpenAI-compatible client** | `http://127.0.0.1:2455/v1`                | [API Reference](/api/overview)     |

## Authentication

API key authentication is **disabled by default**. When disabled, any client can connect without credentials.

<Info>
  To enable API key authentication, go to **Settings → API Key Auth** in the dashboard.
  See [API Key Authentication](/features/api-keys) for details.
</Info>

When API key auth is enabled:

1. Create an API key in the dashboard (**API Keys → Create**)
2. Configure your client to pass the key as a Bearer token:
   ```
   Authorization: Bearer sk-clb-...
   ```
3. The key is shown **only once** at creation — save it securely

## Configuration Pattern

All clients follow a similar setup pattern:

<Steps>
  <Step title="Set the base URL">
    Point the client at Codex-LB's endpoint:

    * `/v1` for OpenAI-compatible clients
    * `/backend-api/codex` for Codex CLI
  </Step>

  <Step title="Configure authentication (optional)">
    If API key auth is enabled, provide your key:

    * Via environment variable (recommended)
    * Directly in config (less secure)
  </Step>

  <Step title="Select your model">
    Use any model available in your Codex-LB instance:

    * `gpt-5.3-codex`
    * `gpt-5.3-codex-spark`
    * Or any custom models you've configured
  </Step>
</Steps>

## Next Steps

<CardGroup cols={2}>
  <Card title="Codex CLI" icon="terminal" href="/clients/codex-cli">
    Configure the Codex CLI and IDE extensions
  </Card>

  <Card title="OpenCode" icon="code" href="/clients/opencode">
    Set up OpenCode AI coding assistant
  </Card>

  <Card title="OpenClaw" icon="sparkles" href="/clients/openclaw">
    Configure OpenClaw agent framework
  </Card>

  <Card title="Python SDK" icon="python" href="/clients/openai-sdk">
    Use the OpenAI Python SDK with Codex-LB
  </Card>
</CardGroup>

## Troubleshooting

<AccordionGroup>
  <Accordion title="Connection refused errors">
    Ensure Codex-LB is running and accessible:

    ```bash theme={null}
    # Check if the service is running
    curl http://127.0.0.1:2455/v1/models
    ```

    If using Docker, verify port mappings:

    ```bash theme={null}
    docker ps | grep codex-lb
    ```
  </Accordion>

  <Accordion title="Authentication errors">
    If you see `401 Unauthorized`:

    1. Check if API key auth is enabled in Settings
    2. Verify your API key is valid and not expired
    3. Ensure the key is passed correctly as a Bearer token
    4. Check that the key has permission for the requested model
  </Accordion>

  <Accordion title="Model not found">
    If a model isn't available:

    1. Verify the model exists in your dashboard
    2. Check that at least one account supports the model
    3. If using API keys with model restrictions, ensure the key allows that model
    4. Run model sync: **Settings → Sync Models**
  </Accordion>

  <Accordion title="Rate limit errors">
    If you hit rate limits:

    1. Check your API key's rate limits in the dashboard
    2. Review account limits and quotas
    3. Consider adding more accounts to the pool
    4. Adjust rate limits in **API Keys → Edit**
  </Accordion>
</AccordionGroup>

<Tip>
  Need help? Check the [Troubleshooting Guide](/guides/troubleshooting) for more common issues and solutions.
</Tip>