> ## 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.

# Introduction

> Load balancer for ChatGPT accounts with usage tracking, dashboard, and OpenAI-compatible endpoints

## Welcome to Codex-LB

Codex-LB is a load balancer and proxy for ChatGPT accounts. Pool multiple accounts, track usage, manage API keys, and monitor everything through a beautiful dashboard.

<img src="https://mintlify.s3.us-west-1.amazonaws.com/soju06-codex-lb-43/images/dashboard.jpg" alt="Codex-LB Dashboard" className="rounded-lg shadow-lg" />

## Why Codex-LB?

Codex-LB sits between your applications and ChatGPT accounts, providing enterprise-grade account management and usage controls without requiring direct OpenAI API access.

<CardGroup cols={2}>
  <Card title="Account Pooling" icon="users">
    Load balance requests across multiple ChatGPT accounts automatically
  </Card>

  <Card title="Usage Tracking" icon="chart-line">
    Track tokens, costs, and 28-day trends per account with real-time updates
  </Card>

  <Card title="API Key Management" icon="key">
    Create API keys with per-key rate limits by token, cost, time window, and model
  </Card>

  <Card title="Dashboard Auth" icon="lock">
    Secure your dashboard with password authentication and optional TOTP
  </Card>

  <Card title="OpenAI Compatible" icon="plug">
    Works with Codex CLI, OpenCode, and any OpenAI-compatible client
  </Card>

  <Card title="Auto Model Sync" icon="arrows-rotate">
    Available models are automatically fetched from upstream ChatGPT
  </Card>
</CardGroup>

## How It Works

1. **Deploy** — Run Codex-LB via Docker or uvx
2. **Add Accounts** — Link your ChatGPT accounts through OAuth
3. **Configure Clients** — Point any OpenAI-compatible client at Codex-LB
4. **Monitor** — Track usage and manage everything from the dashboard

<Note>
  Codex-LB proxies requests to your ChatGPT accounts, not to OpenAI's API. You'll need active ChatGPT accounts to use this service.
</Note>

## Key Features

### Account Management

Add multiple ChatGPT accounts and let Codex-LB distribute requests intelligently. Monitor each account's token usage, cost, and health status from a unified dashboard.

### Usage Analytics

Real-time tracking of:

* Token consumption per account
* Cost calculations with 28-day trends
* Request logs with model and endpoint details
* Per-key usage breakdowns

### Rate Limiting

Create API keys with fine-grained controls:

* Token limits per day/week/month
* Cost limits with currency tracking
* Model restrictions
* Automatic key expiration

### Security

* Optional API key authentication for all proxy endpoints
* Dashboard authentication with password + TOTP
* IP-based firewall rules
* Encrypted token storage

## Supported Clients

Codex-LB works with any OpenAI-compatible client:

<CardGroup cols={2}>
  <Card title="Codex CLI" icon="terminal" href="/clients/codex-cli">
    Configure your Codex CLI to use Codex-LB as the backend
  </Card>

  <Card title="OpenCode" icon="code" href="/clients/opencode">
    Set up OpenCode with Codex-LB as a custom provider
  </Card>

  <Card title="OpenClaw" icon="paw" href="/clients/openclaw">
    Add Codex-LB as a model provider in OpenClaw
  </Card>

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

## Quick Start

Get up and running in under 2 minutes:

<Card title="Quickstart Guide" icon="rocket" href="/quickstart" horizontal>
  Follow our quickstart to install Codex-LB and make your first request
</Card>

## Next Steps

<CardGroup cols={2}>
  <Card title="Installation" icon="download" href="/installation">
    Detailed installation instructions for Docker, uvx, and local development
  </Card>

  <Card title="Add Accounts" icon="user-plus" href="/guides/adding-accounts">
    Learn how to add and manage ChatGPT accounts
  </Card>

  <Card title="Client Setup" icon="plug" href="/clients/overview">
    Configure your favorite OpenAI-compatible client
  </Card>

  <Card title="Configuration" icon="gear" href="/configuration/environment-variables">
    Explore environment variables and advanced settings
  </Card>
</CardGroup>