Run every account and model in the official Codex App

CodexUse is for accounts you already hold — your personal login, an employer seat, separate client or contractor accounts. It signs in with the same OAuth flow the Codex CLI uses, keeps each account in its own local profile, and never shares one subscription between people. It does not create accounts, bypass billing, or forge identities. Switching between accounts that are yours is the same activity as logging out and back in by hand; CodexUse removes the loop. Check your own plan terms before pooling quota for automated workloads.

Yes, on macOS. CodexUse detects profile-matched Codex App windows, shows running state, PID, and uptime, and lets you focus, stop, restart, or launch each one. On a switch it can capture the active thread, resume it through the app-server, and continue in the same conversation. It does not clone a live session.

Yes. A profile can point at any provider that exposes an OpenAI-compatible Responses or Chat Completions endpoint — OpenRouter, DeepSeek, Groq, or a model running on your own Mac. CodexUse runs a local gateway on 127.0.0.1 that presents the Responses API to Codex and translates to the provider's shape, so the official app runs the model with no config editing. That profile is a provider profile rather than an OpenAI account: it spends no OpenAI quota, keeps its credential in the macOS Keychain, and shows only its own models in the picker. Dictation and browser control call ChatGPT's backend, so they are unavailable on a provider profile.

Sometimes, and not automatically. You are trading a flat subscription for metered billing, so heavy use of a frontier model often costs more than the plan does. It usually wins when a cheaper model is good enough for most of your work, or when you already pay a provider and want the Codex App as the interface. Measure your own volume before you switch rather than trusting anyone's estimate.

Free tools swap ~/.codex/auth.json for the Codex CLI. CodexUse also drives the official Codex App — profile-matched window orchestration and thread handoff — plus custom model providers, Telegram remote control, Accounts Pool, and encrypted cloud sync in one signed native Mac app. If you only need CLI account switching, a free tool is a reasonable choice and the comparison page says so.

Not for OpenAI. CodexUse uses the same OAuth login as the Codex CLI, so you sign in with the account you already have. Two exceptions: a custom model provider needs that provider's own credential, which is held in the macOS Keychain and never written into config files; and Accounts Pool mints a separate local key for the app you point at it.

Accounts Pool turns selected saved Codex accounts into one local API for another OpenAI-compatible app. That app gets one base URL and one key, while CodexUse shares quota across the selected accounts, load-balances new requests, and fails over when one account hits limits or runtime trouble. It runs on your machine — it is not a hosted service.

Set a “% left” switch threshold, rank the eligible profiles if you want a specific order, and CodexUse switches to the next one when the active account reaches that level. A confirm countdown cancels stale decisions before they fire. Available during the trial and unlocked with Pro.

Current public desktop releases target macOS on Apple Silicon. Intel Mac and Linux desktop builds are not shipped in the current release line. For terminal workflows on another machine, install the optional codexuse CLI with npm.

The same app. Pro is a one-time lifetime license with free updates and no subscription, so buying skips the 7-day trial and keeps everything unlocked afterwards. Activation is automatic after payment, with a receipt key as a manual fallback, and there is a 30-day refund window.