PhotonMark Codex

Guide

New User Guide

1

Sign up for PhotonMark Cloud Account

First open the sign-up page to create a PhotonMark Cloud Account. This account can also be used for other PhotonMark services such as VPN, Google Veo, AI chat, AI agent, Private collaboration and IT services。

Create Account
2

Log In To Codex Service

After signing up and verifying your email, open the login page and log in to PhotonMark Codex with the same PhotonMark Cloud Account.

Log in
3

Buy Service In The Dashboard

After login, you will enter the dashboard. You can buy or renew any service directly. Current pricing, top-up bonuses, and balance validity follow the pricing page . Pay and Boost balance may come from top-ups, renewals, limited-time bonus credit, or manually enabled grants.

SituationRecommended serviceNotes
No paid ChatGPT account Codex Pay Use PhotonMark managed quota; no local OpenAI Platform API key or ChatGPT authorization is required.
Already have paid ChatGPT or Codex account Codex Boost Use your own quota first, then switch to PhotonMark managed quota when it is insufficient.
Only need stable proxy access Codex Link Use your own official account and Codex quota; this is only a relay / transparent proxy and does not charge by token.
Open Dashboard View Services
4

Copy The TOML From Dedicated Configuration

After payment succeeds or granted balance is activated, find the Dedicated Configuration section in the dashboard and locate the TOML block you want to use. We recommend downloading the macOS / Linux or Windows auto-install script below that config block; you can also copy the full TOML block and merge it manually. The script backs up old config first, then updates the user-level config.toml, and preserves the global notify / personality。

  • Linux / macOS：~/.codex/config.toml
  • Windows：C:\Users\your-username\.codex\config.toml
  • If the dashboard shows multiple Pay / Boost config blocks, each block corresponds to a separate balance or granted credit. To use a specific balance, copy or download the TOML or script below that block.
  • You can keep multiple [model_providers.*] blocks in the same config.toml. What actually decides the active block is the topmost model_provider = "..."。
  • To switch balance manually, only change model_provider to the provider id in that TOML block. Avoid keeping multiple uncommented model_provider lines at the same time.
  • The topmost model_provider must point to the PhotonMark provider you want to use. When merging manually, do not put global notify / personality under [model_providers.*] .
  • If using CC Switch, use the provider id from the dashboard TOML in the Codex provider. For Pay, this is usually photonmark-codex-pay, and use the base_url; after activation, check that the final config.toml still points to PhotonMark and does not write a real OPENAI_API_KEY。
  • Remove or comment out old model_provider, OPENAI_API_KEY, sk-proj-*, old providers, or old auth config.

If you use Codex Pay, this machine does not need an OpenAI Platform API key; keeping an old API key may cause the Codex client to keep sending the wrong credential. The auto-install script contains your dedicated proxy token. Do not forward it to anyone.

5

Start Or Restart The Codex Client

After saving the user-level config.toml , reopen Codex Desktop, Codex CLI, or IDE Extension, or start a new Codex session. The client reads the PhotonMark TOML config at the top and connects through the selected service.

Download Codex View FAQ