FAQ

The key difference is quota source and billing. Link is a relay / transparent proxy for users who already have Codex quota but do not want to handle network/VPN themselves, at USD $0.25 per week. Pay uses PhotonMark managed quota, suitable for users without a paid ChatGPT account. Boost uses your own Codex quota first, then supplements it with PhotonMark balance when needed.The hourly keepalive for Link / Boost helps trigger and preserve as much of your own 5-hour or weekly quota as possible.

Boost first uses the Codex availability in your official account, which does not consume PhotonMark balance. When your own quota is insufficient or limited, it supplements with prepaid balance. This is best for users who already have an official paid account but need extra capacity.

Your own account's Codex availability is determined by OpenAI, not by PhotonMark as a fixed number. Some accounts may see both a shorter 5-hour rolling window and a longer weekly or plan-cycle quota. The actual remaining quota, recovery time, and limit banner depend on what your OpenAI account shows.

If you already have an official account and Codex quota and only need stable proxy access plus hourly keepalive, choose Codex Link。If you do not have a paid ChatGPT account and want to use PhotonMark managed quota directly, choose Codex Pay。If you have your own account but Codex quota is not enough and want PhotonMark to supplement it when needed, choose Codex Boost。

No. Link is a transparent relay service and is not used for balance billing. Pay and Boost record billable usage.

No. PhotonMark Codex is a dedicated access service for the official Codex client. It does not silently replace models and does not reverse-proxy internal interfaces of Cursor, Kiro, GitHub Copilot, or similar clients to imitate official capability. Link transparently forwards the user's own ChatGPT or Codex requests; Pay and Boost use PhotonMark managed Codex authorization.

Currently supports gpt-5.3-codex-spark, gpt-5.4-mini, gpt-5.4, gpt-5.5。New Codex models are added to the public billing table only after official OpenAI prices and Fast multipliers are clear. Models not publicly listed are not shown as external commitments.

If the client or upstream returns an unlisted or unknown model, the system keeps the original model name for audit and temporarily charges it at the same rate as gpt-5.5-pro until we add that model to the public billing table.

gpt-5.3-codex-spark This is currently part of OpenAI Codex research preview, and OpenAI API pricing does not list a separate Spark token price yet. PhotonMark temporarily uses 10% of OpenAI gpt-5.3-codex API token pricing.

Please upgrade Codex App, Codex CLI, or IDE Extension to the latest version. Old clients may still send gpt-5.3-codex and similar deprecated models from older ChatGPT login flows. Requests may fail or may not enter PhotonMark billable usage processing correctly.

No. PhotonMark Codex provides stable proxy access, service configuration, and prepaid quota management, but does not guarantee bypassing OpenAI or ChatGPT risk controls, quota limits, regional policies, or account reviews. Users must still follow OpenAI terms and applicable law, and must not use this service for violations, abuse, restriction evasion, or other non-compliant purposes.

Put it at the top of the user-level Codex config. The dashboard shows the full dedicated config; the project-level .codex/config.toml cannot reliably override provider and auth-related config.

We mean the GitHub project farion1231/cc-switch. The recommended method is still to copy the Pay TOML from the dashboard directly into the user-level config.toml at the top. If you must use CC Switch, follow its current provider docs and create a Codex Custom / OpenAI-compatible provider. Set Provider Name / ID to photonmark-codex-pay, or use the provider id from the TOML block you are using; set Base URL to the base_url；Set API key to any non-empty placeholder, for example photonmark; choose a currently supported Codex model, for example gpt-5.5。

CC Switch may write ~/.codex/auth.json and ~/.codex/config.toml. After activation, check the final config.toml: the top-level model_provider should point to the PhotonMark provider, for example photonmark-codex-pay; the matching [model_providers.*] base_url should be the current dedicated dashboard address; requires_openai_auth = false; do not write a real OPENAI_API_KEY or sk-proj-*. Pay's real access credentials are in the dedicated URL and proxy token, not in the API key. If you see 401, it usually means an old token was copied or the config is not the current Pay config from the dashboard.

Yes. OpenAI Codex Remote connections support using the ChatGPT mobile app to control a connected Mac or Windows Codex App host. The phone does not run PhotonMark service directly; it sends instructions, approvals, and follow-ups to the logged-in, online, awake computer. Project files, commands, plugins, MCP, browser, and Computer Use all come from that host.

Recommended: open the latest Codex App on the computer, go to Settings > Connections, choose Set up Codex mobile and scan with your phone to complete binding. The phone needs the latest ChatGPT app and the same ChatGPT account and workspace. This flow starts from Codex App and cannot be completed with Codex CLI or IDE Extension alone.

If your user-level config.toml already has the three lines below, you can keep them. They usually help the Codex host support remote-connection capabilities and reduce the chance of sleep during long tasks:

[features]
prevent_idle_sleep = true
remote_connections = true
remote_control = true

But do not rely on these three lines alone to decide remote control is enabled. In current public config references, the stable visible option is prevent_idle_sleep，remote_control is mainly a feature flag for older config compatibility, and remote_connections may come from specific client versions or app-written config. Whether remote control actually works still depends on Codex App Connections settings and the connection status shown in ChatGPT mobile.

Codex App can log in with an OpenAI API key. This fits some local Codex workflows, but it uses your own OpenAI Platform API bill, not ChatGPT plan quota and not PhotonMark Pay balance.

For mobile remote control, the desktop Codex App host and the ChatGPT mobile app still need the same ChatGPT account and workspace that can log in normally. API-key login is not the same as completing ChatGPT mobile authorized-device binding.

Correct flow: first complete Codex App remote mobile binding with a ChatGPT account; then put the PhotonMark dashboard Codex Pay TOML into the user-level config.toml at the top so model requests use Pay.The requires_openai_auth = false setting in Pay config means model requests do not need the user's own OpenAI Platform API key; it does not mean ChatGPT account login can be skipped。

If a free ChatGPT account is blocked by phone verification, MFA, SSO, passkey, or another account check, PhotonMark Pay cannot bypass OpenAI account verification. Use an account that can already log in to ChatGPT mobile and see Codex, or complete OpenAI's account verification flow first.

Codex Pay uses PhotonMark managed Codex authorization and does not require a local OpenAI Platform API key. If the error contains sk-proj-*, invalid_api_key or Incorrect API key, it usually means local Codex is still sending OPENAI_API_KEY or old auth config. Clear the local API key and confirm the Pay TOML contains requires_openai_auth = false, then reopen Codex Desktop, Codex CLI, or IDE Extension and try again.

No. The dedicated URL, proxy token, and TOML config in the dashboard are access credentials. Do not publish them, forward them, or commit them to a public repository. If you suspect a leak, contact support.

We do not record project materials, prompts, or outputs you process in Codex, and we do not use them for training, analysis, or secondary processing. Pay / Boost keep only the minimum metadata needed for accounts, purchases, authorization, and billing statistics, such as model name, token statistics, balance, and request time.

Link / Boost saves the most recent valid access token and sends a low-cost reply with OK request every hour to help users preserve as much 5-hour or weekly quota as possible.These requests do not record your project content and are not billed as Pay / Boost user usage.

If OpenAI applies a 5-hour rolling window to your account, it usually starts from requests in that window and recovers according to official rules; there may also be weekly or plan-cycle limits. Keepalive is not bypassing OpenAI limits and cannot make quota unlimited. It periodically reaches official Codex with a tiny request to keep authorization, network path, and quota-window state active, reducing the chance of discovering too late that an access token expired or a quota window was not triggered.

Keepalive requests use a very small amount of your own account's Codex quota, but they do not use PhotonMark managed quota and are not charged from Pay / Boost balance. Actual quota, reset time, and risk-control results still depend on OpenAI's official response.

Each purchased balance is valid for 30 days. Users can top up $5, $10, $20, $30, up to $100. Purchases of $10 or more receive an extra 200% bonus credit, for example $20 becomes $60 and $100 becomes $300; $5 payments do not receive the 200% bonus. Unused balance can be extended by the next top-up for another 30 days from the new top-up date.

Different models have different prices; cached input is usually priced separately from normal input. We record usage fields returned by each upstream response. Cached input, output, and reasoning all come from upstream usage statistics; reasoning is included in output and is not charged again separately.

No. Fast mode affects service tier and credit/billing multiplier, not token counts. Input, cached input, and output tokens shown in the dashboard are still real upstream usage. If Fast is enabled, gpt-5.5 is charged at 2.5x the standard cost，gpt-5.4 is charged at 2x standard cost; other models use standard cost when no official Fast multiplier is available.

Yes. If a Codex request actually calls the OpenAI web search tool, the dashboard records web search calls and web search cost. Current billing is 10% of OpenAI's web search price, USD $0.0010 per web search call, deducted from Pay / Boost balance. Input tokens from search content are still billed by the selected model's input / cached input rules.

Yes. If a Codex request actually calls the OpenAI image generation tool, the dashboard records image calls and image cost. Current billing is 10% of official OpenAI image generation pricing; if the specific image model, quality, or size cannot be identified from the response, the default estimate uses gpt-image-2, Medium, 1024x1024, which is USD $0.0053 per image.The main model's input, cached input, and output tokens are still billed separately by the selected model.

Each billable response calculates normal input, cached input, and output separately by model price:base cost = (input - cached input) / 1,000,000 x input price + cached input / 1,000,000 x cached input price + output / 1,000,000 x output price. If the request uses Fast mode, multiply by the model's Fast multiplier. If web search or image generation is enabled, add the corresponding tool-call cost. Reasoning tokens are included in output statistics and are not charged again separately. Finally, charges are rounded up to four decimal places in USD.

Dashboard balance deduction uses standard prices. Purchases of USD $10 or more receive triple credited balance, so these top-up users' effective cash cost is about one-third of the standard deduction.

Example: if using gpt-5.4-mini, the price is input USD $0.075 / 1M, cached input USD $0.0075 / 1M, output USD $0.45 / 1M. If this response has input 20,000, cached input 10,000, and output 500, normal input is 10,000; the cost is USD $0.00075 + USD $0.000075 + USD $0.000225 = USD $0.00105, rounded up to USD $0.0011.