What's New · PhotonMark Codex

Built-in web search compatibility updated for current Codex releases

2026-07-19 21:23 NZST

PhotonMark now supports the standalone alpha/search endpoint used by the built-in Codex web.run tool across Codex Link, Codex Pay, and Codex Boost. Prefer the recommended Dashboard configuration with model_provider = "openai"; no local hotfix, custom model catalog, or manually injected tool is required. If an old [model_providers.*] block must be retained, its case-sensitive display name must be name = "OpenAI". If search still fails, remove local gateway rules that mutate alpha/search requests, restart Codex, and test again. Successful standalone searches follow the existing Web Search billing rule.

View built-in web search troubleshooting

Refer a new user and receive US$5 in Pay or Boost credit

2026-07-16 22:40 NZST

A limited-time referral reward is now available: each time an existing PhotonMark Codex user successfully refers a new user who makes a single payment of at least US$10 by July 31, 2026 (inclusive, New Zealand time), the referrer can receive US$5 in Codex Pay or Codex Boost credit. Every existing user now has a permanent referral link on the Account page of the Dashboard. The referral is bound automatically when a new user follows the link and first signs in to PhotonMark Codex, and remains recorded if they pay several days later. Existing Codex users, self-referrals, and referrals between accounts controlled by the same person are not eligible. After qualification, we manually review linked accounts, payment, refund, and dispute status before issuing the reward to the Pay or Boost destination selected in the Dashboard.

View and copy my permanent referral link

OpenAI launches GPT-5.6; PhotonMark pricing is updated

2026-07-10 08:37 NZST

OpenAI officially released the GPT-5.6 family on July 10, 2026: Sol for frontier capability, Terra for a balance of intelligence and cost, and Luna for efficient, high-volume workloads. PhotonMark Codex supports all three explicit model names. Please refer to the pricing page for model rates, effective costs after top-ups, and the Fast/Priority and long-context billing rules.

View complete GPT-5.6 pricing and billing rules

Pay child accounts and sharing rules update

2026-07-07 11:18 NZST

Pay child accounts are now available. A primary account can have multiple child accounts, making distribution and unified cost management easier for businesses and teams. This feature currently requires manual activation. When contacting us, please include your use case, expected usage, number of child accounts, and management requirements so we can assess resource needs and configure it.

Contact support

New read-only status APIs for PhotonMark Codex Boost and Pay

2026-07-07 11:18 NZST

Use your existing PhotonMark proxy token to query service status. Status queries do not incur charges. Boost read-only status: curl -H "Authorization: Bearer <your PhotonMark proxy token>" \ https://codex.photonmark.com/api/v1/services/boost/status | jq '{balance_usd,service,spent_usd,status}' Pay read-only status: curl -H "Authorization: Bearer <your PhotonMark proxy token>" \ https://codex.photonmark.com/api/v1/services/pay/status | jq '{balance_usd,service,spent_usd,status}' Replace <your PhotonMark proxy token> with your actual token.

View status API documentation

About prompt pre-screening

2026-07-07 11:18 NZST

When using Pay, or Boost with a platform-managed quota account, the platform applies AI safety pre-screening to user prompts. Requests may be blocked when the system identifies high-risk dangerous, prohibited, sexual, or violent content. This screening may add about 0.5–1 second to each prompt. In general, PhotonMark does not record or store project materials, prompts, or output content processed through Codex. Only the latest related prompt may be retained for necessary safety analysis and service improvement, for no more than 30 days, when Pay or Boost using a platform-managed quota account is flagged by the safety screen. This protects platform-managed quota accounts and reduces the risk of upstream suspension or restrictions so that all users can continue receiving stable service. It is not intended to infringe user privacy. The mechanism may still make mistakes; please contact us about false positives or other issues. As the technology matures, we will evaluate reducing or eliminating these records.

Contact support

Recommended Codex configuration updated

2026-06-28 12:00 NZST

The recommended setup now places the complete standalone PhotonMark provider block from the dashboard at the top of your user-level config.toml. The base_url contains no proxy token, credentials are sent through http_headers, and unnecessary WebSocket probing is disabled. Legacy token-in-URL TOML remains temporarily compatible, but new installations should use the current dashboard config. Complete TOML, proxy tokens, http_headers, and installer scripts are access credentials; do not publish or forward them.

View setup guide