Today for AI
HOT RADAR
toolsHEAT 18.5°

AI CURATED HOT STORY · 10/21/2026

OpenAI Enhances Codex and API Caching with Permanent Retention for Logged-in Users

1 reports archived1 independent sourcesupdated 10/21/2026, 13:17:21
Synthesis & Latest Updates
1 Sources Cross-Validated

OpenAI has announced significant updates to its prompt caching mechanisms for Codex, Work, and the API. For logged-in users of Codex and Work, cache retention is now permanent, ensuring cache hits when resuming old conversations without penalty fees. Additionally, API prompt cache retention can be extended up to 12 hours (default remains 30 minutes), with first-time writes charged at 2.5x the standard rate and subsequent reads costing only 10%.

LATEST/OpenAI has announced significant updates to its prompt caching mechanisms for Codex, Work, and the API. For logged-in users of Codex and Work, cache retention is now permanent, ensuring cache hits when resuming old conversations without penalty fees. Additionally, API prompt cache retention can be extended up to 12 hours (default remains 30 minutes), with first-time writes charged at 2.5x the standard rate and subsequent reads costing only 10%.

HEAT TRENDHourly heat curve

2 fully observed hours
Fewer than 3 fully observed hours; trend not plotted yet.

TIMELINECoverage timeline

Total 1 reports · Latest first
  1. 宝玉 (@dotey)T2·68 pts
    • Cache retention for logged-in Codex and Work users is now permanent, eliminating penalties for resuming historical sessions.
    • API prompt caching supports retention periods up to 12 hours (with a default of 30 minutes).
    • API cache pricing structure clarified: first write costs 2.5x standard rate, while subsequent reads cost only 10%.
    • The update suggests potential disk-based storage implementation for persistent user caches.
OpenAI Enhances Codex and API Caching with Permanent Retention for Logged-in Users | Today for AI