{"slug": "openai-12-hour-cache-api-available-and-cache-forever-for-work-codex-users", "title": "OpenAI – 12 hour cache (API) available and \"cache forever\" for work/codex users", "summary": "OpenAI now offers a 12-hour prompt caching option in its API, announced by Tibo (OpenAI staff) on X as \"Day 16\" of a series, and keeps cache indefinitely for logged-in users across Codex and Work with no penalty for resuming an old conversation after a few hours. OpenAI said developers can keep shared instructions, tools and context cached longer and pay the lower cached-input rate even when requests are hours apart, a setup it said suits persistent agents that reuse context throughout the day.", "body_md": "Tibo on X: \"Day 16/\nYou can now cache for 12h in the API and for logged in users across Codex & Work we keep cache forever and you don’t have any penalty for coming back to an old conversation or resuming after a few hours and are now guaranteed to hit the cache.\" / X\n\nTibo on X: \"Day 16/\nYou can now cache for 12h in the API and for logged in users across Codex & Work we keep cache forever and you don’t have any penalty for coming back to an old conversation or resuming after a few hours and are now guaranteed to hit the cache.\"\n\nDay 16/\nYou can now cache for 12h in the API and for logged in users across Codex & Work we keep cache forever and you don’t have any penalty for coming back to an old conversation or resuming after a few hours and are now guaranteed to hit the cache.\n\nYou can now choose 12-hour prompt caching in the API.\nPersistent agents, like dots, reuse context throughout the day.\nYou can keep shared instructions, tools, and context cached longer and pay the lower cached-input rate, even when requests are hours apart.\n\nDay 16/\nYou can now cache for 12h in the API and for logged in users across Codex & Work we keep cache forever and you don’t have any penalty for coming back to an old conversation or resuming after a few hours and are now guaranteed to hit the cache.\n\nYou can now choose 12-hour prompt caching in the API.\nPersistent agents, like dots, reuse context throughout the day.\nYou can keep shared instructions, tools, and context cached longer and pay the lower cached-input rate, even when requests are hours apart.", "url": "https://wpnews.pro/news/openai-12-hour-cache-api-available-and-cache-forever-for-work-codex-users", "canonical_source": "https://twitter.com/thsottiaux/status/2112712984644784534", "published_at": "2026-10-21 02:00:14+00:00", "updated_at": "2026-10-21 02:18:22.979409+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-agents", "ai-tools", "ai-infrastructure"], "entities": ["OpenAI", "Tibo", "Codex", "Work", "dots"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/openai-12-hour-cache-api-available-and-cache-forever-for-work-codex-users", "markdown": "https://wpnews.pro/news/openai-12-hour-cache-api-available-and-cache-forever-for-work-codex-users.md", "text": "https://wpnews.pro/news/openai-12-hour-cache-api-available-and-cache-forever-for-work-codex-users.txt", "jsonld": "https://wpnews.pro/news/openai-12-hour-cache-api-available-and-cache-forever-for-work-codex-users.jsonld"}}