{"version":1,"type":"story","url":"https://digestai.news/story/openai-adds-improved-prompt-caching-to-gpt-6-offering-up-to-90-input-d","json":"https://digestai.news/story/openai-adds-improved-prompt-caching-to-gpt-6-offering-up-to-90-input-d.json","markdown":"https://digestai.news/story/openai-adds-improved-prompt-caching-to-gpt-6-offering-up-to-90-input-d.md","slug":"openai-adds-improved-prompt-caching-to-gpt-6-offering-up-to-90-input-d","headline":"OpenAI adds improved prompt caching to GPT-6, offering up to 90% input discounts","summary":"OpenAI announced an improved prompt caching system for GPT-6, enabling persistent agents to run for hours on tasks such as code refactoring and document creation. The system reuses shared context across API calls, reducing response times and giving developers discounts of up to 90% on cached input tokens.\n\nCache eligibility now lasts a 30‑minute window for shared prefixes. A new Prompt Caching Dashboard displays hit rates, an input composition chart, and token breakdowns, while a diagnostics tool explains misses, reporting figures such as 5629 affected tokens in a sample miss. Developers can set explicit cache breakpoints, adjust reasoning effort without breaking cache, and keep tool definitions stable using allowedtools or toolchoice settings.\n\nOpenAI also introduced prewarming, which lets applications load known instructions, tool schemas, or reference material before a user query, moving processing out of the latency window. The refreshed prompt caching guide and monitoring tools aim to help developers optimize cache hit rates and overall integration performance.","keyPoints":["Developers receive up to 90% discounts on cached input tokens for GPT‑6 agents.","Cache eligibility lasts 30 minutes; a new dashboard shows hit rates and token breakdowns.","Prewarming, explicit breakpoints, and adjustable reasoning effort let developers keep cache while changing tools."],"whyItMatters":"Higher cache hit rates lower latency and cost for multi‑turn GPT‑6 applications, making complex agents more affordable and responsive for developers and their users.","category":{"slug":"agents","name":"Agents & Tools","url":"https://digestai.news/category/agents"},"entities":{"companies":["OpenAI"],"models":["GPT-6"],"people":[]},"firstPublishedAt":"2026-09-22T21:00:00Z","updatedAt":"2026-09-22T21:00:00Z","sourceCount":1,"hasPrimarySource":true,"sources":[{"outlet":"OpenAI","title":"Better prompt caching for GPT-6","url":"https://openai.com/index/better-prompt-caching-for-gpt-6","publishedAt":"2026-09-22T21:00:00Z","type":"primary","primary":true,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"OpenAI adds improved prompt caching to GPT-6, offering up to 90% input discounts\", 22 September 2026, https://digestai.news/story/openai-adds-improved-prompt-caching-to-gpt-6-offering-up-to-90-input-d","publisher":"Digest AI","title":"OpenAI adds improved prompt caching to GPT-6, offering up to 90% input discounts","datePublished":"2026-09-22T21:00:00Z","url":"https://digestai.news/story/openai-adds-improved-prompt-caching-to-gpt-6-offering-up-to-90-input-d"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}