{"schema_version":"kingy-change-evidence-v1","event":{"id":"ct-1ef62343e057bd1cdf58a65d","vendor":"OpenAI","category":"pricing","type":"documented_source_change","title":"OpenAI cache policy documentation changed","source_id":"openai-cache","source_url":"https://developers.openai.com/api/docs/guides/prompt-caching.md","observed_at":"2026-10-20T19:55:04Z","last_unchanged_at":"2026-10-20T17:50:05Z","before_snapshot":"snap-e80a47aa7e2c1262592ffc266779","after_snapshot":"snap-010877cfecbaa69aefa059060fc0","before_hash":"74dc45350d5de0e7eef80b0b09d67b733a73170275f1bacb0760e066a4254480","after_hash":"715eacd5f0fe6bd7b238b74b770a6eb5b9a5260f464b5d54066b0bf580d3e995","before_excerpt":"For GPT-5.6 and later, cache writes cost 1.25× the standard, uncached input-token rate. Subsequent reads cost 0.1× that rate on most of these models and 0.05× on [GPT-6.1 Sol](https://developers.openai.com/api/docs/models/gpt-6.1-sol). At the 0.1× read rate, writing a prefix once and fully reusing it once costs 1.35× its ordinary input cost, compared with 2× for processing it twice without caching. Across ten requests, one write and nine full reads cost 2.15× at that rate, compared with 10× without caching. Cache entries are not stored indefinitely. A later request can reuse a cached …","after_excerpt":"For GPT-5.6 and later, cache writes cost 1.25× the standard, uncached input-token rate for the default 30-minute lifetime. In the Responses API, you can choose a [12-hour minimum lifetime](#cache-lifetime) at a write rate of 2.5× ordinary input. Subsequent reads cost 0.1× the ordinary input rate on most of these models and 0.05× on [GPT-6.1 Sol](https://developers.openai.com/api/docs/models/gpt-6.1-sol), regardless of the selected lifetime. At the 0.1× read rate with 30-minute writes, writing a prefix once and fully reusing it once costs 1.35× its ordinary input cost, compared with 2× for processing it twice …","status":"published","scope":"Published documentation; runtime behavior and legal interpretation not established.","before_capture":{"http_status":304,"resolved_url":"https://developers.openai.com/api/docs/guides/prompt-caching.md","etag":"\"09b40f4d8be7d628a220eacf4a6f8685\"","last_modified":"Tue, 06 Oct 2026 01:37:43 GMT","source_id":"openai-cache","source_url":"https://developers.openai.com/api/docs/guides/prompt-caching.md","captured_at":"2026-10-20T17:50:05Z","raw_sha256":"74dc45350d5de0e7eef80b0b09d67b733a73170275f1bacb0760e066a4254480","normalized_sha256":"e0d49ced9093652e53e46f40852e7408bc75c3594f5fb5d6aead63421ac463da","collector_version":"1.0.0","normalizer_version":"1.1","locale":"en-US","collection_region":"existing hosting; account-independent public request","id":"snap-e80a47aa7e2c1262592ffc266779"},"after_capture":{"http_status":200,"resolved_url":"https://developers.openai.com/api/docs/guides/prompt-caching.md","etag":"\"d43d1a54892ac8b87dd22e09ae472c58\"","last_modified":"Tue, 20 Oct 2026 19:49:06 GMT","response_date":"Tue, 20 Oct 2026 19:55:04 GMT","source_id":"openai-cache","source_url":"https://developers.openai.com/api/docs/guides/prompt-caching.md","captured_at":"2026-10-20T19:55:04Z","raw_sha256":"715eacd5f0fe6bd7b238b74b770a6eb5b9a5260f464b5d54066b0bf580d3e995","normalized_sha256":"4b775ab2aca5a3d3ca8070446127d40f36671a6af309da44444124d60104a88e","collector_version":"1.0.0","normalizer_version":"1.1","locale":"en-US","collection_region":"existing hosting; account-independent public request","id":"snap-010877cfecbaa69aefa059060fc0"},"display_normalizer_version":"1.1","display_before_sha256":"e0d49ced9093652e53e46f40852e7408bc75c3594f5fb5d6aead63421ac463da","display_after_sha256":"4b775ab2aca5a3d3ca8070446127d40f36671a6af309da44444124d60104a88e"},"content_scope":"Changed excerpts and retained capture metadata; complete raw responses archived privately"}