{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreih5uflpt2n5bhd3qgikndfgknpxtb52t5epmbxktuuk725agjgudu",
"uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mmmytaq2rmd2"
},
"path": "/t/prompt-caching-not-working-for-gpt-5-4-nano/1381702#post_1",
"publishedAt": "2026-05-24T22:05:18.000Z",
"site": "https://community.openai.com",
"textContent": "The Prompt Caching docs make it sound like prompt caching should work out of the box for GPT-5.4-Nano, yet subsequent identical request to the Responses API show no change in the number of cached tokens.\n\nI’m seeing multiple unresolved discussions about the same thing online. Since I can’t add links in a post, Google “prompt caching not working gpt-5.4-nano” and there are at least 3 discussions about this.\n\nAre we all missing something here?\n\nThanks",
"title": "Prompt Caching Not Working for GPT-5.4-Nano"
}