{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreifrp74b6wpg4asuvriv6twfnnc5qzxjvem6ouf5uabdn6vtiuu3ma",
"uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mlqu3fu3smh2"
},
"path": "/t/what-are-considered-requests-when-using-the-real-time-api/1153150#post_3",
"publishedAt": "2026-05-13T16:39:38.000Z",
"site": "https://community.openai.com",
"textContent": "Despite the model being “realtime”, that is just a buffering front end.\n\nThe model generates based on a set input context and a trigger. The trigger is either the end of server voice activity detection, or your response.create event. That is your request to receive a generated output, and what the rate limiter would error out on if over the limiter quota.",
"title": "What are considered \"requests\" when using the real-time API?"
}