{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreigfa7cskysc7pw2y3doyontnyxbxwohsv23qzzuweiu7qbw7xy2nm",
"uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mmgvxfdh6sv2"
},
"path": "/t/how-can-we-clearly-see-token-usage-per-codex-conversation-task-especially-in-codex-web/1381431#post_8",
"publishedAt": "2026-05-22T11:04:28.000Z",
"site": "https://community.openai.com",
"tags": [
"Codex SDK"
],
"textContent": "If you need to hardwire things to that level, I’d recommend using the app-server in the Codex SDK.\n\nIt will give much more information you don’t see in the IDE/App and some that don’t even go to the .jsonl, plus you can control the model, get usage per request, etc.",
"title": "How can we clearly see token usage per Codex conversation/task, especially in Codex web?"
}