{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreic262milnaqgszd5fumva6cquywhbdqjbaxeosbgl5vfq2375xnvi",
"uri": "at://did:plc:pgryn3ephfd2xgft23qokfzt/app.bsky.feed.post/3mj5mltse5hi2"
},
"path": "/t/billing-spike-from-195h-to-1298h-in-24h-for-t4-space-impossible-usage/175144#post_1",
"publishedAt": "2026-04-10T07:29:45.000Z",
"site": "https://discuss.huggingface.co",
"textContent": "Hi Hugging Face Team,\n\nI’m facing a serious billing issue with one of my Spaces and would appreciate urgent assistance.\n\n### Space Details:\n\n * **Space Type:** GPU Space\n\n * **Hardware:** T4 Small\n\n\n\n\n* * *\n\n### Observed Usage:\n\nUp until yesterday:\n\n * **Runtime:** 195 hours 32 minutes\n\n * **Cost:** $78.22\n\n\n\n\nToday:\n\n * **Runtime:** 1298 hours 2 minutes\n\n * **Cost:** $519.24\n\n\n\n\n* * *\n\n### Issue:\n\nThere is a sudden increase of **~1100 hours within less than 24 hours** , which is **technically impossible**.\n\nEven with continuous GPU usage:\n\n * Maximum possible = **24 hours/day per instance**\n\n * This spike would imply dozens of parallel instances, which is not the case.\n\n\n\n\n* * *\n\n### Additional Context:\n\n * I restarted the Space yesterday and it was functioning normally.\n\n * Today morning, I observed the Space in a **runtime error state**.\n\n * It’s possible the GPU remained allocated unintentionally, but even then, such a large spike is not feasible.\n\n\n\n\n* * *\n\n### Concern:\n\nThis appears to be:\n\n * A **billing/metering inconsistency**\n\n * Or a **delayed usage reconciliation issue**\n\n * Or potential **duplicate counting of runtime**\n\n\n\n\n* * *\n\n* * *\n\nThis is a significant and unexpected charge, so I would appreciate a prompt review.\n\nThank you.",
"title": "Billing Spike from 195h to 1298h in <24h for T4 Space (Impossible Usage)"
}