inferenstack — the market read on AI inference · last observation 2026-09-20. See the boards
Provider prices

Where's it cheapest right now?

Rental prices across 22 providers, per single GPU-hour, with marketplace liquidity signals — occupancy, verified hosts, and reliability.vendor-claimed

Live · 3,081 observations since 2026-09-04

Liquidity is per-marketplace, not global. Supply on Vast/RunPod skews to consumer & community hardware — a GPU that looks thin here may be abundant on a neocloud. Treat occupancy as a depth signal for that market only.

h100-sxm-80gb · price history · 0 providers

Full price history & dynamics

This is a 7-day preview. Sign in for 30 days free; the full series and export are the API subscription.

Provider board · h100-sxm-80gb

ProviderTier$/GPU-hrOccupancyVerifiedReliabilitySupplyRegions

Market overview · cheapest by GPU

GPUCheapest $/hrProviderProvidersAvg occupancy

Live data. Prices normalized to USD per single GPU-hour.