Modal alternatives
Every model hosting and inference provider this site tracks, ordered by iScore — the same peers Modal's own score is measured against. The line under each name is where its sourced facts differ from Modal's; where a full comparison exists, the row links to it.
- RunPodvs ModalEntry paid plan: A new account can start with as little as $10 in prepaid credits; deploying a Pod require…
- BasetenEntry paid plan: $0 per month on the Basic plan — pay as you go, with dedicated deployments, model APIs an…
- Replicatevs ModalPricing model: Two meters, chosen by the model rather than by you. Public models bill per run — per outp…
Where Modal stands against these 3
Modal's own sourced figures, placed among the alternatives above that document the same thing in the same unit. A rank here is one criterion, not a verdict; the iScore above weighs all of them.
- H100 SXM, per GPU-hour
- $3.95 per hour for an Nvidia H100 SXM5, published as $0.001097 per secondCheapest of the 4 that document it. Next: RunPod — $3.99 per hour for H100 SXM 80GB, single card, on Secure Cloud (the page's default view).
- Cheapest GPU, per hour
- $0.59 per hour for an Nvidia T4, published as $0.000164 per second — the cheapest GPU on the resource table2nd cheapest of the 3 that document it. Cheapest: RunPod — $0.27 per hour for an RTX A5000 with 24GB, on Secure Cloud (the page's default view).
A rank whose 80% interval overlaps its neighbour's is an ordering, not a finding; the intervals are on each provider's page and in /scores.json.