$GPU Rental Prices.com
verified 2026-07-08

Serverless GPU pricing

Serverless GPU = per-second billing that scales to zero between requests: you pay for compute seconds, not idle hours. For bursty inference it beats renting an instance; for sustained load an on-demand instance is usually cheaper. Rates below are $/hr equivalents of per-second prices.

GPU$/hr equivalent$/secondProviderVerified
L4$0.80$0.000222Modal2026-07-08Try →
L40S$1.95$0.000542Modal2026-07-08Try →
A100 PCIe 40GB$2.10$0.000583Modal2026-07-08Try →
A100 (unspecified)$2.50$0.000694Modal2026-07-08Try →
RTX PRO 6000$2.99$0.000831fal2026-07-08Try →
RTX PRO 6000$3.03$0.000842Modal2026-07-08Try →
H100 (unspecified)$3.95$0.001097Modal2026-07-08Try →
H100 (unspecified)$3.99$0.001108fal2026-07-08Try →
H200 (SXM)$4.50$0.001250fal2026-07-08Try →
H200 (SXM)$4.54$0.001261Modal2026-07-08Try →
B200$6.25$0.001736Modal2026-07-08Try →
B200$6.25$0.001736fal2026-07-08Try →

Serverless bills only active compute seconds but adds cold-start latency and per-request overhead. Sustained workloads above roughly 50-60% utilization are cheaper on-demand: run your numbers in the calculator.

When serverless wins

Pick serverless when

  • Traffic is bursty or unpredictable
  • You serve a model occasionally (demos, side projects, internal tools)
  • You want zero idle cost and no capacity management

Pick an instance when

  • Utilization is sustained (training, batch jobs, steady APIs)
  • Cold starts are unacceptable
  • You need full control of the environment or multi-GPU nodes

Modal includes a recurring monthly free credit tier; see free credits. RunPod also offers serverless endpoints priced separately from the pod rates shown on the RunPod page.