Runpod Serverless Flex pricing: why VRAM alone is the wrong comparison
Runpod's Flex tiers range from $0.58/hour 16GB classes to high-end B300 capacity. The useful decision is model fit, hardware class, and measured cost per job—not VRAM alone.
← Back to GPU Cloud
✦ NEW DEAL
Modal · GPU Cloud · GPU Instance
Modal GPU — NVIDIA H100 SXM5 80GB (serverless allocation)
Modal lists NVIDIA H100 SXM5 GPU allocation at USD $0.001097 per GPU-second (equivalent to $3.9492 per GPU-hour) with 80 GB of VRAM. CPU and memory are billed separately; region selection and non-preemptible execution may add surcharges, and actual regional capacity is not independently checked.
CURRENT PRICE$3.95 / hrNative listed value
Pricing
Pricing details
Secondary price terms only; primary pricing stays in the deal summary.
BILLINGOther
Fit & constraints
Fit & constraints
Use-case fit and limitations from the existing resource record.
KEY RISK
Published Modal H100 GPU allocation price is verified, but live region-specific inventory/account quota is not. GPU-only base rate excludes CPU/RAM, possible regional and non-preemptible surcharges, storage and excess egress.
AVAILABILITY
Unknown
Resource facts
Key specs
Non-price resource facts only; pricing, history, and evidence stay in their own sections.
GPU MODELNVIDIA H100 SXM5
GPU COUNT1
VRAM80 GB
Trust layer
Verified evidence
Decision visuals remain traceable to the existing source and verification record.
Independent ranking · native prices · evidence-linked · commercial relationships isolated from scoring and publication.
WATCH