Runpod Serverless Flex — H100 80GB
Runpod Serverless Flex lists an NVIDIA H100 PRO worker with 80 GB VRAM at USD 4.79 per GPU-hour, billed per second. Optional Global Volumes beta supports region-independent, read-heavy model storage on GPU Serverless endpoints with separate storage and request charges; only one global volume may be attached, and it cannot coexist with a regional network volume. Worker time is billable during startup, execution and idle windows, even when jobs fail or time out.
Pricing details
Secondary price terms only; primary pricing stays in the deal summary.
Fit & constraints
Use-case fit and limitations from the existing resource record.
Failed/timed-out/retried jobs and worker startup/idle time may still incur GPU-second charges.
Available
Price intelligence
Recorded price-change events provide the comparison; no synthetic market reference is created.
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.